Automated voxel-by-voxel tissue classification for hippocampal segmentation: methods and validation.

The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning method based on the use of the Pearson's correlation coefficient was developed. The segmentation results (Dice similarity index = 0.81 ± 0.03) compare well with other state-of-the art approaches. A validation study was conducted on an independent dataset of 100 T1-weighted brain images, achieving significantly better results than those obtained with FreeSurfer.

[1]  Liana G. Apostolova,et al.  Delphi Consensus on Landmarks for the Manual Segmentation of the Hippocampus on MRI: Preliminary Results from the EADC-ADNI Harmonized Protocol Working Group (S04.003) , 2012 .

[2]  David Manset,et al.  Virtual imaging laboratories for marker discovery in neurodegenerative diseases , 2011, Nature Reviews Neurology.

[3]  Saverio Pascazio,et al.  Editorial: Advanced physical methods in brain research , 2012 .

[4]  S Tangaro,et al.  A completely automated CAD system for mass detection in a large mammographic database. , 2006, Medical physics.

[5]  Neda Bernasconi,et al.  Surface-based multi-template automated hippocampal segmentation: Application to temporal lobe epilepsy , 2012, Medical Image Anal..

[6]  Sabina Sonia Tangaro,et al.  Random Forest Classification for Hippocampal Segmentation in 3D MR Images , 2013, 2013 12th International Conference on Machine Learning and Applications.

[7]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  D. Louis Collins,et al.  Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion , 2010, NeuroImage.

[9]  Paul M. Thompson,et al.  Hippocampal shape differences in dementia with Lewy bodies , 2008, NeuroImage.

[10]  Sabina Sonia Tangaro,et al.  Mass lesion detection in mammographic images using Haralik textural features , 2006, CompIMAGE.

[11]  C. Jack,et al.  Alzheimer's Disease Neuroimaging Initiative , 2008 .

[12]  Daniel Rueckert,et al.  Automatic anatomical brain MRI segmentation combining label propagation and decision fusion , 2006, NeuroImage.

[13]  G. Frisoni,et al.  Structural imaging in the clinical diagnosis of Alzheimer's disease: problems and tools , 2001, Journal of neurology, neurosurgery, and psychiatry.

[14]  Jens C. Pruessner,et al.  Survey of protocols for the manual segmentation of the hippocampus: preparatory steps towards a joint EADC-ADNI harmonized protocol. , 2011, Journal of Alzheimer's disease : JAD.

[15]  Michael Weiner,et al.  and the Alzheimer’s Disease Neuroimaging Initiative* , 2007 .

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

[17]  Alan C. Evans,et al.  Volumetry of hippocampus and amygdala with high-resolution MRI and three-dimensional analysis software: minimizing the discrepancies between laboratories. , 2000, Cerebral cortex.

[18]  Sébastien Ourselin,et al.  STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation , 2013, Medical Image Anal..

[19]  Sabina Sonia Tangaro,et al.  Active Learning Machines for Automatic Segmentation of Hippocampus in MRI , 2013, ICDM.

[20]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[21]  P. Bosco,et al.  Alzheimer’s disease markers from structural MRI and FDG-PET brain images , 2012 .

[22]  Andrea Chincarini,et al.  Local MRI analysis approach in the diagnosis of early and prodromal Alzheimer's disease , 2011, NeuroImage.

[23]  Brian B. Avants,et al.  Integrated Graph Cuts for Brain MRI Segmentation , 2006, MICCAI.

[24]  Sandra E. Black,et al.  A direct morphometric comparison of five labeling protocols for multi-atlas driven automatic segmentation of the hippocampus in Alzheimer's disease , 2013, NeuroImage.

[25]  Sang Won Seo,et al.  Fully-automated approach to hippocampus segmentation using a graph-cuts algorithm combined with atlas-based segmentation and morphological opening. , 2013, Magnetic resonance imaging.

[26]  Donato Cascio,et al.  Automatic detection of lung nodules in CT datasets based on stable 3D mass-spring models , 2012, Comput. Biol. Medicine.

[27]  Sabina Sonia Tangaro,et al.  Automated Shape Analysis landmarks detection for medical image processing , 2012, CompIMAGE.

[28]  D. Louis Collins,et al.  Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation , 2011, NeuroImage.

[29]  C. Jack,et al.  Harmonization of magnetic resonance-based manual hippocampal segmentation: A mandatory step for wide clinical use , 2011, Alzheimer's & Dementia.