Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 300-313 |
Number of pages | 14 |
Journal | Academic Radiology |
Volume | 15 |
Issue number | 3 |
DOIs | |
Publication status | Published - 2008 Mar |
Externally published | Yes |
Bibliographical note
Funding Information:Supported (in part) by the Intramural Research Program of the NIH, National Institute of Aging contract N01-HC-95178. Image analysis was supported in part by R01-AG-1497.
Funding Information:
We would like to thank the committee of ACCORD-MIND project, which is funded by the NIA through an intra-agency agreement with NIHLBI (Y3-HC-3065), for providing the datasets, valuable comments and giving us permissions to publish this paper. We also like to thank Ms. Lisa Desiderio for assistance in coordinating this study. Finally, we would like to thank patients recruited by ACCORD-MIND project.
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
Keywords
- White matter lesion segmentation
- machine learning
- support vector machine
ASJC Scopus subject areas
- Radiology Nuclear Medicine and imaging