An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis

Paul Schmidt, Christian Gaser, Milan Arsic, Dorothea Buck, Annette Förschler, Achim Berthele, Muna Hoshi, Rüdiger Ilg, Volker J. Schmid, Claus Zimmer, Bernhard Hemmer, Mark Mühlau
2012 NeuroImage  
Automatization of T2-hyperintense lesion volumetry is desirable 68 with regard to time and cost effectiveness but also constitutes a pre-69 requisite to minimize user bias. Up to now, a number of algorithms 70 have been proposed (Table 1) but no gold standard has been estab-71 lished. Therefore, in the vast majority of clinical trials, lesions were 72 traced manually slice by slicesometimes with the help of semi-73 automated tools for contour detection. 74 Here, we aimed at the development and
more » ... alidation of an automated 75 algorithm for segmentation of T2-hyperintense WM lesions in MS 76 based on a T2-weighted fluid-attenuated (FLAIR) and a three-NeuroImage xxx (2011) xxx-xxx ⁎
doi:10.1016/j.neuroimage.2011.11.032 pmid:22119648 fatcat:ibdycqqfcrhrjembydz6kw573y