Improvement of MRI Brain Image Segmentation Using Fuzzy Unsupervised Learning

Abstract

Background: Magnetic resonance imaging (MRI) plays an important role in clinical diagnosis. The ability of fuzzy c-mean (FCM) algorithm in segmenting MR images has been proven. Some MR images are contaminated with noise. FCM performance is degraded in noisy images. Several efforts are done to overcome this weakness. Objectives: The aim of this study was to propose a new method for MR image segmentation which is more resistant than other methods when noisy MR images are confronted. Materials and Methods: In this study, simulated brain database prepared by BrainWeb was be used for analysis. First FCM and its improvements were analysed and their ability in segmenting noisy MR images were evaluated. Next, knowing that applying genetic algorithm on improver fuzzy c-mean (IFCM) could improve its performance, a new segmentation method was proposed by applying particle swarm optimization on IFCM. Results: The proposed algorithm was applied on some intentionally noise-added MR images. Similarity between the segmented image and the original one was measured using Dice index. Other off-the-shelf algorithms were also tested in the same conditions. The indices were presented together. In order to compare the algorithms' performances, the experiments were repeated using different noisy images. Conclusion: The obtained results show that the proposed algorithms have better performance in segmenting noisy MR images than existing methods.

Multilevel Colonoscopy Histopathology Image Segmentation Using Particle Swarm Optimization Techniques

“…Li et al [ 33 ] proposed a level set model aided by PSO to solve automated medical image segmentation. Saneipour and Mohammadpoor [ 43 ] proposed a method by applying PSO on improver fuzzy c-mean algorithm for the segmentation of noisy MR images. Another PSO method for brain tumour segmentation is quantum-behaved PSO developed by Zhang and Zhang [ 60 ].…”

Integrated approach of brain segmentation using neuro fuzzy k-means

“…Saneipour and Mohammadpoor [12] have shed light on an automatic image segmentation method by using images of MRI machine through greedy snake model and optimization of fuzzy c means method. According to them, brain segmentation process can be grouped into four categories or groups: Threshold based segmentation technique, Region based segmentation, edge based segmentation technique and clustering based segmentation [13], [14].…”