Abstract
Femur segmentation from computed tomography (CT) images is a fundamental problem in femur-related computer-assisted diagnosis and surgical planning/navigation. In this study, an automatic approach for the segmentation of proximal femur from CT images that incorporates the statistical shape prior into the graph-cut framework (SP-GC) is proposed. The proposed segmentation framework includes two major processes, namely training and segmentation. In the training stage, a training set of three-dimensional CT images from a group of normal subjects were segmented semi-automatically. The shape prior was generated by active shape modeling that included mean shape and shape variance information. In the segmentation stage, two shape terms originated from the training stage were included in the GC energy function. The minimization of the energy function was achieved using a max-flow/min-cut algorithm. The performance of the proposed segmentation method was evaluated by testing on 60 CT datasets from bilateral femurs of 30 normal subjects. Qualitative and quantitative analyses of the segmentation results of the proposed method were performed and the results were compared with two widely used methods, namely the active shape model (ASM) and traditional GC, with results from manual delineation used as the ground truth. The mean dice similarity coefficient of the proposed SP-GC was 0.9600, which is higher than those of ASM and GC (0.8769 and 0.9358, respectively). The mean normalized error rate of the SP-GC results was 10 and 6 % lower than those of ASM and GC, respectively. In terms of the average surface distance measurement, the value for SP-GC was 0.885 mm, compared with 2.148 and 1.154 mm for ASM and GC, respectively. In comparison with ASM, SP-GC has superior performance given a small training set (e.g., n = 12). With increasing number of training samples, the segmentation accuracy of ASM saturated, but that of SP-GC slightly increased.
Similar content being viewed by others
References
Ganz, R., Parvizi, J., Beck, M., Leunig, M., Nötzli, H., & Siebenrock, K. A. (2003). Femoroacetabular impingement: a cause for osteoarthritis of the hip. Clinical Orthopaedics and Related Research, 417, 112–120.
Ganz, R., Leunig, M., Leunig-Ganz, K., & Harris, W. H. (2008). The etiology of osteoarthritis of the hip. Clinical Orthopaedics and Related Research, 466, 264–272.
Beaulé, P. E., Zaragoza, E., Motamedi, K., Copelan, N., & Dorey, F. J. (2005). Three-dimensional computed tomography of the hip in the assessment of femoroacetabular impingement. Journal of Orthopaedic Research, 23, 1286–1292.
Clohisy, J. C., Carlisle, J. C., Beaulé, P. E., Kim, Y. J., Trousdale, R. T., Sierra, R. J., et al. (2008). A systematic approach to the plain radiographic evaluation of the young adult hip. Journal of Bone Joint Surgery, 90, 47–66.
Rakhra, K. S., Sheikh, A. M., Allen, D., & Beaulé, P. E. (2009). Comparison of MRI alpha angle measurement planes in femoroacetabular impingement. Clinical Orthopaedics and Related Research, 467, 660–665.
Harris, M. D., Datar, M., Whitaker, R. T., Jurrus, E. R., Peters, C. L., & Anderson, A. E. (2013). Statistical shape modeling of cam femoroacetabular impingement. Journal of Orthopaedic Research, 31, 1620–1626.
Raut, S., Raghuvanshi, M., Dharaskar, R., & Raut, A. (2009). Image segmentation-a state-of-art survey for prediction. Proceedings IEEE International Conference Advanced Computer Control (pp. 420–424).
Naz, S., Majeed, H., & Irshad, H. (2010). Image segmentation using fuzzy clustering: A survey. Proceedings IEEE International Conference Emerging Technologies, (pp. 181–186).
Du, M., Ding, Y., & Jia, Q. (2013). A multi-threshold segmentation method based on ant colony algorithm. 5th International Conference Machine Vision (pp. 878402–878409).
Xiao, B., Jing, Y., & Guan, Y. (2013). A novel automatic thresholding segmentation method with local adaptive thresholds. arXiv preprint, arXiv: 1305.5160.
Yi, F., & Moon, I. (2012). Image segmentation: A survey of graph-cut methods. Proceedings IEEE International Conference Systems and Informatics (pp. 1936–1941).
Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. Journal of Computer Vision, 59, 167–181.
Sundaramoorthi, G., Yezzi, A., & Mennucci, A. C. (2008). Coarse-to-fine segmentation and tracking using sobolev active contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 851–864.
Willett, R. M., & Nowak, R. D. (2007). Minimax optimal level-set estimation. IEEE Transactions on Image Processing, 16, 2965–2979.
Falcão, A. X., Udupa, J. K., & Miyazawa, F. K. (2000). An ultra-fast user-steered image segmentation paradigm: Live wire on the fly. IEEE Transactions on Medical Imaging, 19, 55–62.
Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. (1995). Active shape models-their training and application. Computer Vision and Image Understanding, 61, 38–59.
Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001). Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23, 681–685.
Yokota, F., Okada, T., Takao, M., Sugano, N., Tada, Y., & Tomiyama, N. et al. (2013). Automated CT segmentation of diseased hip using hierarchical and conditional statistical shape models. International Conference Medical Image Computing and Computer-Assisted Intervention (pp. 190–197).
Wang, D., Shi, L., Chu, W. C., Cheng, J. C., & Heng, P. A. (2009). Segmentation of human skull in MRI using statistical shape information from CT data. Journal of Magnetic Resonance Imaging, 30, 490–498.
Boykov, Y. Y., & Kolmogorov, V. (2004). An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 1124–1137.
Krcah, M., Székely, G., & Blanc, R. (2011). Fully automatic and fast segmentation of the femur bone from 3D-CT images with no shape prior. Proceedings IEEE International Conference Biomedical Imaging: From Nano to Macro (pp. 2087–2090).
Freedman, D., & Zhang, T. (2005). Interactive graph cut based segmentation with shape priors. Proceedings IEEE International Conference Computer Vision and Pattern Recognition, 1, 755–762.
Zoroofi, R. A., Sato, Y., Sasama, T., Nishii, T., Sugano, N., Yonenobu, K., et al. (2003). Automated segmentation of acetabulum and femoral head from 3-D CT images. IEEE Transactions on Information Technology in Biomedicine, 7, 329–343.
Cheng, Y., Zhou, S., Wang, Y., Guo, C., Bai, J., & Tamura, S. (2013). Automatic segmentation technique for acetabulum and femoral head in CT images. Pattern Recognition, 46, 2969–2984.
O’Neill, G. T., Lee, W. S., & Beaulé, P. (2012). Segmentation of cam-type femurs from CT scans. The Vision Computing, 28, 205–218.
Nakagomi, K., Shimizu, A., Kobatake, H., Yakami, M., Fujimoto, K., & Togashi, K. (2013). Multi-shape graph cuts with neighbor prior constraints and its application to lung segmentation from a chest CT volume. Medical Image Analysis, 17, 62–77.
Essa, E., Xie, X., Sazonov, I., Nithiarasu, P., & Smith, D. (2013). Shape prior model for media-adventitia border segmentation in IVUS using graph cut. Medical Computer Vision, 7766, 114–123.
Xiong, W., Li, A. L., Ong, S. H., & Sun, Y. (2013) Automatic 3D prostate MR image segmentation using graph cuts and level sets with shape prior. International Conference Advances in Multimedia Information Processing (pp. 211–220).
Wang, H., Zhang, H., & Ray, N. (2013). Adaptive shape prior in graph cut image segmentation. Pattern Recognition, 46, 1409–1414.
Chen, X., Udupa, J. K., Alavi, A., & Torigian, D. A. (2013). GC-ASM: Synergistic integration of graph-cut and active shape model strategies for medical image segmentation. Computer Vision and Image Understanding, 117, 513–524.
Belongie, S., Malik, J., & Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 509–522.
Heinonen, T., Eskola, H., Dastidar, P., Laarne, P., & Malmivuo, J. (1997). Segmentation of T1 MR scans for reconstruction of resistive head models. Computer Methods and Programs in Biomedicine, 54, 173–181.
Gonzalez, G. C., & Woods, R. E. (1992). Digital imaging processing. Cambridge, MA: Wesley.
Boykov, Y. Y., & Jolly, M. P. (2001). Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. Proceedings IEEE International Conference Computer Vision, 1, 105–112.
Lorensen, W. E., & Cline, H. E. (1987). Marching cubes: A high resolution 3D surface construction algorithm. International Conference ACM Siggraph Computer Graphics, 21, 163–169.
van Ginneken, B., Frangi, A. F., Staal, J. J., ter Haar Romeny, B. M., & Viergever, M. A. (2002). Active shape model segmentation with optimal features. IEEE Transactions on Medical Imaging, 21, 924–933.
Golub, G. H., & Reinsch, C. (1970). Singular value decomposition and least squares solutions. Numerische Mathematik, 14, 403–420.
Besl, P. J., & McKay, N. D. (1992). Method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14, 239–256.
Diederichs, G., Seim, H., Meyer, H., Issever, A. S., Link, T. M., Schröder, R. J., & Scheibel, M. (2008). CT-based patient-specific modeling of glenoid rim defects: a feasibility study. American Journal of Roentgenology, 191, 1406–1411.
Shi, L., Wang, D., Chu, W. C., Burwell, G. R., Wong, T. T., Heng, P. A., & Cheng, J. C. (2011). Automatic MRI segmentation and morphoanatomy analysis of the vestibular system in adolescent idiopathic scoliosis. Neuroimage, 54, S180–S188.
Kang, Y., Engelke, K., & Kalender, W. A. (2003). A new accurate and precise 3-D segmentation method for skeletal structures in volumetric CT data. IEEE Transactions on Medical Imaging, 22, 586–598.
Lempitsky, V., Kohli, P., Rother, C., & Sharp, T. (2009). Image segmentation with a bounding box prior. Proceedings IEEE International Conference Computer Vision (pp. 277–284).
Peng, Y., & Liu, R. (2010). Object segmentation based on watershed and graph cut. Proceedings IEEE International Conference Image and Signal Processing, 3, 1431–1435.
Slabaugh, G., & Unal, G. (2005). Graph cuts segmentation using an elliptical shape prior. Proceedings IEEE International Conference Image Processing, 2, 1222–1225.
Acknowledgments
This work was partially supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No.: CUHK 473012).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, J., Griffith, J.F., Wang, D. et al. Graph-Cut-Based Segmentation of Proximal Femur from Computed Tomography Images with Shape Prior. J. Med. Biol. Eng. 35, 594–607 (2015). https://doi.org/10.1007/s40846-015-0079-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40846-015-0079-7