Sparse Representations and Dictionary Learning Based Longitudinal Segmentation of Multiple Sclerosis Lesions

Sparse representations allow modeling data using a few basis elements of an over-complete dictionary and have been used in many image processing applications. We propose to use the sparse representation and dictionary learning paradigm to automatically segment Multiple Sclerosis (MS) lesions from longitudinal MR data. The dictionaries are learned for the lesion and healthy brain tissue classes, and a reconstruction error based classification approach is proposed for validation on challenge data set.