|
Computer science Ph.D. student Bradley Davis (M.S. 2005) was recently awarded the 2007 David Marr Prize for best paper at the Eleventh IEEE International Conference on Computer Vision (ICCV ’07), held in Rio de Janeiro, Brazil. His paper, Population Shape Regression From Random Design Data, was selected for the award from nearly 1300 submissions, only 47 of which were chosen to be presented orally, and was the only paper this year to be honored with the Marr Prize. The paper was co-authored by P. Thomas Fletcher (Ph.D. 2004), research assistant professor in the School of Computing at the University of Utah; Elizabeth Bullitt, Van Weatherspoon Jr. Distinguished Professor of Neurosurgery and head of the Computer-Assisted Surgery and Imaging Laboratory at UNC; and Brad’s advisor, Sarang Joshi, associate professor of bioengineering at the University of Utah and adjunct associate professor of computer science at UNC. The research on which the paper is based was developed in a very multidisciplinary environment provided by the Medical Image Display and Analysis Group (MIDAG), which presently includes approximately 110 faculty, graduate students and staff. The ideas behind Brad’s paper originated while he worked as a research assistant in the department of radiation oncology and matured more fully for the study of the aging of the brain within Elizabeth Bullitt’s Computer-Assisted Surgery and Imaging Laboratory (CASILab). The goal of the research was to better understand both healthy anatomy and disease progression, by measuring and analyzing anatomical change over time from three-dimensional medical images. Classical regression methods are commonly applied to study average anatomical change for populations of individuals, such as brain tissue volume as a function of age. However, when highly complex anatomical organ and tissue shapes and shape change are studied, these regression methods are not always suitable. To overcome this problem, Brad and his team developed a generalized method of regression that is applicable to the study of anatomical shape change from patient populations. Researchers from the Department of Psychiatry at UNC are already putting the method to use. Brad received a bachelor’s degree in computer science in 2001 from Carleton College. His research interests include medical image analysis, computational anatomy and radiation therapy. In 2006, Brad joined Kitware, a business with expertise in medical image analysis, 3D graphics, visualization and quality software process, as a research and development engineer. He is one of a number of alumni and faculty from the department of computer science who play a major role in the company. The Marr Prize is awarded to the best paper at the biennial International Conference on Computer Vision. The prize commemorates David Courtnay Marr, a Cambridge (UK) theoretical neuroscientist with a background in mathematics who made profound contributions to the theory of both human and machine vision at the MIT AI Lab in the 1970s. Brad’s paper is only the 17th to be honored by the award, which has been given since 1987. |
Graduate
Student Brad Davis Receives Marr Prize 
| Department of Computer Science Campus Box 3175, Sitterson Hall College of Arts & Sciences The University of North Carolina at Chapel Hill Chapel Hill, NC 27599-3175 USA Phone: (919) 962-1700 Fax: (919) 962-1799 |