Related Experiment Video
Updated: Feb 18, 2026
09:16
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
7.4K
A novel glomerular basement membrane segmentation using neutrsophic set and shearlet transform on microscopic images
Yanhui Guo1, Amira S Ashour2, Baiqing Sun3
1Department of Computer Science, University of Illinois at Springfield, Springfield, IL USA.
Health Information Science and Systems
|November 23, 2017
Summary
This study introduces a novel computer-aided detection system for accurate glomerular basement membrane segmentation in kidney disease images. The new method enhances segmentation accuracy using shearlet features and a neutrosophic set.
Area of Science:
- Medical Image Analysis
- Computational Pathology
- Nephrology Imaging
Background:
- Accurate segmentation of the glomerular basement membrane (GBM) is crucial for diagnosing kidney diseases from microscopic images.
- Existing methods face challenges due to significant variations in image appearance.
Purpose of the Study:
- To develop a computer-aided detection (CAD) system for precise GBM segmentation.
- To address the challenges of GBM extraction in microscopic kidney images.
Main Methods:
- A novel algorithm combining shearlet transform and neutrosophic set for GBM segmentation.
- Extraction of shearlet features, definition of a neutrosophic image, and reduction of indeterminacy using alpha-mean operation.
- Application of k-means clustering for segmentation and identification of GBM based on intensity features.
Main Results:
- The proposed method demonstrated improved GBM segmentation accuracy.
- Quantitative evaluation using average distance, Hausdorff distance, and percentage overlap area showed smaller errors and larger overlap.
- Specific average metrics achieved: AvgDist 1.99, HDist 4.59, POA 0.67.
Conclusions:
- The integration of shearlet features and neutrosophic set significantly enhances GBM segmentation accuracy.
- The developed method offers a promising approach for automated kidney disease analysis.
