MRI Segmentation through Wavelets and Fuzzy C-Means

Segmentation of images, obtained by Magnetic Resonance Imaging (MRI), is a difficult task due to the inherent noise and inhomogeneity. This paper presents a technique to segment MRI images that is robust against noise. Discrete Wavelet Transform (DWT) is applied to MRI image to extract high level details and after some processing on this high pass image, we add it to the original image to get a sharpened image. The processing includes the Fuzzy C-means (FCM) segmentation algorithmapplied to the wavelet transformed image and Kirch's line/edge detection mask, to further enhance the edge detail in the image. The noise-robust nature of wavelets and the noise-sensitivity of FCM combine in our method to give better accuracy results.

[1]  Mohamed Roushdy.  Comparative Study of Edge Detection Algorithms Applying on the Grayscale Noisy Image Using Morphological Filter , 2006 .

[2]  M. Ashtiyani,et al.  MRI Segmentation Using Fuzzy C-means Clustering Algorithm Basis Neural Network , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[3]  J Toriwaki,et al.  Automatic segmentation of head MRI images by knowledge guided thresholding. , 1991, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[4]  Wei-Guang Teng,et al.  Exploiting the Self-Organizing Map for Medical Image Segmentation , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[5]  M. M. Ahmed,et al.  Segmentation of Brain MR Images for Tumor Extraction by Combining Kmeans Clustering and Perona-Malik Anisotropic Diffusion Model , 2008 .

[6]  Andrzej Bargiela,et al.  Automatic brain MRI segmentation scheme based on feature weighting factors selection on fuzzy c-means clustering algorithms with Gaussian smoothing , 2010, CI 2010.

[7]  Ning Li,et al.  Image Segmentation Algorithm using Watershed Transform and Level Set Method , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[8]  M. Dylan Tisdall,et al.  MRI denoising via phase error estimation , 2005, SPIE Medical Imaging.

[9]  James C. Bezdek,et al.  A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain , 1992, IEEE Trans. Neural Networks.

[10]  Sanjay Sharma,et al.  Brain Tumor Detection based on Multi-parameter MRI Image Analysis , 2009 .

[11]  Edoardo Ardizzone,et al.  Fuzzy C-Means Segmentation on Brain MR Slices Corrupted by RF-Inhomogeneity , 2007, WILF.

[12]  Abdul Rahman Ramli,et al.  Review of brain MRI image segmentation methods , 2010, Artificial Intelligence Review.

[13]  Miao Qi,et al.  A Modified FCM Algorithm for MRI Brain Image Segmentation , 2008, 2008 International Seminar on Future BioMedical Information Engineering.

[14]  Richard A. Robb,et al.  Biomedical Imaging, Visualization, and Analysis , 1999 .

[15]  S. Mashohor,et al.  New multi-scale medical image segmentation based on fuzzy c-mean (FCM) , 2008, 2008 IEEE Conference on Innovative Technologies in Intelligent Systems and Industrial Applications.