Ensemble Semisupervised Frame work for Brain Magnetic Resonance Imaging Tissue Segmentation

Brain magnetic resonance images (mris) tissue segmentation is one of the most important parts of the clinical diagnostic tools. pixelclassification methods have been frequently used in the image segmentation with two supervised and unsupervised approaches up tonow. 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 segmentationmethods have no prior knowledge and lead to low level of performance. however, semi supervised learning which uses a few labeleddata together with a large amount of unlabeled data causes higher accuracy with less trouble. in this paper, we propose an ensemblesemi supervised frame work for segmenting of brain magnetic resonance imaging (mri) tissues that it has been used results ofseveral semi supervised classifiers simultaneously. selecting appropriate classifiers has a significant role in the performance of thisframe work. hence, in this paper, we present two semi supervised algorithms expectation filtering maximization and mco training thatare improved versions of semi supervised methods expectation maximization and co training and increase segmentation accuracy.afterward, we use these improved classifiers together with graph based semi supervised classifier as components of the ensembleframe work. experimental results show that performance of segmentation in this approach is higher than both supervised methodsand the individual semi supervised classifiers.