Rationale and Objectives: Brain lesions, especially white matter lesions (WMLs), are associated with cardiac and vascular disease, but also with normal aging. Quantitative analysis of WML in large clinical trials is becoming more and more important. Materials and Methods: In this article, we present a computer-assisted WML segmentation method, based on local features extracted from multiparametric magnetic resonance imaging (MRI) sequences (ie, T1-weighted, T2-weighted, proton density-weighted, and fluid attenuation inversion recovery MRI scans). A support vector machine classifier is first trained on expert-defined WMLs, and is then used to classify new scans. Results: Postprocessing analysis further reduces false positives by using anatomic knowledge and measures of distance from the training set. Conclusions: Cross-validation on a population of 35 patients from three different imaging sites with WMLs of varying sizes, shapes, and locations tests the robustness and accuracy of the proposed segmentation method, compared with the manual segmentation results from two experienced neuroradiologists.
- machine learning
- support vector machine
- White matter lesion segmentation
ASJC Scopus subject areas
- Radiology Nuclear Medicine and imaging