Higher-Order CRF Tumor Segmentation with Discriminant Manifold Potentials
The delineation of tumor boundaries in medical images is an essential task for the early detection, diagnosis and follow-up of cancer. However accurate segmentation remains challenging due to presence of noise, inhomogeneity and high appearance variability of malignant tissue. In this paper, we propose an automatic segmentation approach using fully-connected higher-order conditional random fields (HOCRF) where potentials are computed within a discriminant Grassmannian manifold. First, the framework learns within-class and between-class similarity distributions from a training set of images to discover the optimal manifold discrimination between normal and pathological tissues. Second, the conditional optimization scheme computes non-local pairwise as well as pattern-based higher-order potentials from the manifold subspace to recognize regions with similar labelings and incorporate global consistency in the inference process. Our HOCRF framework is applied in the context of metastatic liver tumor segmentation in CT images. Compared to state of the art methods, our method achieves better performance on a group of 30 liver tumors and can deal with highly pathological cases.
Unable to display preview. Download preview PDF.
- 1.Li, S.Z.: Markov Random Field Modeling in Image Analysis. Springer (2009)Google Scholar
- 2.Lafferty, J., Pereira, F., McCallum, A.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282–289 (2001)Google Scholar
- 3.Bauer, S., Nolte, L.-P., Reyes, M.: Fully Automatic Segmentation of Brain Tumor Images Using Support Vector Machine Classification in Combination with Hierarchical Conditional Random Field Regularization. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 354–361. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 6.Vineet, V., Warrell, J., Torr, P.H.S.: Filter-based mean-field inference for random fields with higher-order terms and product label-spaces. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 31–44. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 9.Harandi, M., Sanderson, C., et al.: Graph embedding discriminant analysis on grassmannian manifolds for improved image set matching. In: CVPR, p. 2705 (2011)Google Scholar
- 10.Mori, G.: Guiding model search using segmentation. In: ICCV, pp. 1417–1423 (2005)Google Scholar
- 11.Krähenbühl, P., Koltun, V.: Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials. In: NIPS, vol. 24, pp. 109–117 (2011)Google Scholar