Adaboost and Support Vector Machines for White Matter Lesion Segmentation in MR Images

The use of two powerful classification techniques (boosting and SVM) is explored for the segmentation of white-matter lesions in the MRI scans of human brain. Simple features are generated from proton density (PD) scans. Radial basis function (RBF) based Adaboost technique and support vector machines (SVM) are employed for this task. The classifiers are trained on severe, moderate and mild cases. The segmentation is performed in T1 acquisition space rather than standard space (with more slices). Hence, the proposed approach requires less time for manual verification. The results indicate that the proposed approach can handle MR field inhomogeneities quite well and is completely independent from manual selection process so that it can be run under batch mode. Segmentation performance comparison with manual detection is also provided