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

Influence of gadolinium-based contrast agent (GBCA) on the diffusion weightings of breast lesions: an intra-patient analysis.

Magma (New York, N.Y.)·2026
Same author

Leveraging modality-guided pre-training for dual-prompt-driven multi-cancer PET-CT segmentation.

Medical image analysis·2026
Same author

Can multimodal AI bridge imaging and prognosis in breast cancer?

European radiology·2026
Same author

Beyond Static Prediction: Tracking AI Breast Cancer Risk over Time.

Radiology·2026
Same author

Chemotherapy duration and patient-reported outcomes in HER2-positive early breast cancer: Results from the TRAIN-3 study.

European journal of cancer (Oxford, England : 1990)·2026
Same author

Towards robust foundation models for digital pathology.

Nature communications·2026

Related Experiment Video

Updated: Oct 25, 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

22.7K

Automatic breast lesion detection in ultrafast DCE-MRI using deep learning.

Fazael Ayatollahi1,2, Shahriar B Shokouhi1, Ritse M Mann2

  • 1Electrical Engineering Department, Iran University of Science and Technology (IUST), Tehran, Iran.

Medical Physics
|August 9, 2021
PubMed
Summary
This summary is machine-generated.

A new deep learning computer-aided detection (CADe) method effectively identifies breast lesions in ultrafast dynamic contrast-enhanced MRI (DCE-MRI). This AI approach improves detection of both benign and malignant tumors, including challenging cases.

Keywords:
breast lesion detectioncomputer-aided detectiondeep learningtwistultrafast magnetic resonance imaging (MRI)

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

3.1K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K

Related Experiment Videos

Last Updated: Oct 25, 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

22.7K
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

3.1K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Ultrafast dynamic contrast-enhanced MRI (DCE-MRI) offers rapid acquisition of breast imaging sequences.
  • Accurate detection of breast lesions, especially subtle ones, remains a challenge in screening settings.

Purpose of the Study:

  • To develop and evaluate a deep learning-based computer-aided detection (CADe) method for breast lesions in ultrafast DCE-MRI.
  • To leverage both spatial and temporal information from early-phase dynamic acquisitions for improved lesion detection.

Main Methods:

  • A modified 3D RetinaNet deep learning model was employed for lesion detection.
  • Preprocessing included motion compensation, temporal normalization, and cropping of ultrafast T1-weighted sequences.
  • The model was optimized for detecting small and difficult-to-differentiate breast lesions.

Main Results:

  • The CADe method achieved a lesion detection rate of 0.90, sensitivity of 0.95, and a detection rate for benign lesions of 0.81.
  • Performance was evaluated using 10-fold cross-testing on a dataset of 489 ultrafast MRI studies (572 lesions).
  • The system maintained a low false positive rate of 4 per normal breast.

Conclusions:

  • The deep learning CADe system demonstrates efficient detection of benign and malignant breast lesions on ultrafast DCE-MRI.
  • Incorporating hard-to-detect lesions into the training process enhances the model's ability to identify malignant breast cancers.