Explore Your Local Site

Looks like you've landed on our   site. Let's take you home:    

Please note that the content and products on the    site might not be available in your region.

 

Choose the language:

  Homepage
Continue on the current website:  

 

Künstliche Intelligenz in der medizinischen Bildgebung: Was, wie und warum?

Der Begriff „künstliche Intelligenz“ beschreibt Computersysteme mit der Fähigkeit, Probleme durch Anpassung an sich verändernde Umstände zu lösen, wobei diese häufig menschliches Denken und Schlussfolgerungen nachahmen. Verschiedene Trends in Demografie und Gesundheitsversorgung treiben den Einsatz von KI-Lösungen in der medizinischen Bildgebung voran. Die Menge an erfassten medizinischen Bilddaten nimmt ständig zu (Larson et al., 2011; Smith-Bindman et al., 2008, 2012; Winder et al., 2021). Zudem herrscht großer Personalmangel in der Gesundheitsversorgung (Core Health Indicators in the WHO European Region 2015. Special Focus: Human Resources for Health, 2017), während die Arbeitsbelastung weiter steigt (Levin et al., 2017) und die Anzahl der Untersuchungen mit medizinischen Bildgebungsverfahren in den nächsten zwanzig Jahren exponentiell zunehmen dürfte (Tsao, 2020). Radiologen und Radiologietechnologen sind besonders rar (AAMC Report Reinforces Mounting Physician Shortage, 2021, Clinical Radiology UK Workforce Census 2019 Report, 2019). Letztendlich wird davon ausgegangen, dass die alternde Weltbevölkerung (Population Ages 65 and above, o. D.; WHO, o. D.-a) und die global zunehmende Belastung durch chronische Krankheiten (WHO, o. D.-b) die genannten Probleme in absehbarer Zukunft verschärfen dürften.

Grob gesagt könnten die Vorteile der KI in der medizinischen Bildgebung darin bestehen, dass sie Erkenntnisse liefern kann, die mit herkömmlichen Methoden (z. B. durch die Betrachtung von Bildern durch Menschen) nicht möglich wären, und zwar auf schnellere und automatisierte Weise (ohne die Notwendigkeit menschlicher Interaktion). KI-basierte Lösungen in der medizinischen Bildgebung könnten die Erkennung von Krankheiten verbessern und beschleunigen, eine eingehende Risikobewertung der Krankheitsentwicklung und des Krankheitsverlaufs ermöglichen und die Subjektivität bei der Interpretation medizinischer Bilddaten verringern.

Aktueller Stand der KI in der medizinischen Bildgebung

In den letzten Jahren hat sich die Landschaft der KI in der medizinischen Bildgebung dramatisch verändert. Es sind viele vielversprechende Anwendungen entstanden, das Feld hat einen beispiellosen Finanzierungsschub erlebt, und wir haben positive Trends bei der Annahme von KI-Lösungen durch Radiologen sowie deren Zertifizierung durch die Aufsichtsbehörden beobachtet.

Applikationen

Obwohl radiologische Abteilungen eine Fülle von Dienstleistungen anbieten, ist die Kernleistung die bildgebende Untersuchung. Anwendungen der KI in der medizinischen Bildgebung können daher in solche unterteilt werden, die entweder vor, während oder nach der Bildgebung eingesetzt werden.

Vor der Bildakquisition

Bevor ein Patient einer bildgebenden Untersuchung unterzogen wird, müssen im Rahmen des Arbeitsablaufs in einer radiologischen Abteilung mehrere Schritte erfolgen. KI-Anwendungen, die darauf abzielen, diese Schritte zu verbessern, werden als „vorgelagerte KI“ bezeichnet und könnten potenziell die Effizienz steigern und eine stärker personalisierte Entscheidungsfindung in einer radiologischen Abteilung ermöglichen.

Verpasste medizinische Termine sind weit verbreitet, verringern die Effizienz von Krankenhäusern und verschwenden Ressourcen (Dantas et al., 2018). Studien aus Japan (Kurasawa et al., 2016) und dem Vereinigten Königreich (Nelson et al., 2019) haben gezeigt, dass KI genutzt werden kann, um Nichterscheinen mit hoher Genauigkeit vorherzusagen. Dies ermöglicht den Einsatz gezielter Strategien, um die Wahrscheinlichkeit zu verringern, dass ein Patient seinen Termin versäumt, einschließlich des Versands automatischer Erinnerungen.

Eine der wichtigsten Entscheidungen in der radiologischen Abteilung ist die Wahl des genauen Untersuchungsprotokolls für einen bestimmten Patienten. Dies gilt zwar für alle bildgebenden Verfahren, doch bei der Magnetresonanztomographie (MRT) ist die Auswahl am größten. Dazu gehören die Auswahl der geeigneten Sequenzen und die Entscheidung, ob intravenöse Kontrastmittel verabreicht werden sollen oder nicht. Zur Auswahl geeigneter MRT-Protokolle wurden sprachliche Klassifikatoren eingesetzt, die den narrativen Text der Untersuchungsanfragen des überweisenden Arztes interpretieren. In einer Studie sagte ein Gradient-Boosting-Klassifikator das geeignete MRT-Hirnprotokoll auf der Grundlage der Scan-Anforderung mit hoher Genauigkeit (95%) voraus (Brown & Marotta, 2018). Bei MRT-Untersuchungen des Bewegungsapparats konnte ein Deep-Learning-Klassifikator mit einer Genauigkeit von 83% den Bedarf an einem Kontrastmittel bestimmen (Trivedi et al., 2018). Solche Anwendungen können die Effizienz erheblich verbessern, indem sie die zeitaufwändige Aufgabe von Radiologen überflüssig machen, unstrukturierte, von überweisenden Ärzten verfasste Scan-Anfragen durchzugehen.

Während der Bildakquisition

In jüngster Zeit wurden erhebliche Verbesserungen beim Einsatz von KI zur Verbesserung der Bildqualität erzielt. In einer kürzlich durchgeführten Umfrage bezeichneten Radiologen die Verbesserung der Bildqualität als den derzeit wichtigsten Anwendungsfall für KI in der medizinischen Bildgebung (Alexander et al., 2020). Während frühere Versuche, das Bildrauschen mithilfe von Deep-Learning-Techniken zu reduzieren, kritisiert wurden, weil dabei Details aus den Bildern entfernt wurden, die die Sichtbarkeit wesentlicher Merkmale in den Bildern gefährdeten, haben neuere Implementierungen dieses Problem weitgehend überflüssig gemacht.

Potenzial für KI

 

Insbesondere Deep-Learning-Techniken wie Generative Adversarial Networks (GANs) haben großes Potenzial für die Reduktion von Rauschen in den Bildern gezeigt (Wang et al., 2021). Einige dieser Anwendungen zielen auf die Bildrekonstruktionsphase ab (in der die Rohdaten in ein interpretierbares Bild umgewandelt werden), um ein besseres Signal-Rausch-Verhältnis zu erzielen und Bildartefakte zu reduzieren (Zhu et al., 2018). Bei der Lungenkrebsvorsorge verbesserte die Deep-Learning-basierte Rauschreduktion sowohl die Bildqualität als auch die diagnostische Genauigkeit der Ultra-Niedrigdosis-Computertomografie (CT) zur Erkennung verdächtiger Lungenknoten (Hata et al., 2020; Kerpel et al., 2021). Scans, die 40–60% schneller als Standard-Scans erfasst und mit Deep-Learning-basierten Algorithmen verbessert wurden, wiesen eine bessere Bildqualität und einen ähnlichen diagnostischen Wert auf wie Standard-Scans des Gehirns (Bash, Wang, et al., 2021; Rudie et al., 2022) und der Wirbelsäule (Bash, Johnson, et al., 2021). In ähnlicher Weise können neuronale Faltungsnetzwerke verwendet werden, um spezifische CT- und MRT-Artefakte zu reduzieren und die räumliche Auflösung zu verbessern (Hauptmann et al., 2019; K. H. Kim & Park, 2017; Park et al., 2018; Y. Zhang & Yu, 2018).

Auf Deep Learning basierende Rekonstruktionsalgorithmen haben es ermöglicht, Computertomographien mit extrem niedriger Strahlendosis zu erstellen und gleichzeitig die diagnostische Qualität zu erhalten. Dies ist besonders bei Kindern und schwangeren Frauen von Vorteil, wo die Reduzierung der Strahlendosis auf ein absolutes Minimum entscheidend ist. Diese auf Deep Learning basierenden CT-Bildrekonstruktionsverfahren sind mit geringerem Bildrauschen und besserer Bildtextur verbunden als moderne Alternativen wie die iterative Rekonstruktion (Higaki et al., 2020; McLeavy et al., 2021; Singh et al., 2020). Bei der Positronen-Emissions-Tomographie kann Deep Learning die injizierte Tracer-Dosis um ein Drittel und die Scanzeiten um bis zur Hälfte reduzieren, während die Scanqualität erhalten bleibt (Katsari et al., 2021; Le et al., 2020; Xu et al., 2020).

Nach der Bildakquisition

Radiologietechnologen und Radiologen teilen sich in der Regel die Aufgabe, Patientinnen und Patienten wegen Wiederholungsterminen nochmals einzubestellen. Doch da Zeit zunehmend knapp ist, wird es immer schwieriger, dies durchgehend zuverlässig umzusetzen. Die Bildqualität von mittels KI verbesserten MRT-Scans des Gehirns war selbst bei Verwendung von Akquisitionsprotokollen, die die Scanzeit um 45–60% reduzierten, vergleichbar mit konventionellen Scans oder sogar besser (Schreiber-Zinaman & Rosenkrantz, 2017).

Die Priorisierung der Scans auf der Arbeitsliste eines Radiologen erfolgt häufig auf der Grundlage mehrerer Faktoren, darunter die Art des Scans, die überweisende Abteilung und die direkte Kommunikation mit dem Radiologen über die Dringlichkeit des Scans. Es wurden verschiedene Ansätze getestet, um die Reihenfolge der Scans zu beeinflussen, um die Effizienz zu verbessern und sicherzustellen, dass die kritischsten Scans zuerst befundet werden. Dazu gehören die Zuweisung spezifischer Untersuchungen an verschiedene Radiologen, je nachdem, wie schnell sie bestimmte Bilddaten lesen (Wong et al., 2019), und die automatische Erkennung dringender Befunde auf den Bildern und das Verschieben dieser Fälle an den Anfang der Arbeitsliste (Prevedello et al., 2017; Winkel et al., 2019).

Etwa 70% aller KI-basierten Lösungen in der Radiologie konzentrieren sich auf die „Wahrnehmung“ - eine Kategorie von Funktionalitäten, die Segmentierung, Merkmalsextraktion sowie die Erkennung und Klassifizierung von Pathologie umfasst (Rezazade Mehrizi et al., 2021). Innerhalb dieser Kategorie extrahieren die meisten Tools Informationen aus den Bilddaten mit oder ohne Quantifizierung und machen den Benutzer auf mögliche Pathologien aufmerksam (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). In den letzten Jahren gehörten zu den vielversprechendsten Anwendungen in dieser Kategorie die Erkennung von Hirngefäßverschlüssen, Hirnblutungen, Lungenherden, Pneumothorax und Pleuraergüssen, Frakturen und die Charakterisierung von Brustläsionen.

Förderung

Der Gesamtbetrag der Investitionen in KI-basierte Unternehmen der medizinischen Bildgebung belief sich zwischen 2014 und 2019 auf 1,17 Mrd. USD (Alexander et al., 2020). Im gleichen Zeitraum verdreifachte sich die Zahl der Unternehmen in diesem Bereich, was zu einem Rückgang der durchschnittlichen Investition in jedes Unternehmen um fast 30% führte (Alexander et al., 2020). Zwischen 2019 und 2020 stiegen die privaten Investitionen in KI-Unternehmen um 9,3% (D. Zhang et al., 2021). Bis 2030 werden die Investitionen in KI-basierte Lösungen in der medizinischen Bildgebung voraussichtlich 3 Mrd. USD übersteigen (Tsao, 2020).

Einführung

In den letzten Jahren gab es positive Trends bei der Einführung von KI-Tools durch Radiologen und Radiologietechnologe. Laut einer vom American College of Radiology (ACR) durchgeführten Umfrage unter 1.861 Radiologen stieg der Einsatz von KI in radiologischen Abteilungen zwischen 2015 und 2020 um 30% (Allen et al., 2021).

Trotz dieses vielversprechenden Trends wird der Einsatz von KI-Tools weithin als unverhältnismäßig gering angesehen, gemessen an der Höhe der Finanzmittel, der Zahl der Unternehmen und dem wahrgenommenen Potenzial dieser Tools. Die ACR-Umfrage gibt Aufschluss darüber, warum dies so ist, und bietet einen Ansatzpunkt für die Entwicklung von Strategien zur Verbesserung der KI-Einführung.

Fast drei Viertel der Radiologen, die keine künstliche Intelligenz einsetzen, hatten nicht vor, dies in Zukunft zu tun, weil sie entweder nicht von den Vorteilen überzeugt waren oder die damit verbundenen Kosten nicht für gerechtfertigt hielten (Allen et al., 2021).

Zu ähnlichen Ergebnissen kamen auch andere Studien, in denen Radiologen ihre Skepsis gegenüber den Fähigkeiten von KI-Tools und die Tatsache, dass nur relativ wenige von ihnen eine behördliche Zertifizierung haben, als Gründe dafür anführten, sie nicht in ihrer Praxis einzusetzen (Alexander et al., 2020).

Regulatorischer Erfolg

Bis August 2019 hatten 60% der verfügbaren KI-basierten Radiologielösungen keine behördliche Zertifizierung (Rezazade Mehrizi et al., 2021). Im April 2020 verfügten insgesamt 100 KI-Lösungen über eine CE-Kennzeichnung, die Voraussetzung dafür ist, dass sie in Europa als Medizinprodukte kommerziell verfügbar gemacht werden können (van Leeuwen et al., 2021). Zum Zeitpunkt der Erstellung dieses Berichts haben mehr als 150 KI-Lösungen die FDA-Zulassung erhalten (AI Central, n.d.). Derzeit sind mehrere nützliche Datenbanken mit zugelassenen oder genehmigten KI-basierten Lösungen für die medizinische Versorgung verfügbar (AI Central, n.d., AI for Radiology, n.d., Medical AI Evaluation, n.d., The Medical Futurist, n.d.).
 

Die Zukunft der KI in der medizinischen Bildgebung

In den letzten Jahren hat das Interesse an KI in der medizinischen Bildgebung exponentiell zugenommen, sowohl in Bezug auf den Umfang der Forschung als auch auf die Höhe der Investitionen in diesem Bereich. Dieses Interesse erstreckt sich auf die gesamte Bandbreite des radiologischen Arbeitsablaufs, wobei jedoch die “Wahrnehmungs”- Anwendungen - für die Quantifizierung von Biomarkern und die Erkennung von Krankheitsprozessen - bisher dominiert haben. In der Radiologie hat sich der Trend von der Wahrnehmung der KI als unerwünschter Eindringling hin zu einer zunehmenden Akzeptanz verschoben, wenn auch mit einer gewissen Skepsis und einem gewissen Zögern in Bezug auf ihren Wert. Die ersten KI-Lösungen in der medizinischen Bildgebung haben die Zertifizierung erhalten, und es gibt erste Hinweise darauf, wie solche Lösungen erstattet werden könnten.

Neue Ausrichtungen

Angesichts der zunehmenden Erkenntnis, dass ein großer Teil des Potenzials der KI in der medizinischen Bildgebung in “vorgelagerten” oder “nicht-interpretativen” Anwendungen liegen könnte, wird das Feld in den kommenden Jahren wahrscheinlich seinen Schwerpunkt erweitern. Dazu gehört auch die verstärkte Erforschung von Anwendungen, die die Effizienz der radiologischen Arbeitsabläufe verbessern und eine stärker personalisierte Patientenversorgung ermöglichen (Alexander et al., 2020). Die KI wird wahrscheinlich noch früher in den Patientenbehandlungsprozess einbezogen werden, d. h. bevor der Arzt entscheidet, ob eine bildgebende Diagnostik erforderlich ist. Solche Anwendungen, im Wesentlichen klinische Systeme zur Unterstützung von Entscheidungen, wurden bereits in verschiedenen Bereichen erfolgreich für die Entscheidungsfindung über Behandlungen eingesetzt (Bennett & Hauser, 2013; Komorowski et al., 2018).

perception of ai

In Zukunft könnten KI-Lösungen Kliniker auf die Notwendigkeit weiterer bildgebender Untersuchungen aufmerksam machen, indem sie die klinischen Informationen des Patienten, Labortests und frühere bildgebende Untersuchungen überprüfen (Makeeva et al., 2019).

Die überwiegende Mehrheit (77–84%) der derzeit verfügbaren KI-Lösungen für die medizinische Bildgebung zielt auf CT, MRT und Röntgenbilder ab (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). Nuklearmedizinische Bildgebungsverfahren wie die Positronen-Emissions-Tomographie (PET) liefern einzigartige Informationen, die mit anderen Modalitäten nicht ohne weiteres gewonnen werden können. PET wurde bisher in der KI-Forschung weitgehend vernachlässigt (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021) und ist daher ein potenziell vielversprechender Weg für die zukünftige Ausweitung dieses Bereichs.

In der KI-Forschung wird auch ein Wandel in der Art der verwendeten Daten erwartet. Der typische Patient erhält während seines Krankenhausaufenthalts mehr als eine bildgebende Untersuchung (Shinagare et al., 2014). Trotzdem kombinieren nur etwa 3% der aktuellen KI-basierten Radiologielösungen Daten aus mehreren Modalitäten (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). Die Kombination von Daten aus verschiedenen Bildgebungsquellen kann die diagnostischen Fähigkeiten von KI-Lösungen verbessern. Darüber hinaus werden künftige KI-Lösungen in der Radiologie wahrscheinlich bildgebende Informationen, klinische Informationen sowie nicht bildgebende diagnostische Tests kombinieren (Huang et al., 2020). Auf diese Weise könnten KI-Lösungen in der Lage sein, Muster in den während des Krankenhausaufenthalts eines Patienten gesammelten Daten zu erkennen, die für das Gesundheitspersonal möglicherweise nicht ohne Weiteres erkennbar sind (Rockenbach, 2021). Dies könnte letztlich zu genaueren Diagnosen führen und zu besseren und individuelleren Behandlungsentscheidungen beitragen.

Die Erwartungen an KI-basierte Lösungen für die medizinische Bildgebung werden sich wahrscheinlich auch vom derzeitigen Schwerpunkt der Triage, Bildverbesserung und Automatisierung wegbewegen. Mit zunehmender Komplexität der Algorithmen, Datenverfügbarkeit und Erfahrung mit diesen Werkzeugen könnte diese Verschiebung dazu führen, dass KI-Lösungen spezifische Diagnosen stellen und spezifische Schritte im Behandlungsplan eines Patienten empfehlen. Ähnlich wie die Einführung der ersten KI-Tools für das Bildscreening und die Bildverarbeitung die Investitionen in diesem Bereich um 2018 herum angekurbelte, sagen Marketinganalysen einen ähnlichen Investitionsschub in den nächsten Jahren voraus, da KI-Tools, die spezifische Diagnosen und Behandlungsschritte liefern, weiter verbreitet sein werden (Michoud et al., 2019).

Ein wichtiger Kritikpunkt an der derzeitigen, wohl noch im Entstehen begriffenen Landschaft der KI in der medizinischen Bildgebung ist, dass sie zu fragmentiert ist. Fachleute in der Radiologie würden wahrscheinlich eine straffere Integration von KI-Lösungen in ihren täglichen Arbeitsablauf begrüßen. Dazu gehört die nahtlose Integration dieser Lösungen in die etablierten Arbeitsabläufe in der Radiologie, wobei so viel wie möglich “im Hintergrund” ohne Benutzereingabe geschieht. Darüber hinaus könnten die Ergebnisse dieser Lösungen in vorhandene radiologische Informationssysteme integriert werden. Folglich könnte sich das Feld von der Fülle der derzeit verfügbaren KI-Nischenlösungen, die jeweils auf eine einzige sehr spezifische Anwendung ausgerichtet sind, zu breiteren Software-Suiten entwickeln, die viele verschiedene Funktionen für eine bestimmte Bildgebungsmodalität oder Körperregion ausführen.

Die fragmentierten Investitionen in den Markt für KI in der medizinischen Bildgebung (Alexander et al., 2020) fördern die Innovation und ermöglichen es vielen Akteuren, verschiedene Strategien in diesem aufstrebenden Bereich zu erproben. Langfristig könnte jedoch eine Konsolidierung die Akzeptanz erhöhen und die erforderliche nahtlose Integration in bestehende Arbeitsabläufe fördern, so dass weniger Unternehmen diese Lösungen in großem Umfang anbieten können (Alexander et al., 2020).

Herausforderungen

Qualität und Meldung von Nachweisen

Bei einer Überprüfung von 100 CE-gekennzeichneten AI-Lösungen gab es für 64% von ihnen keine von Experten begutachteten wissenschaftlichen Nachweise für ihre Wirksamkeit (van Leeuwen et al., 2021). Dort, wo es wissenschaftliche Belege gab, war das Niveau niedrig und ging selten über den Nachweis der diagnostischen Genauigkeit hinaus (van Leeuwen et al., 2021). Eine weitere systematische Überprüfung der Evidenz für Deep-Learning-Algorithmen in der medizinischen Bildgebung ergab eine allgemein hohe diagnostische Genauigkeit, allerdings mit einem hohen Risiko der Verzerrung zwischen den Studien (Aggarwal et al., 2021). Zu den Hauptquellen für Verzerrungen gehören das Fehlen einer externen Validierung (D. W. Kim et al., 2019; Liu et al., 2019), eine unzureichend detaillierte Berichterstattung über die Ergebnisse (Liu et al., 2019), ein retrospektives Studiendesign (Nagendran et al., 2020) und die Unzugänglichkeit von Daten und Code für Prüfer und Leser (Nagendran et al., 2020).

Insgesamt haben Studien zu KI-Tools einen besorgniserregenden Mangel an standardisierter Befunderstellung und an der Einhaltung der empfohlenen Berichterstattungsrichtlinien gezeigt (Aggarwal et al., 2021; Yusuf et al., 2020). Und das, obwohl derzeit mehrere Erweiterungen etablierter Berichterstattungsleitlinien sowie KI-spezifische Leitlinien verfügbar sind (Shelmerdine et al., 2021). Die flächendeckende Umsetzung dieser Leitlinien sollte in Zukunft ein Schwerpunkt der KI-Entwickler sein.

KI-Entwickler sollten sich auch darüber im Klaren sein, dass das derzeit “akzeptable” Beweisniveau für KI-basierte Lösungen in naher Zukunft wahrscheinlich veraltet sein wird. Sowohl die Aufsichtsbehörden als auch die potenziellen Nutzer werden wahrscheinlich ein höheres Maß an Evidenz für diese Lösungen verlangen, ähnlich der Evidenz, die für neue pharmazeutische Medikamente erforderlich ist. In den nächsten Jahren werden mehr dieser KI-Lösungen in randomisierten klinischen Studien getestet werden. In der ferneren Zukunft ist es plausibel, dass diese Erwartungen über den Nachweis der Sicherheit, Wirksamkeit oder diagnostischen Leistung dieser Lösungen hinausgehen und den Nachweis erbringen, dass sie einen zusätzlichen monetären oder gesellschaftlichen Nutzen bieten.

Sich der Herausforderung zu stellen, die Qualität und die Berichterstattung über KI-basierte Lösungen zu verbessern, könnte sich langfristig auszahlen. Es könnte das Risiko von Verzerrungen in KI-Studien verringern, eine gründliche und transparente Bewertung der Studienqualität durch potenzielle Nutzer und Regulierungsbehörden ermöglichen und systematische Überprüfungen und Meta-Analysen erleichtern. Diese Schritte könnten das Vertrauen in und die Akzeptanz von KI-basierten Lösungen erhöhen und sicherstellen, dass sie realistische, nachhaltige Verbesserungen für das Leben der Menschen bieten.

Regulierung

Mehrere der KI innewohnenden Aspekte stellen eine Herausforderung für Versuche dar, sie wie andere Maßnahmen im Gesundheitswesen zu regulieren. Das Innenleben von KI-Lösungen ist oft undurchsichtig und lässt sich nur schwer so umfassend beschreiben, wie es die Regulierungsbehörden traditionell erwarten.

Die letzten Jahre haben uns gezeigt, dass diese regulatorischen Herausforderungen alles andere als unlösbar sind. Sowohl die Food and Drug Administration als auch die Europäische Kommission haben vor kurzem erste regulatorische Rahmenbedingungen für KI-Lösungen vorgeschlagen (Center for Devices & Radiological Health, 2021; Europäische Kommission, 2021).

Zum Teil als Reaktion auf die für die behördliche Zulassung erforderliche Transparenz haben die Forscher erhebliche Fortschritte dabei gemacht, die Entscheidungsfindung der KI verständlicher und erklärbarer zu machen. Diese Entwicklung hin zu “interpretierbarer KI” wird in naher Zukunft weiter an Fahrt gewinnen, da die KI in der klinischen Praxis immer häufiger zur Entscheidungsfindung herangezogen wird.

Dies hat viele Vorteile, darunter die Erleichterung der behördlichen Zertifizierung, die Stärkung des Vertrauens der Nutzer in diese Lösungen, die Minimierung von Verzerrungen und die Verbesserung der Reproduzierbarkeit dieser Lösungen (Holzinger et al., 2017; Kolyshkina & Simoff, 2021; “Towards Trustable Machine Learning”, 2018; Yoon et al., 2021).

Datenschutz

Von der Entwicklung und Erprobung bis hin zur Implementierung erfordern KI-Lösungen in der medizinischen Bildgebung den Zugang zu Patientendaten. Dies hat Bedenken hinsichtlich des Datenschutzes aufgeworfen, der ein vielschichtiges und hochkomplexes Thema ist (Murdoch, 2021), das in den Regulierungswegen verschiedener Länder prominent vertreten ist (COCIR, Europäischer Koordinierungsausschuss der radiologischen, elektromedizinischen und Gesundheits-IT-Industrie, 2020). Die vorgeschlagenen Lösungen für die Datenschutzfrage reichen von solchen, die sich auf die Aufsicht konzentrieren, bis hin zu eher technischen Ansätzen. Die Patienten, die die Daten zur Verfügung stellen, müssen über diesen Umstand in Kenntnis gesetzt und auch darüber informiert werden, wie und warum ihre Daten verarbeitet werden (Lotan et al., 2020), wie es ausdrücklich in der „Datenschutz-Grundverordnung“ der EU (DSGVO) vorgeschrieben ist (Datenschutz-Grundverordnung (DSGVO) – offizieller Rechtstext, 2016). Es wurde infrage gestellt, dass die schnelle Entwicklung der KI-Lösungen es zulässt, die Patienten ausreichend zu informieren, da die Algorithmen laufend neu trainiert werden (Kritikos, 2020). Obwohl vollständig anonymisierte Daten nicht in den strengen Geltungsbereich der DSGVO fallen (What Is Personal Data?, 2021), ist die Anonymisierung der für die medizinische Bildgebung erforderlichen Daten überaus schwierig.

Die Frage des Datenschutzes muss an mehreren Fronten angegangen werden. Neben der Gesetzgebung, die die Verwendung von Patientendaten regelt, wird immer deutlicher, dass jeder, der an der Entwicklung und Nutzung von KI-Lösungen beteiligt ist - Entwickler, Kostenträger, Aufsichtsbehörden, Forscher und Radiologen - eine Rolle dabei spielen muss, sicherzustellen, dass die Daten geschützt und verantwortungsvoll genutzt werden.

Außerdem wird in den nächsten Jahren wahrscheinlich weiter an technischen Ansätzen zur Stärkung des Datenschutzes geforscht werden. Dazu gehören bessere Methoden zur Verringerung der Wahrscheinlichkeit, dass Daten zu Einzelpersonen zurückverfolgt werden können, Methoden zur lokalen Speicherung sensibler Daten, auch wenn der zu trainierende Algorithmus an einem “zentralen” Ort gehostet wird, Datenstörungen zur Minimierung der Informationen in einem bestimmten Datensatz, die sich auf einzelne Patienten beziehen, und Datenverschlüsselung (G. Kaissis et al., 2021; G. A. Kaissis et al., 2020).

Hexagon chart

Demokratisierung

Wenn die KI in der medizinischen Bildgebung ihr Potenzial voll ausschöpfen soll, müssen die entwickelten Algorithmen für alle funktionieren. Diese “Demokratisierung” der KI setzt voraus, dass die Leistungserbringer im Gesundheitswesen über die erforderlichen Kenntnisse und Fähigkeiten verfügen, um KI-basierte Lösungen zu nutzen. Mit wenigen Ausnahmen (Paranjape et al., 2019) enthalten die Lehrpläne für Medizinstudenten derzeit wenig bis gar keine spezielle Ausbildung über KI (Banerjee et al., 2021; Blease et al., 2022). Umfragen aus der ganzen Welt haben gezeigt, dass Medizinstudenten und Ärzte (Ahmed et al., 2022; Bisdas et al., 2021; Collado-Mesa et al., 2018; Kansal et al., 2022; Pinto Dos Santos et al., 2019; Sit et al., 2020) während ihrer Ausbildung nur wenig mit KI in Berührung kommen, obwohl die Nachfrage nach mehr KI-Ausbildung groß ist (Kansal et al., 2022; Ooi et al., 2021; Sit et al., 2020). Darüber hinaus gibt es nach wie vor große Unterschiede zwischen den Geschlechtern und Ländern in Bezug auf das wahrgenommene Wissen über KI unter Medizinstudenten (Bisdas et al., 2021). Es gibt viele Gründe für diese Unterschiede und viele Herausforderungen im Zusammenhang mit der umfassenden Integration der KI-Ausbildung in die Lehrpläne der Gesundheitsausbildung. In den kommenden Jahren sollten Strategien zur Bewältigung dieser Probleme untersucht werden, um sicherzustellen, dass künftige Gesundheitsdienstleister mit dem Wissen und den Fähigkeiten ausgestattet sind, die sie für die Arbeit in einem Umfeld benötigen, in dem KI eine immer größere Rolle spielt.

Zur Demokratisierung gehört auch, dass Patienten verschiedener Geschlechter, Lebensstile, Ethnien und geografischer Standorte von KI-basierten Lösungen profitieren können. Dazu müssen diese Lösungen zugänglich und ihre Leistung verallgemeinerbar sein. Letzteres erfordert den Erwerb verschiedener Daten von mehreren Einrichtungen, vorzugsweise aus mehreren Ländern, um KI-basierte Lösungen zu trainieren. Außerdem müssen Schutzmaßnahmen ergriffen werden, um sicherzustellen, dass Verzerrungen während des Entwicklungsprozesses nicht auf den trainierten Algorithmus übertragen werden (Vokinger et al., 2021) - ein Thema, das erst kürzlich in den Vordergrund gerückt ist (Larrazabal et al., 2020; Obermeyer et al., 2019; Seyyed-Kalantari et al., 2021).

Kostenübernahme

Während die Politik der Länder zur Regulierung von KI im Gesundheitswesen allmählich Gestalt annimmt, ist ein wichtiger Aspekt, der Aufmerksamkeit erfordert, wer für diese KI-Lösungen zahlen wird und nach welchem Rahmen.

Viele halten das deutsche Gesetz zur digitalen Versorgung 2020 für einen Schritt in die richtige Richtung für die Erstattung von digitalen Gesundheitslösungen. Danach sind ärztlich verordnete digitale Anwendungen von den gesetzlichen Krankenkassen erstattungsfähig, wenn sie nachweislich sicher und datenschutzkonform sind und die Patientenversorgung verbessern. Das Vereinigte Königreich wiederum hat einen Leitfaden für potenzielle Käufer von KI-basierten Lösungen herausgegeben, der den Unternehmen als Ausgangspunkt für die Vorbereitung von Erstattungsanträgen dient (A Buyer's Guide to AI in Health and Care, 2020).

Bislang gibt es nur wenige Erfolgsgeschichten im Bereich der Kostenerstattung im Bereich der digitalen Gesundheit (Brink- mann-Sass et al., 2020; Hassan, 2021). Dies ist zum Teil darauf zurückzuführen, dass die Anforderungen von Land zu Land sehr unterschiedlich sind (COCIR, Europäischer Koordinierungsausschuss der Radiologie-, Elektromedizin- und Gesundheits-IT-Industrie, 2020). Generell müssen Anbieter von digitalen Gesundheitslösungen den Gesamtwert dieser Lösungen nachweisen, einschließlich detaillierter gesundheitsökonomischer Studien, die potenzielle Kosteneinsparungen belegen.

Die Position der Radiologie als Dienstleister für mehrere Krankenhausabteilungen bedeutet, dass von KI-basierten Lösungen in diesem Bereich eine weitreichende Wirkung erwartet wird (van Duffelen, 2021). Die Unternehmen müssen sowohl einen kurzfristigen Nutzen (z. B. schnelleres/besseres Lesen von Bildern und Erstellen von Berichten) als auch einen langfristigen Nutzen (z. B. frühzeitige Diagnose und Behandlung, Krankheitsprävention, Verringerung unnötiger Folgeuntersuchungen) nachweisen. In den kommenden Jahren werden die Unternehmen darum konkurrieren, diese Wirkung nachzuweisen, während sie gleichzeitig mit verschiedenen Preismodellen experimentieren und sich in der sich entwickelnden bürokratischen Erstattungslandschaft zurechtfinden müssen.

Fazit

In den letzten Jahren hat der Bereich der KI in der medizinischen Bildgebung einen schnellen, aber stetigen Wandel erfahren. KI kann heute in der Radiologie Dinge leisten, die noch vor einem Jahrzehnt kaum jemand für möglich gehalten hätte. Das Feld überwindet auch allmählich eine seiner größten Hürden - die behördliche Genehmigung. Während vor einigen Jahren noch Angst und Skepsis die Wahrnehmung der Radiologen hinsichtlich der Zukunft der KI in ihrem Fachgebiet dominierten, ist dies heute nicht mehr der Fall.

Die massiven Fortschritte und das Interesse am Bereich der KI in der medizinischen Bildgebung werden voraussichtlich bis 2023 und darüber hinaus anhalten. Mehrere aufregende Veränderungen stehen in diesem Bereich bevor. In den kommenden Jahren wird sich der Fokus wahrscheinlich erweitern, um die Effizienz der radiologischen Arbeitsabläufe zu verbessern, bisher vernachlässigte Bildgebungsmodalitäten einzubeziehen, Daten aus verschiedenen Modalitäten zu kombinieren und konkretere Diagnosevorhersagen und Managementempfehlungen zu geben. Einfach zu bedienende und umfassende Software-Suiten, die KI nutzen, werden in die bestehenden Arbeitsabläufe in der Radiologie integriert werden und die Arbeit von Radiologen und Radiologietechnologe einfacher und effizienter machen.

Wie in jedem schnell wachsenden Bereich gibt es auch in der medizinischen Bildgebung mehrere wissenschaftliche, regulatorische und wirtschaftliche Herausforderungen für die KI. Die letzten Jahre haben uns jedoch gezeigt, dass selbst die schwierigsten Probleme gelöst werden können. Entwickler und Nutzer von KI-basierten Lösungen müssen sich dieser Probleme bewusst sein, damit sie ihre Strategien an die sich ändernden Erwartungen auf regulatorischer und gesellschaftlicher Ebene anpassen können. Auf diese Weise können sie in einem faszinierenden Bereich gedeihen, der das Potenzial hat, praktisch jeden Aspekt der Gesundheitsversorgung zu verbessern.

Referenzen  

AAMC Report Reinforces Mounting Physician Shortage. (2021). AAMC. https://www.aamc.org/news-insights/press-releases/aamc-report-reinforces-mounting-physician-shortage

A buyer’s guide to AI in health and care. (2020). NHS Transformation Directorate. https://www.nhsx.nhs.uk/ai-lab/ explore-all-resources/adopt-ai/a-buyers-guide-to-ai-in-health- and-care/

Aggarwal, R., Sounderajah, V., Martin, G., Ting, D. S. W., Karthikesalingam, A., King, D., Ashrafian, H., & Darzi, A. (2021). Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digital Medicine, 4(1), 65.

Ahmed, Z., Bhinder, K. K., Tariq, A., Tahir, M. J., Mehmood, Q., Tabassum, M. S., Malik, M., Aslam, S., Asghar, M. S., & Yousaf, Z. (2022). Knowledge, attitude, and practice of artificial intelligence among doctors and medical students in Pakistan: A cross-sectional online survey. Annals of Medicine and Surgery (2012), 76, 103493.

AI Central. (n.d.). Retrieved February 23, 2022, from https://aicentral.acrdsi.org/

AI for Radiology. (n.d.). Retrieved February 23, 2022, from https://grand-challenge.org/aiforradiology/

Alexander, A., Jiang, A., Ferreira, C., & Zurkiya, D. (2020). An Intelligent Future for Medical Imaging: A Market Outlook on Artificial Intelligence for Medical Imaging. Journal of the American College of Radiology: JACR, 17(1 Pt B), 165–170.

Allen, B., Agarwal, S., Coombs, L., Wald, C., & Dreyer, K. (2021). 2020 ACR Data Science Institute Artificial Intelligence Survey. Journal of the American College of Radiology: JACR, 18(8), 1153–1159.

Banerjee, M., Chiew, D., Patel, K. T., Johns, I., Chappell, D., Linton, N., Cole, G. D., Francis, D. P., Szram, J., Ross, J., & Zaman, S. (2021). The impact of artificial intelligence on clinical education: perceptions of postgraduate trainee doctors in London (UK) and recommendations for trainers. BMC Medical Education, 21(1), 429.

Bash, S., Johnson, B., Gibbs, W., Zhang, T., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Image Processing Enables 40% Faster Spinal MR Scans Which Match or Exceed Quality of Standard of Care : A Prospective Multicenter Multireader Study. Clinical Neuroradiology. https://doi.org/10.1007/s00062-021-01121-2

Bash, S., Wang, L., Airriess, C., Zaharchuk, G., Gong, E., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Enables 60% Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial. AJNR. American Journal of Neuroradiology, 42(12), 2130–2137.

Bennett, C. C., & Hauser, K. (2013). Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach. Artificial Intelligence in Medicine, 57(1), 9–19.

Bisdas, S., Topriceanu, C.-C., Zakrzewska, Z., Irimia, A.-V., Shakallis, L., Subhash, J., Casapu, M.-M., Leon-Rojas, J., Pinto Dos Santos, D., Andrews, D. M., Zeicu, C., Bouhuwaish, A. M., Lestari, A. N., Abu-Ismail, L. ’i, Sadiq, A. S., Khamees, A. ’atasim, Mohammed, K. M. G., Williams, E., Omran, A. I.,… Ebrahim, E. H. (2021). Artificial Intelligence in Medicine: A Multinational Multi-Center Survey on the Medical and Dental Students’ Perception. Frontiers in Public Health, 9, 795284.

Blease, C., Kharko, A., Bernstein, M., Bradley, C., Houston, M., Walsh, I., Hägglund, M., DesRoches, C., & Mandl, K. D. (2022). Machine learning in medical education: a survey of the experiences and opinions of medical students in Ireland. BMJ Health & Care Informatics, 29(1). https://doi.org/10.1136/ bmjhci-2021-100480

Brown, A. D., & Marotta, T. R. (2018). Using machine learning for sequence-level automated MRI protocol selection in neuroradiology. Journal of the American Medical Informatics Association: JAMIA, 25(5), 568–571.

Center for Devices, & Radiological Health. (2021, June 22). Digital Health Software Precertification (Pre-Cert) program.
U.S. Food and Drug Administration. https://www.fda.gov/ medical-devices/digital-health-center-excellence/digital-health- software-precertification-pre-cert-program

Clinical radiology UK workforce census 2019 report. (2019). https://www.rcr.ac.uk/publication/clinical-radiology-uk- workforce-census-2019-report

COCIR, the European Coordination Committee of the Radiological, Electromedical and Healthcare IT Industry. (2020). Market Access Pathways for Digital Health Solutions. https://www.cocir.org/fileadmin/Publications_2020/20062_COCIR_Market_Access_Pathways_Digital_Health.pdf

Collado-Mesa, F., Alvarez, E., & Arheart, K. (2018). The Role of Artificial Intelligence in Diagnostic Radiology: A Survey at a Single Radiology Residency Training Program. Journal of the American College of Radiology: JACR, 15(12), 1753–1757.

Core Health Indicators in the WHO European Region 2015. Special focus: Human resources for health. (2017, August 14). World Health Organization. https://www.euro.who.int/en/ data-and-evidence/evidence-resources/core-health-indicators- in-the-who-european-region/core-health-indicators-in-the- who-european-region-2015.-special-focus-human-resources- for-health

Dantas, L. F., Fleck, J. L., Cyrino Oliveira, F. L., & Hamacher, S. (2018). No-shows in appointment scheduling - a systematic literature review. Health Policy, 122(4), 412–421.

Esses, S. J., Lu, X., Zhao, T., Shanbhogue, K., Dane, B., Bruno, M., & Chandarana, H. (2018). Automated image quality evaluation of T2 -weighted liver MRI utilizing deep learning architecture. Journal of Magnetic Resonance Imaging: JMRI, 47(3), 723–728.

European Commission. (2021). Proposal for a Regulation Of The European Parliament And Of The Council Laying Down
Harmonised Rules On Artificial Intelligence (Artificial Intelligence Act) And Amending Certain Union Legislative Act. https://eur-lex. europa.eu/resource.html?uri=cellar:e0649735-a372-11eb- 9585-01aa75ed71a1.0001.02/DOC_1&format=PDF

General Data Protection Regulation (GDPR) – Official Legal Text. (2016, July 13). General Data Protection Regulation (GDPR). https://gdpr-info.eu/

Hata, A., Yanagawa, M., Yoshida, Y., Miyata, T., Tsubamoto, M., Honda, O., & Tomiyama, N. (2020). Combination of Deep Learning-Based Denoising and Iterative Reconstruction for Ultra-Low-Dose CT of the Chest: Image Quality and Lung-RADS Evaluation. AJR. American Journal of Roentgenology, 215(6), 1321–1328.

Hauptmann, A., Arridge, S., Lucka, F., Muthurangu, V., & Steeden, J. A. (2019). Real-time cardiovascular MR with
spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magnetic Resonance in Medicine: Official Journal of the Society of Magnetic Resonance in Medicine / Society of Magnetic Resonance in Medicine, 81(2), 1143–1156.

Higaki, T., Nakamura, Y., Zhou, J., Yu, Z., Nemoto, T., Tatsugami, F., & Awai, K. (2020). Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics. Academic Radiology, 27(1), 82–87.

Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B. (2017). What do we need to build explainable AI systems for the medical domain? In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/1712.09923

Hötker, A. M., Da Mutten, R., Tiessen, A., Konukoglu, E., & Donati, O. F. (2021). Improving workflow in prostate MRI: AI- based decision-making on biparametric or multiparametric MRI. Insights into Imaging, 12(1), 112.

Huang, S.-C., Pareek, A., Seyyedi, S., Banerjee, I., & Lungren, M. P. (2020). Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digital Medicine, 3, 136.

Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2(6), 305–311.

Kaissis, G., Ziller, A., Passerat-Palmbach, J., Ryffel, T., Usynin, D., Trask, A., Lima, I., Mancuso, J., Jungmann, F., Steinborn, M.-M., Saleh, A., Makowski, M., Rueckert, D., & Braren, R. (2021). End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nature Machine Intelligence, 3(6), 473–484.

Kansal, R., Bawa, A., Bansal, A., Trehan, S., Goyal, K., Goyal, N., & Malhotra, K. (2022). Differences in Knowledge and Perspectives on the Usage of Artificial Intelligence Among Doctors and Medical Students of a Developing Country: A Cross- Sectional Study. Cureus, 14(1), e21434.

Katsari, K., Penna, D., Arena, V., Polverari, G., Ianniello, A., Italiano, D., Milani, R., Roncacci, A., Illing, R. O., & Pelosi, E. (2021). Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment. EJNMMI Physics, 8(1), 25.

Kerpel, A., Marom, E. M., Green, M., Eifer, M., Konen, E., Mayer, A., & Betancourt Cuellar, S. L. (2021). Ultra-Low Dose Chest CT with Denoising for Lung Nodule Detection. The Israel Medical Association Journal: IMAJ, 23(9), 550–555.

Kim, D. W., Jang, H. Y., Kim, K. W., Shin, Y., & Park, S. H. (2019).
Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of
Medical Images: Results from Recently Published Papers. Korean Journal of Radiology: Official Journal of the Korean Radiological Society, 20(3), 405–410.

Kim, K. H., & Park, S.-H. (2017). Artificial neural network for suppression of banding artifacts in balanced steady-state free precession MRI. Magnetic Resonance Imaging, 37, 139–146.

Kolyshkina, I., & Simoff, S. (2021). Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach. Frontiers in Big Data, 4, 660206.

Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C., & Faisal, A. A. (2018). The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nature Medicine, 24(11), 1716–1720.

Kritikos, M. (2020). What if artificial intelligence in medical imaging could accelerate Covid-19 treatment? Think Tank
- European Parliament. https://www.europarl.europa.eu/ thinktank/en/document/EPRS_ATA(2020)656333

Kurasawa, H., Hayashi, K., Fujino, A., Takasugi, K., Haga, T., Waki, K., Noguchi, T., & Ohe, K. (2016). Machine-Learning- Based Prediction of a Missed Scheduled Clinical Appointment by Patients With Diabetes. Journal of Diabetes Science and Technology, 10(3), 730–736.

Larrazabal, A. J., Nieto, N., Peterson, V., Milone, D. H., & Ferrante, E. (2020). Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proceedings of the National Academy of Sciences of the United States of America, 117(23), 12592–12594.

Larson, D. B., Johnson, L. W., Schnell, B. M., Salisbury, S. R., & Forman, H. P. (2011). National trends in CT use in the emergency department: 1995-2007. Radiology, 258(1), 164–173.

Le, V., Frye, S., Botkin, C., Christopher, K., Gulaka, P., Sterkel, B., Frye, R., Muzaffar, R., & Osman, M. (2020). Effect of PET Scan with Count Reduction Using AI-Based Processing Techniques on Image Quality. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 3095–3095.

Levin, D. C., Parker, L., & Rao, V. M. (2017). Recent Trends in Imaging Use in Hospital Settings: Implications for Future Planning. Journal of the American College of Radiology: JACR, 14(3), 331–336.

Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., Mahendiran, T., Moraes, G., Shamdas, M., Kern, C., Ledsam, J. R., Schmid, M. K., Balaskas, K., Topol, E.J., Bachmann, L. M., Keane, P. A., & Denniston, A. K. (2019). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet. Digital Health, 1(6), e271–e297.

Lotan, E., Tschider, C., Sodickson, D. K., Caplan, A. L., Bruno, M., Zhang, B., & Lui, Y. W. (2020). Medical Imaging and Privacy in the Era of Artificial Intelligence: Myth, Fallacy, and the Future. Journal of the American College of Radiology: JACR, 17(9), 1159–1162.

Mairhöfer, D., Laufer, M., Simon, P. M., Sieren, M., Bischof, A., Käster, T., Barth, E., Barkhausen, J., & Martinetz, T. (2021). An AI-based Framework for Diagnostic Quality Assessment of Ankle Radiographs. https://openreview.net/pdf?id=bj04hJss_xZ

Makeeva, V., Gichoya, J., Hawkins, C. M., Towbin, A. J., Heilbrun, M., & Prater, A. (2019). The Application of Machine Learning to Quality Improvement Through the Lens of the Radiology Value Network. Journal of the American College of Radiology: JACR, 16(9 Pt B), 1254–1258.

McLeavy, C. M., Chunara, M. H., Gravell, R. J., Rauf, A., Cushnie, A., Staley Talbot, C., & Hawkins, R. M. (2021). The future of CT: deep learning reconstruction. Clinical Radiology, 76(6), 407–415.

Medical AI Evaluation. (n.d.). Retrieved February 23, 2022, from https://ericwu09.github.io/medical-ai-evaluation/

Michoud, L., Tschudi, Y., & Villien, Y. (2019). Artificial Intelligence for Medical Imaging: Market and Technology Report 2020. Yole Développement. https://s3.i-micronews.com/ uploads/2020/01/YDR20059-AI-for-Medical-Imaging_Yole_ sample.pdf

Murdoch, B. (2021). Privacy and artificial intelligence: challenges for protecting health information in a new era. BMC Medical Ethics, 22(1), 122.

Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020). Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ, 368. https://doi.org/10.1136/bmj.m689

Nelson, A., Herron, D., Rees, G., & Nachev, P. (2019). Predicting scheduled hospital attendance with artificial intelligence. Npj Digital Medicine, 2(1), 26.

Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.

Ooi, S. K. G., Makmur, A., Soon, A. Y. Q., Fook-Chong, S., Liew, C., Sia, S. Y., Ting, Y. H., & Lim, C. Y. (2021). Attitudes toward artificial intelligence in radiology with learner needs assessment within radiology residency programmes: a national multi-programme survey. Singapore Medical Journal, 62(3), 126–134.

Paranjape, K., Schinkel, M., Nannan Panday, R., Car, J., & Nanayakkara, P. (2019). Introducing Artificial Intelligence Training in Medical Education. JMIR Medical Education, 5(2), e16048.

Park, J., Hwang, D., Kim, K. Y., Kang, S. K., Kim, Y. K., & Lee, J. S. (2018). Computed tomography super-resolution using deep convolutional neural network. Physics in Medicine and Biology, 63(14), 145011.

Pinto Dos Santos, D., Giese, D., Brodehl, S., Chon, S. H., Staab, W., Kleinert, R., Maintz, D., & Baeßler, B. (2019). Medical students’ attitude towards artificial intelligence: a multicentre survey. European Radiology, 29(4), 1640–1646.

Population ages 65 and above. (n.d.). The World Bank. Retrieved February 23, 2022, from https://data.worldbank.org/ indicator/SP.POP.65UP.TO.ZS

Prevedello, L. M., Erdal, B. S., Ryu, J. L., Little, K. J., Demirer, M., Qian, S., & White, R. D. (2017). Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging. Radiology, 285(3), 923–931.

Rezazade Mehrizi, M. H., van Ooijen, P., & Homan, M. (2021). Applications of artificial intelligence (AI) in diagnostic radiology: a technography study. European Radiology, 31(4), 1805–1811.

Rockenbach, M. A. B. (2021, June 13). Multimodal AI in healthcare: Closing the gaps. CodeX. https://medium.com/codex/ multimodal-ai-in-healthcare-1f5152e83be2

Rudie, J. D., Gleason, T., Barkovich, M. J., Wilson, D. M., Shankaranarayanan, A., Zhang, T., Wang, L., Gong, E., Zaharchuk, G., & Villanueva-Meyer, J. E. (2022). Clinical Assessment of Deep Learning–based Super-Resolution for 3D Volumetric Brain MRI. Radiology: Artificial Intelligence, e210059.

Schreiber-Zinaman, J., & Rosenkrantz, A. B. (2017). Frequency and reasons for extra sequences in clinical abdominal MRI examinations. Abdominal Radiology (New York), 42(1), 306–311.

Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y., & Ghassemi, M. (2021). Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nature Medicine, 27(12), 2176–2182.

Shelmerdine, S. C., Arthurs, O. J., Denniston, A., & Sebire, N. J. (2021). Review of study reporting guidelines for clinical studies using artificial intelligence in healthcare. BMJ Health & Care Informatics, 28(1). https://doi.org/10.1136/ bmjhci-2021-100385

Shinagare, A. B., Ip, I. K., Abbett, S. K., Hanson, R., Seltzer, S. E., & Khorasani, R. (2014). Inpatient imaging utilization: trends of the past decade. AJR. American Journal of Roentgenology, 202(3), W277–W283.

Singh, R., Digumarthy, S. R., Muse, V. V., Kambadakone, A. R., Blake, M. A., Tabari, A., Hoi, Y., Akino, N., Angel, E., Madan, R., & Kalra, M. K. (2020). Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT. AJR. American Journal of Roentgenology, 214(3), 566–573.

Sit, C., Srinivasan, R., Amlani, A., Muthuswamy, K., Azam, A., Monzon, L., & Poon, D. S. (2020). Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: a multicentre survey. Insights into Imaging, 11(1), 14.

Smith-Bindman, R., Miglioretti, D. L., Johnson, E., Lee, C., Feigelson, H. S., Flynn, M., Greenlee, R. T., Kruger, R. L., Hornbrook, M. C., Roblin, D., Solberg, L. I., Vanneman, N., Weinmann, S., & Williams, A. E. (2012). Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996-2010. JAMA: The Journal of the American Medical Association, 307(22), 2400–2409.

Smith-Bindman, R., Miglioretti, D. L., & Larson, E. B. (2008). Rising use of diagnostic medical imaging in a large integrated health system. Health Affairs, 27(6), 1491–1502.

The Medical Futurist. (n.d.). The Medical Futurist. Retrieved February 23, 2022, from https://medicalfuturist.com/fda- approved-ai-based-algorithms/

Towards trustable machine learning. (2018). Nature Biomedical Engineering, 2(10), 709–710.

Trivedi, H., Mesterhazy, J., Laguna, B., Vu, T., & Sohn, J. H. (2018). Automatic Determination of the Need for Intravenous Contrast in Musculoskeletal MRI Examinations Using IBM Watson’s Natural Language Processing Algorithm. Journal of Digital Imaging, 31(2), 245–251.

Tsao, D. N. (2020, July 27). AI in medical diagnostics 2020- 2030: Image recognition, players, clinical applications, forecasts: IDTechEx. https://www.idtechex.com/en/research- report/ai-in-medical-diagnostics-2020-2030-image- recognition-players-clinical-applications-forecasts/766

van Duffelen, J. (2021, February 22). Making a case for buying medical imaging AI: How to define the return on investment.
Aidence. https://www.aidence.com/articles/medical-imaging- ai-roi/

van Leeuwen, K. G., Schalekamp, S., Rutten, M. J. C. M., van Ginneken, B., & de Rooij, M. (2021). Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. European Radiology, 31(6), 3797–3804.

Vokinger, K. N., Feuerriegel, S., & Kesselheim, A. S. (2021). Mitigating bias in machine learning for medicine. Communication & Medicine, 1, 25.

Wang, S., Cao, G., Wang, Y., Liao, S., Wang, Q., Shi, J., Li, C., & Shen, D. (2021). Review and Prospect: Artificial Intelligence in Advanced Medical Imaging. Frontiers in Radiology, 1. https://doi. org/10.3389/fradi.2021.781868

What is personal data? (2021, January 1). ICO - Information Commissioner’s Office; ICO. https://ico.org.uk/for-organisations/ guide-to-data-protection/guide-to-the-general-data-protection- regulation-gdpr/what-is-personal-data/what-is-personal-data

WHO. (n.d.-a). Ageing and health. Retrieved February 23, 2022, from https://www.who.int/news-room/fact-sheets/detail/ ageing-and-health

WHO. (n.d.-b). Noncommunicable diseases. Retrieved March 6, 2022, from https://www.who.int/news-room/fact-sheets/detail/ noncommunicable-diseases

Winder, M., Owczarek, A. J., Chudek, J., Pilch-Kowalczyk, J., & Baron, J. (2021). Are We Overdoing It? Changes in Diagnostic Imaging Workload during the Years 2010-2020 including the Impact of the SARS-CoV-2 Pandemic. Healthcare (Basel, Switzerland), 9(11). https://doi.org/10.3390/healthcare9111557

Winkel, D. J., Heye, T., Weikert, T. J., Boll, D. T., & Stieltjes, B. (2019). Evaluation of an AI-Based Detection Software for Acute Findings in Abdominal Computed Tomography Scans: Toward an Automated Work List Prioritization of Routine CT Examinations. Investigative Radiology, 54(1), 55–59.

Wong, T. T., Kazam, J. K., & Rasiej, M. J. (2019). Effect of Analytics-Driven Worklists on Musculoskeletal MRI
Interpretation Times in an Academic Setting. AJR. American Journal of Roentgenology, 1–5.

Xu, F., Pan, B., Zhu, X., Gulaka, P., Xiang, L., Gong, E., Zhang, T., Wang, J., Lin, L., Ma, Y., & Gong, N.-J. (2020). Evaluation of Deep Learning Based PET Image Enhancement Method in Diagnosis of Lymphoma. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 431–431.

Yoon, C. H., Torrance, R., & Scheinerman, N. (2021). Machine learning in medicine: should the pursuit of enhanced interpretability be abandoned? Journal of Medical Ethics. https://doi.org/10.1136/medethics-2020-107102

Yusuf, M., Atal, I., Li, J., Smith, P., Ravaud, P., Fergie, M., Callaghan, M., & Selfe, J. (2020). Reporting quality of studies using machine learning models for medical diagnosis: a systematic review. BMJ Open, 10(3), e034568.

Zhang, D., Mishra, S., Brynjolfsson, E., Etchemendy, J., Ganguli, D., Grosz, B., Lyons, T., Manyika, J., Niebles, J. C., Sellitto, M., Shoham, Y., Clark, J., & Perrault, R. (2021). The AI Index 2021 Annual Report. In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/2103.06312

Zhang, Y., & Yu, H. (2018). Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography. IEEE Transactions on Medical Imaging, 37(6), 1370–1381.

Zhu, B., Liu, J. Z., Cauley, S. F., Rosen, B. R., & Rosen, M. S. (2018). Image reconstruction by domain-transform manifold learning. Nature, 555(7697), 487–492.

References 

AAMC Report Reinforces Mounting Physician Shortage. (2021). AAMC. https://www.aamc.org/news-insights/press- releases/aamc-report-reinforces-mounting-physician-shortage

A buyer’s guide to AI in health and care. (2020). NHS Transformation Directorate. https://www.nhsx.nhs.uk/ai-lab/ explore-all-resources/adopt-ai/a-buyers-guide-to-ai-in-health- and-care/

Aggarwal, R., Sounderajah, V., Martin, G., Ting, D. S. W., Karthikesalingam, A., King, D., Ashrafian, H., & Darzi, A. (2021). Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digital Medicine, 4(1), 65.

Ahmed, Z., Bhinder, K. K., Tariq, A., Tahir, M. J., Mehmood, Q., Tabassum, M. S., Malik, M., Aslam, S., Asghar, M. S., & Yousaf, Z. (2022). Knowledge, attitude, and practice of artificial intelligence among doctors and medical students in Pakistan: A cross-sectional online survey. Annals of Medicine and Surgery (2012), 76, 103493.

AI Central. (n.d.). Retrieved February 23, 2022, from https://aicentral.acrdsi.org/

AI for Radiology. (n.d.). Retrieved February 23, 2022, from https://grand-challenge.org/aiforradiology/

Alexander, A., Jiang, A., Ferreira, C., & Zurkiya, D. (2020). An Intelligent Future for Medical Imaging: A Market Outlook on Artificial Intelligence for Medical Imaging. Journal of the American College of Radiology: JACR, 17(1 Pt B), 165–170.

Allen, B., Agarwal, S., Coombs, L., Wald, C., & Dreyer, K. (2021). 2020 ACR Data Science Institute Artificial Intelligence Survey. Journal of the American College of Radiology: JACR, 18(8), 1153–1159.

Banerjee, M., Chiew, D., Patel, K. T., Johns, I., Chappell, D., Linton, N., Cole, G. D., Francis, D. P., Szram, J., Ross, J., & Zaman, S. (2021). The impact of artificial intelligence on clinical education: perceptions of postgraduate trainee doctors in London (UK) and recommendations for trainers. BMC Medical Education, 21(1), 429.

Bash, S., Johnson, B., Gibbs, W., Zhang, T., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Image Processing Enables 40 % Faster Spinal MR Scans Which Match or Exceed Quality of Standard of Care : A Prospective Multicenter Multireader Study. Clinical Neuroradiology. https://doi.org/10.1007/s00062-021-01121-2

Bash, S., Wang, L., Airriess, C., Zaharchuk, G., Gong, E., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Enables 60 % Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial. AJNR. American Journal of Neuroradiology, 42(12), 2130–2137.

Bennett, C. C., & Hauser, K. (2013). Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach. Artificial Intelligence in Medicine, 57(1), 9–19.

Bisdas, S., Topriceanu, C.-C., Zakrzewska, Z., Irimia, A.-V., Shakallis, L., Subhash, J., Casapu, M.-M., Leon-Rojas, J., Pinto Dos Santos, D., Andrews, D. M., Zeicu, C., Bouhuwaish, A. M., Lestari, A. N., Abu-Ismail, L. ’i, Sadiq, A. S., Khamees, A. ’atasim, Mohammed, K. M. G., Williams, E., Omran, A. I.,… Ebrahim, E. H. (2021). Artificial Intelligence in Medicine: A Multinational Multi-Center Survey on the Medical and Dental Students’ Perception. Frontiers in Public Health, 9, 795284.

Blease, C., Kharko, A., Bernstein, M., Bradley, C., Houston, M., Walsh, I., Hägglund, M., DesRoches, C., & Mandl, K. D. (2022). Machine learning in medical education: a survey of the experiences and opinions of medical students in Ireland. BMJ Health & Care Informatics, 29(1). https://doi.org/10.1136/ bmjhci-2021-100480

Brown, A. D., & Marotta, T. R. (2018). Using machine learning for sequence-level automated MRI protocol selection in neuroradiology. Journal of the American Medical Informatics Association: JAMIA, 25(5), 568–571.

Center for Devices, & Radiological Health. (2021, June 22). Digital Health Software Precertification (Pre-Cert) program.
U.S. Food and Drug Administration. https://www.fda.gov/ medical-devices/digital-health-center-excellence/digital-health- software-precertification-pre-cert-program

Clinical radiology UK workforce census 2019 report. (2019). https://www.rcr.ac.uk/publication/clinical-radiology-uk- workforce-census-2019-report

COCIR, the European Coordination Committee of the Radiological, Electromedical and Healthcare IT Industry. (2020). Market Access Pathways for Digital Health Solutions. https://www.cocir.org/fileadmin/Publications_2020/20062_ COCIR_Market_Access_Pathways_Digital_Health.pdf

Collado-Mesa, F., Alvarez, E., & Arheart, K. (2018). The Role of Artificial Intelligence in Diagnostic Radiology: A Survey at a Single Radiology Residency Training Program. Journal of the American College of Radiology: JACR, 15(12), 1753–1757.

Core Health Indicators in the WHO European Region 2015. Special focus: Human resources for health. (2017, August 14). World Health Organization. https://www.euro.who.int/en/ data-and-evidence/evidence-resources/core-health-indicators- in-the-who-european-region/core-health-indicators-in-the- who-european-region-2015.-special-focus-human-resources- for-health

Dantas, L. F., Fleck, J. L., Cyrino Oliveira, F. L., & Hamacher, S. (2018). No-shows in appointment scheduling - a systematic literature review. Health Policy, 122(4), 412–421.

Esses, S. J., Lu, X., Zhao, T., Shanbhogue, K., Dane, B., Bruno, M., & Chandarana, H. (2018). Automated image quality evaluation of T2 -weighted liver MRI utilizing deep learning architecture. Journal of Magnetic Resonance Imaging: JMRI, 47(3), 723–728.

European Commission. (2021). Proposal for a Regulation Of The European Parliament And Of The Council Laying Down
Harmonised Rules On Artificial Intelligence (Artificial Intelligence Act) And Amending Certain Union Legislative Act.
https://eur-lex. europa.eu/resource.html?uri=cellar:e0649735-a372-11eb- 9585-01aa75ed71a1.0001.02/DOC_1&format=PDF

General Data Protection Regulation (GDPR) – Official Legal Text. (2016, July 13). General Data Protection Regulation (GDPR). https://gdpr-info.eu/

Hata, A., Yanagawa, M., Yoshida, Y., Miyata, T., Tsubamoto, M., Honda, O., & Tomiyama, N. (2020). Combination of Deep Learning-Based Denoising and Iterative Reconstruction for Ultra-Low-Dose CT of the Chest: Image Quality and Lung-RADS Evaluation. AJR. American Journal of Roentgenology, 215(6), 1321–1328.

Hauptmann, A., Arridge, S., Lucka, F., Muthurangu, V., & Steeden, J. A. (2019). Real-time cardiovascular MR with
spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magnetic Resonance in Medicine: Official Journal of the Society of Magnetic Resonance in Medicine / Society of Magnetic Resonance in Medicine, 81(2), 1143–1156.

Higaki, T., Nakamura, Y., Zhou, J., Yu, Z., Nemoto, T., Tatsugami, F., & Awai, K. (2020). Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics. Academic Radiology, 27(1), 82–87.

Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B. (2017). What do we need to build explainable AI systems for the medical domain? In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/1712.09923

Hötker, A. M., Da Mutten, R., Tiessen, A., Konukoglu, E., & Donati, O. F. (2021). Improving workflow in prostate MRI: AI- based decision-making on biparametric or multiparametric MRI. Insights into Imaging, 12(1), 112.

Huang, S.-C., Pareek, A., Seyyedi, S., Banerjee, I., & Lungren, M. P. (2020). Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digital Medicine, 3, 136.

Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2(6), 305–311.

Kaissis, G., Ziller, A., Passerat-Palmbach, J., Ryffel, T., Usynin, D., Trask, A., Lima, I., Mancuso, J., Jungmann, F., Steinborn, M.-M., Saleh, A., Makowski, M., Rueckert, D., & Braren, R. (2021). End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nature Machine Intelligence, 3(6), 473–484.

Kansal, R., Bawa, A., Bansal, A., Trehan, S., Goyal, K., Goyal, N., & Malhotra, K. (2022). Differences in Knowledge and Perspectives on the Usage of Artificial Intelligence Among Doctors and Medical Students of a Developing Country: A Cross- Sectional Study. Cureus, 14(1), e21434.

Katsari, K., Penna, D., Arena, V., Polverari, G., Ianniello, A., Italiano, D., Milani, R., Roncacci, A., Illing, R. O., & Pelosi, E. (2021). Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment. EJNMMI Physics, 8(1), 25.

Kerpel, A., Marom, E. M., Green, M., Eifer, M., Konen, E., Mayer, A., & Betancourt Cuellar, S. L. (2021). Ultra-Low Dose Chest CT with Denoising for Lung Nodule Detection. The Israel Medical Association Journal: IMAJ, 23(9), 550–555.

Kim, D. W., Jang, H. Y., Kim, K. W., Shin, Y., & Park, S. H. (2019).
Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of
Medical Images: Results from Recently Published Papers. Korean Journal of Radiology: Official Journal of the Korean Radiological Society, 20(3), 405–410.

Kim, K. H., & Park, S.-H. (2017). Artificial neural network for suppression of banding artifacts in balanced steady-state free precession MRI. Magnetic Resonance Imaging, 37, 139–146.

Kolyshkina, I., & Simoff, S. (2021). Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach. Frontiers in Big Data, 4, 660206.

Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C., & Faisal, A. A. (2018). The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nature Medicine, 24(11), 1716–1720.

Kritikos, M. (2020). What if artificial intelligence in medical imaging could accelerate Covid-19 treatment? Think Tank
- European Parliament. https://www.europarl.europa.eu/ thinktank/en/document/EPRS_ATA(2020)656333

Kurasawa, H., Hayashi, K., Fujino, A., Takasugi, K., Haga, T., Waki, K., Noguchi, T., & Ohe, K. (2016). Machine-Learning- Based Prediction of a Missed Scheduled Clinical Appointment by Patients With Diabetes. Journal of Diabetes Science and Technology, 10(3), 730–736.

Larrazabal, A. J., Nieto, N., Peterson, V., Milone, D. H., & Ferrante, E. (2020). Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proceedings of the National Academy of Sciences of the United States of America, 117(23), 12592–12594.

Larson, D. B., Johnson, L. W., Schnell, B. M., Salisbury, S. R., & Forman, H. P. (2011). National trends in CT use in the emergency department: 1995-2007. Radiology, 258(1), 164–173.

Le, V., Frye, S., Botkin, C., Christopher, K., Gulaka, P., Sterkel, B., Frye, R., Muzaffar, R., & Osman, M. (2020). Effect of PET Scan with Count Reduction Using AI-Based Processing Techniques on Image Quality. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 3095–3095.

Levin, D. C., Parker, L., & Rao, V. M. (2017). Recent Trends in Imaging Use in Hospital Settings: Implications for Future Planning. Journal of the American College of Radiology: JACR, 14(3), 331–336.

Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., Mahendiran, T., Moraes, G., Shamdas, M., Kern, C., Ledsam, J. R., Schmid, M. K., Balaskas, K., Topol, E.J., Bachmann, L. M., Keane, P. A., & Denniston, A. K. (2019). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet. Digital Health, 1(6), e271–e297.

Lotan, E., Tschider, C., Sodickson, D. K., Caplan, A. L., Bruno, M., Zhang, B., & Lui, Y. W. (2020). Medical Imaging and Privacy in the Era of Artificial Intelligence: Myth, Fallacy, and the Future. Journal of the American College of Radiology: JACR, 17(9), 1159–1162.

Mairhöfer, D., Laufer, M., Simon, P. M., Sieren, M., Bischof, A., Käster, T., Barth, E., Barkhausen, J., & Martinetz, T. (2021). An AI-based Framework for Diagnostic Quality Assessment of Ankle Radiographs. https://openreview.net/pdf?id=bj04hJss_xZ

Makeeva, V., Gichoya, J., Hawkins, C. M., Towbin, A. J., Heilbrun, M., & Prater, A. (2019). The Application of Machine Learning to Quality Improvement Through the Lens of the Radiology Value Network. Journal of the American College of Radiology: JACR, 16(9 Pt B), 1254–1258.

McLeavy, C. M., Chunara, M. H., Gravell, R. J., Rauf, A., Cushnie, A., Staley Talbot, C., & Hawkins, R. M. (2021). The future of CT: deep learning reconstruction. Clinical Radiology, 76(6), 407–415.

Medical AI Evaluation. (n.d.). Retrieved February 23, 2022, from https://ericwu09.github.io/medical-ai-evaluation/

Michoud, L., Tschudi, Y., & Villien, Y. (2019). Artificial Intelligence for Medical Imaging: Market and Technology Report 2020. Yole Développement. https://s3.i-micronews.com/ uploads/2020/01/YDR20059-AI-for-Medical-Imaging_Yole_ sample.pdf

Murdoch, B. (2021). Privacy and artificial intelligence: challenges for protecting health information in a new era. BMC Medical Ethics, 22(1), 122.

Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020). Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ, 368. https://doi.org/10.1136/bmj.m689

Nelson, A., Herron, D., Rees, G., & Nachev, P. (2019). Predicting scheduled hospital attendance with artificial intelligence. Npj Digital Medicine, 2(1), 26.

Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.

Ooi, S. K. G., Makmur, A., Soon, A. Y. Q., Fook-Chong, S., Liew, C., Sia, S. Y., Ting, Y. H., & Lim, C. Y. (2021). Attitudes toward artificial intelligence in radiology with learner needs assessment within radiology residency programmes: a national multi-programme survey. Singapore Medical Journal, 62(3), 126–134.

Paranjape, K., Schinkel, M., Nannan Panday, R., Car, J., & Nanayakkara, P. (2019). Introducing Artificial Intelligence Training in Medical Education. JMIR Medical Education, 5(2), e16048.

Park, J., Hwang, D., Kim, K. Y., Kang, S. K., Kim, Y. K., & Lee, J. S. (2018). Computed tomography super-resolution using deep convolutional neural network. Physics in Medicine and Biology, 63(14), 145011.

Pinto Dos Santos, D., Giese, D., Brodehl, S., Chon, S. H., Staab, W., Kleinert, R., Maintz, D., & Baeßler, B. (2019). Medical students’ attitude towards artificial intelligence: a multicentre survey. European Radiology, 29(4), 1640–1646.

Population ages 65 and above. (n.d.). The World Bank. Retrieved February 23, 2022, from https://data.worldbank.org/ indicator/SP.POP.65UP.TO.ZS

Prevedello, L. M., Erdal, B. S., Ryu, J. L., Little, K. J., Demirer, M., Qian, S., & White, R. D. (2017). Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging. Radiology, 285(3), 923–931.

Rezazade Mehrizi, M. H., van Ooijen, P., & Homan, M. (2021). Applications of artificial intelligence (AI) in diagnostic radiology: a technography study. European Radiology, 31(4), 1805–1811.

Rockenbach, M. A. B. (2021, June 13). Multimodal AI in healthcare: Closing the gaps. CodeX. https://medium.com/codex/ multimodal-ai-in-healthcare-1f5152e83be2

Rudie, J. D., Gleason, T., Barkovich, M. J., Wilson, D. M., Shankaranarayanan, A., Zhang, T., Wang, L., Gong, E., Zaharchuk, G., & Villanueva-Meyer, J. E. (2022). Clinical Assessment of Deep Learning–based Super-Resolution for 3D Volumetric Brain MRI. Radiology: Artificial Intelligence, e210059.

Schreiber-Zinaman, J., & Rosenkrantz, A. B. (2017). Frequency and reasons for extra sequences in clinical abdominal MRI examinations. Abdominal Radiology (New York), 42(1), 306–311.

Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y., & Ghassemi, M. (2021). Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nature Medicine, 27(12), 2176–2182.

Shelmerdine, S. C., Arthurs, O. J., Denniston, A., & Sebire, N. J. (2021). Review of study reporting guidelines for clinical studies using artificial intelligence in healthcare. BMJ Health & Care Informatics, 28(1). https://doi.org/10.1136/ bmjhci-2021-100385

Shinagare, A. B., Ip, I. K., Abbett, S. K., Hanson, R., Seltzer, S. E., & Khorasani, R. (2014). Inpatient imaging utilization: trends of the past decade. AJR. American Journal of Roentgenology, 202(3), W277–W283.

Singh, R., Digumarthy, S. R., Muse, V. V., Kambadakone, A. R., Blake, M. A., Tabari, A., Hoi, Y., Akino, N., Angel, E., Madan, R., & Kalra, M. K. (2020). Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT. AJR. American Journal of Roentgenology, 214(3), 566–573.

Sit, C., Srinivasan, R., Amlani, A., Muthuswamy, K., Azam, A., Monzon, L., & Poon, D. S. (2020). Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: a multicentre survey. Insights into Imaging, 11(1), 14.

Smith-Bindman, R., Miglioretti, D. L., Johnson, E., Lee, C., Feigelson, H. S., Flynn, M., Greenlee, R. T., Kruger, R. L., Hornbrook, M. C., Roblin, D., Solberg, L. I., Vanneman, N., Weinmann, S., & Williams, A. E. (2012). Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996-2010. JAMA: The Journal of the American Medical Association, 307(22), 2400–2409.

Smith-Bindman, R., Miglioretti, D. L., & Larson, E. B. (2008). Rising use of diagnostic medical imaging in a large integrated health system. Health Affairs, 27(6), 1491–1502.

The Medical Futurist. (n.d.). The Medical Futurist. Retrieved February 23, 2022, from https://medicalfuturist.com/fda- approved-ai-based-algorithms/

Towards trustable machine learning. (2018). Nature Biomedical Engineering, 2(10), 709–710.

Trivedi, H., Mesterhazy, J., Laguna, B., Vu, T., & Sohn, J. H. (2018). Automatic Determination of the Need for Intravenous Contrast in Musculoskeletal MRI Examinations Using IBM Watson’s Natural Language Processing Algorithm. Journal of Digital Imaging, 31(2), 245–251.

Tsao, D. N. (2020, July 27). AI in medical diagnostics 2020- 2030: Image recognition, players, clinical applications, forecasts: IDTechEx. https://www.idtechex.com/en/research- report/ai-in-medical-diagnostics-2020-2030-image- recognition-players-clinical-applications-forecasts/766

van Duffelen, J. (2021, February 22). Making a case for buying medical imaging AI: How to define the return on investment.
Aidence. https://www.aidence.com/articles/medical-imaging- ai-roi/

van Leeuwen, K. G., Schalekamp, S., Rutten, M. J. C. M., van Ginneken, B., & de Rooij, M. (2021). Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. European Radiology, 31(6), 3797–3804.

Vokinger, K. N., Feuerriegel, S., & Kesselheim, A. S. (2021). Mitigating bias in machine learning for medicine. Communication & Medicine, 1, 25.

Wang, S., Cao, G., Wang, Y., Liao, S., Wang, Q., Shi, J., Li, C., & Shen, D. (2021). Review and Prospect: Artificial Intelligence in Advanced Medical Imaging. Frontiers in Radiology, 1. https://doi. org/10.3389/fradi.2021.781868

What is personal data? (2021, January 1). ICO - Information Commissioner’s Office; ICO. https://ico.org.uk/for-organisations/ guide-to-data-protection/guide-to-the-general-data-protection- regulation-gdpr/what-is-personal-data/what-is-personal-data

WHO. (n.d.-a). Ageing and health. Retrieved February 23, 2022, from https://www.who.int/news-room/fact-sheets/detail/ ageing-and-health

WHO. (n.d.-b). Noncommunicable diseases. Retrieved March 6, 2022, from https://www.who.int/news-room/fact-sheets/detail/ noncommunicable-diseases

Winder, M., Owczarek, A. J., Chudek, J., Pilch-Kowalczyk, J., & Baron, J. (2021). Are We Overdoing It? Changes in Diagnostic Imaging Workload during the Years 2010-2020 including the Impact of the SARS-CoV-2 Pandemic. Healthcare (Basel, Switzerland), 9(11). https://doi.org/10.3390/healthcare9111557

Winkel, D. J., Heye, T., Weikert, T. J., Boll, D. T., & Stieltjes, B. (2019). Evaluation of an AI-Based Detection Software for Acute Findings in Abdominal Computed Tomography Scans: Toward an Automated Work List Prioritization of Routine CT Examinations. Investigative Radiology, 54(1), 55–59.

Wong, T. T., Kazam, J. K., & Rasiej, M. J. (2019). Effect of Analytics-Driven Worklists on Musculoskeletal MRI
Interpretation Times in an Academic Setting. AJR. American Journal of Roentgenology, 1–5.

Xu, F., Pan, B., Zhu, X., Gulaka, P., Xiang, L., Gong, E., Zhang, T., Wang, J., Lin, L., Ma, Y., & Gong, N.-J. (2020). Evaluation of Deep Learning Based PET Image Enhancement Method in Diagnosis of Lymphoma. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 431–431.

Yoon, C. H., Torrance, R., & Scheinerman, N. (2021). Machine learning in medicine: should the pursuit of enhanced interpretability be abandoned? Journal of Medical Ethics. https://doi.org/10.1136/medethics-2020-107102

Yusuf, M., Atal, I., Li, J., Smith, P., Ravaud, P., Fergie, M., Callaghan, M., & Selfe, J. (2020). Reporting quality of studies using machine learning models for medical diagnosis: a systematic review. BMJ Open, 10(3), e034568.

Zhang, D., Mishra, S., Brynjolfsson, E., Etchemendy, J., Ganguli, D., Grosz, B., Lyons, T., Manyika, J., Niebles, J. C., Sellitto, M., Shoham, Y., Clark, J., & Perrault, R. (2021). The AI Index 2021 Annual Report. In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/2103.06312

Zhang, Y., & Yu, H. (2018). Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography. IEEE Transactions on Medical Imaging, 37(6), 1370–1381.

Zhu, B., Liu, J. Z., Cauley, S. F., Rosen, B. R., & Rosen, M. S. (2018). Image reconstruction by domain-transform manifold learning. Nature, 555(7697), 487–492.

Artificial Intelligence in medical imaging: What, How and Why?

    Artificial intelligence (AI) is a field that enables computer systems to solve problems by adapting to changing circumstances, often by mimicking human reasoning and judgement. Several demographic and healthcare trends are driving the use of AI in medical imaging. The amount of medical imaging data being acquired is steadily increasing (Larson et al., 2011; Smith-Bindman et al., 2008, 2012; Winder et al., 2021). There is also a widespread shortage of healthcare workers (Core Health Indicators in the WHO European Region 2015. Special Focus: Human Resources for Health, 2017) with an ever-increasing workload (Levin et al., 2017), and the number of medical imaging examinations is expected to grow exponentially over the next two decades (Tsao, 2020). Radiologists and radiology technologists are in particularly scarce supply (AAMC Report Reinforces Mounting Physician Shortage, 2021, Clinical Radiology UK Workforce Census 2019 Report, 2019). Finally, the ageing world population (Population Ages 65 and above, n.d.; WHO, n.d.-a) and an increasing global burden of chronic illnesses (WHO, n.d.-b) are expected to compound these problems in the near future.

    Broadly speaking, the advantages of AI in medical imaging could potentially include the ability to provide insights that would otherwise not be possible using traditional methods (such as humans looking at images) and to may do so in a faster and automated way (without the need for human interaction). AI-based solutions in medical imaging could improve and accelerate the detection of disease, generate in-depth risk assessment of disease development and progression, and may reduce subjectivity in the interpretation of medical imaging data.

    Over the past few years, the landscape of AI in medical imaging has changed dramatically. Many promising applications have arisen, the field has seen an unprecedented surge in funding, and we have seen positive trends in the adoption of AI solutions by radiologists, as well as their approval by regulatory bodies.

    Applications

    Although radiology departments provide a plethora of services, the core service provided is the imaging study. Applications of AI in medical imaging can therefore be categorized into those applied either before, during, or after the imaging study.

    Before Image Acquisition

    Several steps have to take place within the context of a radiology department’s workflow before a patient is undergoing imaging study. AI applications that aim to improve these steps are referred to as “upstream AI” and could potentially increase efficiency and provide more personalized decision making in a radiology department.

    Missed medical appointments are common, reduce the efficiency of hospitals, and waste resources (Dantas et al., 2018). Studies from Japan (Kurasawa et al., 2016) and the United Kingdom (Nelson et al., 2019) have shown that AI can be used to predict no-shows with high accuracy. This allows the use of targeted strategies to reduce the likelihood of a patient missing their appointment, including sending automated reminders.

    One of the most important decisions made in the radiology department is the exact scan protocol to use on a given patient. While this applies to all imaging modalities, the widest range of choice is seen with magnetic resonance imaging (MRI). This includes choosing the appropriate set of sequences and making decisions about whether or not to administer intravenous contrast agents. Natural language classifiers that interpret the narrative text of the clinician’s scan requests have been used to select appropriate MRI protocols. In one study, a gradient boosting classifier predicted the appropriate MRI brain protocol to use based on the scan request with high accuracy (95 %) (Brown & Marotta, 2018). For musculoskeletal MRI, a deep learning classifier was 83 % accurate in determining the need for a contrast agent (Trivedi et al., 2018). Such applications can substantially improve efficiency by foregoing the time-consuming task of radiologists going through unstructured narrative scan requests written by referring clinicians.

    During Image Acquisition

    Substantial improvements have recently been made in the use of AI for improving image quality. In a recent survey, radiologists identified the enhancement of image quality as being the most mainstream current use case for AI in medical imaging (Alexander et al., 2020). While earlier attempts at reducing image noise using deep learning techniques were criticized for removing details from the images that jeopardized the visibility of essential features within the images, more recent implementations have made this issue largely obsolete.

     

    Potentials of AI

     

    In particular, deep learning techniques like generative adversarial networks have shown great potential in image denoising (Wang et al., 2021). Some of these applications target the image reconstruction stage (where the raw sensor data is converted into an interpretable image) providing superior signal-to-noise ratios and reducing image artefacts (Zhu et al., 2018). In lung cancer screening, deep-learning-based image denoising improved both the image quality and the diagnostic accuracy of ultra-low-dose computed tomography (CT) for detecting suspicious lung nodules (Hata et al., 2020; Kerpel et al., 2021). Scans that were 40-60 % acquired faster than standard scans and enhanced with deep-learning-based algorithms were of better image quality than, and similar diagnostic value as, standard scans of the brain (Bash, Wang, et al., 2021; Rudie et al., 2022) and spine (Bash, Johnson, et al., 2021). Similarly, convolutional neural networks can be used to reduce specific CT and MRI artefacts and improve spatial resolution (Hauptmann et al., 2019; K. H. Kim & Park, 2017; Park et al., 2018; Y.Zhang & Yu, 2018).

    Reconstruction algorithms based on deep learning have enabled ultra-low-dose computed tomography scans to be acquired while maintaining diagnostic quality. This is of particular benefit in children and pregnant women, where reduction of radiation dose to the absolute minimum is critical. These deep- learning-based CT image reconstruction approaches are associated with lower image noise and better image texture than state-of-the-art alternatives like iterative reconstruction (Higaki et al., 2020; McLeavy et al., 2021; Singh et al., 2020). In positron emission tomography, deep learning can reduce injected tracer dosage by one-third and scan times by up to half while maintaining scan quality (Katsari et al., 2021; Le et al., 2020; Xu et al., 2020).

    After Image Acquisition

    Radiology technologists and radiologists usually share the task of calling back patients for repeat examinations, but doing so consistently and reliably is exceedingly difficult due to time constraints. Image quality of AI enhanced brain MRI scans has been shown to be equal to or better than conventional scans, even when using acquisition protocols that reduce scan times by 45-60% (Schreiber-Zinaman & Rosenkrantz, 2017).

    Prioritizing scan reading on a radiologist’s worklist is often done based on several factors including the type of scan, the referring department, and direct communication with the radiologist about the scan’s urgency. Several approaches have been tested to influence the order in which scans are read to improve efficiency and ensure the most critical scans are seen first. These include assigning different radiologists specific exams based on how quickly they read certain scan types (Wong et al., 2019) and automatically detecting emergent findings on the images and pushing these cases to the “top of the list” (Prevedello et al., 2017; Winkel et al., 2019).

    About 70 % of all AI-based solutions in radiology focus on “perception” - a category of functionalities that includes segmentation, feature extraction, as well as detection and classification of pathology (Rezazade Mehrizi et al., 2021). Within this category, the majority of tools extract information from the imaging data with or without quantification as well as draw the user’s attention to potential pathology (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). Over the past few years, some of the most promising applications in this category have included the detection of brain vessel occlusion, brain haemorrhage, lung nodules, pneumothorax and pleural effusions, fractures, and the characterization of breast lesions.

    Funding

    The total amount of investment in AI-based medical imaging companies amounted to $ 1.17 billion between 2014 and 2019 (Alexander et al., 2020). In the same period, the number of companies in this space tripled, leading to a drop of almost 30 % in the median investment in each company (Alexander et al., 2020). Between 2019 and 2020, private investment in AI companies increased by 9.3 % (D. Zhang et al., 2021). By 2030, investment in AI-based solutions in medical imaging is expected to exceed $3 billion (Tsao, 2020).

    Adoption

    There have been positive trends in the adoption of AI tools by radiologists and radiology technologists over the past few years. Between 2015 and 2020, AI use in radiology departments went up by 30 %, according to a survey of 1,861 radiologists conducted by the American College of Radiology (ACR) (Allen et al., 2021).

    Despite this promising trend, the adoption of AI tools is widely considered to be disproportionately low relative to the amount of funding, the number of companies, and the perceived promise of these tools. The ACR survey provides some insight into why and offers a starting point for developing strategies to improve AI adoption.

    Almost three-quarters of radiologists who were not using AI had no plans to do so in the future because they either were not convinced of its benefits or did not think the associated costs were justified (Allen et al., 2021).

    Similar results have been found in other studies, with radiologists citing scepticism in the capabilities of AI tools and the fact that relatively few have regulatory approval as reasons for not adopting them in their practice (Alexander et al., 2020).

    Regulatory success

    Until August 2019, 60 % of available AI-based radiology solutions had no regulatory approval (Rezazade Mehrizi et al., 2021). As of April 2020, a total of 100 AI solutions had a CE mark, a prerequisite for them to be made commercially available as medical devices in Europe (van Leeuwen et al., 2021). As of the time of writing, more than 150 AI solutions have gained FDA clearance (AI Central, n.d.). Several useful databases of approved or cleared AI-based solutions in medical healthcare are currently available (AI Central, n.d., AI for Radiology, n.d., Medical AI Evaluation, n.d., The Medical Futurist, n.d.)
     

    The past few years have seen exponential growth in the interest in AI in medical imaging, both in terms of the amount of research and the amount of money being invested in the field. This interest runs the gamut of the radiology workflow, but “perception” applications - for the quantification of biomarkers and the detection of disease processes - have dominated so far. In the radiology community, trends have shifted from AI being perceived as an unwelcome intruder to increased adoption, albeit with some scepticism and hesitation regarding its value. The first AI solutions in medical imaging were granted regulatory approval, and we have seen the first indications of how such solutions may be reimbursed.

    New directions

    With increasing acknowledgement that a large proportion of AI’s potential in medical imaging may lie in “upstream” or “non-interpretative” applications, the field is likely to expand its focus in the coming years. This will include more research into applications that improve the efficiency of radiology workflows and provide more personalized patient care (Alexander et al., 2020). AI is likely to become more involved even earlier in the patient management process - i.e. before the clinician decides that a diagnostic image test is necessary. Such applications, essentially clinical decision support systems, have successfully been used for decision-making about treatments in several settings (Bennett & Hauser, 2013; Komorowski et al., 2018), successfully used in treatment decision making (Bennett & Hauser, 2013). In the future, AI solutions may draw clinicians’ attention to the need for further imaging tests based on reviewing the patient’s clinical information, laboratory tests, and prior imaging tests (Makeeva et al., 2019).

     

    Perception of AI

    The vast majority (77-84 %) of currently available AI solutions in medical imaging target CT, MRI and plain radiographs (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). Nuclear imaging techniques, such as positron emission tomography (PET). provide unique information not readily gained from other modalities. PET has thus far been largely neglected in terms of AI research (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021), and is thus a potentially promising avenue for the field’s expansion.

    AI research is also expected to undergo a shift in the type of data being used. The typical inpatient receives more than one imaging study during their hospital stay (Shinagare et al., 2014). Despite this, only about 3 % of current AI-based radiology solutions combine data from multiple modalities (Rezazade Mehrizi et al., 2021; van Leeuwen et al., 2021). Combining data from multiple imaging sources may improve the diagnostic capabilities of AI solutions. Furthermore, future AI solutions in radiology are likely to combine imaging information, clinical information, as well as non- imaging diagnostic tests (Huang et al., 2020). By doing this, AI solutions may be able to identify patterns in the data collected during a patient’s hospital stay that may not be readily identifiable by healthcare workers (Rockenbach, 2021). This could ultimately lead to more accurate diagnoses and could help inform better and more personalized treatment decisions.

    The expectations for AI-based medical imaging solutions are also likely to shift from the current focus of triage, image enhancement and automation. With increasing algorithmic complexity, data availability, and experience with these tools, this shift may lead to AI solutions reaching specific diagnoses and recommending specific steps in a patient’s management plan. Similar to how the introduction of the first AI tools for image screening and processing around 2018 spurred investment in the field, marketing analyses predict a similar investment boost in the next few years as AI tools providing specific diagnoses and management steps become more widespread (Michoud et al., 2019).

    One important criticism of the current, arguably still nascent, landscape of AI in medical imaging is that it is too fragmented. Radiology professionals would likely welcome a more streamlined integration of AI solutions in their daily workflow. This includes seamless integration of these solutions into established radiology workflows, with as much as possible happening “in the background” without user input. Furthermore, the outputs of these solutions could be integrated into available radiological information systems. Consequently, the field could move from the plethora of currently available niche AI solutions, each targeted towards a single very specific application, to broader software suites that perform many different functions for a given imaging modality or body region.

    The fragmented investment in the AI in medical imaging market (Alexander et al., 2020) fosters innovation, allowing many players to test out different strategies in this emerging field. However, in the long term, consolidation may increase adoption and stimulate the kind of seamless integration into existing workflows that is needed, allowing fewer companies to offer these solutions at scale (Alexander et al., 2020).

    Challenges

    Quality and reporting of evidence

    In a review of 100 CE-marked AI solutions, 64 % of them had no peer-reviewed scientific evidence for their efficacy (van Leeuwen et al., 2021). Where there was scientific evidence, the level was low, rarely exceeding the demonstration of diagnostic accuracy (van Leeuwen et al., 2021). Another systematic review of the evidence for deep learning algorithms in medical imaging found a generally high diagnostic accuracy, albeit with a high risk of bias across studies (Aggarwal et al., 2021). The main sources of bias include the lack of external validation (D. W. Kim et al., 2019; Liu et al., 2019), insufficiently detailed reporting of results (Liu et al., 2019), retrospective study design (Nagendran et al., 2020), and the inaccessibility of data and code to reviewers and readers (Nagendran et al., 2020).

    Overall, studies on AI tools have shown a worrying lack of standardized reporting and adherence to recommended reporting guidelines (Aggarwal et al., 2021; Yusuf et al., 2020). This is despite the fact that several extensions to established reporting guidelines, as well as AI-specific guidelines, are currently available (Shelmerdine et al., 2021). Widespread implementation of these guidelines should be a focus of AI developers in the future.

    AI developers should also be cognizant that the currently “acceptable” level of evidence for AI-based solutions is likely to become obsolete in the near future. Both regulators and potential users will likely demand higher levels of evidence for these solutions, akin to the evidence required for new pharmaceutical drugs. In the next few years, will see more of these AI solutions being tested in randomized clinical trials. In the more distant future, it is plausible that such expectations will go beyond providing evidence of the safety, efficacy, or diagnostic performance of these solutions, to the demonstration that they provide added monetary or societal value.

    Rising up to the challenge of improving the quality and reporting of evidence for AI-based solutions may pay off in the long run. It could reduce the risk of bias in AI studies, could allow the thorough and transparent assessment of study quality by potential users and regulators, and could facilitate systematic reviews and meta-analyses. These steps may increase the trust in, and uptake of, AI-based solutions and ensure that they offer realistic, sustainable improvements in people’s lives.

    Regulation

    Several aspects inherent to AI pose challenges to attempts at regulating it like other healthcare interventions. The inner workings of AI solutions are often opaque and difficult to comprehensively describe in a manner traditionally expected by regulatory bodies.

    The past few years have shown us that these regulatory challenges are far from intractable. Both the Food and Drug Administration and the European Commission have recently proposed initial regulatory frameworks for AI solutions (Center for Devices & Radiological Health, 2021; European Commission, 2021).

    In part as a response to the transparency necessary for regulatory approval, researchers have made substantial progress in making AI’s decision-making more understandable and explainable. This movement towards “interpretable AI” will gain further impetus in the near future as reliance on AI for real-world clinical decision-making increases.

    This has many advantages, including making regulatory approval easier, increasing trust in these solutions by users, minimizing biases, and improving the reproducibility of these solutions (Holzinger et al., 2017; Kolyshkina & Simoff, 2021; “Towards Trustable Machine Learning,” 2018; Yoon et al., 2021).

    Data privacy

    From development and testing to implementation, AI solutions in medical imaging require access to patient data. This has raised concerns about data privacy, which is a multifaceted and highly complex issue (Murdoch, 2021) that is prominently represented in the regulatory pathways of different countries (COCIR, the European Coordination Committee of the Radiological, Electromedical and Healthcare IT Industry, 2020). Suggested solutions to the data privacy question have ranged from those focusing on oversight to more technical approaches.

    The patients providing the data have to be made aware that they are doing so, as well as be informed about why and how their data will be used (Lotan et al., 2020), as explicitly stipulated in the EU’s General Data Protection Regulation (GDPR) (General Data Protection Regulation (GDPR) – Official Legal Text, 2016). Considering the fast-paced nature of the development of AI solutions, whether patients can be kept sufficiently informed as these algorithms are continuously retrained has been questioned (Kritikos, 2020). While fully anonymized data is not subject to such strict requirements under the GDPR (What Is Personal Data?, 2021), anonymization is exceedingly difficult to achieve for medical imaging data.

    The data privacy issue will have to be approached on several fronts. In addition to legislation governing the use of patient data, it is becoming increasingly clear that everyone involved in the development and use of AI solutions - developers, payers, regulatory bodies, researchers and radiologists - has a role to play in ensuring that the data is protected and used responsibly.

    Moreover, the next few years will likely see further research into technical approaches to strengthen data protection. These include better ways to reduce the chances of data being traced back to individuals, methods for keeping sensitive data stored locally even when the algorithm being trained is hosted in some “central” location, data perturbation to minimize the information within a given dataset pertaining to individual patients, and data encryption (G. Kaissis et al., 2021; G. A. Kaissis et al., 2020).

    hexagon

     

    Democratization

    If AI in medical imaging is to live up to its potential, the algorithms being developed have to work for everyone. This “democratization” of AI involves ensuring that healthcare providers have the knowledge and skills needed to use AI-based solutions. With a few exceptions (Paranjape et al., 2019), medical student curricula currently include little to no dedicated education about AI (Banerjee et al., 2021; Blease et al., 2022). Surveys from around the world have shown that medical students’ and doctors’ (Ahmed et al., 2022; Bisdas et al., 2021; Collado-Mesa et al., 2018; Kansal et al., 2022; Pinto Dos Santos et al., 2019; Sit et al., 2020) exposure to AI during training was low despite the high demand for more AI education (Kansal et al., 2022; Ooi et al., 2021; Sit et al., 2020). In addition, there are still large differences between genders and countries in the perceived knowledge about AI amongst medical students (Bisdas et al., 2021). There are many reasons for these differences and many challenges associated with the widespread integration of AI education into healthcare training curricula. In the coming years, strategies to tackle these issues should be investigated to ensure that future healthcare providers are equipped with the knowledge and skills they need to work in an environment where AI plays a growing role.

    Democratization also involves ensuring that patients of different genders, lifestyles, ethnicities, and geographical locations can benefit from AI-based solutions. For this to happen, these solutions have to be accessible and their performance generalizable. The latter requires the acquisition of diverse data from multiple institutions, preferably from multiple countries, for training AI-based solutions. It also requires the implementation of safeguards to ensure that sources of bias throughout the development process are not propagated to the trained algorithm (Vokinger et al., 2021), an issue that has only recently come to the forefront (Larrazabal et al., 2020; Obermeyer et al., 2019; Seyyed-Kalantari et al., 2021).

    Reimbursement

    As countries’ policies for regulating AI in healthcare gradually begin to take shape, one important aspect that needs attention is who will pay for these AI solutions, and according to what framework.

    Many consider Germany’s 2020 Digital Supply Act a step in the right direction for reimbursement of digital health solutions. Under this policy, digital applications prescribed by physicians are reimbursable by statutory health insurance if they are proven to be safe, be compliant with data privacy statutes, and improve patient care. The UK, on the other hand, has released a guide for potential buyers of AI-based solutions, which serves as a starting point for companies to prepare for reimbursement applications (A Buyer’s Guide to AI in Health and Care, 2020).

    Thus far, reimbursement success stories in the digital health space have been few and far between (Brink- mann-Sass et al., 2020; Hassan, 2021). This is in part due to requirements varying greatly by country (COCIR, the European Coordination Committee of the Radiological, Electromedical and Healthcare IT Industry, 2020). In general, providers of digital health solutions will need to provide evidence for the overall value that these solutions bring, including detailed health economics studies showing potential cost savings.

    Radiology’s position as a service provider to multiple hospital departments means that AI-based solutions in this space will be expected to show a far-reaching impact (van Duffelen, 2021). Companies will need to show short-term value (e.g. faster/better image reading and reporting) as well as long-term value (e.g. early diagnosis and treatment, disease prevention, reduction in unnecessary follow-up). The coming years will see companies compete to demonstrate such impact, while at the same time experimenting with different pricing models and navigating the evolving bureaucratic reimbursement landscape.

    Over the past few years, the field of AI in medical imaging has undergone a rapid but steady transformation. AI can now achieve things in radiology that few people thought possible a mere decade ago. The field is also gradually overcoming one of its most significant perceived hurdles - regulatory approval. In addition, while fear and scepticism dominated radiologists’ perception of the future of AI in their speciality a few years ago, this is no longer the case.

    The massive progress and interest in the field of AI in medical imaging is expected to continue into 2022 and beyond. Several exciting transformations await the field - it will likely expand its focus in the coming years to improve radiology workflow efficiency, involve hitherto neglected imaging modalities, combine data from multiple modalities, and provide more concrete diagnostic predictions and management recommendations. Easy-to-use and comprehensive software suites utilizing AI will be incorporated into existing radiology workflows, making radiologists’ and radiographers’ work easier and more efficient.

    As in any rapidly growing field, several scientific, regulatory, and economic challenges face AI in medical imaging. But the past few years have shown us that even the most difficult problems can be solved. Developers and users of AI-based solutions need to be aware of these issues so that they can adapt their strategies to changing expectations on a regulatory and societal level. Doing this will allow them to thrive in a fascinating field with the potential to improve virtually every aspect of healthcare.

    AAMC Report Reinforces Mounting Physician Shortage. (2021). AAMC. https://www.aamc.org/news-insights/press- releases/aamc-report-reinforces-mounting-physician-shortage

    A buyer’s guide to AI in health and care. (2020). NHS Transformation Directorate. https://www.nhsx.nhs.uk/ai-lab/ explore-all-resources/adopt-ai/a-buyers-guide-to-ai-in-health- and-care/

    Aggarwal, R., Sounderajah, V., Martin, G., Ting, D. S. W., Karthikesalingam, A., King, D., Ashrafian, H., & Darzi, A. (2021). Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digital Medicine, 4(1), 65.

    Ahmed, Z., Bhinder, K. K., Tariq, A., Tahir, M. J., Mehmood, Q., Tabassum, M. S., Malik, M., Aslam, S., Asghar, M. S., & Yousaf, Z. (2022). Knowledge, attitude, and practice of artificial intelligence among doctors and medical students in Pakistan: A cross-sectional online survey. Annals of Medicine and Surgery (2012), 76, 103493.

    AI Central. (n.d.). Retrieved February 23, 2022, from https://aicentral.acrdsi.org/

    AI for Radiology. (n.d.). Retrieved February 23, 2022, from https://grand-challenge.org/aiforradiology/

    Alexander, A., Jiang, A., Ferreira, C., & Zurkiya, D. (2020). An Intelligent Future for Medical Imaging: A Market Outlook on Artificial Intelligence for Medical Imaging. Journal of the American College of Radiology: JACR, 17(1 Pt B), 165–170.

    Allen, B., Agarwal, S., Coombs, L., Wald, C., & Dreyer, K. (2021). 2020 ACR Data Science Institute Artificial Intelligence Survey. Journal of the American College of Radiology: JACR, 18(8), 1153–1159.

    Banerjee, M., Chiew, D., Patel, K. T., Johns, I., Chappell, D., Linton, N., Cole, G. D., Francis, D. P., Szram, J., Ross, J., & Zaman, S. (2021). The impact of artificial intelligence on clinical education: perceptions of postgraduate trainee doctors in London (UK) and recommendations for trainers. BMC Medical Education, 21(1), 429.

    Bash, S., Johnson, B., Gibbs, W., Zhang, T., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Image Processing Enables 40 % Faster Spinal MR Scans Which Match or Exceed Quality of Standard of Care : A Prospective Multicenter Multireader Study. Clinical Neuroradiology. https://doi.org/10.1007/s00062-021-01121-2

    Bash, S., Wang, L., Airriess, C., Zaharchuk, G., Gong, E., Shankaranarayanan, A., & Tanenbaum, L. N. (2021). Deep Learning Enables 60 % Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial. AJNR. American Journal of Neuroradiology, 42(12), 2130–2137.

    Bennett, C. C., & Hauser, K. (2013). Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach. Artificial Intelligence in Medicine, 57(1), 9–19.

    Bisdas, S., Topriceanu, C.-C., Zakrzewska, Z., Irimia, A.-V., Shakallis, L., Subhash, J., Casapu, M.-M., Leon-Rojas, J., Pinto Dos Santos, D., Andrews, D. M., Zeicu, C., Bouhuwaish, A. M., Lestari, A. N., Abu-Ismail, L. ’i, Sadiq, A. S., Khamees, A. ’atasim, Mohammed, K. M. G., Williams, E., Omran, A. I.,… Ebrahim, E. H. (2021). Artificial Intelligence in Medicine: A Multinational Multi-Center Survey on the Medical and Dental Students’ Perception. Frontiers in Public Health, 9, 795284.

    Blease, C., Kharko, A., Bernstein, M., Bradley, C., Houston, M., Walsh, I., Hägglund, M., DesRoches, C., & Mandl, K. D. (2022). Machine learning in medical education: a survey of the experiences and opinions of medical students in Ireland. BMJ Health & Care Informatics, 29(1). https://doi.org/10.1136/ bmjhci-2021-100480

    Brown, A. D., & Marotta, T. R. (2018). Using machine learning for sequence-level automated MRI protocol selection in neuroradiology. Journal of the American Medical Informatics Association: JAMIA, 25(5), 568–571.

    Center for Devices, & Radiological Health. (2021, June 22). Digital Health Software Precertification (Pre-Cert) program.
    U.S. Food and Drug Administration. https://www.fda.gov/ medical-devices/digital-health-center-excellence/digital-health- software-precertification-pre-cert-program

    Clinical radiology UK workforce census 2019 report. (2019). https://www.rcr.ac.uk/publication/clinical-radiology-uk- workforce-census-2019-report

    COCIR, the European Coordination Committee of the Radiological, Electromedical and Healthcare IT Industry. (2020). Market Access Pathways for Digital Health Solutions. https://www.cocir.org/fileadmin/Publications_2020/20062_ COCIR_Market_Access_Pathways_Digital_Health.pdf

    Collado-Mesa, F., Alvarez, E., & Arheart, K. (2018). The Role of Artificial Intelligence in Diagnostic Radiology: A Survey at a Single Radiology Residency Training Program. Journal of the American College of Radiology: JACR, 15(12), 1753–1757.

    Core Health Indicators in the WHO European Region 2015. Special focus: Human resources for health. (2017, August 14). World Health Organization. https://www.euro.who.int/en/ data-and-evidence/evidence-resources/core-health-indicators- in-the-who-european-region/core-health-indicators-in-the- who-european-region-2015.-special-focus-human-resources- for-health

    Dantas, L. F., Fleck, J. L., Cyrino Oliveira, F. L., & Hamacher, S. (2018). No-shows in appointment scheduling - a systematic literature review. Health Policy, 122(4), 412–421.

    Esses, S. J., Lu, X., Zhao, T., Shanbhogue, K., Dane, B., Bruno, M., & Chandarana, H. (2018). Automated image quality evaluation of T2 -weighted liver MRI utilizing deep learning architecture. Journal of Magnetic Resonance Imaging: JMRI, 47(3), 723–728.

    European Commission. (2021). Proposal for a Regulation Of The European Parliament And Of The Council Laying Down
    Harmonised Rules On Artificial Intelligence (Artificial Intelligence Act) And Amending Certain Union Legislative Act.
    https://eur-lex. europa.eu/resource.html?uri=cellar:e0649735-a372-11eb- 9585-01aa75ed71a1.0001.02/DOC_1&format=PDF

    General Data Protection Regulation (GDPR) – Official Legal Text. (2016, July 13). General Data Protection Regulation (GDPR). https://gdpr-info.eu/

    Hata, A., Yanagawa, M., Yoshida, Y., Miyata, T., Tsubamoto, M., Honda, O., & Tomiyama, N. (2020). Combination of Deep Learning-Based Denoising and Iterative Reconstruction for Ultra-Low-Dose CT of the Chest: Image Quality and Lung-RADS Evaluation. AJR. American Journal of Roentgenology, 215(6), 1321–1328.

    Hauptmann, A., Arridge, S., Lucka, F., Muthurangu, V., & Steeden, J. A. (2019). Real-time cardiovascular MR with
    spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magnetic Resonance in Medicine: Official Journal of the Society of Magnetic Resonance in Medicine / Society of Magnetic Resonance in Medicine, 81(2), 1143–1156.

    Higaki, T., Nakamura, Y., Zhou, J., Yu, Z., Nemoto, T., Tatsugami, F., & Awai, K. (2020). Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics. Academic Radiology, 27(1), 82–87.

    Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B. (2017). What do we need to build explainable AI systems for the medical domain? In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/1712.09923

    Hötker, A. M., Da Mutten, R., Tiessen, A., Konukoglu, E., & Donati, O. F. (2021). Improving workflow in prostate MRI: AI- based decision-making on biparametric or multiparametric MRI. Insights into Imaging, 12(1), 112.

    Huang, S.-C., Pareek, A., Seyyedi, S., Banerjee, I., & Lungren, M. P. (2020). Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digital Medicine, 3, 136.

    Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2(6), 305–311.

    Kaissis, G., Ziller, A., Passerat-Palmbach, J., Ryffel, T., Usynin, D., Trask, A., Lima, I., Mancuso, J., Jungmann, F., Steinborn, M.-M., Saleh, A., Makowski, M., Rueckert, D., & Braren, R. (2021). End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nature Machine Intelligence, 3(6), 473–484.

    Kansal, R., Bawa, A., Bansal, A., Trehan, S., Goyal, K., Goyal, N., & Malhotra, K. (2022). Differences in Knowledge and Perspectives on the Usage of Artificial Intelligence Among Doctors and Medical Students of a Developing Country: A Cross- Sectional Study. Cureus, 14(1), e21434.

    Katsari, K., Penna, D., Arena, V., Polverari, G., Ianniello, A., Italiano, D., Milani, R., Roncacci, A., Illing, R. O., & Pelosi, E. (2021). Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment. EJNMMI Physics, 8(1), 25.

    Kerpel, A., Marom, E. M., Green, M., Eifer, M., Konen, E., Mayer, A., & Betancourt Cuellar, S. L. (2021). Ultra-Low Dose Chest CT with Denoising for Lung Nodule Detection. The Israel Medical Association Journal: IMAJ, 23(9), 550–555.

    Kim, D. W., Jang, H. Y., Kim, K. W., Shin, Y., & Park, S. H. (2019).
    Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of
    Medical Images: Results from Recently Published Papers. Korean Journal of Radiology: Official Journal of the Korean Radiological Society, 20(3), 405–410.

    Kim, K. H., & Park, S.-H. (2017). Artificial neural network for suppression of banding artifacts in balanced steady-state free precession MRI. Magnetic Resonance Imaging, 37, 139–146.

    Kolyshkina, I., & Simoff, S. (2021). Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach. Frontiers in Big Data, 4, 660206.

    Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C., & Faisal, A. A. (2018). The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nature Medicine, 24(11), 1716–1720.

    Kritikos, M. (2020). What if artificial intelligence in medical imaging could accelerate Covid-19 treatment? Think Tank
    - European Parliament. https://www.europarl.europa.eu/ thinktank/en/document/EPRS_ATA(2020)656333

    Kurasawa, H., Hayashi, K., Fujino, A., Takasugi, K., Haga, T., Waki, K., Noguchi, T., & Ohe, K. (2016). Machine-Learning- Based Prediction of a Missed Scheduled Clinical Appointment by Patients With Diabetes. Journal of Diabetes Science and Technology, 10(3), 730–736.

    Larrazabal, A. J., Nieto, N., Peterson, V., Milone, D. H., & Ferrante, E. (2020). Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proceedings of the National Academy of Sciences of the United States of America, 117(23), 12592–12594.

    Larson, D. B., Johnson, L. W., Schnell, B. M., Salisbury, S. R., & Forman, H. P. (2011). National trends in CT use in the emergency department: 1995-2007. Radiology, 258(1), 164–173.

    Le, V., Frye, S., Botkin, C., Christopher, K., Gulaka, P., Sterkel, B., Frye, R., Muzaffar, R., & Osman, M. (2020). Effect of PET Scan with Count Reduction Using AI-Based Processing Techniques on Image Quality. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 3095–3095.

    Levin, D. C., Parker, L., & Rao, V. M. (2017). Recent Trends in Imaging Use in Hospital Settings: Implications for Future Planning. Journal of the American College of Radiology: JACR, 14(3), 331–336.

    Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., Mahendiran, T., Moraes, G., Shamdas, M., Kern, C., Ledsam, J. R., Schmid, M. K., Balaskas, K., Topol, E.J., Bachmann, L. M., Keane, P. A., & Denniston, A. K. (2019). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet. Digital Health, 1(6), e271–e297.

    Lotan, E., Tschider, C., Sodickson, D. K., Caplan, A. L., Bruno, M., Zhang, B., & Lui, Y. W. (2020). Medical Imaging and Privacy in the Era of Artificial Intelligence: Myth, Fallacy, and the Future. Journal of the American College of Radiology: JACR, 17(9), 1159–1162.

    Mairhöfer, D., Laufer, M., Simon, P. M., Sieren, M., Bischof, A., Käster, T., Barth, E., Barkhausen, J., & Martinetz, T. (2021). An AI-based Framework for Diagnostic Quality Assessment of Ankle Radiographs. https://openreview.net/pdf?id=bj04hJss_xZ

    Makeeva, V., Gichoya, J., Hawkins, C. M., Towbin, A. J., Heilbrun, M., & Prater, A. (2019). The Application of Machine Learning to Quality Improvement Through the Lens of the Radiology Value Network. Journal of the American College of Radiology: JACR, 16(9 Pt B), 1254–1258.

    McLeavy, C. M., Chunara, M. H., Gravell, R. J., Rauf, A., Cushnie, A., Staley Talbot, C., & Hawkins, R. M. (2021). The future of CT: deep learning reconstruction. Clinical Radiology, 76(6), 407–415.

    Medical AI Evaluation. (n.d.). Retrieved February 23, 2022, from https://ericwu09.github.io/medical-ai-evaluation/

    Michoud, L., Tschudi, Y., & Villien, Y. (2019). Artificial Intelligence for Medical Imaging: Market and Technology Report 2020. Yole Développement. https://s3.i-micronews.com/ uploads/2020/01/YDR20059-AI-for-Medical-Imaging_Yole_ sample.pdf

    Murdoch, B. (2021). Privacy and artificial intelligence: challenges for protecting health information in a new era. BMC Medical Ethics, 22(1), 122.

    Nagendran, M., Chen, Y., Lovejoy, C. A., Gordon, A. C., Komorowski, M., Harvey, H., Topol, E. J., Ioannidis, J. P. A., Collins, G. S., & Maruthappu, M. (2020). Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ, 368. https://doi.org/10.1136/bmj.m689

    Nelson, A., Herron, D., Rees, G., & Nachev, P. (2019). Predicting scheduled hospital attendance with artificial intelligence. Npj Digital Medicine, 2(1), 26.

    Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.

    Ooi, S. K. G., Makmur, A., Soon, A. Y. Q., Fook-Chong, S., Liew, C., Sia, S. Y., Ting, Y. H., & Lim, C. Y. (2021). Attitudes toward artificial intelligence in radiology with learner needs assessment within radiology residency programmes: a national multi-programme survey. Singapore Medical Journal, 62(3), 126–134.

    Paranjape, K., Schinkel, M., Nannan Panday, R., Car, J., & Nanayakkara, P. (2019). Introducing Artificial Intelligence Training in Medical Education. JMIR Medical Education, 5(2), e16048.

    Park, J., Hwang, D., Kim, K. Y., Kang, S. K., Kim, Y. K., & Lee, J. S. (2018). Computed tomography super-resolution using deep convolutional neural network. Physics in Medicine and Biology, 63(14), 145011.

    Pinto Dos Santos, D., Giese, D., Brodehl, S., Chon, S. H., Staab, W., Kleinert, R., Maintz, D., & Baeßler, B. (2019). Medical students’ attitude towards artificial intelligence: a multicentre survey. European Radiology, 29(4), 1640–1646.

    Population ages 65 and above. (n.d.). The World Bank. Retrieved February 23, 2022, from https://data.worldbank.org/ indicator/SP.POP.65UP.TO.ZS

    Prevedello, L. M., Erdal, B. S., Ryu, J. L., Little, K. J., Demirer, M., Qian, S., & White, R. D. (2017). Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging. Radiology, 285(3), 923–931.

    Rezazade Mehrizi, M. H., van Ooijen, P., & Homan, M. (2021). Applications of artificial intelligence (AI) in diagnostic radiology: a technography study. European Radiology, 31(4), 1805–1811.

    Rockenbach, M. A. B. (2021, June 13). Multimodal AI in healthcare: Closing the gaps. CodeX. https://medium.com/codex/ multimodal-ai-in-healthcare-1f5152e83be2

    Rudie, J. D., Gleason, T., Barkovich, M. J., Wilson, D. M., Shankaranarayanan, A., Zhang, T., Wang, L., Gong, E., Zaharchuk, G., & Villanueva-Meyer, J. E. (2022). Clinical Assessment of Deep Learning–based Super-Resolution for 3D Volumetric Brain MRI. Radiology: Artificial Intelligence, e210059.

    Schreiber-Zinaman, J., & Rosenkrantz, A. B. (2017). Frequency and reasons for extra sequences in clinical abdominal MRI examinations. Abdominal Radiology (New York), 42(1), 306–311.

    Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y., & Ghassemi, M. (2021). Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nature Medicine, 27(12), 2176–2182.

    Shelmerdine, S. C., Arthurs, O. J., Denniston, A., & Sebire, N. J. (2021). Review of study reporting guidelines for clinical studies using artificial intelligence in healthcare. BMJ Health & Care Informatics, 28(1). https://doi.org/10.1136/ bmjhci-2021-100385

    Shinagare, A. B., Ip, I. K., Abbett, S. K., Hanson, R., Seltzer, S. E., & Khorasani, R. (2014). Inpatient imaging utilization: trends of the past decade. AJR. American Journal of Roentgenology, 202(3), W277–W283.

    Singh, R., Digumarthy, S. R., Muse, V. V., Kambadakone, A. R., Blake, M. A., Tabari, A., Hoi, Y., Akino, N., Angel, E., Madan, R., & Kalra, M. K. (2020). Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT. AJR. American Journal of Roentgenology, 214(3), 566–573.

    Sit, C., Srinivasan, R., Amlani, A., Muthuswamy, K., Azam, A., Monzon, L., & Poon, D. S. (2020). Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: a multicentre survey. Insights into Imaging, 11(1), 14.

    Smith-Bindman, R., Miglioretti, D. L., Johnson, E., Lee, C., Feigelson, H. S., Flynn, M., Greenlee, R. T., Kruger, R. L., Hornbrook, M. C., Roblin, D., Solberg, L. I., Vanneman, N., Weinmann, S., & Williams, A. E. (2012). Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996-2010. JAMA: The Journal of the American Medical Association, 307(22), 2400–2409.

    Smith-Bindman, R., Miglioretti, D. L., & Larson, E. B. (2008). Rising use of diagnostic medical imaging in a large integrated health system. Health Affairs, 27(6), 1491–1502.

    The Medical Futurist. (n.d.). The Medical Futurist. Retrieved February 23, 2022, from https://medicalfuturist.com/fda- approved-ai-based-algorithms/

    Towards trustable machine learning. (2018). Nature Biomedical Engineering, 2(10), 709–710.

    Trivedi, H., Mesterhazy, J., Laguna, B., Vu, T., & Sohn, J. H. (2018). Automatic Determination of the Need for Intravenous Contrast in Musculoskeletal MRI Examinations Using IBM Watson’s Natural Language Processing Algorithm. Journal of Digital Imaging, 31(2), 245–251.

    Tsao, D. N. (2020, July 27). AI in medical diagnostics 2020- 2030: Image recognition, players, clinical applications, forecasts: IDTechEx. https://www.idtechex.com/en/research- report/ai-in-medical-diagnostics-2020-2030-image- recognition-players-clinical-applications-forecasts/766

    van Duffelen, J. (2021, February 22). Making a case for buying medical imaging AI: How to define the return on investment.
    Aidence. https://www.aidence.com/articles/medical-imaging- ai-roi/

    van Leeuwen, K. G., Schalekamp, S., Rutten, M. J. C. M., van Ginneken, B., & de Rooij, M. (2021). Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. European Radiology, 31(6), 3797–3804.

    Vokinger, K. N., Feuerriegel, S., & Kesselheim, A. S. (2021). Mitigating bias in machine learning for medicine. Communication & Medicine, 1, 25.

    Wang, S., Cao, G., Wang, Y., Liao, S., Wang, Q., Shi, J., Li, C., & Shen, D. (2021). Review and Prospect: Artificial Intelligence in Advanced Medical Imaging. Frontiers in Radiology, 1. https://doi. org/10.3389/fradi.2021.781868

    What is personal data? (2021, January 1). ICO - Information Commissioner’s Office; ICO. https://ico.org.uk/for-organisations/ guide-to-data-protection/guide-to-the-general-data-protection- regulation-gdpr/what-is-personal-data/what-is-personal-data

    WHO. (n.d.-a). Ageing and health. Retrieved February 23, 2022, from https://www.who.int/news-room/fact-sheets/detail/ ageing-and-health

    WHO. (n.d.-b). Noncommunicable diseases. Retrieved March 6, 2022, from https://www.who.int/news-room/fact-sheets/detail/ noncommunicable-diseases

    Winder, M., Owczarek, A. J., Chudek, J., Pilch-Kowalczyk, J., & Baron, J. (2021). Are We Overdoing It? Changes in Diagnostic Imaging Workload during the Years 2010-2020 including the Impact of the SARS-CoV-2 Pandemic. Healthcare (Basel, Switzerland), 9(11). https://doi.org/10.3390/healthcare9111557

    Winkel, D. J., Heye, T., Weikert, T. J., Boll, D. T., & Stieltjes, B. (2019). Evaluation of an AI-Based Detection Software for Acute Findings in Abdominal Computed Tomography Scans: Toward an Automated Work List Prioritization of Routine CT Examinations. Investigative Radiology, 54(1), 55–59.

    Wong, T. T., Kazam, J. K., & Rasiej, M. J. (2019). Effect of Analytics-Driven Worklists on Musculoskeletal MRI
    Interpretation Times in an Academic Setting. AJR. American Journal of Roentgenology, 1–5.

    Xu, F., Pan, B., Zhu, X., Gulaka, P., Xiang, L., Gong, E., Zhang, T., Wang, J., Lin, L., Ma, Y., & Gong, N.-J. (2020). Evaluation of Deep Learning Based PET Image Enhancement Method in Diagnosis of Lymphoma. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine, 61(supplement 1), 431–431.

    Yoon, C. H., Torrance, R., & Scheinerman, N. (2021). Machine learning in medicine: should the pursuit of enhanced interpretability be abandoned? Journal of Medical Ethics. https://doi.org/10.1136/medethics-2020-107102

    Yusuf, M., Atal, I., Li, J., Smith, P., Ravaud, P., Fergie, M., Callaghan, M., & Selfe, J. (2020). Reporting quality of studies using machine learning models for medical diagnosis: a systematic review. BMJ Open, 10(3), e034568.

    Zhang, D., Mishra, S., Brynjolfsson, E., Etchemendy, J., Ganguli, D., Grosz, B., Lyons, T., Manyika, J., Niebles, J. C., Sellitto, M., Shoham, Y., Clark, J., & Perrault, R. (2021). The AI Index 2021 Annual Report. In arXiv [cs.AI]. arXiv. http://arxiv.org/ abs/2103.06312

    Zhang, Y., & Yu, H. (2018). Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography. IEEE Transactions on Medical Imaging, 37(6), 1370–1381.

    Zhu, B., Liu, J. Z., Cauley, S. F., Rosen, B. R., & Rosen, M. S. (2018). Image reconstruction by domain-transform manifold learning. Nature, 555(7697), 487–492.