Hierarchical Conditional Random Fields for Detection of Gad-Enhancing Lesions in Multiple Sclerosis
The detection of gad-enhancing lesions in brain MRI of Multiple Sclerosis (MS) patients is of great interest since they are important markers of disease activity. However, many of the enhancing voxels are associated with normal structures (i.e. blood vessels) or noise in the MRI, making the detection of gad-enhancing lesions a challenging task. Furthermore, these lesions are typically small and in close proximity to vessels. In this paper, we present an automatic, probabilistic Hierarchical Conditional Random Field (HCRF) framework for detection of gad-enhancing lesions in brain images of patients with MS. In the first level, a CRF with unary and pairwise potentials is used to identify candidate lesion voxel. In the second level, these lesion candidates are grouped based on anatomical and spatial features, and feature-specific lesion based CRF models are designed for each group. This lesion level CRF incorporates higher order potentials which account for shape, group intensities and symmetries. The proposed algorithm is trained on 92 multimodal clinical datasets acquired from Relapsing-Remitting MS patients during multicenter clinical trials and is evaluated on 30 independent cases. The experimental results show a sensitivity of 98%, a positive predictive value of 66% and an average false positive count of 1.55, outperforming the CRF and MRF frameworks proposed in .
KeywordsMultiple Sclerosis Conditional Random Field Enhance Lesion Binary Mask Relapse Remit Multiple Sclerosis
- 2.Miki, Y., Grossman, R., Udupa, J., Samarasekera, S., Buchem, M., Cooney, B., Kolson, D., Constantinescu, C., Pollack, S., Polansky, M., Mannon, L.: Computer-assisted quantitation of enhancing lesions in multiple sclerosis: correlation with clinical classification. Am. J. Neuroradiol. 18, 705–710 (1997)Google Scholar
- 6.Kohli, P., Ladicky, L., Torr, P.: Robust higher order potentials for enforcing label consistency. Int. J. Comput. Vision, 302–324 (2009)Google Scholar
- 7.Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: CML, pp. 282–289 (2001)Google Scholar
- 8.Sutton, C., McCallum, A.: Piecewise pseudo-likelihood for efficient training of conditional random fields. In: ICML, pp. 863–870 (2007)Google Scholar
- 9.Boykov, Y., Kolmogorov, V.: An experimental comparison of min- cut/max-flow algorithms for energy minimization in vision. IEEE T. Pattern Anal., 1124–1137 (2004)Google Scholar