Validation of a fully automated 3D hippocampal segmentation method using subjects with Alzheimer's disease mild cognitive impairment, and elderly controls

Abstract

We introduce a new method for brain MRI segmentation, called the auto context model (ACM), to segment the hippocampus automatically in 3D T1-weighted structural brain MRI scans of subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). In a training phase, our algorithm used 21 hand-labeled segmentations to learn a classification rule for hippocampal versus non-hippocampal regions using a modified AdaBoost method, based on ∼18,000 features (image intensity, position, image curvatures, image gradients, tissue classification maps of gray/white matter and CSF, and mean, standard deviation, and Haar filters of size 1×1×1 to 7×7×7). We linearly registered all brains to a standard template to devise a basic shape prior to capture the global shape of the hippocampus, defined as the pointwise summation of all the training masks. We also included curvature, gradient, mean, standard deviation, and Haar filters of the shape prior and the tissue classified images as features. During each iteration of ACM - our extension of AdaBoost - the Bayesian posterior distribution of the labeling was fed back in as an input, along with its neighborhood features, as new features for AdaBoost to use. In validation studies, we compared our results with hand-labeled segmentations by two experts. Using a leave-one-out approach and standard overlap and distance error metrics, our automated segmentations agreed well with human raters; any differences were comparable to differences between trained human raters. Our error metrics compare favorably with those previously reported for other automated hippocampal segmentations, suggesting the utility of the approach for large-scale studies.

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

“…For HC segmentation, recently published results (Barnes et al, 2008;Chupin et al, 2007;Morey et al, 2009;Morra et al, 2008;Pohl et al, 2007;van der Lijn et al, 2008) indicated high kappa index values greater than 0.80. The latest published methods based on the nonlinear warping of the best templates and involving a label fusion step (Collins and Pruessner, 2010;Gousias et al, 2008;Lotjonen et al, 2010) obtained kappa index values equal to or greater than 0.88.…”

The use of biomarkers for the etiologic diagnosis of MCI in Europe: An EADC survey

“…Although this is inevitable in the case of amyloid imaging where the only FDA-and EMA-approved procedure is structured visual rating, a number of automated or semiautomated tools are available for structural MR and FDG-PET [36][37][38][39][40]. However, despite their demonstrated superiority over visual assessments [28][29][30]41,42], these more quantitative measures are used by a minority of centers.…”

A commonly carried allele of the obesity-relatedFTOgene is associated with reduced brain volume in the healthy elderly

“…CDF plots, based on the above correlation tests, were used to rank the proportion of significant voxels in association with SNP rs3751812, BMI, and WMB (Fig. S3) (24,25,51). See SI Text.…”