RETRACTED ARTICLE: Identification of lesion using an efficient hybrid algorithm for MRI brain image segmentation

Abstract

Splitting the image into mutually exclusive regions is referred to as image segmentation. The demarcation, portrayal, and cognitive imaging of expanses of preference in any MR images is segmentation. Identifying the expanses of preference is considered the most complicated task since there are great diversities identified in the MRI images. Diversities in the image content, huddled objects, constriction, image noise, non-uniform object quality, and other factors are responsible for complications identified in the segmentation process. Various techniques and algorithms are being designed and made available for image segmentation. But still, there is a good scope for developing a resourceful, dissolute procedure for curative image segmentation. The proposed work aims to spot the disbelieving region from the related region in the MRI brain Image using Fractional Order BAT Algorithm Fuzzy C. In this paper, Delaunay triangulation (DT) recompenses and fractional order nature-inspired algorithms are used to segment the lesion's assembly from brain tissue meritoriously. The approach is corroborated with 450 MR images gained from different sources or subjects. The relevant features are extracted and based on the results of Fuzzy C Means, and the image is segmented as normal or abnormal. The method provided a considerable improvement over the existing mechanisms adopted for segmentation based on evaluation parameters like sensitivity, accuracy, Jaccard Index. The mechanism helps radiologists in validating their screening activities effectively.