Multiple Sclerosis lesion segmentation using Active Contours model and adaptive outlier detection method

The segmentation of Multiple Sclerosis (MS) lesions on Magnetic Resonance Imaging (MRI) has become a crucial criterion for diagnosis and predicting prognosis in early disease. Automated MS lesion segmentation is highly desirable for its low time computation, cost, effectiveness and minimum user bias. We proposed to develop and evaluate an automated lesion segmentation method based on Active Contours (AC) model incorporating tissue knowledge issued from T1-weighted and tissues distribution on Attenuated Inversion recovery (FLAIR) image. The Gray Matter (GM) and White Matter (WM) as well as CerebroSpinal Fluid (CSF) tissue classes issued from from T1-weighted and the tissues intensities issued from FLAIR are used in order to determine an automatic outlier of each tissue class is used in order to detect outliers. The L2 metric used an integrated square estimator to detect outlier in order separate MS lesions from the other tissues. The algorithm is evaluated for (T1-weighted and FLAIR) public datasets of 20 MS patients. Comparing our results with lesion delineation by a human expert and with previously extensively validated results shows the promise of the proposed approach. These results require validation with data from other protocols based on a conventional FLAIR sequence and a T1-weighted sequence. Yet, we believe that our method allows fast and reliable segmentation of FLAIR-hyperintense lesions, which might simplify the quantification of lesions in basic research and even clinical trials.