Anant Madabhushi, professor of biomedical engineering and director of the Center for Computational Imaging and Personalized Diagnostics, was recently awarded U.S. patent 9,292,933, titled “Method and apparatus for shape based deformable segmentation of multiple overlapping objects.”
The present invention provides a system and method for simultaneous variational and adaptive segmentation of single non-overlapping and multiple overlapping/occluded-objects in an image scene. The method according to the present invention synergistically combines shape priors with boundary and region-based active contours in a level set formulation with a watershed scheme for model initialization for identifying and resolving multiple object overlaps in an image scene. The method comprises learning a shape prior for a target object of interest and applying the shape prior into a hybrid active contour model to segment overlapping and non-overlapping objects simultaneously.
Co-inventor on this technology is Sahirzeeshan Ali, graduate student in electrical engineering and computer science at CWRU.
The technology has been licensed to Florida-based cancer diagnostics company Inspirata Inc.
Madabhushi also recently received a grant from China’s State Administration Program for High-end Foreign Experts.
The grant is for one year and is for approximately $33,000. The goal of the program is to have foreign scientists who are leaders in natural science and technology, humanities, and social science visit China with the intent of engendering research collaborations.
Madabhushi will be hosted by Jun Xu, a former research associate of Madabhushi’s and now a professor at Nanjing University of Information Science and Technology.
As part of a project on “Computer-aided Diagnosis of Cancer,” Madabhushi will participate in a technical workshop at the Shanghai University of Engineering Science and meet and interact with imaging and clinical researchers with an interest in computational imaging and precision medicine.