Automatic Method for Thalamus Parcellation Using Multi-modal Feature Classification
Abstract
Segmentation and parcellation of the thalamus is an important step in providing volumetric assessment of the impact of disease on brain structures. Conventionally, segmentation is carried out on T1-weighted magnetic resonance (MR) images and nuclear parcellation using diffusion weighted MR images. We present the first fully automatic method that incorporates both tissue contrasts and several derived features to first segment and then parcellate the thalamus. We incorporate fractional anisotrophy, fiber orientation from the 5D Knutsson representation of the principal eigenvectors, and connectivity between the thalamus and the cortical lobes, as features. Combining these multiple information sources allows us to identify discriminating dimensions and thus parcellate the thalamic nuclei. A hierarchical random forest framework with a multidimensional feature per voxel, first distinguishes thalamus from background, and then separates each group of thalamic nuclei. Using a leave one out cross-validation on 12 subjects we have a mean Dice score of 0.805 and 0.799 for the left and right thalami, respectively. We also report overlap for the thalamic nuclear groups.
Keywords
Brain imaging diffusion MRI magnetic resonance imaging machine learning segmentation thalamus parcellationPreview
Unable to display preview. Download preview PDF.
References
- 1.Bazin, P.L., Pham, D.L.: Homeomorphic brain image segmentation with topological and statistical atlases. Medical Image Analysis 12(5), 616–625 (2008)CrossRefGoogle Scholar
- 2.Behrens, T.E.J., et al.: Non-invasive mapping of connections between human thalamus and cortex using diffusion imaging. Nature Neuroscience 6(7), 750–757 (2003)CrossRefGoogle Scholar
- 3.Behrens, T.E.J., et al.: Probabilistic diffusion tractography with multiple fibre orientations: What can we gain? NeuroImage 34(1), 144–155 (2007)CrossRefGoogle Scholar
- 4.Braak, H., Braak, E.: Alzheimer’s disease affects limbic nuclei of the thalamus. Acta Neuropathologica 81(3), 261–268 (1991)CrossRefGoogle Scholar
- 5.Breiman, L.: Random Forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
- 6.Byne, W., et al.: Postmortem Assessment of Thalamic Nuclear Volumes in Subjects With Schizophrenia. Am. J. Psychiatry 159(1), 59–65 (2002)CrossRefGoogle Scholar
- 7.Carass, A., et al.: Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis. NeuroImage 56(4), 1982–1992 (2011)CrossRefGoogle Scholar
- 8.Cifelli, A., et al.: Thalamic neurodegeneration in multiple sclerosis. Annals of Neurology 52(5), 650–653 (2002)CrossRefGoogle Scholar
- 9.Dale, A.M., et al.: Cortical Surface-Based Analysis I: Segmentation and Surface Reconstruction. NeuroImage 9(2), 179–194 (1999)CrossRefMathSciNetGoogle Scholar
- 10.Danos, P., et al.: Volumes of association thalamic nuclei in schizophrenia: a postmortem study. Schizophrenia Research 60(2-3), 141–155 (2003)CrossRefGoogle Scholar
- 11.Duan, Y., et al.: Thalamus Segmentation from Diffusion Tensor Magnetic Resonance Imaging. International Journal of Biomedical Imaging 5(2), 1–5 (2007)CrossRefGoogle Scholar
- 12.Jellinger, K.A.: Post mortem studies in Parkinson’s disease–is it possible to detect brain areas for specific symptoms? J. Neural. Transm. Suppl. 56, 1–29 (1999)CrossRefGoogle Scholar
- 13.Jenkinson, M., et al.: FSL. NeuroImage 62(2), 782–790 (2012)CrossRefMathSciNetGoogle Scholar
- 14.Jonasson, L., et al.: A level set method for segmentation of the thalamus and its nuclei in DT-MRI. Signal Processing 87(2), 309–321 (2007)CrossRefzbMATHGoogle Scholar
- 15.Knutsson, H.: Producing a Continuous and Distance Preserving 5-D Vector Representation of 3-D Orientation. In: IEEE Computer Society Workshop on Computer Architecture for Pattern Analysis and Image Database Management, pp. 175–182 (1985)Google Scholar
- 16.Morel, A., et al.: Multiarchitectonic and Stereotactic Atlas of the Human Thalamus. J. Comparative Neurology 387(4), 588–630 (1997)CrossRefGoogle Scholar
- 17.Rittner, L., et al.: Segmentation of thalamic nuclei based on tensorial morphological gradient of diffusion tensor fields. In: 7th International Symposium on Biomedical Imaging (ISBI 2010), pp. 1173–1176 (2010)Google Scholar
- 18.Sherman, S.M., Guillery, R.: Exploring the Thalamus. Elsevier (2000)Google Scholar
- 19.Sled, J.G., et al.: A non-parametric method for automatic correction of intensity non-uniformity in MRI data. IEEE Trans. Med. Imag. 17(1), 87–97 (1998)CrossRefGoogle Scholar
- 20.Stough, J., et al.: Thalamic Parcellation from Multi-Modal Data using Random Forest Learning. In: 10th International Symposium on Biomedical Imaging (ISBI 2013), pp. 852–855 (2013)Google Scholar
- 21.Studholme, C., et al.: Accurate alignment of functional EPI data to anatomical MRI using a physics-based distortion model. IEEE Trans. Med. Imag. 19(11), 1115–1127 (2000)CrossRefGoogle Scholar
- 22.Thévenaz, P., et al.: Interpolation revisited (medical images application). IEEE Trans. Med. Imag. 19(7), 739–758 (2000)CrossRefGoogle Scholar
- 23.Wiegell, M.R., et al.: Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging. NeuroImage 19(2), 391–401 (2003)CrossRefGoogle Scholar
- 24.Ye, C., et al.: Parcellation of the Thalamus Using Diffusion Tensor Images and a Multi-object Geometric Deformable Model. In: Proceedings of SPIE Medical Imaging (SPIE-MI 2013), Orlando, FL, February 9-14, vol. 8669, pp. 866909–866909–7 (2013)Google Scholar