Related Experiment Video
Updated: May 25, 2026
07:15
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
Published on: July 11, 2025
Bleeding detection in wireless capsule endoscopy images based on color invariants and spatial pyramids using support
Guolan Lv1, Guozheng Yan, Zhiwu Wang
1School of Electronics, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. 1090359015@sjtu.edu.cn
Summary
This study introduces an automated method for detecting bleeding in wireless capsule endoscopy (WCE) videos. The novel approach effectively identifies bleeding patterns, saving physicians valuable time.
Area of Science:
- Medical Imaging
- Gastroenterology
- Computer Vision
Background:
- Wireless capsule endoscopy (WCE) offers non-invasive gastrointestinal tract inspection.
- Manual review of WCE videos is time-consuming and labor-intensive for clinicians.
Purpose of the Study:
- To develop an automated method for detecting bleeding in WCE images.
- To improve the efficiency of WCE video analysis.
Main Methods:
- A novel series of descriptors combining color and spatial information was designed.
- Local and global features were incorporated into the descriptors.
- A kernel-based classification method using histogram intersection or chi-square was employed.
Main Results:
- The proposed descriptors demonstrated effectiveness in bleeding detection.
- The kernel-based classification scheme proved highly effective.
- Experimental results validated the proposed method's performance.
Conclusions:
- The developed automatic bleeding detection method is effective for WCE images.
- This technique can significantly reduce the time and effort required for WCE analysis.
- The proposed approach offers a promising solution for efficient gastrointestinal bleeding diagnosis.
