Search research articles

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

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

Sort by

Same author

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

Bioengineering (Basel, Switzerland)·2025

Same author

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

Bioengineering (Basel, Switzerland)·2025

Same author

A Survey of Dental Caries Segmentation and Detection Techniques.

TheScientificWorldJournal·2022

Same author

Dental Images' Segmentation Using Threshold Connected Component Analysis.

Computational intelligence and neuroscience·2021

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 27, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

Vincent Majanga¹, Ernest Mnkandla¹, Donatien Koulla Moulla¹

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

Bioengineering (Basel, Switzerland)

|February 27, 2026

Summary

This summary is machine-generated.

This study introduces a novel Watershed Encoder-Decoder Neural Network (WEDN) for segmenting cancerous lesions in breast histology images. The WEDN model achieves high accuracy in early breast cancer detection using deep learning.

Keywords:

augmentation deep learning optimization watershed segmentation

More Related Videos

Using Computer Vision Libraries to Streamline Nuclei Quantification

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Jun 27, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Using Computer Vision Libraries to Streamline Nuclei Quantification

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

Area of Science:

Medical Image Analysis
Deep Learning in Oncology
Histopathology Segmentation

Background:

Deep learning excels in medical image analysis, particularly for cancer diagnosis.
Histology image segmentation is crucial for breast cancer diagnosis but faces challenges like poor quality and complex structures.
Existing U-Net models offer high accuracy with limited data, but improvements are needed.

Purpose of the Study:

To propose a novel Watershed Encoder-Decoder Neural Network (WEDN) for accurate segmentation of cancerous lesions in supervised breast histology images.
To enhance image pre-processing and segmentation techniques for improved lesion identification.
To evaluate the performance of the WEDN model in terms of accuracy, Dice coefficient, and IoU.

Main Methods:

Image augmentation to increase dataset size.
Data enhancement using thresholding, opening, dilation, and distance transform.
Connected component analysis and watershed filling for precise boundary identification.
WEDN model with residual convolutional blocks for feature extraction and learning.

Main Results:

The WEDN model achieved significant results on an augmented dataset of 3000 images.
Validation accuracy reached 98.53%.
Validation Dice coefficient was 96.98%, and validation Intersection over Union (IoU) was 97.84%.

Conclusions:

The proposed WEDN method effectively segments cancerous lesions in breast histology images.
The combination of data enhancement and WEDN shows high potential for improving breast cancer diagnosis.
The model demonstrates superior performance metrics, highlighting its clinical applicability.