• Oskar Maier, Matthias Wilms, Janina von der Gablentz, Ulrike M Krämer, Thomas F Münte, and Heinz Handels.
• Institute of Medical Informatics, University of Lübeck, Germany; Graduate School for Computing in Medicine and Live Science, University of Lübeck, Germany. Electronic address: maier@imi.uni-luebeck.de.
• J. Neurosci. Methods. 2015 Jan 30; 240: 89-100.

BackgroundTo analyse the relationship between structure and (dys-)function of the brain after stroke, accurate and repeatable segmentation of the lesion area in magnetic resonance (MR) images is required. Manual delineation, the current gold standard, is time consuming and suffers from high intra- and inter-observer differences.New MethodA new approach is presented for the automatic and reproducible segmentation of sub-acute ischemic stroke lesions in MR images in the presence of other pathologies. The proposition is based on an Extra Tree forest framework for voxel-wise classification and mainly intensity derived image features are employed.ResultsA thorough investigation of multi-spectral variants, which combine the information from multiple MR sequences, finds the fluid attenuated inversion recovery sequence to be both required and sufficient for a good segmentation result. The accuracy can be further improved by adding features extracted from the T1-weighted and the diffusion weighted sequences. The use of other sequences is discouraged, as they impact negatively on the results.Comparison With Existing MethodsQuantitative evaluation was carried out on 37 clinical cases. With a Dice coefficient of 0.65, the method outperforms earlier published methods.ConclusionsThe approach proves especially suitable to differentiate between new stroke and other white matter lesions based on the FLAIR sequence alone. This, and the high overlap, renders it suitable for automatic screening of large databases of MR scans, e.g. for a subsequent neuropsychological investigation. Finally, each feature's importance is assessed in detail and the approach's statistical dependency on clinical and image characteristics is investigated.Copyright © 2014 Elsevier B.V. All rights reserved.

23 keywords...

hide…