Zhang to develop new method for type of cancer imaging

Zhang

Weixiong Zhang, professor of computer science & engineering in the McKelvey School of Engineering and of genetics at the School of Medicine, has received a two-year, $174,003 grant from the Varian Research Collaboration Program. With the funding, Zhang will develop a new method for semantic image segmentation, a type of computer vision often used to diagnose, plan treatment and provide a prognosis to patients with cancer. The new method will incorporate a spectral graph convolution neural network-based method and a representation scheme of Markov random fields to increase the segmentation accuracy. He is collaborating with Baozhou Sun, assistant professor of radiation oncology at the School of Medicine. They also plan to develop a software system and module that can be integrated into Varian's treatment planning system.