Computer Vision for Connectomics // Dr. Toufiq Parag, Harvard University


Friday, February 24, 2017, 12:30pm to 2:00pm


Harvard SEAS, Maxwell Dworkin G115, 33 Oxford Street, Cambridge MA 02138

Abstract: Connectomics is an area of neuroscience aimed to discover the neuron shape and interconnections (neural network) within animal brain. A comprehensive knowledge of the biological neural network is critically important for a complete understanding of brain functionality. Recent advances in Electron Microscopic (EM) imaging have enabled us to capture the minuscule cellular processes at nanometer scale.  However, such ultra-high resolution recording also produces a massive amount of data that must be analyzed to extract the neurons. Practical neural reconstruction approaches rely on machine learning and computer vision algorithms such as segmentation and synaptic junction detection to perform this task. In this talk, I will describe how these tasks are addressed in multiple EM neural reconstruction efforts and mention a few biological discoveries made from some of these efforts.

Lunch will be served at 12:30pm on a first come, first served basis.  The talk will begin promptly at 1pm.

Bio: Dr Toufiq Parag is a Researcher in SEAS at Harvard University. His recent research interest is  the automatic reconstruction of neural circuits from Electron Microscopy (EM) images. At Harvard, he is working with Pfister lab (SEAS) and Lichtman lab (MCB) to reconstruct neurons from SEM images of mouse brain taken at nanometer scale. Before Harvard, he had been working at Janelia Research Campus on a similar connectomics effort on fruit fly brain. Dr Parag's algorithms were utilized in several neural reconstructions that led to important biological discoveries published in prestigious biological journal such as PNAS. He received his PhD from Rutgers Unversity in 2011 with a focus in computer vision and machine learning. Dr Parag has published many papers in leading computer vision conferences, journals and has been serving on their review boards for several years.

Free and open to the public.  No registration required.

See also: Seminar