Medical Image Segmentation Using Soft Computing Techniques

Purpose: In this research, soft computing technique for medical image segmentation is proposed that integrates with geographical information. Segmentation separates an image into discrete provinces, each containing pixels with similar properties. The regions should have a strong connection to the portrayed objects or aspects of interest in order to be expressive and effective for picture analysis and interpretation. For efficient accuracy, many soft computing and hard computing algorithms are employed for medical image segmentation. Soft computing is a recent method based on the concepts of approximation, uncertainty, and flexibility. Design/Methodology/Approach: For image segmentation, the suggested method is soft computing techniqueThis study discusses a variety of image segmentation approaches for medical image analysis. We have detailed the most recent segmentation algorithms used in medical image analysis in this study. Each method's benefits and drawbacks are discussed, as well as an evaluation of each algorithm's use in Magnetic Resonance Imaging. Findings/Result: The efficiency of the fuzzy logical information C-means clustering algorithm for identifying tissues in brain MR images is significantly higher than that of the FCM and fuzzy local information C-means clustering algorithm segmentation approaches.