IITM team consisting of Suthirth Vaidya (ED10B059) and Abhijit Chunduru (ED10B047), final year DD students of the Department of Engineering Design, has won the First Place at the Longitudinal Multiple Sclerosis Segmentation Challenge at ISBI 2015 held at New York. Out of 34 teams from 27 universities/institutions across 15 countries that entered the Challenge, a total of 12 teams (including Harvard, University College London, McGill, University of Lubeck) participated in the final round and the IITM entry was declared the best performing algorithm among all teams. The team was guided by Dr. Ganapathy Krishnamurthi and Dr. M. Ramanathan. The team’s participation in New York was supported by Alumni through their Travel Grant Programme.
An Abstract about the Challenge:
In the Longitudinal MS Lesion Segmentation Challenge, competing teams apply their automatic lesion segmentation algorithms to MR neuroimaging data acquired at multiple time points from MS patients. Algorithms would be evaluated against manual segmentations from multiple raters in terms of their segmentation accuracy and ability to track lesion evolution. This challenge comes seven years following the successful MICCAI 2008 lesion segmentation challenge. The image segmentation field has continued to develop new approaches in this time, and the added longitudinal dimension in the data will provide a new element for the competitors to consider in their algorithm development. Furthermore, the training and test data, which will be made publicly accessible, would provide a valuable new resource to the entire biomedical imaging community for determining the efficacy of longitudinal lesion segmentation algorithms in natural history studies and clinical trials.