MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009 pp 1017-1024 | Cite as
Segmentation of Lumbar Vertebrae Using Part-Based Graphs and Active Appearance Models
Abstract
The aim of the work is to provide a fully automatic method of segmenting vertebrae in spinal radiographs. This is of clinical relevance to the diagnosis of osteoporosis by vertebral fracture assessment, and to grading incident fractures in clinical trials. We use a parts based model of small vertebral patches (e.g. corners). Many potential candidates are found in a global search using multi-resolution normalised correlation. The ambiguity in the possible solution is resolved by applying a graphical model of the connections between parts, and applying geometric constraints. The resulting graph optimisation problem is solved using loopy belief propagation.
The minimum cost solution is used to initialise a second phase of active appearance model search. The method is applied to a clinical data set of computed radiography images of lumbar spines. The accuracy of this fully automatic method is assessed by comparing the results to a gold standard of manual annotation by expert radiologists.
Keywords
Vertebral Fracture Vertebral Level Vertebral Fracture Assessment Active Appearance Model Compute Radiography ImageReferences
- 1.Guermazi, A., Mohr, A., Grigorian, M., Taouli, B., Genant, H.K.: Identification of vertebral fractures in osteoporosis. Seminars in Musculoskeletal Radiology 6(3), 241–252 (2002)CrossRefGoogle Scholar
- 2.de Bruijne, M., Lund, M.T., Tankó, L.B., Pettersen, P.P., Nielsen, M.: Quantitative vertebral morphometry using neighbor-conditional shape models. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 1–8. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 3.Roberts, M.G., Cootes, T.F., Pacheco, E.M., Adams, J.E.: Quantitative vertebral fracture detection on DXA images using shape and appearance models. Academic Radiology 14, 1166–1178 (2007)CrossRefGoogle Scholar
- 4.Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 681–685 (2001)CrossRefGoogle Scholar
- 5.Roberts, M.G., Cootes, T.F., Adams, J.E.: Vertebral morphometry: semi-automatic determination of detailed shape from DXA images using active appearance models. Investigative Radiology 41(12), 849–859 (2006)CrossRefGoogle Scholar
- 6.de Bruijne, M., Nielsen, M.: Image segmentation by shape particle filtering. In: International Conference on Pattern Recognition, pp. 722–725. IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
- 7.Fergus, R., Perona, P., Zisserman, A.: A visual category filter for google images. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 242–256. Springer, Heidelberg (2004)Google Scholar
- 8.Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. Int. Journal of Computer Vision 61(1), 55–79 (2005)CrossRefGoogle Scholar
- 9.Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.): Towards Category-Level Object Recognition. Springer, Heidelberg (2006)Google Scholar
- 10.Donner, R., Micusik, B., Langs, G., Bischof, H.: Sparse MRF appearance models for fast anatomical structure localisation. In: Proc. British Machine Vision Conference, vol. 2, pp. 1080–1089 (2007)Google Scholar
- 11.Weiss, Y., Freeman, W.: On the optimality of solutions of the max-product belief propagation algorithm in arbitrary graphs. IEEE Trans. Inf. Theory 47, 736–744 (2001)MATHCrossRefMathSciNetGoogle Scholar