Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures

The large amount of imaging data collected in several ongoing multi-center studies requires automated methods to delineate brain structures of interest. We have previously reported on using artificial neural networks (ANN) to define subcortical brain structures. Here we present several automated segmentation methods using multidimensional registration. A direct comparison between template, probability, artificial neural network (ANN) and support vector machine (SVM)-based automated segmentation methods is presented. Three metrics for each segmentation method are reported in the delineation of subcortical and cerebellar brain regions. Results show that the machine learning methods outperform the template and probability-based methods. Utilization of these automated segmentation methods may be as reliable as manual raters and require no rater intervention.

[1]  K S Cheng,et al.  Segmentation of multispectral magnetic resonance image using penalized fuzzy competitive learning network. , 1996, Computers and biomedical research, an international journal.

[2]  Phillip L Pearl,et al.  Imaging data in autism: from structure to malfunction. , 2004, Seminars in pediatric neurology.

[3]  K. Cheng,et al.  Multispectral magnetic resonance images segmentation using fuzzy Hopfield neural network. , 1996, International journal of bio-medical computing.

[4]  Barry T. Thomas,et al.  Using Neural Networks to Automatically Detect Brain Tumours in MR Images , 1997, Int. J. Neural Syst..

[5]  Anke Meyer-Bäse,et al.  Cluster analysis of dynamic cerebral contrast-enhanced perfusion MRI time-series , 2006, IEEE Transactions on Medical Imaging.

[6]  Edwin N. Cook,et al.  Automated segmentation and classification of multispectral magnetic resonance images of brain using artificial neural networks , 1997, IEEE Transactions on Medical Imaging.

[8]  Jayaram K. Udupa,et al.  Shape-based interpolation of multidimensional grey-level images , 1994, Medical Imaging.

[9]  R. Kikinis,et al.  An Automated Registration Algorithm for Measuring MRI Subcortical Brain Structures , 1997, NeuroImage.

[10]  G Wagenknecht,et al.  MRI-based individual 3D region-of-interest atlases of the human brain: a new method for analyzing functional data. , 2004, Methods of information in medicine.

[11]  Daniel S. O'Leary,et al.  Manual and Semiautomated Measurement of Cerebellar Subregions on MR Images , 2002, NeuroImage.

[12]  Jean-Philippe Thirion,et al.  Image matching as a diffusion process: an analogy with Maxwell's demons , 1998, Medical Image Anal..

[13]  J C Mazziotta,et al.  Automated image registration: II. Intersubject validation of linear and nonlinear models. , 1998, Journal of computer assisted tomography.

[14]  Anke Meyer-Bäse,et al.  Fully automated biomedical image segmentation by self-organized model adaptation , 2004, Neural Networks.

[15]  D W Piraino,et al.  Segmentation of magnetic resonance images using an artificial neural network. , 1991, Proceedings. Symposium on Computer Applications in Medical Care.

[16]  H. Jeremy Bockholt,et al.  A hybrid tissue segmentation approach for brain MR images , 2006, Medical and Biological Engineering and Computing.

[17]  Manuel Graña,et al.  Computer-assisted enhanced volumetric segmentation magnetic resonance imaging data using a mixture of artificial neural networks. , 2003, Magnetic resonance imaging.

[18]  N C Andreasen,et al.  Image processing for the study of brain structure and function: problems and programs. , 1992, The Journal of neuropsychiatry and clinical neurosciences.

[19]  Qing Ji,et al.  Prediction of total cerebral tissue volumes in normal appearing brain from sub-sampled segmentation volumes. , 2003, Magnetic resonance imaging.

[20]  Annette Sterr,et al.  MRI fuzzy segmentation of brain tissue using neighborhood attraction with neural-network optimization , 2005, IEEE Transactions on Information Technology in Biomedicine.

[21]  J. Ehrhardt,et al.  Measurement of brain structures with artificial neural networks: two- and three-dimensional applications. , 1999, Radiology.

[22]  D Caramella,et al.  Neural network segmentation of magnetic resonance spin echo images of the brain. , 1993, Journal of biomedical engineering.

[23]  Michel Bilello,et al.  Identification, segmentation, and image property study of acute infarcts in diffusion-weighted images by using a probabilistic neural network and adaptive Gaussian mixture model. , 2006, Academic radiology.

[24]  Raquel Valdés-Cristerna,et al.  Coupling of radial-basis network and active contour model for multispectral brain MRI segmentation , 2004, IEEE Transactions on Biomedical Engineering.

[25]  P. Fieguth,et al.  Adaboost and Support Vector Machines for White Matter Lesion Segmentation in MR Images , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[26]  Fred L. Bookstein,et al.  Thin-Plate Splines and the Atlas Problem for Biomedical Images , 1991, IPMI.

[27]  S.M. Krishnan,et al.  Extraction of Brain Tumor from MR Images Using One-Class Support Vector Machine , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[28]  Ronen Basri,et al.  Atlas Guided Identification of Brain Structures by Combining 3D Segmentation and SVM Classification , 2006, MICCAI.

[29]  Alan C. Evans,et al.  Enhancement of MR Images Using Registration for Signal Averaging , 1998, Journal of Computer Assisted Tomography.

[30]  Amar Gajjar,et al.  Neurocognitive deficits in medulloblastoma survivors and white matter loss , 1999, Annals of neurology.

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

[32]  Federico Girosi,et al.  Support Vector Machines: Training and Applications , 1997 .

[33]  Greg Harris,et al.  Structural MR image processing using the BRAINS2 toolbox. , 2002, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[34]  Minjie Wu,et al.  Quantitative comparison of AIR, SPM, and the fully deformable model for atlas‐based segmentation of functional and structural MR images , 2006, Human brain mapping.

[35]  N C Andreasen,et al.  Voxel processing techniques for the antemortem study of neuroanatomy and neuropathology using magnetic resonance imaging. , 1993, The Journal of neuropsychiatry and clinical neurosciences.

[36]  N C Andreasen,et al.  Improving tissue classification in MRI: a three-dimensional multispectral discriminant analysis method with automated training class selection. , 1999, Journal of computer assisted tomography.

[37]  Nancy C. Andreasen,et al.  Manual and Automated Measurement of the Whole Thalamus and Mediodorsal Nucleus Using Magnetic Resonance Imaging , 2002, NeuroImage.

[38]  R P Velthuizen,et al.  MRI: stability of three supervised segmentation techniques. , 1993, Magnetic resonance imaging.

[39]  N C Andreasen,et al.  A new method for the in vivo volumetric measurement of the human hippocampus with high neuroanatomical accuracy , 2000, Hippocampus.