Dr. Joshua Cates - Research Computer Scientist
Josh has a background in computer science, biology, and mathematics. He has worked on various problems in computer vision, including image processing (differential geometry and p.d.e-based methods), image segmentation, computed tomography, and algorithm validation. He received his MS in Computer Science in May 2000 from the University of TN, Knoxville.
Josh has extensive programming experience in many languages and methodologies, including numerical methods, parallel processing, and graphics. He has produced professional quality software in collaboration with a broad range of researchers and engineers in industry, academics, and medicine. He is one of the principal architects of the National Library of Medicine's Insight Toolkit Project, an international, open-source software initiative for the medical imaging community.
Josh's research interests include shape analysis, image reconstruction, segmentation, and registration. His current research is in a new method for constructing compact statistical point-based models of ensembles of similar shapes. The proposed method uses a dynamic particle system formulation to construct an optimized, point-based sampling of a population of shape surfaces. The optimization simultaneously maximizes both the geometric accuracy and the statistical simplicity of the model. We have been using this method for hypothesis testing for group differences of deep brain structure in patient (schizophrenia, autism) versus control populations.