Open Access
Subscription or Fee Access
A Brain MRI Segmentation Scheme Based on FCM Algorithm and MRF Models
Dangui Chen, Jia Tang
Abstract
Brain magnetic resonance imaging (MRI) has been a large number of applications in the clinic and accurate split of brain tissue’s structure. They can improve the reliability of the diagnosis of brain diseases and the effectiveness of treatment programs. For specializes in solving image fuzziness and uncertainty, fuzzy C-means clustering (FCM) algorithm is the most common used in brain MRI segmentation. But FCM is only utilized for the image gray information, without considering regional information. It would lead to its anti-noise performance. They often are improved in conjunction with regional information. Markov Random Field (MRF) models have taken full advantage of the image area information. It is prone to over-segmentation phenomenon combined with improved FCM and MRF. The improvements compared with the existed FCM and MRF method are combined a new adaptive weights combined with FCM and MRF algorithm for brain MRI segmentation. The algorithm has used image pixel area of the image neighborhood correlation. The adaptive joint field weight can improve existing combination weights. The combination of FCM and MRF is more reasonable than before. The experiment results are shown that the proposed algorithm is compared with FCM and the existed some FCM improvements of algorithm are greater noise immunity and higher segmentation accuracy.
Keywords
Markov Random Field, Fuzzy C-means Clustering, Brain MRI, Image Segmentation.
Full Text:
PDF
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.