Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Plasma trimethylamine N-oxide and related metabolites and overall survival of high-grade serous ovarian cancer: a nested case-control study.

European journal of nutrition·2026
Same author

Associations of Accelerometer-Derived "Weekend Warrior" Physical Activity Pattern With Incident First Cardiometabolic Disease and Cardiometabolic Multimorbidity in Individuals With Hypertension.

Journal of the American Heart Association·2026
Same author

Dietary index for gut microbiota, Life's Essential 8 scores, and risk of cardiovascular disease: a multinational cohort study.

European journal of preventive cardiology·2026
Same author

The association between steatotic liver disease and chronic kidney disease: a meta-analysis and Mendelian randomization study highlighting metabolic comorbidities.

Nutrition & diabetes·2026
Same author

Sulfur microbial diet, genetical predisposition, and the risk of chronic kidney disease: a cohort study.

European journal of clinical nutrition·2026
Same author

Turning Routine CT into Reference Values for Quantitative Radiology.

Radiology. Artificial intelligence·2026

Related Experiment Video

Updated: May 16, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

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

He-Li Xu1,2,3, Ting-Ting Gong4, Xin-Jian Song1,2,3

  • 1Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang, China.

Journal of Medical Internet Research
|April 1, 2025
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) shows promise for cancer diagnosis, but clinical implementation requires further research. This umbrella review critically evaluates AI

Keywords:
artificial intelligencebiomedical imagingcancer diagnosismeta-analysissystematic reviewumbrella review

More Related Videos

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.1K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

745

Related Experiment Videos

Last Updated: May 16, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.1K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

745

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Artificial intelligence (AI) offers transformative potential in cancer diagnosis, aiming to improve patient outcomes.
  • AI in medical imaging is rapidly evolving, necessitating a comprehensive evaluation of its diagnostic capabilities.
  • This study addresses the need for a critical synthesis of evidence on AI for cancer imaging diagnosis.

Purpose of the Study:

  • To conduct an umbrella review summarizing and critically appraising the evidence for AI-based imaging diagnosis of cancers.
  • To evaluate the diagnostic performance and quality of evidence for AI algorithms across various cancer types.
  • To identify hurdles and areas for future research in AI-driven cancer diagnostics.

Main Methods:

  • Systematic search of major databases (PubMed, Embase, Web of Science, Cochrane, IEEE) for relevant systematic reviews.
  • Data abstraction and quality assessment using Joanna Briggs Institute (JBI) Critical Appraisal Checklist.
  • Evidence quality assessment using Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria; narrative synthesis of diagnostic performance data.

Main Results:

  • Analysis of 158 studies evaluating AI in noninvasive imaging diagnosis across 8 major cancer types.
  • Variable accuracy for central nervous system cancers (48%-100%); consistent performance across other cancer sites.
  • Most meta-analyses showed positive summary performance, with notable ranges for esophageal, breast, and ovarian cancers; lung cancer showed lower pooled specificity (65%-80%).
  • High quality (JBI) in 80.4% of studies, but overall GRADE assessment indicated moderate to low evidence quality.

Conclusions:

  • AI demonstrates significant potential for accelerated, accurate, and objective cancer diagnoses.
  • Hurdles remain for clinical implementation, requiring a concerted effort from researchers, clinicians, and policymakers.
  • Translating AI's potential into improved patient outcomes and healthcare delivery necessitates collaborative action.