Electron Microscopy Image Segmentation
Department of Electrical and Computer Engineering
University of Utah
Thursday, June 20, 14:40-15:30
In this talk, we will focus on the neuroscience application of connectomics. Connectomics is the problem of reconstructing neural circuit maps with implications for building models of neurons that are well grounded in anatomy. Electron microscopy image stacks provide sufficient resolution for this task; however, they also pose a daunting image analysis task due to their size, and the complexity of the structures that are imaged. Connectomics requires all individual neurons in the image stack to be segmented. We will introduce a series of image processing and machine learning steps towards solving this problem. More specifically, we will first describe a classification approach that labels each pixel in the electron microscopy images as cell membrane or not. We will then describe how to perceptually group the resulting cell membrane detection results to obtain cell segmentations.
Tolga Tasdizen received the B.S. degree in electrical and electronics engineering from Bogazici University in 1995. He received his M.S. and Ph.D. degrees in engineering from Brown University in 1997 and 2001, respectively. After working as a postdoctoral researcher position at the Scientific Computing and Imaging (SCI) Institute at the University of Utah, he was a Research Assistant Professor in the School of Computing at the same institution. Since 2008, he has been with the Department of Electrical and Computer Engineering at the University of Utah where he is currently an Associate Professor. Dr. Tasdizen is also a Utah Science Technology and Research Initiative (USTAR) faculty member in the SCI Institute. His research interests are in image processing, computer vision and pattern recognition with a focus on applications in biological and medical image analysis. Dr. Tasdizen is a recipient of the National Science Foundation’s CAREER award. He is a member of Bio Imaging and Signal Processing Technical Committee (BISP TC) of the IEEE Signal Processing Society and serves as an associate editor for the IEEE Signal Processing Letters and BMC Bioinformatics.