Automated segmentation of atherosclerotic histology based on pattern classification
Related Experiment Video
Updated: May 10, 2026
Quantitative Analysis and Characterization of Atherosclerotic Lesions in the Murine Aortic Sinus
Published on: December 7, 2013
Arna van Engelen1, Wiro J Niessen, Stefan Klein
1Biomedical Imaging Group Rotterdam, Department of Medical Informatics and Radiology, Erasmus Medical Centre, Rotterdam, Netherlands.
Insights
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.
Background:
Histology sections provide accurate information on atherosclerotic plaque composition, and are used in various applications. To our knowledge, no automated systems for plaque component segmentation in histology sections currently exist.
Materials And Methods:
We perform pixel-wise classification of fibrous, lipid, and necrotic tissue in Elastica Von Gieson-stained histology sections, using features based on color channel intensity and local image texture and structure. We compare an approach where we train on independent data to an approach where we train on one or two sections per specimen in order to segment the remaining sections. We evaluate the results on segmentation accuracy in histology, and we use the obtained histology segmentations to train plaque component classification methods in ex vivo Magnetic resonance imaging (MRI) and in vivo MRI and computed tomography (CT).
Results:
In leave-one-specimen-out experiments on 176 histology slices of 13 plaques, a pixel-wise accuracy of 75.7 ± 6.8% was obtained. This increased to 77.6 ± 6.5% when two manually annotated slices of the specimen to be segmented were used for training. Rank correlations of relative component volumes with manually annotated volumes were high in this situation (P = 0.82-0.98). Using the obtained histology segmentations to train plaque component classification methods in ex vivo MRI and in vivo MRI and CT resulted in similar image segmentations for training on the automated histology segmentations as for training on a fully manual ground truth. The size of the lipid-rich necrotic core was significantly smaller when training on fully automated histology segmentations than when manually annotated histology sections were used. This difference was reduced and not statistically significant when one or two slices per section were manually annotated for histology segmentation.
Conclusions:
Good histology segmentations can be obtained by automated segmentation, which show good correlations with ground truth volumes. In addition, these can be used to develop segmentation methods in other imaging modalities. Accuracy increases when one or two sections of the same specimen are used for training, which requires a limited amount of user interaction in practice.
