An efficient automated methodology for detecting and segmenting the ischemic stroke in brain MRI images. Issue 3 (September 2017)

• Record Type: Journal Article
• Authors: Sivakumar, P.; Ganeshkumar, P.
• Is Part Of: International journal of imaging systems and technology. Volume 27:Issue 3(2017)
• Page Start: 265
• Page End: 272
• Publication Date: 2017-09
• Subjects: brain stroke -- classification -- ischemic stroke -- morphological features -- texture features; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22231
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Brain tumor and brain stroke are two important causes of death in and around the world. The abnormalities in brain cell leads to brain stroke and obstruction in blood flow to brain cells leads to brain stroke. In this article, a computer aided automatic methodology is proposed to detect and segment ischemic stroke in brain MRI images using Adaptive Neuro Fuzzy Inference (ANFIS) classifier. The proposed method consists of preprocessing, feature extraction and classification. The brain image is enhanced using Heuristic histogram equalization technique. Then, texture and morphological features are extracted from the preprocessed image. These features are optimized using Genetic Algorithm and trained and classified using ANFIS classifier. The performance of the proposed ischemic stroke detection system is analyzed in terms of sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and Mathew's correlation coefficient.