Results 1 - 10
of
324
Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
- NEUROIMAGE 46 (2009) 786–802
, 2009
"... ..."
A Generative Model for Image Segmentation Based on Label Fusion
- IEEE TRANSACTIONS IN MEDICAL IMAGING
, 2010
"... We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between the test image and individual training images. The training labels ..."
Abstract
-
Cited by 62 (5 self)
- Add to MetaCart
(Show Context)
We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between the test image and individual training images. The training labels are then transferred to the test image and fused to compute the final segmentation of the test subject. Such label fusion methods have been shown to yield accurate segmentation, since the use of multiple registrations captures greater inter-subject anatomical variability and improves robustness against occasional registration failures. To the best of our knowledge, this manuscript presents the first comprehensive probabilistic framework that rigorously motivates label fusion as a segmentation approach. The proposed framework allows us to compare different label fusion algorithms theoretically and practically. In particular, recent label fusion or multiatlas segmentation
A Bayesian model for joint segmentation and registration
- NEUROIMAGE
, 2006
"... A statistical model is presented that combines the registration of an atlas with the segmentation of magnetic resonance images. We use an Expectation Maximization-based algorithm to find a solution within the model, which simultaneously estimates image artifacts, anatomical labelmaps, and a structur ..."
Abstract
-
Cited by 58 (2 self)
- Add to MetaCart
(Show Context)
A statistical model is presented that combines the registration of an atlas with the segmentation of magnetic resonance images. We use an Expectation Maximization-based algorithm to find a solution within the model, which simultaneously estimates image artifacts, anatomical labelmaps, and a structure-dependent hierarchical mapping from the atlas to the image space. The algorithm produces segmentations for brain tissues as well as their substructures. We demonstrate the approach on a set of 22 magnetic resonance images. On this set of images, the new approach performs significantly better than similar methods which sequentially apply registration and segmentation.
A spatially unbiased atlas template of the human cerebellum. NeuroImage 33(1), 127–138 (2006) M. De Craene et al
"... This article presents a new high-resolution atlas template of the human, cerebellum and brainstem, based on the anatomy of 20 young healthy individuals. The atlas is spatially unbiased, i.e., the location of each structure is equal to the expected location of that structure across individuals in MNI ..."
Abstract
-
Cited by 47 (6 self)
- Add to MetaCart
(Show Context)
This article presents a new high-resolution atlas template of the human, cerebellum and brainstem, based on the anatomy of 20 young healthy individuals. The atlas is spatially unbiased, i.e., the location of each structure is equal to the expected location of that structure across individuals in MNI space, a result that is cross-validated with an independent sample of 16 individuals. At the same time, the new template preserves the anatomical detail of cerebellar structures through a nonlinear atlas generation algorithm. In comparison to current whole-brain templates, it allows for an improved voxel-byvoxel normalization for functional MRI and lesion analysis. Alignment to the template requires that the cerebellum and brainstem are isolated from the surrounding tissue, a process for which an automated algorithm has been developed. Compared to normalization to the MNI whole-brain template, the new method strongly improves the alignment of individual fissures, reducing their spatial spread by 60%, and improves the overlap of the deep cerebellar nuclei. Applied to functional MRI data, the new normalization technique leads to a 5–15 % increase in peak t values and in the activated volume in the cerebellar cortex for movement vs. rest contrasts. This indicates that the new template significantly improves the overlap of functionally equivalent cerebellar regions across individuals. The template and software are freely available as an SPM-toolbox, which also allows users to relate the new template to the annotated volumetric
London taxi drivers and bus drivers: a structural MRI and neuropsychological analysis.
- Hippocampus
, 2006
"... ABSTRACT: Licensed London taxi drivers show that humans have a remarkable capacity to acquire and use knowledge of a large complex city to navigate within it. Gray matter volume differences in the hippocampus relative to controls have been reported to accompany this expertise. While these gray matt ..."
Abstract
-
Cited by 42 (3 self)
- Add to MetaCart
ABSTRACT: Licensed London taxi drivers show that humans have a remarkable capacity to acquire and use knowledge of a large complex city to navigate within it. Gray matter volume differences in the hippocampus relative to controls have been reported to accompany this expertise. While these gray matter differences could result from using and updating spatial representations, they might instead be influenced by factors such as self-motion, driving experience, and stress. We examined the contribution of these factors by comparing London taxi drivers with London bus drivers, who were matched for driving experience and levels of stress, but differed in that they follow a constrained set of routes. We found that compared with bus drivers, taxi drivers had greater gray matter volume in mid-posterior hippocampi and less volume in anterior hippocampi. Furthermore, years of navigation experience correlated with hippocampal gray matter volume only in taxi drivers, with right posterior gray matter volume increasing and anterior volume decreasing with more navigation experience. This suggests that spatial knowledge, and not stress, driving, or self-motion, is associated with the pattern of hippocampal gray matter volume in taxi drivers. We then tested for functional differences between the groups and found that the ability to acquire new visuo-spatial information was worse in taxi drivers than in bus drivers. We speculate that a complex spatial representation, which facilitates expert navigation and is associated with greater posterior hippocampal gray matter volume, might come at a cost to new spatial memories and gray matter volume in the anterior hippocampus. V V C 2006 Wiley-Liss, Inc.
Bayesian decoding of brain images
, 2008
"... This paper introduces a multivariate Bayesian (MVB) scheme to decode or recognise brain states from neuroimages. It resolves the illposed many-to-one mapping, from voxel values or data features to a target variable, using a parametric empirical or hierarchical Bayesian model. This model is inverted ..."
Abstract
-
Cited by 32 (2 self)
- Add to MetaCart
This paper introduces a multivariate Bayesian (MVB) scheme to decode or recognise brain states from neuroimages. It resolves the illposed many-to-one mapping, from voxel values or data features to a target variable, using a parametric empirical or hierarchical Bayesian model. This model is inverted using standard variational techniques, in this case expectation maximisation, to furnish the model evidence and the conditional density of the model’s parameters. This allows one to compare different models or hypotheses about the mapping from functional or structural anatomy to perceptual and behavioural consequences (or their deficits). We frame this approach in terms of decoding measured brain states to predict or classify outcomes using the rhetoric established in pattern classification of neuroimaging data. However, the aim of MVB is not to predict (because the outcomes are known) but to enable inference on different models of structure– function mappings; such as distributed and sparse representations. This allows
Image-driven population analysis through mixture-modeling
- IEEE TRANSACTIONS ON MEDICAL IMAGING
, 2009
"... We present iCluster, a fast and efficient algorithm that clusters a set of images while co-registering them using a parameterized, nonlinear transformation model. The output of the algorithm is a small number of template images that represent different modes in a population. This is in contrast wit ..."
Abstract
-
Cited by 28 (6 self)
- Add to MetaCart
(Show Context)
We present iCluster, a fast and efficient algorithm that clusters a set of images while co-registering them using a parameterized, nonlinear transformation model. The output of the algorithm is a small number of template images that represent different modes in a population. This is in contrast with traditional, hypothesis-driven computational anatomy approaches that assume a single template to construct an atlas. We derive the algorithm based on a generative model of an image population as a mixture of deformable template images. We validate and explore our method in four experiments. In the first experiment, we use synthetic data to explore the behavior of the algorithm and inform a design choice on parameter settings. In the second experiment, we demonstrate the utility of having multiple atlases for the application of localizing temporal lobe brain structures in a pool of subjects that contains healthy controls and schizophrenia patients. Next, we employ
Bayesian Comparison of Spatially Regularised General Linear Models. Human Brain Mapping, 2006. Accepted for publication
- Human Brain Mapping
, 2005
"... In previous work [34] we have developed a spatially regularised General Linear Model (GLM) for the analysis of fMRI data which allows for the characterisation of regionally specific effects using Posterior Probability Maps (PPMs). In this paper we show how it also provides an approximation to the mo ..."
Abstract
-
Cited by 24 (10 self)
- Add to MetaCart
In previous work [34] we have developed a spatially regularised General Linear Model (GLM) for the analysis of fMRI data which allows for the characterisation of regionally specific effects using Posterior Probability Maps (PPMs). In this paper we show how it also provides an approximation to the model evidence. This is important as it is the basis of Bayesian model comparison and provides a unified framework for Bayesian Analysis of Variance (ANOVA), Cluster of Interest (COI) analyses and the principled selection of signal and noise models. We also provide extensions that implement spatial and anatomical regularisation of noise process parameters. 1
