Related Experiment Video
Updated: May 3, 2026
07:05
Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
Published on: February 15, 2022
2.0K
Color edges extraction using statistical features and automatic threshold technique: application to the breast cancer
Salim Ben Chaabane1, Farhat Fnaiech
1SIME Research Laboratory, ENSIT University of Tunis, 5 Av, Taha Hussein, 1008 Tunis, Tunisia. ben_chaabane_salim@yahoo.fr.
Biomedical Engineering Online
|January 25, 2014
Summary
This study introduces a new color image segmentation method for breast cancer cells, significantly improving accuracy and cell counting for medical diagnosis. The enhanced technique offers clearer cell visualization and aids doctors in disease follow-up.
Area of Science:
- Medical Imaging
- Computer Vision
- Biomedical Engineering
Background:
- Color image segmentation is crucial in various fields, including medical imaging for disease follow-up.
- Breast cancer image analysis benefits from accurate cell segmentation for diagnosis and monitoring.
- Existing segmentation techniques may struggle with incomplete or overlapping cells, necessitating improved methods.
Purpose of the Study:
- To develop and enhance a novel color image segmentation method for breast cancer cell analysis.
- To accurately segment, rebuild, and enhance individual cells from three-component images.
- To provide a tool that assists doctors in clearly identifying and counting cells for disease management.
Main Methods:
- A novel method for color edge extraction using statistical features and automatic thresholding.
- Extension of traditional edge detection to the statistical domain by considering pixel neighborhoods.
- Integration of edge results across three color components using a combination rule for primitive colors.
Main Results:
- The proposed method was evaluated on breast cancer cell images, showing superior performance.
- Quantitative and qualitative assessments demonstrated improved detection of cell points and easier cell counting.
- The method achieved high classification accuracy, reaching 97.94% in simulations.
Conclusions:
- The novel segmentation method significantly enhances image segmentation with lower error rates compared to existing algorithms.
- High classification accuracy and improved cell counting facilitate better breast cancer diagnosis and patient monitoring.
- The segmentation technique shows potential for application in other medical imaging modalities with similar characteristics.
