Related Experiment Video
Updated: Apr 14, 2026
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
Published on: July 28, 2013
P-Count: Persistence-based Counting of White Matter Hyperintensities in Brain MRI
Xiaoling Hu1, Annabel Sorby-Adams1, Frederik Barkhof2,3
1Martinos Center for Biomedical Imaging, MGH and Harvard Medical School.
Abstract:
White matter hyperintensities (WMH) are a hallmark of cerebrovascular disease and multiple sclerosis. Automated WMH segmentation methods enable quantitative analysis via estimation of total lesion load, spatial distribution of lesions, and number of lesions (i.e., number of connected components after thresholding), all of which are correlated with patient outcomes. While the two former measures can generally be estimated robustly, the number of lesions is highly sensitive to noise and segmentation mistakes - even when small connected components are eroded or disregarded. In this article, we present P-Count, an algebraic WMH counting tool based on persistent homology that accounts for the topological features of WM lesions in a robust manner. Using computational geometry, P-Count takes the persistence of connected components into consideration, effectively filtering out the noisy WMH positives, resulting in a more accurate count of true lesions. We validated P-Count on the ISBI2015 longitudinal lesion segmentation dataset, where it produces significantly more accurate results than direct thresholding.
Insights
Persistent homology tool P-Count accurately counts white matter hyperintensities (WMH) lesions by considering topological features. This method enhances lesion counting accuracy, overcoming limitations of traditional segmentation methods in cerebrovascular disease and multiple sclerosis research.
Area of Science:
- Neuroimaging
- Computational Geometry
- Medical Image Analysis
Background:
- White matter hyperintensities (WMH) are key indicators in cerebrovascular disease and multiple sclerosis.
- Accurate WMH quantification, including lesion count, is crucial for patient outcome prediction.
- Traditional automated segmentation methods struggle with accurate lesion counting due to noise sensitivity.
Purpose of the Study:
- Introduce P-Count, a novel algebraic tool for robust WMH lesion counting.
- Utilize persistent homology to account for topological features of WM lesions.
- Improve the accuracy of WMH lesion enumeration compared to existing methods.
Main Methods:
- Developed P-Count, an algebraic tool leveraging persistent homology.
- Employed computational geometry to analyze the persistence of connected components.
- Filtered noisy WMH positives by considering lesion topology.
Main Results:
- P-Count demonstrated significantly more accurate WMH lesion counts.
- The method effectively filtered out false positives caused by noise and segmentation errors.
- Validation performed on the ISBI2015 longitudinal lesion segmentation dataset.
Conclusions:
- P-Count offers a robust and accurate method for counting WMH lesions.
- This topological approach overcomes limitations of direct thresholding in lesion quantification.
- P-Count enhances quantitative analysis for cerebrovascular disease and multiple sclerosis research.
More Related Videos
12:50Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
Published on: April 14, 2014
09:06Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
Published on: June 9, 2018
