Segmentation of MS lesions using Active Contour Model, Adaptive Mixtures Method and MRF model
Ahmad Bijar, Rasoul Mahdavifar Khayati · International Symposium on Image and Signal Processing and Analysis · 2011
This paper presents an approach for fully automatic segmentation of MS lesions in fluid attenuated inversion recovery (FLAIR) Magnetic Resonance (MR) images. The proposed method estimates a gaussian mixture model with three components as cerebrospinal fluid (CSF), normal tissue and MS lesions. To estimate this model, a region based Active Contour Model (ACM) is used to find the best initial values of model parameters. Then, Adaptive Mixture Method and Markov Random Field (MRF) model are utilized to obtain and upgrade the class conditional probability density function and the apriori probability of each class. After estimation of Model parameters and apriori probabilities, brain tissues are classified using Bayesian Classification. To evaluate the result of proposed method, the similarity criteria of different slices related to 20 MS patients are calculated and compared with other methods which include manual segmentation. Also, volume of segmented lesions are computed and compared with gold standard using correlation coefficient. The proposed method has better performance in comparison with previous works which are reported here.