Results 1  10
of
44
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 59 (3 self)
 Add to MetaCart
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 intersubject 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
Groupwise construction of appearance models using piecewise affine deformations
 in Proceedings of 16 th British Machine Vision Conference
, 2005
"... We describe an algorithm for obtaining correspondences across a group of images of deformable objects. The approach is to construct a statistical model of appearance which can encode the training images as compactly as possible (a Minimum Description Length framework). Correspondences are defined by ..."
Abstract

Cited by 41 (15 self)
 Add to MetaCart
(Show Context)
We describe an algorithm for obtaining correspondences across a group of images of deformable objects. The approach is to construct a statistical model of appearance which can encode the training images as compactly as possible (a Minimum Description Length framework). Correspondences are defined by piecewise linear interpolation between a set of control points defined on each image. Given such points a model can be constructed, which can approximate every image in the set. The description length encodes the cost of the model, the parameters and most importantly, the residuals not explained by the model. By modifying the positions of the control points we can optimise the description length, leading to good correspondence. We describe the algorithm in detail and give examples of its application to MR brain images and to faces. We also describe experiments which use a recentlyintroduced specificity measure to evaluate the performance of different components of the algorithm. 1
Imagedriven population analysis through mixturemodeling
 IEEE TRANSACTIONS ON MEDICAL IMAGING
, 2009
"... We present iCluster, a fast and efficient algorithm that clusters a set of images while coregistering 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 coregistering 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, hypothesisdriven 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
Shape modeling and analysis with entropybased particle systems
 In Proceedings of the 20th International Conference on Information Processing in Medical Imaging
, 2007
"... Many important fields of basic research in medicine and biology routinely employ tools for the statistical analysis of collections of similar shapes. Biologists, for example, have long relied on homologous, anatomical landmarks as shape models to characterize the growth and development of species. I ..."
Abstract

Cited by 26 (13 self)
 Add to MetaCart
(Show Context)
Many important fields of basic research in medicine and biology routinely employ tools for the statistical analysis of collections of similar shapes. Biologists, for example, have long relied on homologous, anatomical landmarks as shape models to characterize the growth and development of species. Increasingly, however, researchers are exploring the use of more detailed models that are derived computationally from threedimensional images and surface descriptions. While computationallyderived models of shape are promising new tools for biomedical research, they also present some significant engineering challenges, which existing modeling methods have only begun to address. In this dissertation, I propose a new computational framework for statistical shape modeling that significantly advances the stateoftheart by overcoming many of the limitations of existing methods. The framework uses a particlesystem representation of shape, with a fast correspondencepoint optimization based on information content. The optimization balances the simplicity of the model (compactness) with the accuracy of the shape representations by using two commensurate entropy
Learningbased deformable registration of MR brain images
 IEEE Transactions on Medical Imaging
, 2006
"... Abstract—This paper presents a learningbased method for deformable registration of magnetic resonance (MR) brain images. There are two novelties in the proposed registration method. First, a set of bestscale geometric features are selected for each point in the brain, in order to facilitate corres ..."
Abstract

Cited by 22 (8 self)
 Add to MetaCart
Abstract—This paper presents a learningbased method for deformable registration of magnetic resonance (MR) brain images. There are two novelties in the proposed registration method. First, a set of bestscale geometric features are selected for each point in the brain, in order to facilitate correspondence detection during the registration procedure. This is achieved by optimizing an energy function that requires each point to have its bestscale geometric features consistent over the corresponding points in the training samples, and at the same time distinctive from those of nearby points in the neighborhood. Second, the active points used to drive the brain registration are hierarchically selected during the registration procedure, based on their saliency and consistency measures. That is, the image points with salient and consistent features (across different individuals) are considered for the initial registration of two images, while other less salient and consistent points join the registration procedure later. By incorporating these two novel strategies into the framework of the HAMMER registration algorithm, the registration accuracy has been improved according to the results on simulated brain data, and also visible improvement is observed particularly in the cortical regions of real brain data. Index Terms—Best features, best scale selection, consistency measurement, deformable registration, featurebased registration, hierarchical registration, learningbased method, saliency measurement. I.
C.J.: Computing accurate correspondences across groups of images
 IEEE Trans. Pattern Analysis and Machine Intelligence
, 2010
"... Abstract—Groupwise image registration algorithms seek to establish dense correspondences between sets of images. Typically they involve iteratively improving the registration between each image and an evolving mean. A variety of methods have been proposed, which differ in their choice of objective f ..."
Abstract

Cited by 19 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Groupwise image registration algorithms seek to establish dense correspondences between sets of images. Typically they involve iteratively improving the registration between each image and an evolving mean. A variety of methods have been proposed, which differ in their choice of objective function, representation of deformation field and optimisation methods. Given the complexity of the task, the final accuracy is significantly affected by the choices made for each component. Here we present a groupwise registration algorithm which can take advantage of the statistics of both the image intensities and the range of shapes across the group to achieve accurate matching. By testing on large sets of images (in both 2D and 3D), we explore the effects of using different image representations and different statistical shape constraints. We demonstrate that careful choice of such representations can lead to significant improvements in overall performance. Index Terms—Nonrigid registration, correspondence problem, appearance models 1
Alzheimer’s Disease Neuroimaging Initiative
, 2008
"... 3D characterization of brain atrophy in Alzheimer's disease and mild cognitive impairment using tensorbased morphometry ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
(Show Context)
3D characterization of brain atrophy in Alzheimer's disease and mild cognitive impairment using tensorbased morphometry
Learning taskoptimal registration cost functions for localizing cytoarchitecture and function in the cerebral cortex
 IEEE Trans. Med. Imaging
, 2010
"... Abstract—Image registration is typically formulated as an optimization problem with multiple tunable, manually set parameters. We present a principled framework for learning thousands of parameters of registration cost functions, such as a spatiallyvarying tradeoff between the image dissimilarity a ..."
Abstract

Cited by 8 (0 self)
 Add to MetaCart
(Show Context)
Abstract—Image registration is typically formulated as an optimization problem with multiple tunable, manually set parameters. We present a principled framework for learning thousands of parameters of registration cost functions, such as a spatiallyvarying tradeoff between the image dissimilarity and regularization terms. Our approach belongs to the classic machine learning framework of model selection by optimization of crossvalidation error. This
Generalized L2divergence and its Application to Shape Alignment
 In: Proc. Info. Proc. Med. Imaging
, 2009
"... Abstract. This paper proposes a novel and robust approach to the groupwise pointsets registration problem in the presence of large amounts of noise and outliers. Each of the point sets is represented by a mixture of Gaussians and the pointsets registration is treated as a problem of aligning the m ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
(Show Context)
Abstract. This paper proposes a novel and robust approach to the groupwise pointsets registration problem in the presence of large amounts of noise and outliers. Each of the point sets is represented by a mixture of Gaussians and the pointsets registration is treated as a problem of aligning the multiple mixtures. We develop a novel divergence measure which is defined between any arbitrary number of probability distributions based on L2 distance, and we call this new divergence measure ”Generalized L2divergence”. We derive a closedform expression for the GeneralizedL2 divergence between multiple Gaussian mixtures, which in turn leads to a computationally efficient registration algorithm. This new algorithm has an intuitive interpretation, is simple to implement and exhibits inherent statistical robustness. Experimental results indicate that our algorithm achieves very good performance in terms of both robustness and accuracy. 1
Groupwise nonrigid registration: The minimum description length approach
 In Proceedings of the British Machine Vision Conference (BMVC
, 2004
"... The principled nonrigid registration of groups of images requires a fully groupwise objective function. We consider the problem as one of finding the optimal dense correspondence between the images in the set, where optimality is defined using the Minimum Description Length (MDL) principle, that th ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
(Show Context)
The principled nonrigid registration of groups of images requires a fully groupwise objective function. We consider the problem as one of finding the optimal dense correspondence between the images in the set, where optimality is defined using the Minimum Description Length (MDL) principle, that the transmission of a model of the data, together with the parameters of that model, should be as short as possible. We demonstrate that this approach provides a suitable objective function by applying it to the task of nonrigid registration of a set of 2D T1weighted MR images of the human brain. Furthermore, we show that even in the case when substantial portions of the images are missing, the algorithm not only converges to the correct solution, but also allows meaningful integration of image data across the training set, allowing the original image to be reconstructed. 1