Supervised Nonparametric Image Parcellation
Author(s)Sabuncu, Mert R.; Yeo, B. T. Thomas; Van Leemput, Koen; Fischl, Bruce; Golland, Polina
MetadataShow full item record
Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data are summarized using a parametric atlas. Summarizing the data alleviates the computational burden at the expense of possibly losing valuable information on inter-subject variability. This paper presents a novel framework for Supervised Nonparametric Image Parcellation (SNIP). SNIP models the intensity and label images as samples of a joint distribution estimated from the training data in a non-parametric fashion. By capitalizing on recently developed fast and robust pairwise image alignment tools, SNIP employs the entire training data to segment a new image via Expectation Maximization. The use of multiple registrations increases robustness to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with manual labels for the white matter, cortex and subcortical structures. SNIP yields better segmentation than state-of-the-art algorithms in multiple regions of interest.
Author Manuscript 2010 August 25. 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part II
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009
Springer Berlin / Heidelberg
Sabuncu, Mert R. et al. “Supervised Nonparametric Image Parcellation.” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009. Ed. Guang-Zhong Yang et al. LNCS Vol. 5762. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. 1075–1083.
Author's final manuscript