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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.6K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.6K

You might also read

Related Articles

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

Sort by
Same author

Life's Essential 8 in Pregnancy and Time to Incident Cardiometabolic Disease Over 7 Years Follow-Up.

JAMA network open·2026
Same author

Imaging Assessment after Nonradiation Locoregional Therapy for HCC.

Radiology·2026
Same author

Operating Room Extubation in Major Aortic Surgery: Policy Change Leading to Improved Recovery.

Journal of cardiothoracic and vascular anesthesia·2026
Same author

eIF4G2-Dependent Translation Restrains Pancreatic Cancer Progression.

Cancer research·2026
Same author

Life's Essential 8 in Pregnancy and Time to Incident Cardiometabolic Disease Over 7 Years Follow-Up.

medRxiv : the preprint server for health sciences·2026
Same author

Assessing the Effectiveness of the <i>Radiology</i> In Training Program in Fostering Highly Skilled Reviewers.

Radiology·2026

Related Experiment Video

Updated: Aug 27, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K

Improving breast cancer diagnostics with deep learning for MRI.

Jan Witowski1,2, Laura Heacock1, Beatriu Reig1

  • 1Department of Radiology, New York University Grossman School of Medicine, New York, NY 10016, USA.

Science Translational Medicine
|September 28, 2022
PubMed
Summary
This summary is machine-generated.

A new deep learning (DL) system enhances breast cancer diagnosis accuracy using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). This AI tool shows potential to reduce unnecessary biopsies, improving patient management.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

37

Related Experiment Videos

Last Updated: Aug 27, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
10:37

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

37

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) offers high sensitivity for breast cancer detection but frequently results in unnecessary biopsies.
  • Improving diagnostic accuracy and personalizing patient management in DCE-MRI are critical clinical needs.

Purpose of the Study:

  • To develop and validate a deep learning (DL) system for enhancing breast cancer diagnosis accuracy using DCE-MRI.
  • To assess the DL system's performance against board-certified radiologists and its generalizability across diverse datasets.
  • To evaluate the potential of the DL system in reducing unnecessary biopsies for BI-RADS category 4 lesions.

Main Methods:

  • A deep learning system was developed and tested on a large internal dataset (n = 3936 exams).
  • Retrospective reader studies were conducted comparing the DL system's performance to that of five breast radiologists.
  • Generalizability was assessed using multiple datasets from Poland and the United States, including an additional reader study on a Polish dataset.
  • Decision curve analysis and subgroup analyses were performed to evaluate clinical utility and robustness.

Main Results:

  • The DL system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 on the internal test set.
  • No statistically significant difference was found between the DL system and radiologists (mean ΔAUROC, +0.04).
  • Averaging radiologist and DL predictions improved performance (mean ΔAUPRC, +0.07).
  • The DL system demonstrated robustness to distribution shift and consistent results across cancer subtypes and demographics.
  • Decision curve analysis indicated the DL system could reduce benign biopsies by up to 20% for BI-RADS category 4 lesions.

Conclusions:

  • The developed DL system significantly improves breast cancer diagnosis accuracy with DCE-MRI, comparable to expert radiologists.
  • The DL system shows promise in reducing unnecessary biopsies, thereby personalizing patient management and healthcare costs.
  • This AI-driven approach provides a foundation for the clinical deployment and prospective evaluation of DL models in breast MRI interpretation.