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 Experiment Video

Updated: Dec 1, 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

22.9K

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses on Breast DCE-MRI Images Using

Akiyoshi Hizukuri1, Ryohei Nakayama2, Mayumi Nara3

  • 1Department of Electronic and Computer Engineering, Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga, 525-8577,, Japan. hizukuri@fc.ritsumei.ac.jp.

Journal of Digital Imaging
|November 7, 2020
PubMed
Summary

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

Report From the 32nd Annual Congress of the Japanese Society for Aeromedical Services.

Air medical journal·2026
Same author

Computerized Classification Method for Glioma Molecular Subtypes on Brain MR Images Using SAM-Med3D with Low-Rank Adaptation.

Journal of imaging informatics in medicine·2026
Same author

[Weight change following a self-selected, type-tailored lifestyle modification program for employees with suspected visceral fat accumulation: A single-arm before-after study].

Sangyo eiseigaku zasshi = Journal of occupational health·2026
Same author

Case Report: response of HER2-positive ductal carcinoma <i>in situ</i> to osimertinib with supporting <i>in vitro</i> evidence.

Frontiers in oncology·2026
Same author

Earlier first-time memory clinic visits during the COVID-19 pandemic: A comparison of dementia severity and caregiver burden.

Journal of family medicine and primary care·2026
Same author

Everyday Memory Failures as a Latent Risk Factor for Falls in Patients With Alzheimer's Disease.

Geriatrics & gerontology international·2026

A novel computer-aided diagnosis (CAD) scheme using deep convolutional neural networks (DCNNs) with Bayesian optimization significantly improved the accuracy of distinguishing benign from malignant breast masses on dynamic contrast-enhanced MRI (DCE-MRI). This AI tool aids radiologists in breast cancer diagnosis.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Dynamic contrast-enhanced MRI (DCE-MRI) offers higher sensitivity for early breast cancer detection than mammography but suffers from lower specificity.
  • Accurate differentiation between benign and malignant breast masses is crucial for effective patient management and treatment decisions.

Purpose of the Study:

  • To develop and evaluate a computer-aided diagnosis (CAD) scheme utilizing a deep convolutional neural network (DCNN) optimized with Bayesian methods.
  • The goal was to enhance the specificity and accuracy in classifying breast masses detected via DCE-MRI.

Main Methods:

  • A DCNN model was optimized using Bayesian optimization to tune hyperparameters like layers, filter size, and number of filters.
  • Regions of interest containing entire masses were extracted from 56 DCE-MRI examinations (26 benign, 30 malignant).
Keywords:
Bayesian optimizationBreast magnetic resonance imagingComputer-aided diagnosisDeep convolutional neural networkMass

More Related Videos

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

7.2K

Related Experiment Videos

Last Updated: Dec 1, 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

22.9K
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

7.2K
  • A three-fold cross-validation method was employed for model training and testing.

    • Main Results:

    • The optimized DCNN achieved a high classification accuracy of 92.9% (52/56).
    • Sensitivity and specificity were reported at 93.3% (28/30) and 92.3% (24/26), respectively.
    • Positive and negative predictive values were also high, indicating robust diagnostic performance.

    Conclusions:

    • The proposed DCNN-based CAD scheme demonstrates superior performance compared to conventional methods relying on handcrafted features.
    • This AI-driven approach shows significant potential as a valuable diagnostic aid for radiologists in interpreting breast DCE-MRI scans.
    • The findings suggest that DCNNs with Bayesian optimization can effectively improve the differential diagnosis of breast masses.