-
[show abstract]
[hide abstract]
ABSTRACT: The perirhinal cortex (Brodmann's area 35) is a multimodal area that is important for normal memory function. Specifically, perirhinal cortex is involved in the detection of novel objects and manifests neurofibrillary tangles in Alzheimer's disease very early in disease progression. We scanned ex vivo brain hemispheres at standard resolution (1mm×1mm×1mm) to construct pial/white matter surfaces in FreeSurfer and scanned again at high resolution (120μm×120μm×120μm) to determine cortical architectural boundaries. After labeling perirhinal area 35 in the high resolution images, we mapped the high resolution labels to the surface models to localize area 35 in fourteen cases. We validated the area boundaries determined using histological Nissl staining. To test the accuracy of the probabilistic mapping, we measured the Hausdorff distance between the predicted and true labels and found that the median Hausdorff distance was 4.0mm for the left hemispheres (n=7) and 3.2mm for the right hemispheres (n=7) across subjects. To show the utility of perirhinal localization, we mapped our labels to a subset of the Alzheimer's Disease Neuroimaging Initiative dataset and found decreased cortical thickness measures in mild cognitive impairment and Alzheimer's disease compared to controls in the predicted perirhinal area 35. Our ex vivo probabilistic mapping of the perirhinal cortex provides histologically validated, automated and accurate labeling of architectonic regions in the medial temporal lobe, and facilitates the analysis of atrophic changes in a large dataset for earlier detection and diagnosis.
NeuroImage 08/2012; 64C:32-42. · 5.89 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Extensive imaging is routinely used in brain tumor patients to monitor the state of the disease and to evaluate therapeutic options. A large number of multi-modal and multi-temporal image volumes is acquired in standard clinical cases, requiring new approaches for comprehensive integration of information from different image sources and different time points. In this work we propose a joint generative model of tumor growth and of image observation that naturally handles multimodal and longitudinal data. We use the model for analyzing imaging data in patients with glioma. The tumor growth model is based on a reaction-diffusion framework. Model personalization relies only on a forward model for the growth process and on image likelihood. We take advantage of an adaptive sparse grid approximation for efficient inference via Markov Chain Monte Carlo sampling. The approach can be used for integrating information from different multi-modal imaging protocols and can easily be adapted to other tumor growth models.
Information processing in medical imaging: proceedings of the ... conference 01/2011; 22:735-47.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents the Relevance Voxel Machine (RVoxM), a Bayesian multivariate pattern analysis (MVPA) algorithm that is specifically designed for making predictions based on image data. In contrast to generic MVPA algorithms that have often been used for this purpose, the method is designed to utilize a small number of spatially clustered sets of voxels that are particularly suited for clinical interpretation. RVoxM automatically tunes all its free parameters during the training phase, and offers the additional advantage of producing probabilistic prediction outcomes. Experiments on age prediction from structural brain MRI indicate that RVoxM yields biologically meaningful models that provide excellent predictive accuracy.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2011; 14(Pt 3):99-106.
-
[show abstract]
[hide abstract]
ABSTRACT: 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 algorithms are interpreted as special cases of our framework. We conduct two sets of experiments to validate the proposed methods. In the first set of experiments, we use 39 brain MRI scans-with manually segmented white matter, cerebral cortex, ventricles and subcortical structures-to compare different label fusion algorithms and the widely-used FreeSurfer whole-brain segmentation tool. Our results indicate that the proposed framework yields more accurate segmentation than FreeSurfer and previous label fusion algorithms. In a second experiment, we use brain MRI scans of 282 subjects to demonstrate that the proposed segmentation tool is sufficiently sensitive to robustly detect hippocampal volume changes in a study of aging and Alzheimer's Disease.
IEEE transactions on medical imaging. 10/2010; 29(10):1714-29.
-
[show abstract]
[hide abstract]
ABSTRACT: Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented.
Medical image analysis 10/2010; 14(5):654-65. · 3.09 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We introduce a generative probabilistic model for segmentation of tumors in multi-dimensional images. The model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities. We augment a probabilistic atlas of healthy tissue priors with a latent atlas of the lesion and derive the estimation algorithm to extract tumor boundaries and the latent atlas from the image data. We present experiments on 25 glioma patient data sets, demonstrating significant improvement over the traditional multivariate tumor segmentation.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2010; 13(Pt 2):151-9.
-
[show abstract]
[hide abstract]
ABSTRACT: Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive,
reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a joint segmentation of
corresponding, aligned structures in the entire population that does not require a probability atlas. Instead, a latent atlas,
initialized by a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The proposed method
is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria.
We evaluate the method by segmenting 50 brain MR volumes. Segmentation accuracy for cortical and subcortical structures approaches
the quality of state-of-the-art atlas-based segmentation results, suggesting that the latent atlas method is a reasonable alternative when existing atlases are not compatible with the data to be processed.
09/2009: pages 272-280;
-
[show abstract]
[hide abstract]
ABSTRACT: Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data
are summarized using a parametric atlas. Summarizing the data alleviates the computational burden at the expense of possibly
losing valuable information on inter-subject variability. This paper presents a novel framework for Supervised Nonparametric
Image Parcellation (SNIP). SNIP models the intensity and label images as samples of a joint distribution estimated from the
training data in a non-parametric fashion. By capitalizing on recently developed fast and robust pairwise image alignment
tools, SNIP employs the entire training data to segment a new image via Expectation Maximization. The use of multiple registrations increases robustness
to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with manual labels for the white
matter, cortex and subcortical structures. SNIP yields better segmentation than state-of-the-art algorithms in multiple regions
of interest.
09/2009: pages 1075-1083;
-
[show abstract]
[hide abstract]
ABSTRACT: We present a nonparametric, probabilistic mixture model for the supervised parcellation of images. The proposed model yields segmentation algorithms conceptually similar to the recently developed label fusion methods, which register a new image with each training image separately. Segmentation is achieved via the fusion of transferred manual labels. We show that in our framework various settings of a model parameter yield algorithms that use image intensity information differently in determining the weight of a training subject during fusion. One particular setting computes a single, global weight per training subject, whereas another setting uses locally varying weights when fusing the training data. The proposed nonparametric parcellation approach capitalizes on recently developed fast and robust pairwise image alignment tools. The use of multiple registrations allows the algorithm to be robust to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with expert manual labels for the white matter, cerebral cortex, ventricles and subcortical structures. The results demonstrate that the proposed nonparametric segmentation framework yields significantly better segmentation than state-of-the-art algorithms.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 09/2009; 12(WS):301-313.
-
Bruce Fischl,
Allison A Stevens,
Niranjini Rajendran,
B T Thomas Yeo,
Douglas N Greve, Koen Van Leemput,
Jonathan R Polimeni,
Sita Kakunoori,
Randy L Buckner,
Jennifer Pacheco,
David H Salat,
Jennifer Melcher,
Matthew P Frosch,
Bradley T Hyman,
P Ellen Grant,
Bruce R Rosen,
André J W van der Kouwe,
Graham C Wiggins,
Lawrence L Wald,
Jean C Augustinack
[show abstract]
[hide abstract]
ABSTRACT: Entorhinal cortex (EC) is a medial temporal lobe area critical to memory formation and spatial navigation that is among the earliest parts of the brain affected by Alzheimer's disease (AD). Accurate localization of EC would thus greatly facilitate early detection and diagnosis of AD. In this study, we used ultra-high resolution ex vivo MRI to directly visualize the architectonic features that define EC rostrocaudally and mediolaterally, then applied surface-based registration techniques to quantify the variability of EC with respect to cortical geometry, and made predictions of its location on in vivo scans. The results indicate that EC can be localized quite accurately based on cortical folding patterns, within 3 mm in vivo, a significant step forward in our ability to detect the earliest effects of AD when clinical intervention is most likely to be effective.
NeuroImage 05/2009; 47(1):8-17. · 5.89 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. However, a fundamental bottleneck in MRI studies of the hippocampus at the subfield level is that they currently depend on manual segmentation, a laborious process that severely limits the amount of data that can be analyzed. In this article, we present a computational method for segmenting the hippocampal subfields in ultra-high resolution MRI data in a fully automated fashion. Using Bayesian inference, we use a statistical model of image formation around the hippocampal area to obtain automated segmentations. We validate the proposed technique by comparing its segmentations to corresponding manual delineations in ultra-high resolution MRI scans of 10 individuals, and show that automated volume measurements of the larger subfields correlate well with manual volume estimates. Unlike manual segmentations, our automated technique is fully reproducible, and fast enough to enable routine analysis of the hippocampal subfields in large imaging studies.
Hippocampus 05/2009; 19(6):549-57. · 5.18 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. Instead, a latent atlas, initialized by a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The proposed method is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria, We evaluate the method by segmenting 50 brain MR volumes. Segmentation accuracy for cortical and subcortical structures approaches the quality of state-of-the-art atlas-based segmentation results, suggesting that the latent atlas method is a reasonable alternative when existing atlases are not compatible with the data to be processed.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2009; 12(Pt 1):272-80.
-
[show abstract]
[hide abstract]
ABSTRACT: A natural requirement in pairwise image registration is that the resulting deformation is independent of the order of the images. This constraint is typically achieved via a symmetric cost function and has been shown to reduce the effects of local optima. Consequently, symmetric registration has been successfully applied to pairwise image registration as well as the spatial alignment of individual images with a template. However, recent work has shown that the relationship between an image and a template is fundamentally asymmetric. In this paper, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2009; 12(Pt 1):565-73.
-
[show abstract]
[hide abstract]
ABSTRACT: Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data are summarized using a parametric atlas. Summarizing the data alleviates the computational burden at the expense of possibly losing valuable information on inter-subject variability. This paper presents a novel framework for Supervised Nonparametric Image Parcellation (SNIP). SNIP models the intensity and label images as samples of a joint distribution estimated from the training data in a non-parametric fashion. By capitalizing on recently developed fast and robust pairwise image alignment tools, SNIP employs the entire training data to segment a new image via Expectation Maximization. The use of multiple registrations increases robustness to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with manual labels for the white matter, cortex and subcortical structures. SNIP yields better segmentation than state-of-the-art algorithms in multiple regions of interest.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2009; 12(Pt 2):1075-83.
-
Medical Image Computing and Computer-Assisted Intervention - MICCAI 2009, 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part II; 01/2009
-
Medical Image Computing and Computer-Assisted Intervention - MICCAI 2009, 12th International Conference, London, UK, September 20-24, 2009, Proceedings, Part I; 01/2009
-
[show abstract]
[hide abstract]
ABSTRACT: Recent developments in MR data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. Because of the role of the hippocampus in human memory and its implication in a variety of disorders and conditions, the ability to reliably and efficiently quantify its subfields through in vivo neuroimaging is of great interest to both basic neuroscience and clinical research. In this paper, we propose a fully-automated method for segmenting the hippocampal subfields in ultra-high resolution MRI data. Using a Bayesian approach, we build a computational model of how images around the hippocampal area are generated, and use this model to obtain automated segmentations. We validate the proposed technique by comparing our segmentation results with corresponding manual delineations in ultra-high resolution MRI scans of five individuals.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 02/2008; 11(Pt 1):235-43.
-
Bruce Fischl,
Allison A. Stevens,
Niranjini Rajendran,
B.T. Thomas Yeo,
Douglas N. Greve, Koen Van Leemput,
Jonathan R. Polimeni,
Sita Kakunoori,
Randy L. Buckner,
Jennifer Pacheco,
David H. Salat,
Jennifer Melcher,
Matthew P. Frosch,
Bradley T. Hyman,
P. Ellen Grant,
Bruce R. Rosen,
André J.W. van der Kouwe,
Graham C. Wiggins,
Lawrence L. Wald,
Jean C. Augustinack
[show abstract]
[hide abstract]
ABSTRACT: Entorhinal cortex (EC) is a medial temporal lobe area critical to memory formation and spatial navigation that is among the earliest parts of the brain affected by Alzheimer's disease (AD). Accurate localization of EC would thus greatly facilitate early detection and diagnosis of AD. In this study, we used ultra-high resolution ex vivo MRI to directly visualize the architectonic features that define EC rostrocaudally and mediolaterally, then applied surface-based registration techniques to quantify the variability of EC with respect to cortical geometry, and made predictions of its location on in vivo scans. The results indicate that EC can be localized quite accurately based on cortical folding patterns, within 3 mm in vivo, a significant step forward in our ability to detect the earliest effects of AD when clinical intervention is most likely to be effective.
NeuroImage.
