Supervised Nonparametric Image Parcellation

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 algo...

• Type: Conference
• Year: 2009
• Where: MICCAI
• Authors: Mert R. Sabuncu, B. T. Thomas Yeo, Koen Van Leemput, Bruce Fischl, Polina Golland
• Keywords: Medical Imaging, MICCAI 2009, Robust Pairwise Image, SNIP Yields, Supervised Nonparametric Image