IPMI 2013 - LNCS 7917

Diseased Region Detection of Longitudinal Knee MRI Data

Chao Huang^1,3, Liang Shan², Cecil Charles⁴, Marc Niethammer², and Hongtu Zhu³

¹Department of Mathematics, Southeast University, China

²Department of Computer Sciences and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, USA

³Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, USA
htzhu@email.unc.edu

⁴Department of Radiology, Duke University, USA

Abstract. Statistical analysis of longitudinal cartilage changes in osteoarthritis (OA) is of great importance and still a challenge in knee MRI data analysis. A major challenge is to establish a reliable correspondence across subjects within the same latent subpopulations. We develop a novel Gaussian hidden Markov model (GHMM) to establish spatial correspondence of cartilage thinning across both time and subjects within the same latent subpopulations and make statistical inference on the detection of diseased regions in each OA patient. A hidden Markov random field (HMRF) is proposed to extract such latent subpopulation structure. The EM algorithm and pseudo-likelihood method are both considered in making statistical inference. The proposed model can effectively detect diseased regions and present a localized analysis of longitudinal cartilage thickness within each latent subpopulation. Simulation studies and diseased region detection on 2D thickness maps extracted from full 3D longitudinal knee MRI Data for Pfizer Longitudinal Dataset are performed, which show that our proposed model outperforms standard voxel-based analysis.

Keywords: Diseased regions detection, EM algorithm, Gaussian hidden Markov model, Longitudinal cartilage thickness, Pseudo-likelihood method

LNCS 7917, p. 632 ff.

Full article in PDF | BibTeX