Title: Automatic detection and classification of brain tumours using k-means clustering with classifiers
Authors: Narayanan Hema Rajini; Rajaram Bhavani
Addresses: Department of Computer Science and Engineering, Alagappa Chettiar Government College of Engineering and Technology, Karaikudi, 630003, India ' Department of Computer Science and Engineering, Annamalai University, Annamalai Nagar, 608 002, Tamilnadu, India
Abstract: A brain tumour detection and classification system has been designed and developed. This work presents a new approach to the automated detection and classification of astrocytoma, medulloblastoma, glioma, glioblastoma multiforme and craniopharyngioma type of brain tumours based on k-means clustering and texture features, which separate brain tumour from healthy tissues in magnetic resonance images. The magnetic resonance feature image used for the tumour detection consists of T2-weighted magnetic resonance images for each axial slice through the head. The application of the proposed method for tracking tumour is demonstrated to help pathologists distinguish exactly tumour region and its type of tumour. The results are quantitatively evaluated by a human expert. The average overlap metric, average precision and the average recall between the results obtained using the proposed approach and ground truth are 0.92, 0.97 and 0.92, respectively. A classification with accuracy of 100%, 99% and 98% has been obtained by SVM, ANN and decision tree.
Keywords: magnetic resonance imaging; MRI; k-means clustering; segmentation; grey level co-occurrence matrix; GLCM; tumour.
International Journal of Enterprise Network Management, 2019 Vol.10 No.1, pp.64 - 77
Received: 14 Feb 2018
Accepted: 09 May 2018
Published online: 28 Feb 2019 *