Related Experiment Video
Updated: May 10, 2026
06:43
Quantitative Analysis and Characterization of Atherosclerotic Lesions in the Murine Aortic Sinus
Published on: December 7, 2013
Automated segmentation of atherosclerotic histology based on pattern classification
Arna van Engelen1, Wiro J Niessen, Stefan Klein
1Biomedical Imaging Group Rotterdam, Department of Medical Informatics and Radiology, Erasmus Medical Centre, Rotterdam, Netherlands.
Journal of Pathology Informatics
|June 15, 2013
Summary
Automated histology segmentation accurately identifies atherosclerotic plaque components. This method aids in developing segmentation for other imaging techniques like MRI and CT, with improved accuracy using minimal manual input.
Area of Science:
- Biomedical Imaging
- Computational Pathology
- Cardiovascular Research
Background:
- Histology sections are crucial for analyzing atherosclerotic plaque composition.
- Current methods lack automated systems for plaque component segmentation in histology.
Purpose of the Study:
- To develop an automated system for segmenting fibrous, lipid, and necrotic tissue in histology sections.
- To evaluate the utility of automated histology segmentations for training cross-modality imaging techniques.
Main Methods:
- Pixel-wise classification using color intensity, texture, and structure features on Elastica Von Gieson-stained histology sections.
- Comparison of training strategies: independent data vs. limited manual annotation per specimen.
- Application of histology segmentations to train plaque component classification in ex vivo and in vivo MRI and CT.
Main Results:
- Achieved 75.7% pixel-wise accuracy in histology segmentation, improving to 77.6% with two manually annotated slices per specimen.
- High correlation (P = 0.82-0.98) between automated and manual relative component volumes.
- Automated histology segmentations enabled comparable training for MRI and CT plaque classification as manual ground truth.
Conclusions:
- Automated histology segmentation provides reliable plaque component analysis and correlates well with ground truth.
- The automated method effectively supports the development of segmentation algorithms for other imaging modalities.
- Incorporating one to two manually annotated sections per specimen significantly enhances accuracy with minimal user effort.
