Related Experiment Video
Updated: Apr 18, 2026
A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue
Published on: November 11, 2022
Texture analysis of collagen second-harmonic generation images based on local difference local binary pattern and
Yao Liu1, Xiaoqin Zhu1, Zufang Huang1
1Fujian Normal University, Institute of Laser and Optoelectronics Technology, Fujian Provincial Key Laboratory for Photonics Technology, Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, No.32 Shangsan Road, Can.
This study introduces a new texture analysis method using second-harmonic generation (SHG) images to accurately differentiate normal from abnormal scars. The advanced technique aids physicians in scar diagnosis by analyzing collagen morphology.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Dermatology
Background:
- Noninvasive scar diagnosis presents a significant clinical challenge.
- Quantitative methods are needed to objectively assess scar characteristics.
- Alterations in collagen morphology are key indicators of scar abnormality.
Purpose of the Study:
- To develop and validate a texture analysis method for quantitative scar classification.
- To discriminate between normal and abnormal scars using second-harmonic generation (SHG) imaging.
- To leverage collagen morphology changes for improved diagnostic accuracy.
Main Methods:
- Utilized a local difference local binary pattern (LD-LBP) operator combined with wavelet transform for feature extraction.
- Analyzed quantitative parameters such as homogeneity, directional, and coarse features from SHG images.
- Employed a support vector machine classifier with leave-one-out cross-validation for scar classification.
Main Results:
- Demonstrated significant differences in collagen morphological structure between normal and abnormal scars.
- The proposed LD-LBP and wavelet transform method achieved higher classification accuracy compared to existing techniques.
- Receiver operating characteristic (ROC) analysis confirmed the reliability and effectiveness of the developed method.
Conclusions:
- The developed texture analysis method effectively classifies scars based on SHG image features.
- Extracted texture features accurately reflect collagen morphology, aiding in scar differentiation.
- This approach offers valuable assistance to physicians in the noninvasive diagnosis of scars.
