Efficient ribcage segmentation from CT scans using shape features

Rib cage structure and morphology is important for anatomical analysis of chest CT scans. A fundamental challenge in rib cage extraction is varying intensity levels and connection with adjacent bone structures including shoulder blade and sternum. In this study, we present a fully automated 3-D algorithm to segment the rib cage by detection and separation of other bone structures. The proposed approach consists of four steps. First, all high-intensity bone structures are segmented. Second, multi-scale Hessian analysis is performed to capture plateness and vesselness information. Third, with the plate/vessel features, bone structures other than rib cage are detected. Last, the detected bones are separated from rib cage with iterative relative fuzzy connectedness method. The algorithm was evaluated using 400 human CT scans and 100 small animal images with various resolution. The results suggested that the percent accuracy of rib cage extraction is over 95% with the proposed algorithm.