Skip to main content Skip to navigation
BioImage Informatics Conference 2017

New Segmentation Approaches for High Throughput Connectomics

Nir Shavit, Professor of Electrical Engineering and Computer Science at MIT, and a Professor of Computer Science at Tel-Aviv University

Connectomics EM image stacks offer a difficult test for CNN-based segmentation/reconstruction systems because of the number of neuronal objects and their shapes can vary greatly from slice to slice. I will survey recent classification methods that improve the accuracy of segmentation by using CNNs to mimic the approach taken by human annotators. I will survey the gamut of new techniques from ones that track single neurons to ones that track hundred of neuronal objects simultaneously through the image stack. These techniques may be beneficial for other problem domains where the number of segmented objects and their shapes continuously vary.

Nir Shavit is a professor of electrical engineering and computer science at MIT and a professor of computer science at Tel-Aviv University. He received B.Sc. and M.Sc. degrees in Computer Science from the Technion – Israel Institute of Technology in 1984 and 1986, and a Ph.D. in Computer Science from the Hebrew University of Jerusalem in 1990. Shavit is a winner of the 2004 Gödel Prize in theoretical computer science and the 2012 Dijkstra Prize in Distributed Computing. He is a co-author of the book The Art of Multiprocessor Programming and is a fellow of the ACM. In recent years he has applied his knowledge of multicore programming to solving computational problems in neurobiology.