期刊名称：Indian Journal of Computer Science and Engineering
印刷版ISSN：2231-3850
电子版ISSN：0976-5166
出版年度：2021
卷号：12
期号：2
页码：465-477
DOI：10.21817/indjcse/2021/v12i2/211202063
出版社：Engg Journals Publications
摘要：Medical image classification becomes an essential process in the healthcare sector for decision making using medicinal images. At the same time, brain tumor (BT) is considered the deadliest disease over the globe and it affects the brain tissues. So, it is needed to diagnose BT at the preliminary stages to enhance the survival rate of the patients. The goal of this paper is to derive an effective segmentation and classification technique for BT diagnosis. This paper designs an optimal Tsallis entropy based segmentation with deep extreme learning machine (OTSE-DELM) model for medical image classification using MRI images. The presented model involves multi-level thresholding based image segmentation using Tsallis entropy and the optimal threshold values are chosen by black widow optimization (BWO) algorithm. Besides, the presented model encompasses directional local extrema patterns (DLEP) based feature extractor. In addition, the OTSE-DELM model involves DELM based classification model to allocate the proper class labels of the test MRI images. A wide range of simulations was performed to showcase the betterment of the OTSE-DELM model and the outcomes are investigated under distinct dimensions. The experimental values make sure that the OTSE-DELM model is found to be superior to other methods by providing an increased sensitivity of 98.34%, specificity of 98.98%, and accuracy of 98.76%.
关键词：Brain tumor; image segmentation; image classification; deep learning; multi-level thresholding.
