Ischemic Stroke Lesion Segmentation in Multi-Spectral MR Images with Support Vector Machine Classifiers

Oskar Maier, Matthias Wilms, Janina von der Gablentz, U Krämer, Heinz Handels


Automatic segmentation of ischemic stroke lesions in magnetic resonance (MR) images is important in clinical practice and for neuroscientific trials. The key problem is to detect largely inhomogeneous regions of varying sizes, shapes and locations. We present a stroke lesion segmentation method based on local features extracted from multi-spectral MR data that are selected to model a human observer’s discrimination criteria. A support vector machine classifier is trained on expert-segmented examples and then used to classify formerly unseen images. Leave-one-out cross validation on eight datasets with lesions of varying appearances is performed, showing our method to compare favourably with other published approaches in terms of accuracy and robustness. Furthermore, we compare a number of feature selectors and closely examine each feature’s and MR sequence’s contribution.
Original languageEnglish
Title of host publicationMedical Imaging 2014: Computer-Aided Diagnosis
EditorsGeorgia D. Tourassi, Samuel G. Armato
Number of pages12
Publication date24.03.2014
ISBN (Print)9781510600201
Publication statusPublished - 24.03.2014
EventSPIE Medical Imaging 2014: Computer-Aided Diagnosis
- San Diego, United States
Duration: 15.02.201420.02.2014


Dive into the research topics of 'Ischemic Stroke Lesion Segmentation in Multi-Spectral MR Images with Support Vector Machine Classifiers'. Together they form a unique fingerprint.

Cite this