Catálogo de publicaciones - libros

In this paper, we present an unsupervised 2D/3D reconstruction scheme combining a parameterized multiple-component geometrical model and a point distribution model, and show its application to automatically reconstruct a surface model of a proximal femur from a limited number of calibrated fluoroscopic images with no user intervention at all. The parameterized multiple-component geometrical model is regarded as a simplified description capturing the geometrical features of a proximal femur. Its parameters are optimally and automatically estimated from the input images using a particle filter based inference method. The estimated geometrical parameters are then used to initialize a point distribution model based 2D/3D reconstruction scheme for an accurate reconstruction of a surface model of the proximal femur. We designed and conducted and experiments to compare the present unsupervised reconstruction scheme to a supervised one. An average mean error of 1.2 mm was found when the supervised reconstruction scheme was used. It increased to 1.3 mm when the unsupervised one was used. However, the unsupervised reconstruction scheme has the advantage of elimination of user intervention, which holds the potential to facilitate the application of the 2D/3D reconstruction in surgical navigation.

A novel method called local shape controlled voting has been developed for spherical object detection in 3D voxel images. By introducing local shape properties into the voting procedure of normal overlap, the proposed method improves the capability of differentiating spherical objects from other structures, as the normal overlap technique only measures the ‘density’ of normal overlapping, while how the normals are distributed in 3D is not discovered. The proposed method was applied to computer aided detection of pulmonary nodules based on helical CT images. Experiments showed that this method attained a better performance compared to the original normal overlap technique.

This paper proposes to use the Laplace-Beltrami spectrum (LBS) as a global shape descriptor for medical shape analysis, allowing for shape comparisons using minimal shape preprocessing: no registration, mapping, or remeshing is necessary. The discriminatory power of the method is tested on a population of female caudate shapes of normal control subjects and of subjects with schizotypal personality disorder.

In this paper we present a framework for real-time tracking of deformable contours in volumetric datasets. The framework supports composite deformation models, controlled by parameters for contour shape in addition to global pose. Tracking is performed in a sequential state estimation fashion, using an extended Kalman filter, with measurement processing in information space to effectively predict and update contour deformations in real-time. A deformable B-spline surface coupled with a global pose transform is used to model shape changes of the left ventricle of the heart.

Successful tracking of global motion and local shape changes without user intervention is demonstrated on a dataset consisting of 21 3D echocardiography recordings. Real-time tracking using the proposed approach requires a modest CPU load of 13% on a modern computer. The segmented volumes compare to a semi-automatic segmentation tool with 95% limits of agreement in the interval 4.1 ±24.6 ml ( = 0.92).

Segmentation of vessels and brain aneurysms on non-invasive and flow-sensitive phase contrast magnetic resonance angiographic (PCMRA) images is essential in the detection of vascular diseases, in particular, intracranial aneurysms. In this paper, we devise a novel method based on multi-range filters and local variances to perform segmentation of vessels and intracranial aneurysms on PCMRA images. The proposed method is validated and compared using a synthetic and numerical image volume and four clinical cases. It is experimentally shown that the proposed method is capable of segmenting vessels and aneurysms with various sizes on PCMRA images.

The segmentation of macroscopically ill-defined and highly variable structures, such as the hippocampus and the amygdala , from MRI requires specific constraints. Here, we describe and evaluate a hybrid segmentation method that uses knowledge derived from a probabilistic atlas and from anatomical landmarks based on stable anatomical characteristics of the structures. Combined in a previously published semi-automatic segmentation method, they lead to a fast, robust and accurate fully automatic segmentation of and . The probabilistic atlas was built from 16 young controls and registered with the ”unified segmentation” of SPM5. The algorithm was quantitatively evaluated with respect to manual segmentation on two MRI datasets: the 16 young controls, with a leave-one-out strategy, and a mixed cohort of 8 controls and 15 subjects with epilepsy with variable hippocampal sclerosis. The segmentation driven by hybrid knowledge leads to greatly improved results compared to that obtained by registration of the thresholded atlas alone: mean overlap for on the 16 young controls increased from 78% to 87% ( < 0.001) and on the mixed cohort from 73% to 82% ( < 0.001) while the error on volumes decreased from 10% to 7% ( < 0.005) and from 18% to 8% ( < 0.001), respectively. Automatic results were better than the semi-automatic results: for the 16 young controls, average overlap increased from 84% to 87% ( < 0.001) for and from 81% to 84% ( < 0.002) for , with equivalent improvements in volume error.

This paper presents a Bayesian framework for neonatal brain-tissue segmentation in magnetic resonance (MR) images. This is a challenging task because of the low contrast-to-noise ratio and large variance in both tissue intensities and brain structures, as well as imaging artifacts and partial-volume effects in clinical neonatal scanning. We propose to incorporate a spatially adaptive likelihood model using a data-driven nonparametric statistical technique. The method initially learns an , relying on the empirical Markov statistics from training data, using fuzzy nonlinear support vector machines (SVM). In an iterative scheme, the models adapt to spatial variations of image intensities via nonparametric density estimation. The method is effective even in the absence of anatomical atlas priors. The implementation, however, can naturally incorporate probabilistic atlas priors and Markov-smoothness priors to impose additional regularity on segmentation. The maximum-a-posteriori (MAP) segmentation is obtained within a graph-cut framework. Cross validation on clinical neonatal brain-MR images demonstrates the efficacy of the proposed method, both qualitatively and quantitatively.

We introduce a non-linear shape prior for the deformable model framework that we learn from a set of shape samples using recent manifold learning techniques. We model a category of shapes as a finite dimensional manifold which we approximate using Diffusion maps. Our method computes a Delaunay triangulation of the reduced space, considered as Euclidean, and uses the resulting space partition to identify the closest neighbors of any given shape based on its Nyström extension. We derive a non-linear shape prior term designed to attract a shape towards the shape prior manifold at given constant embedding. Results on shapes of ventricle nuclei demonstrate the potential of our method for segmentation tasks.

In medical image analysis there is frequently a need to invert dense displacement fields which map one image space to another. In this paper we describe inversion techniques and determine their accuracy in the context of 18 inter-subject brain image registrations. Scattered data interpolation (SDI) is used to initialise locally and globally consistent iterative techniques. The inverse-consistency error, is computed over the whole image and over 10 specific brain regions. SDI produced good results with mean (max) ~0.02mm (2.0mm). Both iterative method produced mean errors of ~0.005mm but the globally consistent method resulted in a smaller maximum error (1.9mm compared with 1.4mm). The largest errors were in the cerebral cortex with large outlier errors in the ventricles. Simple iterative techniques are, on this evidence, able to produce reasonable estimates of inverse displacement fields provided there is good initialisation.

Registration of Diffusion Weighted (DW)-MRI datasets has been commonly achieved to date in literature by using either scalar or 2-order tensorial information. However, scalar or 2-order tensors fail to capture complex local tissue structures, such as fiber crossings, and therefore, datasets containing fiber-crossings cannot be registered accurately by using these techniques. In this paper we present a novel method for non-rigidly registering DW-MRI datasets that are represented by a field of 4-order tensors. We use the Hellinger distance between the normalized 4-order tensors represented as distributions, in order to achieve this registration. Hellinger distance is easy to compute, is scale and rotation invariant and hence allows for comparison of the true shape of distributions. Furthermore, we propose a novel 4-order tensor re-transformation operator, which plays an essential role in the registration procedure and shows significantly better performance compared to the re-orientation operator used in literature for DTI registration. We validate and compare our technique with other existing scalar image and DTI registration methods using simulated diffusion MR data and real HARDI datasets.