"A Comparative Study of Clustering Algorithms for Mri Spine Image Segmentation: Fuzzy C-Means, Region Growing, K-Means and Expectation-Maximization"
Main Article Content
Abstract
This study compares four methods—Fuzzy C-Means, Region Growing, K-Means, and Expectation-Maximization—for splitting MRI spine images into different sections. Accurate segmentation of MRI spine images is key for diagnosing, planning treatments, and keeping track of spine conditions. We assess each algorithm's performance in MRI spine picture segmentation and discuss its advantages, disadvantages, and common uses.FCM's ability to handle noise and overlapping structures, Region Growing's suitability for capturing irregular shapes, K-Means' computational efficiency, and EM's probabilistic modeling capabilities are examined in the context of MRI spine image segmentation. The comparative analysis aims to provide valuable insights into the performance and suitability of these algorithms for MRI spine image segmentation, thereby aiding medical professionals and researchers in selecting appropriate segmentation techniques for clinical and research purposes.