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

Advanced deep learning framework for breast cancer detection using digital breast tomosynthesis images.

Biomedizinische Technik. Biomedical engineering·2026
Same author

Classification of EMG signals with CNN features and voting ensemble classifier.

Computer methods in biomechanics and biomedical engineering·2024
Same author

Estimation of protein from the images of health drink powders.

Journal of food science and technology·2020
Same author

Development of an ICU discharge instrument predicting psychological morbidity: a multinational study.

Intensive care medicine·2018
Same author

Toward Optimum Benefit-Risk and Reduced Access Lag For Cancer Drugs in Asia: A Global Development Framework Guided by Clinical Pharmacology Principles.

Clinical and translational science·2016
Same author

Improved algorithm for analysis of DNA sequences using multiresolution transformation.

TheScientificWorldJournal·2015

Related Experiment Video

Updated: Jun 7, 2025

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

2.7K

Segmentation of breast lesion using fuzzy thresholding and deep learning.

C Sahaya Pushpa Sarmila Star1, T M Inbamalar2, A Milton1

  • 1Dept. of Electronics and Communication Engineering, St. Xavier's Catholic College of Engineering, Chunkankadai, Tamil Nadu, India.

Computers in Biology and Medicine
|November 12, 2024
PubMed
Summary

This study enhances breast cancer lesion detection using Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI). Combining Fuzzy C-mean Thresholding (FCMTH) with deep learning significantly improves segmentation accuracy for better screening outcomes.

Keywords:
Anisotropic diffusion filterBreast lesionDeepLabV3+Fuzzy C-Mean clusterSegNetThresholding

More Related Videos

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

Related Experiment Videos

Last Updated: Jun 7, 2025

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

2.7K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Breast cancer remains a leading cause of morbidity and mortality in women.
  • Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) shows potential for breast cancer screening by analyzing tissue enhancement patterns.
  • Accurate segmentation of breast lesions is crucial for effective screening and diagnosis.

Purpose of the Study:

  • To propose and evaluate an enhanced segmentation method for breast lesions in DCE-MRI images.
  • To compare the performance of different segmentation techniques, including Fuzzy C-mean Thresholding (FCMTH) and deep learning models.
  • To determine the optimal combination of preprocessing and segmentation for improved lesion detection.

Main Methods:

  • Experiments were conducted on 123 breast DCE-MRI slices from seven patients obtained from The Cancer Image Archive.
  • Three segmentation approaches were tested: FCMTH with morphological operations, deep learning on original images, and deep learning on preprocessed images.
  • Deep learning networks were trained using images preprocessed with the FCMTH technique.

Main Results:

  • FCMTH achieved Dice and Jaccard coefficients of 0.8458 and 0.7471, respectively.
  • DeepLabv3+ with MobileNetv2, trained on FCMTH-preprocessed images, achieved superior Dice and Jaccard coefficients of 0.9468 and 0.8990.
  • Preprocessing using FCMTH significantly enhanced the accuracy of deep learning-based segmentation.

Conclusions:

  • The combination of deep learning and FCMTH techniques offers the best performance for breast lesion segmentation in DCE-MRI.
  • This enhanced approach holds promise for improving the accuracy and reliability of breast cancer screening.
  • Further research can explore this hybrid methodology for clinical application in breast cancer diagnosis.