MIAL

Reliability-Driven, Spatially-Adaptive Regularization for Medical Image Analysis

PhD Student: Lisa Tang
Principal Investigator: Rafeef Abugharbieh
Principal Investigator: Ghassan Hamarneh
Alumni: Josna Rao

Computer vision and medical image analysis problems, e.g. segmentation and registration, are typically formulated as minimization of a cost function. The cost function comprises data fidelity (external energy or likelihood) and regularization (internal energy or prior) terms. The choice of the weight balancing the trade-off between these two terms can have significant effect on the result. Previous methods relied on a training data set for finding optimal weights for a class of images. We propose a spatially adaptive regularization weight that is derived from the image data itself, and relies on estimates of noise, reliability-gated edges, texture, and curvature estimates. We applied our approach, with promising results, to segmentation and registration problems.

Publications

Josna Rao, Rafeef Abugharbieh, and Ghassan Hamarneh. Adaptive Regularization for Image Segmentation Using Local Image Curvature Cues. In European Conference on Computer Vision (ECCV), pages 14 pages, 2010.  [Poster

Lisa Tang, Ghassan Hamarneh, and Rafeef Abugharbieh. Reliability-Driven, Spatially-Adaptive Regularization for Deformable Registration. In Workshop on Biomedical Image Registration (WBIR), pages 173-185, 2010.  [Presentation slides]

Josna Rao, Ghassan Hamarneh, and Rafeef Abugharbieh. Adaptive Contextual Energy Parameterization for Automated Image Segmentation. In Lecture Notes in Computer Science, International Symposium on Visual Computing: Special Track on Optimization for Vision, Graphics and Medical Imaging: Theory and Applications (ISVC OVGMI), volume 5875-I, pages 1089-1100, 2009.   

Josna Rao, Rafeef Abugharbieh, and Ghassan Hamarneh. Adaptive Regularization for Image Segmentation Using Local Image Curvature Cues. Technical report TR 2010-08, School of Computing Science, Simon Fraser University, Burnaby, BC, Canada, June 2010.  

Josna Rao, Ghassan Hamarneh, and Rafeef Abugharbieh. Automatic Spatially-Adaptive Balancing of Energy Terms for Image Segmentation. Technical report TR 2009-10, School of Computing Science, Simon Fraser University, Burnaby, BC, Canada, April 2009. 

Site by Faculty of Applied Science web team, Simon Fraser University