Improvements on the gray level co-occurrence matrix technique to compute ischemic stroke volume

Abstract

The purpose of this work was to apply and test Haralick's gray level co-occurrence matrix (GLCM) technique for automatic calculation and segmentation of the ischemic stroke volume from CT image. For this task, the 3-nearest neighbors classifier was trained to perform stroke and non-stroke area classification. The segmentation and classification results were compared versus a manual segmentation. Approximately half of the automatically computed and segmented stroke volumes from CT images differed less than 15% from the corresponding manually segmented stroke volumes.