Multi-classifier framework for atlas-based image segmentation

Three different systematic approaches to generate multiple classifiers in atlas-based biomedical image segmentation are compared. Different atlases, as well as different parametrization of the registration algorithm, lead to different atlas-based classifiers. The classifier outputs are combined and compared to a manual ground truth segmentation. Classifier combination consistently improved classification accuracy with the biggest improvement from multiple atlases. We conclude that multi-classifier techniques have a natural application to atlas-based segmentation and increase classification accuracy in real-world segmentation problems.

[1]  Benoit M. Dawant,et al.  Automatic 3-D segmentation of internal structures of the head in MR images using a combination of similarity and free-form transformations. I. Methodology and validation on normal subjects , 1999, IEEE Transactions on Medical Imaging.

[2]  Dinggang Shen,et al.  HAMMER: hierarchical attribute matching mechanism for elastic registration , 2002, IEEE Transactions on Medical Imaging.

[3]  D. Hill,et al.  Medical image registration , 2001, Physics in medicine and biology.

[4]  Torsten Rohlfing,et al.  Segmentation of three-dimensional images using non-rigid registration: methods and validation with application to confocal microscopy images of bee brains , 2003, SPIE Medical Imaging.

[5]  Gary E. Christensen,et al.  Consistent image registration , 2001, IEEE Transactions on Medical Imaging.

[6]  Morten Bro-Nielsen,et al.  Fast Fluid Registration of Medical Images , 1996, VBC.

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

[8]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[9]  Josien P. W. Pluim,et al.  Image Registration , 2003, IEEE Trans. Medical Imaging.

[10]  Thomas W. Sederberg,et al.  Free-form deformation of solid geometric models , 1986, SIGGRAPH.

[11]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[12]  D. Louis Collins,et al.  Animal: Validation and Applications of Nonlinear Registration-Based Segmentation , 1997, Int. J. Pattern Recognit. Artif. Intell..

[13]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[14]  D. Louis Collins,et al.  Automatic 3‐D model‐based neuroanatomical segmentation , 1995 .

[15]  Torsten Rohlfing,et al.  Expectation Maximization Strategies for Multi-atlas Multi-label Segmentation , 2003, IPMI.

[16]  David R. Forsey,et al.  Hierarchical B-spline refinement , 1988, SIGGRAPH.

[17]  Torsten Rohlfing,et al.  Nonrigid image registration in shared-memory multiprocessor environments with application to brains, breasts, and bees , 2003, IEEE Transactions on Information Technology in Biomedicine.

[18]  Torsten Rohlfing,et al.  Volume-preserving nonrigid registration of MR breast images using free-form deformation with an incompressibility constraint , 2003, IEEE Transactions on Medical Imaging.

[19]  Torsten Rohlfing,et al.  Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains , 2004, NeuroImage.

[20]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[21]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Ching Y. Suen,et al.  A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Anthony J. Yezzi,et al.  A geometric snake model for segmentation of medical imagery , 1997, IEEE Transactions on Medical Imaging.

[24]  Torsten Rohlfing,et al.  Intensity-Based Non-rigid Registration Using Adaptive Multilevel Free-Form Deformation with an Incompressibility Constraint , 2001, MICCAI.

[25]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Jan Modersitzki,et al.  FLIRT: A Flexible Image Registration Toolbox , 2003, WBIR.

[27]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.