Romeil Sandhu

RomeRomeil Sandhu – Assistant Professor

Biomedical Informatics Department

CS Building 2313 F

Stony Brook University

Stony Brook, NY 11794


My group is working at the intersection of discrete geometry, statistics and control. At the core of our work, we are interested in developing mathematical methods that are able to characterize and alter a system’s behavior.   Targeted therapy (cancer treatment tailored specifically to each patient) and drug resistance are among the clinical applications of our lab.   We also focus our efforts in related fields of complex networks, risk analysis, computer vision, shape analysis, and machine learning with applications that span not only biomedical research, but also those found in defense and security.  While such areas are seemingly far apart, my group utilizes the mathematical underpinnings of these applications, to attack old problems in a new light (geometry of cancer).

Personal Web Page

Highlighted Publications:

A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery

Y Gao, R Sandhu, G Fichtinger, AR Tannenbaum

IEEE transactions on medical imaging 29 (10), 1781-1794

Point set registration via particle filtering and stochastic dynamics

R Sandhu, S Dambreville, A Tannenbaum

IEEE transactions on pattern analysis and machine intelligence 32 (8), 1459-1473

Robust 3d pose estimation and efficient 2d region-based segmentation from a 3d shape prior

S Dambreville, R Sandhu, A Yezzi, A Tannenbaum

Computer Vision–ECCV 2008, 169-182

Particle filtering for registration of 2D and 3D point sets with stochastic dynamics

R Sandhu, S Dambreville, A Tannenbaum

Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on

A new distribution metric for image segmentation

R Sandhu, TT Georgiou, AR Tannenbaum

Georgia Institute of Technology