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

5.4K
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...
5.4K

You might also read

Related Articles

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

Sort by
Same author

A multimodal deep learning classifier for prediction of HER2-low expression in triple-negative breast cancer.

BMC medical imaging·2026
Same author

Association of the planetary health diet score with obesity, high blood pressure, dyslipidemia, and cardiometabolic risk markers: Using data from the 2016-2020 Korea National Health and Nutrition Examination Survey.

PloS one·2026
Same author

COVID-19 Vaccination Effectiveness and Clinical Outcomes in Chronic Liver Disease: A Nationwide Retrospective Cohort Study.

Liver international : official journal of the International Association for the Study of the Liver·2026
Same author

The long non-coding RNA NEXUS arose from a chromosomal structural variation and enhances drought tolerance through epigenetic regulation in allotetraploid cotton.

Plant communications·2026
Same author

Determination of HU override for gold fiducial markers in proton therapy.

Journal of applied clinical medical physics·2026
Same author

Reynosin targets the PRDX6-AKT-WEE1 axis to suppress osteosarcoma and preserve the bone microenvironment.

Tissue & cell·2026

Related Experiment Video

Updated: Aug 14, 2025

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

6.9K

Deep Learning-based Automatic Diagnosis of Breast Cancer on MRI Using Mask R-CNN for Detection Followed by ResNet50

Yang Zhang1, Yan-Lin Liu2, Ke Nie3

  • 1Department of Radiological Sciences, University of California, Irvine, California; Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, New Jersey.

Academic Radiology
|January 11, 2023
PubMed
Summary

This study introduces an AI system combining Mask Region-Convolutional Neural Network (R-CNN) and ResNet50 for breast cancer detection on MRI. The AI accurately identifies suspicious lesions and estimates malignancy, significantly reducing false positives for improved diagnosis.

Keywords:
Breast MRIComputer-Aided Diagnosis (CAD)Deep LearningMask Reginal-Convolutional Neural Network (R-CNN)ResNet50

More Related Videos

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

Related Experiment Videos

Last Updated: Aug 14, 2025

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

6.9K
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

Area of Science:

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

Background:

  • Accurate breast cancer diagnosis on MRI is crucial for patient outcomes.
  • Current methods require manual identification and characterization of lesions.
  • Developing automated systems can enhance diagnostic efficiency and accuracy.

Purpose of the Study:

  • To implement and evaluate a deep learning model for automated breast cancer detection and malignancy assessment using MRI.
  • To combine lesion detection and characterization into a single diagnostic workflow.
  • To assess the system's performance in terms of sensitivity and false positive reduction.

Main Methods:

  • A Mask Region-Convolutional Neural Network (R-CNN) was employed for the initial detection of suspicious lesions in MRI scans.
  • ResNet50 was utilized for characterizing detected lesions and estimating their probability of malignancy.
  • Two distinct datasets were used for training and independent testing, incorporating pre-contrast and subtraction images for symmetry analysis.

Main Results:

  • The combined Mask R-CNN and ResNet50 system achieved a high sensitivity of 96% in detecting cancer on the first dataset and 81% on the independent test set.
  • ResNet50 effectively reduced false positives, eliminating approximately 80% of suspicious findings initially identified by Mask R-CNN.
  • The system demonstrated strong performance in differentiating malignant from benign lesions and normal tissue.

Conclusions:

  • The integration of Mask R-CNN for detection and ResNet50 for characterization shows significant potential for an automated breast cancer diagnostic system.
  • This AI-driven approach can improve the accuracy and efficiency of breast cancer diagnosis on MRI.
  • Further development could lead to a fully automated computer-aided diagnostic tool for clinical use.