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

Watershed Encoder-Decoder Neural Network for Nuclei Segmentation of Breast Cancer Histology Images.

Bioengineering (Basel, Switzerland)·2026
Same author

Quantum AI in Speech Emotion Recognition.

Entropy (Basel, Switzerland)·2025
Same author

Automatic Blob Detection Method for Cancerous Lesions in Unsupervised Breast Histology Images.

Bioengineering (Basel, Switzerland)·2025
Same author

Few-Shot Learning for Image-Based Nonintrusive Appliance Signal Recognition.

Computational intelligence and neuroscience·2022
Same author

Conservative dynamics in a novel class of 3D generalized thermostatted systems.

Chaos (Woodbury, N.Y.)·2022
Same author

A Survey of Dental Caries Segmentation and Detection Techniques.

TheScientificWorldJournal·2022

Related Experiment Video

Updated: Sep 18, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

Active Contours Connected Component Analysis Segmentation Method of Cancerous Lesions in Unsupervised Breast

Vincent Majanga1, Ernest Mnkandla1, Zenghui Wang1

  • 1Department of Computer Science, University of South Africa, Preller Street, Muckleneuk Ridge, Pretoria 1709, South Africa.

Bioengineering (Basel, Switzerland)
|June 26, 2025
PubMed
Summary

This study introduces a hybrid active contour method for segmenting nuclei in breast cancer histology images, improving accuracy in computer-aided diagnosis. The novel approach effectively separates overlapping nuclei, aiding early cancer detection.

Keywords:
active contours segmentationdata augmentationdeep learningstain normalization technique

More Related Videos

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
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

2.5K

Related Experiment Videos

Last Updated: Sep 18, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
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

2.5K

Area of Science:

  • Medical Imaging
  • Computational Pathology
  • Artificial Intelligence

Background:

  • Accurate nuclei segmentation in breast cancer histology is crucial for early diagnosis and computer-aided approaches.
  • Overlapping nuclei and tissue variability present significant challenges for conventional segmentation methods.
  • Existing active contour methods struggle with resolving intersecting objects and segmenting multiple overlapping nuclei.

Purpose of the Study:

  • To develop a hybrid active contour method for accurate segmentation of cancerous lesions in unsupervised human breast histology images.
  • To overcome the limitations of traditional active contour methods in handling overlapping nuclei.
  • To enhance computer-aided diagnosis by providing precise nuclei segmentation.

Main Methods:

  • A hybrid approach combining connected components analysis and active contours was developed.
  • Data augmentation and stain normalization were applied for robust feature extraction.
  • Morphological operations (erosion, dilation, distance transform) and connected components analysis were used to preprocess nuclei objects.
  • A deep learning recurrent neural network (RNN) model segmented nuclei using active contours based on preprocessed data.

Main Results:

  • The proposed hybrid method achieved a high accuracy score of 98.71% on an augmented dataset of 15,179 images.
  • The method effectively addressed the challenge of segmenting overlapping nuclei.
  • Significant improvements in nuclei segmentation accuracy were demonstrated.

Conclusions:

  • The hybrid active contour method offers a robust solution for nuclei segmentation in breast cancer histology.
  • This approach enhances the capabilities of computer-aided diagnostic systems for early cancer detection.
  • The integration of connected components analysis with active contours effectively resolves limitations in segmenting complex histological structures.