Accurate and robust shape descriptors for the identification of RIB cage structures in CT-images with Random Forests

This paper presents a new automatic technique for the segmentation of the rib cage on CT images. Motivated by a usage scenario in the context of large, heterogeneous databases of CT-images, we introduce two shape descriptors to be used in conjunction with a Random Forests (RF) classifier. These descriptors were specifically designed to address the challenges of rib identification under various acquisition conditions affecting subject´s orientation and image quality. Extensive experiments demonstrate the superiority of our proposed shape descriptors in nominal configurations. Robustness with respect to subject´s orientation variation and additive noise is also demonstrated, with an improvement of classification performance of up to 25%, comparing to intensity-based descriptors, without neither pre-registration nor pre-smoothing.