Thalamic segmentation based on improved fuzzy connectedness in structural MRI

Thalamic segmentation serves an important function in localizing targets for deep brain stimulation (DBS). However, thalamic nuclei are still difficult to identify clearly from structural MRI. In this study, an improved algorithm based on the fuzzy connectedness framework was developed. Three-dimensional T1-weighted images in axial orientation were acquired through a 3D SPGR sequence by using a 1.5 T GE magnetic resonance scanner. Twenty-five normal images were analyzed using the proposed method, which involved adaptive fuzzy connectedness combined with confidence connectedness (AFCCC). After non-brain tissue removal and contrast enhancement, the seed point was selected manually, and confidence connectedness was used to perform an ROI update automatically. Both image intensity and local gradient were taken as image features in calculating the fuzzy affinity. Moreover, the weight of the features could be automatically adjusted. Thalamus, ventrointermedius (Vim), and subthalamic nucleus were successfully segmented. The results were evaluated with rules, such as similarity degree (SD), union overlap, and false positive. SD of thalamus segmentation reached values higher than 85%. The segmentation results were also compared with those achieved by the region growing and level set methods, respectively. Higher SD of the proposed method, especially in Vim, was achieved. The time cost using AFCCC was low, although it could achieve high accuracy. The proposed method is superior to the traditional fuzzy connectedness framework and involves reduced manual intervention in time saving.

[1]  D. Collins,et al.  Comparison of piece‐wise linear, linear, and nonlinear atlas‐to‐patient warping techniques: Analysis of the labeling of subcortical nuclei for functional neurosurgical applications , 2009, Human brain mapping.

[2]  P. Dechent,et al.  Optimized high‐resolution mapping of magnetization transfer (MT) at 3 Tesla for direct visualization of substructures of the human thalamus in clinically feasible measurement time , 2009, Journal of magnetic resonance imaging : JMRI.

[3]  James S. Duncan,et al.  Neighbor-constrained segmentation with level set based 3-D deformable models , 2004, IEEE Transactions on Medical Imaging.

[4]  Demetri Terzopoulos,et al.  United Snakes , 1999, Medical Image Anal..

[5]  Jayaram K. Udupa,et al.  Fuzzy connectedness and image segmentation , 2003, Proc. IEEE.

[6]  Jean-Marie Bonny,et al.  Anatomy of the Human Thalamus Based on Spontaneous Contrast and Microscopic Voxels in High‐Field Magnetic Resonance Imaging , 2010, Neurosurgery.

[7]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[8]  Wolfgang Grodd,et al.  Directional colour encoding of the human thalamus by diffusion tensor imaging , 2008, Neuroscience Letters.

[9]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[10]  M. Mallar Chakravarty,et al.  A novel in vivo atlas of human hippocampal subfields using high-resolution 3T magnetic resonance imaging , 2013, NeuroImage.

[11]  Juan Zhou,et al.  Segmentation of subcortical brain structures using fuzzy templates , 2005, NeuroImage.

[12]  Martin Styner,et al.  Subcortical structure segmentation using probabilistic atlas priors , 2007, SPIE Medical Imaging.

[13]  Vincent Barra,et al.  Automatic segmentation of subcortical brain structures in MR images using information fusion , 2001, IEEE Transactions on Medical Imaging.

[14]  Qing He,et al.  A Context-Sensitive Active Contour for 2D Corpus Callosum Segmentation , 2007, Int. J. Biomed. Imaging.

[15]  Alexander Hammers,et al.  Reproducibility of thalamic segmentation based on probabilistic tractography , 2010, NeuroImage.

[16]  Andreas Reichenbach,et al.  A comparative fractal analysis of various mammalian astroglial cell types , 1992, NeuroImage.

[17]  Rasoul Khayati,et al.  Fully automated tumor segmentation based on improved fuzzy connectedness algorithm in brain MR images , 2011, Comput. Biol. Medicine.

[18]  Paul M. Thompson,et al.  Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models , 2008, IEEE Transactions on Medical Imaging.

[19]  W. Eric L. Grimson,et al.  Mutual information in coupled multi-shape model for medical image segmentation , 2004, Medical Image Anal..

[20]  David S Tuch,et al.  Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging , 2003, NeuroImage.

[21]  J. Mink,et al.  Deep brain stimulation. , 2006, Annual review of neuroscience.

[22]  Hamid Soltanian-Zadeh,et al.  Automatic segmentation of thalamus from brain MRI integrating fuzzy clustering and dynamic contours , 2004, IEEE Transactions on Biomedical Engineering.

[23]  James S. Duncan,et al.  3D image segmentation of deformable objects with joint shape-intensity prior models using level sets , 2004, Medical Image Anal..

[24]  Azriel Rosenfeld,et al.  Fuzzy Digital Topology , 1979, Inf. Control..

[25]  Supun Samarasekera,et al.  Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation , 1996, CVGIP Graph. Model. Image Process..

[26]  Timothy Edward John Behrens,et al.  Non-invasive mapping of connections between human thalamus and cortex using diffusion imaging , 2003, Nature Neuroscience.

[27]  Tim McInerney,et al.  Sketch initialized Snakes for rapid, accurate and repeatable interactive medical image segmentation , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[28]  Ali R. Khan,et al.  FreeSurfer-initiated fully-automated subcortical brain segmentation in MRI using Large Deformation Diffeomorphic Metric Mapping , 2008, NeuroImage.

[29]  Daniel Rueckert,et al.  Automatic segmentation of brain MRIs of 2-year-olds into 83 regions of interest , 2008, NeuroImage.

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

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

[32]  Jue Wu,et al.  A novel framework for segmentation of deep brain structures based on Markov dependence tree , 2009, NeuroImage.

[33]  James A. Sethian,et al.  Level Set Methods and Fast Marching Methods: Evolving Interfaces in Computational Geometry, Fluid , 2012 .

[34]  Stephanie Powell,et al.  Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures , 2008, NeuroImage.

[35]  Matthew J. McAuliffe,et al.  Medical Image Processing, Analysis and Visualization in clinical research , 2001, Proceedings 14th IEEE Symposium on Computer-Based Medical Systems. CBMS 2001.

[36]  Gareth J. Barker,et al.  Segmentation of the thalamus in MRI based on T1 and T2 , 2011, NeuroImage.

[37]  Edward R. Dougherty,et al.  Hands-on Morphological Image Processing , 2003 .

[38]  Geoffrey S. Young,et al.  SUSCEPTIBILITY‐ENHANCED 3‐TESLA T1‐WEIGHTED SPOILED GRADIENT ECHO OF THE MIDBRAIN NUCLEI FOR GUIDANCE OF DEEP BRAIN STIMULATION IMPLANTATION , 2009, Neurosurgery.

[39]  Terry S. Yoo,et al.  Insight into Images: Principles and Practice for Segmentation, Registration, and Image Analysis , 2004 .

[40]  A. Connelly,et al.  Super‐resolution track‐density imaging of thalamic substructures: Comparison with high‐resolution anatomical magnetic resonance imaging at 7.0T , 2013, Human brain mapping.

[41]  Fazel Naghdy,et al.  An analysis of medical image processing methods for segmentation of the inner ear , 2009 .

[42]  Manojkumar Saranathan,et al.  Visualization of intra-thalamic nuclei with optimized white-matter-nulled MPRAGE at 7T , 2014, NeuroImage.

[43]  Christian Barillot,et al.  Brain Segmentation with Competitive Level Sets and Fuzzy Control , 2005, IPMI.

[44]  Silvana G. Dellepiane,et al.  Extraction of intensity connectedness for image processing , 1995, Pattern Recognit. Lett..

[45]  Milan Sonka,et al.  Segmentation and interpretation of MR brain images. An improved active shape model , 1998, IEEE Transactions on Medical Imaging.

[46]  Chun Lan Yang,et al.  Segmentation of Target Nuclei in Parkinson's Disease Based on Fuzzy Connectedness , 2013 .