U-Net Supported Segmentation of Ischemic-Stroke-Lesion from Brain MRI Slices
Seifedine Kadry, Robertas Damaševičius, David Taniar, V. Rajinikanth, Isah A. Lawal
Abstract
The brain abnormality is one of the major sicknesses in human's health and the untreated brain defect will cause major illness. Ischemic stroke is one of the major medical emergencies and the timely diagnosis and treatment will save the patient from serious sickness. The proposed research employs the U-Net scheme to extort the Ischemic-Stoke-Lesion (ISL) from the brain MRI slices of ISLES2015 database. In this work, a pre-trained U-Net encoder-decoder system is employed to extort the ISL fragment from the chosen test image. After the extraction, a relative assessment is performed with the ground-truth available along with consequent test image. In this work, 20 patients' images (20 patient x 25 slices = 500 images) are adopted for the assessment and the general result achieved with the executed methodology helped to achieve a better value of Jaccard (>90%), Dice (>95%) and Accuracy (>98%) on the considered image dataset.