ensemble semi-supervised framework for brain mris tissue segmentation

brain mr images tissue segmentation is one of the most important parts of the clinical diagnostic tools. pixel classification methods have been frequently used in the image segmentation with two supervised and unsupervised approaches up to now. supervised segmentation methods lead to high accuracy but they need a large amount of labeled data, which is hard, expensive and slow to obtain. moreover, they cannot use unlabeled data to train classifiers. on the other hand, unsupervised segmentation methods have no prior knowledge and lead to low level of performance. however, semi-supervised learning (ssl) which uses a few labeled data together with a large amount of unlabeled data causes higher accuracy with less trouble. in this paper, we propose an ensemble semi-supervised framework for segmenting of brain mris tissues that it has been used results of several semi-supervised classifiers simultaneously. selecting appropriate classifiers has an important role in the performance of this framework. hence, in this paper we present two semi-supervised algorithms efm and mco_training that are improved versions of semi-supervised methods em and co_training and increase segmentation accuracy. afterwards, we use these improved classifiers together with graph-based semi-supervised classifier as components of the ensemble framework. experimental results show that performance of segmentation in this approach is higher than both supervised methods and the individual semi-supervised classifiers