Computational NeuroscienceAutomated quantification of white matter lesion in magnetic resonance imaging of patients with acute infarction

PurposeIt has been reported that increased white matter lesions (WML) is one of the risk factors for stroke. To quantify WML objectively with the presence of acute infarcts, we proposed an automated segmentation scheme to locate WMLs in combined T1-weighted MRI, fluid attenuation inversion recovery (FLAIR) and diffusion weighted imaging (DWI).Materials and methodsThe proposed method detects WMLs by a coarse-to-fine mathematical morphology method. It has been evaluated quantitatively and qualitatively using voxel-based, volume-based, score-based, and atlas-based approaches on MRI data of 91 subjects with acute infarction.ResultThe proposed WML detection algorithm yields average sensitivity, positive predictive value and similarity index of 0.803, 0.818, and 0.836, respectively. Experimental results demonstrated that the segmentation from the proposed method is in high agreement with that from manual segmentation (intraclass correlation coefficient = 0.9892), and with a good correlation with visual scores (R = 0.8442, p < 0.0001).

► Detects WML by a coarse-to-fine mathematical morphology method. ► Able to differentiate the WML and acute infarction. ► Evaluated using voxel-based, volume-based, score-based, and atlas-based approaches on MRI data of 91 subjects with acute infarction. ► WMLs detection accuracy: average sensitivity: 0.803; positive predictive value: 0.818 and similarity index: 0.836.