EUVIMEDAvasta EUVIMED
Systematische ÜbersichtUmbrella ReviewOpen access

Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews

Leistung von Künstlicher Intelligenz bei bildbasierter Krebsidentifikation: Umbrella-Review systematischer Übersichtsarbeiten

He-Li Xu iD, Ting-Ting Gong iD, Xin-Jian Song iD, Qian Chen iD, Qi Bao iD, Wei Yao iD, Meng-Meng Xie iD, Chen Li iD, Marcin Grzegorzek iD, Yu Shi iD, Hong-Zan Sun iD, Xiao-Han Li iD and 3 more

Journal of Medical Internet Research · 2025-04-01 · 27 · e53567

DOI: 10.2196/53567 ↗

Auf einen Blick

Das Umbrella-Review fasst die Evidenz zur KI-gestützten bildbasierten Krebsdiagnostik zusammen. Die meisten Metaanalysen zeigten positive diagnostische Leistungen, die Evidenzqualität war insgesamt moderat bis niedrig.

Fragestellung

Wie gut ist die diagnostische Leistung von KI in der bildbasierten Krebsdiagnostik?

Methode

Umbrella-Review systematischer Übersichtsarbeiten; Suche in PubMed, Embase, Web of Science, Cochrane und IEEE bis 19. Juni 2024; Bewertung mit JBI und GRADE.

Ergebnisse

158 eingeschlossene Studien zu 8 großen Krebsgruppen. Die Genauigkeit bei ZNS-Krebs reichte von 48 % bis 100 %. Für Ösophaguskrebs lagen Sensitivität und Spezifität in 9 Reviews bei 90 %-95 % bzw. 80 %-93,8 %.

Einschränkungen

Die Evidenzqualität war insgesamt moderat bis niedrig.

Schlussfolgerung der Autor:innen

KI zeigt großes Potenzial für schnellere, genaue und objektivere Krebsdiagnosen, es bestehen aber Hürden vor der klinischen Anwendung.

Kernaussagen

  • 158 Studien zu 8 Krebsgruppen
  • ZNS-Krebs: Genauigkeit 48 % bis 100 %
  • GRADE: insgesamt moderat bis niedrig

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Journal of Medical Internet Research, published online on 2025-04-01. Written by He-Li Xu and 14 co-authors. Institution: Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang, China. Major MEDLINE topics: Artificial Intelligence, Neoplasms. Cited 20 times so far (Crossref); 212 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstraktSubjectsBibliograafilised andmedCiteRelated studies

Abstract (original language)

Background

Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes.

Objective

We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers.

Methods

PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively.

Results

In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low.

Conclusions

Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery. Trial Registration PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceNeoplasmsHumansAlgorithmsSystematic Reviews as Topic

Author keywords

artificial intelligencebiomedical imagingcancer diagnosismeta-analysissystematic reviewumbrella review

Authors and institutions

  • Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang, China.
  • Clinical Research Center, Shengjing Hospital of China Medical University, Shenyang, China.
  • Liaoning Key Laboratory of Precision Medical Research on Major Chronic Disease, Shengjing Hospital of China Medical University, Shenyang, China.
  • Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, China.
  • Department of Epidemiology, School of Public Health, China Medical University, Shenyang, China.
  • Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.

ORCID profiles: He-Li Xu, Ting-Ting Gong, Xin-Jian Song, Qian Chen, Qi Bao, Wei Yao, Meng-Meng Xie, Chen Li, Marcin Grzegorzek, Yu Shi, Hong-Zan Sun, Xiao-Han Li, Yu-Hong Zhao, Song Gao, Qi-Jun Wu

Cite

APA

Xu, H. L., Gong, T. T., Song, X. J., Chen, Q., Bao, Q., Yao, W., Xie, M. M., Li, C., Grzegorzek, M., Shi, Y., Sun, H. Z., Li, X. H., Zhao, Y. H., Gao, S., & Wu, Q. J. (2025). Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews. Journal of Medical Internet Research, 27, e53567. https://doi.org/10.2196/53567

Vancouver

Xu HL, Gong TT, Song XJ, Chen Q, Bao Q, Yao W, et al. Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews. Journal of Medical Internet Research. 2025;27:e53567. doi:10.2196/53567

BibTeX
@article{Xu2025,
  author = {Xu, He-Li and Gong, Ting-Ting and Song, Xin-Jian and Chen, Qian and Bao, Qi and Yao, Wei and Xie, Meng-Meng and Li, Chen and Grzegorzek, Marcin and Shi, Yu and Sun, Hong-Zan and Li, Xiao-Han and Zhao, Yu-Hong and Gao, Song and Wu, Qi-Jun},
  title = {Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e53567},
  doi = {10.2196/53567}
}
Start for free →