Thalamus segmentation using multi-modal feature classification: Validation and pilot study of an age-matched cohort

Automatic segmentation of the thalamus can be used to measure differences and track changes in thalamic volume that may occur due to disease, injury or normal aging. An automatic thalamus segmentation algorithm incorporating features from diffusion tensor imaging (DTI) and thalamus priors constructed from multiple atlases is proposed. Multiple atlases with corresponding manual thalamus segmentations are registered to the target image and averaged to generate the thalamus prior. At each voxel in a region of interest around the thalamus, a multidimensional feature vector that includes the thalamus prior as well as a set of DTI features, including fractional anisotropy, mean diffusivity, and fiber orientation is formed. A random forest is trained to classify each voxel as belonging to the thalamus or background within the region of interest. Using a leave-one-out cross-validation on nine subjects, the proposed algorithm achieves a mean Dice score of 0.878 and 0.890 for the left and right thalami, respectively, which are higher Dice scores than the three state-of-art methods we compared to. We demonstrate the utility of the method with a pilot study exploring the difference in the thalamus fraction between 21 multiple sclerosis (MS) patients and 21 age-matched healthy controls. The left and right thalamic volumes (normalized by intracranial volumes) are larger in healthy controls by 7.6% and 7.3% respectively, compared to MS patients (though neither result is statistically significant).

[1]  Jack L Lancaster,et al.  MR imaging volumetry of subcortical structures and cerebellar hemispheres in normal persons. , 2003, AJNR. American journal of neuroradiology.

[2]  Jean-Francois Mangin,et al.  Multi-contrast deep nuclei segmentation using a probabilistic atlas , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[3]  H. Braak,et al.  Alzheimer's disease affects limbic nuclei of the thalamus , 2004, Acta Neuropathologica.

[4]  Aaron Carass,et al.  Automatic estimation of midsagittal plane and AC-PC alignment on nonrigid registration , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[5]  Subhabrata Chakraborti,et al.  Nonparametric Statistical Inference , 2011, International Encyclopedia of Statistical Science.

[6]  Carl-Fredrik Westin,et al.  Processing and visualization for diffusion tensor MRI , 2002, Medical Image Anal..

[7]  Colin Studholme,et al.  Accurate alignment of functional EPI data to anatomical MRI using a physics-based distortion model , 2000, IEEE Transactions on Medical Imaging.

[8]  S. Osher,et al.  Level Set , 2000 .

[9]  Xavier Bresson,et al.  A level set method for segmentation of the thalamus and its nuclei in DT-MRI , 2007, Signal Process..

[10]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[11]  P. Basser,et al.  Microstructural and physiological features of tissues elucidated by quantitative-diffusion-tensor MRI. 1996. , 1996, Journal of magnetic resonance.

[12]  Daniel C. Alexander,et al.  Camino: Open-Source Diffusion-MRI Reconstruction and Processing , 2006 .

[13]  D. Louis Collins,et al.  ANIMAL+INSECT: Improved Cortical Structure Segmentation , 1999, IPMI.

[14]  Stephen M. Smith,et al.  A Bayesian model of shape and appearance for subcortical brain segmentation , 2011, NeuroImage.

[15]  R. Guillery,et al.  Exploring the Thalamus , 2000 .

[16]  J L Lancaster,et al.  MR imaging volumetry of subcortical structures and cerebellar hemispheres in temporal lobe epilepsy. , 2006, AJNR. American journal of neuroradiology.

[17]  Aaron Carass,et al.  Segmentation of thalamus from MR images via task-driven dictionary learning , 2016, SPIE Medical Imaging.

[18]  C R G Guttmann,et al.  Thalamic atrophy and cognition in multiple sclerosis , 2007, Neurology.

[19]  Bennett A Landman,et al.  Non-local statistical label fusion for multi-atlas segmentation , 2013, Medical Image Anal..

[20]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.

[21]  P. Basser,et al.  Microstructural and physiological features of tissues elucidated by quantitative-diffusion-tensor MRI. , 1996, Journal of magnetic resonance. Series B.

[22]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[23]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[24]  K. Jellinger.  Post mortem studies in Parkinson's disease--is it possible to detect brain areas for specific symptoms? , 1999, Journal of neural transmission. Supplementum.

[25]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[27]  Dennis Velakoulis,et al.  Validation of a protocol for manual segmentation of the thalamus on magnetic resonance imaging scans , 2015, Psychiatry Research: Neuroimaging.

[28]  P. Jezzard,et al.  Thalamic neurodegeneration in relapsing-remitting multiple sclerosis , 2003, Neurology.

[29]  Peter A. Calabresi,et al.  Thalamus parcellation using multi-modal feature classification and thalamic nuclei priors , 2016, SPIE Medical Imaging.

[30]  Mark Jenkinson,et al.  Combining shape and connectivity analysis: An MRI study of thalamic degeneration in Alzheimer's disease , 2010, NeuroImage.

[31]  A. Dale,et al.  NeurotechniqueWhole Brain Segmentation : Automated Labeling of Neuroanatomical Structures , 2002 .

[32]  Jerry L. Prince,et al.  Parcellation of the thalamus using diffusion tensor images and a multi-object geometric deformable model , 2013, Medical Imaging.

[33]  Paul J. Harrison,et al.  A postmortem study of the mediodorsal nucleus of the thalamus in schizophrenia , 2003, Schizophrenia Research.

[34]  Jerry L. Prince,et al.  Thalamic parcellation from multi-modal data using random forest learning , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[35]  Arthur W. Toga,et al.  A Probabilistic Atlas of the Human Brain: Theory and Rationale for Its Development The International Consortium for Brain Mapping (ICBM) , 1995, NeuroImage.

[36]  Ye Duan,et al.  Thalamus segmentation from diffusion tensor magnetic resonance imaging. , 2006, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[37]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[38]  Jerry L. Prince,et al.  A novel contrast for DTI visualization for thalamus delineation , 2010, Medical Imaging.

[39]  Peter Falkai,et al.  Volumes of association thalamic nuclei in schizophrenia: a postmortem study , 2003, Schizophrenia Research.

[40]  Aaron Carass,et al.  Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis , 2011, NeuroImage.

[41]  Carl-Fredrik Westin,et al.  Segmentation of Thalamic Nuclei from DTI Using Spectral Clustering , 2006, MICCAI.

[42]  H. Knutsson.  Producing a Continuous and Distance Preserving 5-D Vector Representation of 3-D Orientation , 1985 .

[43]  Denis Le Bihan,et al.  Imagerie de diffusion in-vivo par résonance magnétique nucléaire , 1985 .

[44]  A. Dale,et al.  Whole Brain Segmentation Automated Labeling of Neuroanatomical Structures in the Human Brain , 2002, Neuron.

[45]  Pierre-Louis Bazin,et al.  Homeomorphic brain image segmentation with topological and statistical atlases , 2008, Medical Image Anal..

[46]  Aaron Carass,et al.  Automatic Method for Thalamus Parcellation Using Multi-modal Feature Classification , 2014, MICCAI.

[47]  P. Matthews,et al.  Thalamic neurodegeneration in multiple sclerosis , 2002, Annals of neurology.

[48]  A. Morel.  Stereotactic Atlas of the Human Thalamus and Basal Ganglia , 2007 .

[49]  William Byne,et al.  Postmortem assessment of thalamic nuclear volumes in subjects with schizophrenia. , 2002, The American journal of psychiatry.