A Bayesian model of shape and appearance for subcortical brain segmentation

FMRIB Centre, Department of Clinical Neurology, University of Oxford, Oxford, UK.
NeuroImage (Impact Factor: 6.13). 02/2011; 56(3):907-22. DOI: 10.1016/j.neuroimage.2011.02.046
Source: PubMed

ABSTRACT Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.

Download full-text


Available from: Brian Patenaude, Apr 24, 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Observational studies support a neuroprotective role of hormone therapy (HT) in the perimenopause, with hippocampal size being a widely used biomarker. We investigated the effect of HT started before the onset of menopause and lasting for at least 3 years on hippocampal volume and shape in 80 postmenopausal women and 80 controls matched on age and intracranial volume taken from a large community-based sample (HUNT-MRI). The main effect of hormone group showed a statistically significant difference in hippocampal volumes (p=0.028). Both the right (3.2%) and left (2.8%) hippocampal volumes were larger in the HT-group; but only significant for the right hippocampus (p=0.023). Shape analysis revealed significant regional sparing of the medial aspect of the right hippocampal head and lateral aspect of the body extending to the tail, corresponding to the CA1, including part of the subiculum, in the HT-group. A similar non-significant pattern was observed in the left hippocampus. The current study provides support for the critical window theory demonstrating that HT initiated in the perimenopause has neuroprotective properties.
    Neurobiology of Aging 06/2015; 474. DOI:10.1016/j.neurobiolaging.2015.05.023 · 4.85 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Neuroimaging pipelines are known to generate different results depending on the computing platform where they are compiled and executed. We quantify these differences for brain tissue classification, fMRI analysis, and cortical thickness (CT) extraction, using three of the main neuroimaging packages (FSL, Freesurfer and CIVET) and different versions of GNU/Linux. We also identify some causes of these differences using library and system call interception. We find that these packages use mathematical functions based on single-precision floating-point arithmetic whose implementations in operating systems continue to evolve. While these differences have little or no impact on simple analysis pipelines such as brain extraction and cortical tissue classification, their accumulation creates important differences in longer pipelines such as subcortical tissue classification, fMRI analysis, and cortical thickness extraction. With FSL, most Dice coefficients between subcortical classifications obtained on different operating systems remain above 0.9, but values as low as 0.59 are observed. Independent component analyses (ICA) of fMRI data differ between operating systems in one third of the tested subjects, due to differences in motion correction. With Freesurfer and CIVET, in some brain regions we find an effect of build or operating system on cortical thickness. A first step to correct these reproducibility issues would be to use more precise representations of floating-point numbers in the critical sections of the pipelines. The numerical stability of pipelines should also be reviewed.
    Frontiers in Neuroinformatics 04/2015; 9(12). DOI:10.3389/fninf.2015.00012
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Multiple sclerosis (MS) is characterized by temporal and spatial dissemination of demyelinating lesions in the central nervous system. Associated neurodegenerative changes contributing to disability have been recognized even at early disease stages. Recent studies show the importance of gray matter damage for the accrual of clinical disability rather than white matter where demyelination is easily visualized by MRI. The susceptibility to MS is influenced by genetic risk, but genetic factors associated with the disability are not known. We used MRI data to determine cortical thickness in 557 MS cases and 75 controls and in another cohort of 219 cases. We identified 9 areas showing different thickness between cases and controls (regions of interest, ROI) (8 of them were negatively correlated with Kurtzke's expanded disability status scale, EDSS) and conducted genome-wide association (GWA) in 464 and 211 cases available from the two data sets. No marker exceeded genome-wide significance in the discovery cohort. We next combined nominal statistical evidence of association with physical evidence of interaction from a curated human protein interaction network, and searched for subnetworks enriched with nominally associated genes and searched for commonalities between the two data sets.This network-based pathway analysis of GWAS detected gene sets involved in glutamate signaling, neural development and an adjustment of intracellular calcium concentration. We report here for the first time gene sets associated with cortical thinning of MS. These genes are potentially correlated with disability of MS.
    Genes Brain and Behavior 02/2015; DOI:10.1111/gbb.12190 · 3.51 Impact Factor