A spatial fuzzy C-means algorithm with application to MRI image segmentation

Abstract

The standard fuzzy C-means (FCM) algorithm does not fully utilize the spatial information for image segmentation and is sensitive to noise especially in the presence of intensity inhomogeneity in magnetic resonance imaging (MRI) images. The underlying reason is that a single fuzzy membership function in FCM algorithm cannot properly represent pattern associations to all clusters. In this paper, we present a spatial fuzzy C-means (SpFCM) algorithm for the segmentation of MRI images. The algorithm utilizes spatial information from the neighbourhood of each pixel under consideration and is realized by defining a probability function. A new membership function is introduced using this spatial information to generate local membership values for each pixel. Finally, new clustering centers and weighted joint membership functions are presented based on the local and global membership functions. The resulting SpFCM algorithm solves the problem of sensitivity to noise and intensity inhomogeneity in MRI data and thereby improves the segmentation results. The experimental results on several simulated and real-patient MRI brain images show that the SpFCM algorithm has superior performance on image segmentation when compared to some FCM-based algorithms.

A Hybrid Enhanced Independent Component Analysis Approach for Segmentation of Brain Magnetic Resonance Image

“…In this equation mean squared error (MSE) for two * MN monochrome images f and z and it is given by Eqn. (16). Max Bits gives the maximum possible pixel value (255) of the image.…”

“…Support vector machine was used as a classifier. Adhikari 16 , et al presented a spatial fuzzy C-means (SPfCM) algorithm for segmentation of magnetic resonance images. They employed spatial information from the neighborhood of each pixel and realised by defining a probability function.…”

Image segmentation by multi-level thresholding based on fuzzy entropy and genetic algorithm in cloud

“…But it has some serious limitations as it is very sensitive to noise and imaging artifacts. It can also generate local optimal solution due to poor initialization [22,23]. In order to make the soft computing more robust we present a new soft computing based segmentation procedures by using a new fuzzy entropy based criteria (cost function), Genetic algorithm.…”

“…Intensity-based methods identify local features such as edges and texture in order to extract regions of interest [10,11,[18][19][20][21][22][23][24][25]. Thresholding method is one of the most common methods for the segmentation.…”

Segmentation of Cerebrospinal Fluid from 3D CT Brain Scans Using Modified Fuzzy C-Means Based on Super-Voxels

“…it provides the best results for overlapped data sets of pixels) it is especially popular when the segmentation of medical images is required [2]. In particular, there was a significant number of attempts to apply FCM clustering for brain segmentation [3], [4], [5]. These works however consider mainly MRI datasets.…”