Authors: Dulumani Das; Sanjib Kumar Kalita
Addresses: Department of Computer Science, Gauhati University, Guwahati-781014, Assam, India ' Department of Computer Science, Gauhati University, Guwahati-781014, Assam, India
Abstract: Skull stripping is the process of removing non-brain tissues like skull, skin, neck etc. from brain MRI as they cause difficulty in further analysis. The aim of this work is to extract the main region of brain by removing the non-brain tissues. The problem in skull stripping is to differentiate brain tissues from non-brain tissues due to their intensity inhomogeneity. In this work, five entropy-based thresholding methods are analysed to find a precise threshold for brain tissues. Those are maximum entropy sum method, entropic correlation method, Renyi's entropy, Tsallis entropy and modified Tsallis entropy method. In this study, 50 T1p weighted coronal MR images are considered for experiment. 80.4% accuracy is obtained with modified Tsallis entropy-based method. Further, the extracted brain is analysed for perimeter, hole size and boundary distance to diagnose Alzheimer's disease.
Keywords: skull stripping; Alzheimer's disease; magnetic resonance imaging; MRI; entropy-based thresholding; mathematical morphology.
International Journal of Biomedical Engineering and Technology, 2021 Vol.36 No.4, pp.331 - 349
Received: 06 May 2017
Accepted: 11 May 2018
Published online: 02 Aug 2021 *