Efficient ribcage segmentation from CT scans using shape features
2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2014), pp. 2899–2902
Abstract
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.
Abstract sourceThis 2014 EMBC paper describes an automated method for separating the rib cage from other bone structures in CT scans. The authors evaluated the method on human and small-animal scans; the reported results are specific to that evaluation and do not establish prospective clinical validation.
Summary
The paper presents a method for segmenting the rib cage in chest CT scans, where ribs can connect to nearby bones such as the sternum and shoulder blades. The approach first segments bone structures, then uses multi-scale Hessian analysis to identify plate-like and tubular shape features, and iterative relative fuzzy connectedness to separate other bones from the rib cage.
The authors evaluated the method on 400 human CT scans and 100 small-animal images. They report rib-cage extraction accuracy above 95%. This result describes the study’s evaluation; it does not establish prospective clinical validation. Read the full paper.
- Authors: Ziyue Xu, Ulas Bagci, Colleen Jonsson, Sanjay Jain, and Daniel J Mollura.
- Venue: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2014), pp. 2899–2902.
- DOI: 10.1109/EMBC.2014.6944229.
Cite this work
Ziyue Xu; Ulas Bagci; Colleen Jonsson; Sanjay Jain; Daniel J Mollura (2014). Efficient ribcage segmentation from CT scans using shape features. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2014), pp. 2899–2902 https://doi.org/10.1109/EMBC.2014.6944229
BibTeX