Feature selection for automatic CT-based prostate segmentation

The paper addresses a problem of feature selection for automatic prostate segmentation in Computed Tomography (CT) planning data for radiotherapy process. The following image descriptors have been tested in 2D and 3D scenarios: standard Hounsfield Unit (HU) profiles, histogram of oriented gradient (HoG), Haar wavelets, and Modality Independent Neighborhood Descriptor (MIND). The task was to distinguish a prostate interior and exterior. 22 CT volumes with different spatial resolution and different organ outlines have been used. The k-Nearest Neighbors (kNN) classifier was applied and the following recognition measures were evaluated, with 10-fold cross-validation: accuracy, precision, sensitivity and specificity.