Abstract
Purpose
A framework for radiographic image segmentation under topological control based on two-dimensional (2D) image analysis was developed. The system is intended for use in common radiological tasks including fracture treatment analysis, osteoarthritis diagnostics and osteotomy management planning.
Methods
The segmentation framework utilizes a generic three-dimensional (3D) model of the bone of interest to define the anatomical topology. Non-rigid registration is performed between the projected contours of the generic 3D model and extracted edges of the X-ray image to achieve the segmentation. For fractured bones, the segmentation requires an additional step where a region-based active contours curve evolution is performed with a level set Mumford–Shah method to obtain the fracture surface edge. The application of the segmentation framework to analysis of human femur radiographs was evaluated. The proposed system has two major innovations. First, definition of the topological constraints does not require a statistical learning process, so the method is generally applicable to a variety of bony anatomy segmentation problems. Second, the methodology is able to handle both intact and fractured bone segmentation.
Results
Testing on clinical X-ray images yielded an average root mean squared distance (between the automatically segmented femur contour and the manual segmented ground truth) of 1.10 mm with a standard deviation of 0.13 mm. The proposed point correspondence estimation algorithm was benchmarked against three state-of-the-art point matching algorithms, demonstrating successful non-rigid registration for the cases of interest.
Conclusions
A topologically constrained automatic bone contour segmentation framework was developed and tested, providing robustness to noise, outliers, deformations and occlusions.
Similar content being viewed by others
References
Sonka, M, Fitzpatrick, JM (eds) (2000) Handbook of medical imaging, vol 2. SPIE Press, Bellingham
Seise M, McKenna SJ, Ricketts IW, Wigderowitz CA (2008) Parts-based segmentation with overlapping part models using Markov chain Monte Carlo. Image Vis Comput 27(5): 504–513
Dong X, Zheng G (2008) Automatic extraction of proximal femur contours from calibrated X-ray images using 3D statistical models. MIAR 2008. LNCS, vol 5128. Springer, Berlin, pp 421–429
Behiels G, Maes F, Vandermeulen D, Suetens P (2002) Evaluation of image features and search strategies for segmentation of bone structures in radiographs using active shape models. Med Image Anal 6: 47–62
Pilgram R, Walch C (2008) Knowledge-based femur detection in conventional radiographs of the pelvis. Comput Biol Med 38: 535–544
Chen Y, Ee X, Leow WK, Howe TS (2005) Automatic extraction of femur contours from hip X-ray images. CVBIA 2005. LNCS, vol 3765. Springer, Berlin, pp 200–209
Zheng Y, Doermann D (2006) Robust point matching for nonrigid shapes by preserving local neighborhood structures. IEEE Trans Pattern Recogn Mach Intell 28: 643–649
Zheng G, Ballester MA, Styner M, Nolte LP (2006) Reconstruction of patient-specific 3D bone surface from 2D calibrated fluoroscopic images and point distribution model. MICCAI 2006, vol 4190. Springer, Berlin, pp 25–32
Gamage P, Xie SQ, Delmas P, Xu P, Mukherjee S (2008) Radiograph based patient-specific customization of a generic femur. In: 15th International Conference on Mechatronics and Machine Vision in Practice, 2008, M2VIP 2008, pp 622–627
Mengko TL, Wachjudi RG, Suksmono AB, Danudirdjo D (2005) Automated detection of unimpaired joint space for knee osteoarthritis assessment. In: Proceedings of the 7th International Workshop on Enterprise Networking and Computing in Healthcare Industry, HEALTHCOM 2005, pp 400–403
Gamage P, Xie S, Delmas P, Xu P (2009) 3D pose estimation of femur fracture segments for vision guided robotic orthopaedic surgery. Int J Biomechatron Biomed Robot 1: 57–66
Ozanian TO, Phillips R (2001) Enhancement of fluoroscopic images with varying contrast. Comput Methods Programs Biomed 65: 1–16
Orthomark: http://www.orthomark.net. Orthopedic X-ray calibration & marking device (2009)
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24: 509–522
Thayananthan A, Stenger B, Torr PHS, Cipolla R (2003) Shape context and chamfer matching in cluttered scenes. Proc IEEE Comput Soc Conf Comput Vis Pattern Recogn 1: I/127–I/133
Olson CF, Huttenlocher DP (1997) Automatic target recognition by matching oriented edge pixels. Trans Image Process 6: 103–113
Kuhn HW (1955) The Hungarian Method for the assignment problem. Naval Res Logist Q 2: 83–97
Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10: 266–277
Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22: 61–79
Chui H, Rangarajan A (2000) A new algorithm for non-rigid point matching. CVPR 2: 44–51
Myronenko A, Song X, Carreira-Perpinan MA (2006) Non-rigid point set registration: Coherent Point Drift. NIPS, pp 1009–1016
Besl PJ, McKay ND (1992) A method for registration of 3-D shapes. IEEE Trans pattern Anal Mach Intell 14: 239–256
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gamage, P., Xie, S.Q., Delmas, P. et al. Segmentation of radiographic images under topological constraints: application to the femur. Int J CARS 5, 425–435 (2010). https://doi.org/10.1007/s11548-009-0399-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-009-0399-6