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

Stereo-electroencephalography-guided responsive neuromodulation: A propensity-matched cohort study.

Epilepsia·2026
Same author

Differences in overall survival for invasive epithelial ovarian cancer by race and ethnicity: results from the Ovarian Cancer Association Consortium.

British journal of cancer·2026
Same author

Sex, Not Age, Predicts Weight Loss Outcomes With Tirzepatide: A Retrospective Analysis.

Obesity (Silver Spring, Md.)·2026
Same author

Population-scale Y chromosome assemblies reveal recurrent remodeling within constrained architectures.

bioRxiv : the preprint server for biology·2026
Same author

Prevalence and Burden of Cardiac Amyloidosis in a Population-Based Autopsy Cohort.

Circulation·2026
Same author

A long-term image-derived AI-based risk model for primary prevention of breast cancer in individuals at high risk.

Science translational medicine·2026

Related Experiment Video

Updated: Oct 21, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K

Deep Learning Predicts Interval and Screening-detected Cancer from Screening Mammograms: A Case-Case-Control Study in

Xun Zhu1, Thomas K Wolfgruber1, Lambert Leong1

  • 1From the Department of Epidemiology, University of Hawaii Cancer Center, 701 Ilalo St, Suite 522, Honolulu, HI 96813 (X.Z., T.K.W., L.L., J.A.S.); Department of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, Hawaii (L.L., P.S.); Department of Health Sciences Research, Mayo Clinic, Rochester, Minn (M.J., C.S., S.W., C.V.); and Departments of Medicine and Epidemiology/Biostatistics, University of California, San Francisco, San Francisco, Calif (K.K.).

Radiology
|September 7, 2021
PubMed
Summary

Deep learning models show promise in identifying screening-detected breast cancer risk. However, they underperform compared to clinical factors for predicting interval breast cancer risk.

More Related Videos

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

8.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Related Experiment Videos

Last Updated: Oct 21, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K
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

8.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Oncology

Background:

  • Deep learning (DL) models' ability to predict breast cancer risk, specifically differentiating between screening-detected and interval cancers, remains underexplored.
  • This study investigates the efficacy of DL in assessing risk for both types of breast cancer, with and without incorporating clinical risk factors.

Purpose of the Study:

  • To evaluate the performance of DL models in estimating the risk of screening-detected and interval breast cancers.
  • To compare DL model performance against traditional clinical risk factors and Breast Imaging Reporting and Data System (BI-RADS) density assessments.

Main Methods:

  • A DL model was trained on 25,096 digital screening mammograms from women diagnosed between 2006 and 2013.
  • The model classified women into those who developed no cancer, screening-detected cancer, or interval invasive cancer.
  • Model effectiveness was measured using the concordance statistic (C statistic) on a held-out test set.

Main Results:

  • The DL model demonstrated strong performance for screening-detected cancer risk (C statistic: 0.66), comparable to combined models.
  • For interval cancer risk, the DL model (C statistic: 0.64) underperformed compared to BI-RADS density (C statistic: 0.71) and combined models (C statistic: 0.72).
  • Statistical analysis showed no significant difference between DL and combined models for screening-detected cancer (P=.99) but significant differences for interval cancer (P=.03).

Conclusions:

  • DL models show potential for identifying women at risk for screening-detected breast cancer.
  • Clinical risk factors, particularly breast density, remain superior for predicting interval breast cancer risk.
  • Further research is needed to enhance DL model performance for interval cancer detection.