Abstract not found

This paper presents a very high resolution voxel-based morphometric method, by using a mass-preserving deformation mechanism and a fully automated spatial normalization approach, referred to as HAMMER. By using a hierarchical attribute-based deformation strategy, HAMMER partly overcomes limitations of several existing spatial normalization methods, and it achieves a level of accuracy that makes possible morphometric measurements of spatial specificity close to the voxel dimensions. The proposed method is validated by a series of experiments, with both simulated and real brain images. I.

It is well known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. We have previously shown this to be true for atlas-based segmentation of biomedical images. The conventional method for combining individual classifiers weights each classifier equally (vote or sum rule fusion). In this paper, we propose two methods that estimate the performances of the individual classifiers and combine the individual classifiers by weighting them according to their estimated performance. The two methods are multiclass extensions of an expectation-maximization (EM) algorithm for ground truth estimation of binary classification based on decisions of multiple experts (Warfield et al., 2004). The first method performs parameter estimation independently for each class with a subsequent integration step. The second method considers all classes simultaneously. We demonstrate the efficacy of these performance-based fusion methods by applying them to atlas-based segmentations of three-dimensional confocal microscopy images of bee brains. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. In a second evaluation study, multiple actual atlas-based segmentations are combined and their ...

We present a novel variational and statistical approach for shape registration. Shapes of interest are implicitly embedded in a higher dimensional space of distance transforms. In this implicit embedding space, registration is formulated in a hierarchical manner: the Mutual Information criterion supports various transformation models and is optimized to perform global registration; then a B-spline based Incremental Free Form Deformations (IFFD) model is used to minimize a Sum-of-Squared-Differences (SSD) measure and further recover a dense local nonrigid registration field. The key advantage of such framework is twofold: (1) it naturally deals with shapes of arbitrary dimension (2D, 3D or higher) and arbitrary topology (multiple parts, closed/open), and (2) it preserves shape topology during local deformation, and produces local registration fields that are smooth, continuous and establish one-to-one correspondences. Its invariance to initial conditions is evaluated through empirical validation, and various hard 2D/3D geometric shape registration examples are used to show its robustness to noise, severe occlusion and missing parts. We demonstrate the power of the proposed framework using two applications: one for statistical modeling of anatomical structures, another for 3D face scan registration and expression tracking. We also compare the performance of our algorithm with that of several other well-known shape registration algorithms.

Nonrigid registration of medical images is important for a number of applications such as the creation of population averages, atlas-based segmentation, or geometric correction of functional magnetic resonance imaging (fMRI) images to name a few. In recent years, a number of methods have been proposed to solve this problem, one class of which involves maximizing a mutual information (MI)-based objective function over a regular grid of splines. This approach has produced good results but its computational complexity is proportional to the compliance of the transformation required to register the smallest structures in the image. Here, we propose a method that permits the spatial adaptation of the transformation’s compliance. This spatial adaptation allows us to reduce the number of degrees of freedom in the overall transformation, thus speeding up the process and improving its convergence properties. To develop this method, we introduce several novelties: 1) we rely on radially symmetric basis functions rather than B-splines traditionally used to model the deformation field; 2) we propose a metric to identify regions that are poorly registered and over which the transformation needs to be improved; 3) we partition the global registration problem into several smaller ones; and 4) we introduce a new constraint scheme that allows us to produce transformations that are topologically correct. We compare the approach we propose to more traditional ones and show that our new algorithm compares favorably to those in current use.

Abstract not found

In this paper, we demonstrate a technique for modeling liver motion during the respiratory cycle using intensitybased free-form deformation registration of gated MR images. We acquired 3-D MR image sets (multislice 2-D) of the abdomen of four volunteers at end-inhalation, end-exhalation, and eight time points in between using respiratory gating. We computed the deformation field between the images using intensity-based rigid and non-rigid registration algorithms. The non-rigid transformation is a free-form deformation with B-spline interpolation between uniformlyspaced control points. The transformations between inhalation and exhalation were visually inspected. Much of the liver motion is cranial-caudal translation, and thus the rigid transformation captures much of the motion. However, there is still substantial residual deformation of up to 2 cm. The free-form deformation produces a motion field that appears on visual inspection to be accurate. This is true for the liver surface, internal liver structures such as the vascular tree, and the external skin surface. We conclude that abdominal organ motion due to respiration can be satisfactorily modeled using an intensity-based non-rigid 4-D image registration approach. This allows for an easier and potentially more accurate and patient-specific deformation field computation than physics-based models using assumed tissue properties and acting forces.

We propose a novel MRF-based model for deformable image matching. Given two images, the task is to estimate a mapping from one image to the other maximizing the quality of the match. We consider mappings defined by a discrete deformation field constrained to preserve 2D continuity. We pose the task as finding MAP configurations of a pairwise MRF. We propose a more compact MRF representation of the problem which leads to a weaker, though computationally more tractable, linear programming relaxation – the approximation technique we choose to apply. The number of dual LP variables grows linearly with the search window side, rather than quadratically as in previous approaches. To solve the relaxed problem (suboptimally), we apply TRW-S (Sequential Tree-Reweighted Message passing) algorithm [13, 5]. Using our representation and the chosen optimization scheme, we are able to match much wider deformations than was considered previously in global optimization framework. We further elaborate on continuity and data terms to achieve more appropriate description of smooth deformations. The performance of our technique is demonstrated on both synthetic and real-world experiments. 1.

Abstract. We present different approaches to reconstructing an inextensible surfaces from point correspondences between an input image and a template image representing a flat reference shape from a frontoparallel point of view. We first propose two 'point-wise' methods, i.e. methods that only retrieve the 3D positions of the point correspondences. These methods are formulated as second-order cone programs and they handle inaccuracies in the point measurements. They relie on the fact that the Euclidean distance between two 3D points must be shorter than their geodesic distance (which can easily be computed from the template image). We then present an approach that reconstructs a smooth 3D surface based on Free-Form Deformations. The surface is represented as a smooth map from the template image space to the 3D space. Our idea is to say that the 2D-3D map must be everywhere locally isometric. This induces conditions on the Jacobian matrix of the map which are included in a least-squares minimization problem.

Multi-subject non-rigid registration algorithms using dense deformation fields often encounter cases where the transformation to be estimated has a large spatial variability. In these cases, linear stationary regularization methods are not su#cient. In this paper, we present an algorithm that uses a priori information about the nature of imaged objects in order to adapt the regularization of the deformations. We also present a robustness improvement that gives higher weight to those points in images that contain more information. Finally, a fast parallel implementation using networked personal computers is presented. In order to improve the usability of the parallel software by a clinical user, we have implemented it as a grid service that can be controlled by a graphics workstation embedded in the clinical environment. Results on inter-subject pairs of images show that our method can take into account the large variability of most brain structures. The registration time for images 124 is 5 minutes on 15 standard PCs. A comparison of our non-stationary visco-elastic smoothing versus solely elastic or fluid regularizations shows that our algorithm converges faster towards a more optimal solution in terms of accuracy and transformation regularity.