Meeting Banner
Abstract #4318

Knowledge-Driven Automated Segmentation of Cortical Lesions on MR Brain Images in MS

Sushmita Datta1, Jerry S. Wolinsky2, Ponnada A. Narayana1

1Diagnostic and Interventional Imaging, The University of Texas Medical School at Houston, Houston, TX, United States; 2Neurology, The University of Texas Medical School at Houston, Houston, TX, United States


A knowledge-based technique for segmenting cortical lesions in multiple sclerosis (MS) with minimal human intervention is presented. This method relies on double inversion recovery and phase sensitive inversion recovery images combined with morphological operations. To the best of our knowledge, this is the first study that addresses the segmentation of cortical lesions in MS.

Keywords