Marinette Revenu

Acquisition, segmentation and tracking of the cerebral vascular tree on 3D magnetic resonance angiography images

This paper presents a method for the detection, representation and visualisation of the cerebral vascular tree and its application to magnetic resonance angiography (MRA) images. The detection method is an iterative tracking of the vessel centreline with subvoxel accuracy and precise orientation estimation. This tracking algorithm deals with forks. Centrelines of the vessels are modelled by second-order B-spline. This method is used to obtain a high-level description of the whole vascular network. Applications to real angiographic data are presented. An MRA sequence has been designed, and a global segmentation of the whole vascular tree is realised in three steps. Applications of this work are accurate 3D representation of the vessel centreline and of the vascular tree, and visualisation. The tracking process is also successfully applied to 3D contrast enhanced MR digital subtracted angiography (3D-CE-MRA) of the inferior member vessels. In addition, detection of artery stenosis for routine clinical use is possible due to the high precision of the tracking algorithm.

Borg: a knowledge-based system for automatic generation of image processing programs

This article deals with the design of a system that automates the generation of image processing applications. Users describe tasks to perform on images and the system constructs a specific plan, which, after being executed, should yield the desired results. Our approach to this problem belongs to a more general category of systems for the supervision of a library of operators. The generation of an application is considered as the dynamic building of chains of image processing through the selection, parameter tuning and scheduling of existing operators. To develop such a system, we suggest to use a knowledge-rich resolution model and to integrate seven design rules. The Borg system has been developed following these prescriptions. It hinges on hierarchical, opportunistic and incremental planning by means of knowledge sources of the blackboard model, which enable to take into account the planning, evaluation and knowledge acquisition issues.

MRI geometric distortion: a simple approach to correcting the effects of non-linear gradient fields.

We present a method to correct intensity variations and voxel shifts caused by non‐linear gradient fields in magnetic resonance images. The principal sources of distortion are briefly discussed, as well as the methods of correction currently in use. The implication of the gradient field non‐linearities on the signal equations are described in a detailed way for the case of two‐ and three‐dimensional Fourier imaging. A model of these non‐linearities, derived from the geometry of the gradient coils, is proposed and then applied in post‐processing to correct any images regardless of the acquisition sequence. Initial position errors, as large as 4 mm (i.e., four voxels of 1 × 1 × 1.4 mm3 ) before correction, are reduced to less than the voxel sizes after correction. J. Magn. Reson. Imaging 1999;9:821–831.

Region-Based Active Contours with Exponential Family Observations

In this paper, we focus on statistical region-based active contour models where image features (e.g. intensity) are random variables whose distribution belongs to some parametric family (e.g. exponential) rather than confining ourselves to the special Gaussian case. In the framework developed in this paper, we consider the general case of region-based terms involving functions of parametric probability densities, for which the anti-log-likelihood function is a special case. Using shape derivative tools, our effort focuses on constructing a general expression for the derivative of the energy (with respect to a domain), and on deriving the corresponding evolution speed. More precisely, we first show by an example that the estimator of the distribution parameters is crucial for the derived speed expression. On the one hand, when using the maximum likelihood (ML) estimator for these parameters, the evolution speed has a closed-form expression that depends simply on the probability density function. On the other hand, complicating additive terms appear when using other estimators, e.g. method of moments. We then proceed by stating a general result within the framework of multi-parameter exponential family. This result is specialized to the case of the anti-log-likelihood function with the ML estimator and to the case of the relative entropy. Experimental results on simulated data confirm our expectations that using the appropriate noise model leads to the best segmentation performance. We also report preliminary experiments on real life Synthetic Aperture Radar (SAR) images to demonstrate the potential applicability of our approach.

Robust GrayScale Distribution Estimation for Contactless Palmprint Recognition

More and more research have been developed very recently for automatic hand recognition. This paper proposes a new method for contactless hand authentication in complex images. Our system uses skin color and hand shape information for an accurate hand detection process. Then, the palm is extracted and characterized by a robust and normalized decomposition. During enrollment, a distribution estimation is used to defined the optimal discrimination of the palmprint features. Finally, some specific thresholds are defined to separate in test phase impostor and genuine users. The experimental results present an error rate of 1.5% with a population of 49 people.

Contact less hand recognition using shape and texture features

The hand recognition in biometric security was developed successfully for authentication or identification. In this paper, we propose an original method of contact less biometric recognition combining information from color, texture and form. First of all, the segmentation integrates the skin color components and a form model. Then, the authentication process amalgamates by convolution the geometrical characteristics of the fingers and the texture of the analyzed palm. The experimental results show an error recognition rate lower than 2% within a population of 16 people

Detection and statistical analysis of human cortical sulci.

Many studies dealing with the human brain use the spatial coordinate system of brain anatomy to localize functional regions. Unfortunately, brain anatomy, and especially cortical sulci, is characterized by a high interindividual variability. Specific tools called anatomical atlases must then be considered to make the interpretation of anatomical examinations easier. The work described here first aims at building a numerical atlas of the main cortical sulci. Our system is based on a database containing a collection of anatomical MRI of healthy volunteer brains. Their sulci have been manually drawn and labeled for both hemispheres. Sulci are represented as 3D superficial curves. After a nonlinear registration process, a statistical atlas of the cortical topography of a particular MRI is built from the database. It is an a priori model of cortical sulci, including three major components: an average curve represents the average shape and position of each sulcus; a search area accounts for its spatial variation domain; a set of quantitative parameters describes the variability of sulci geometry and topology. This atlas is completely individualized and adapted to the features of the brain under examination. The atlas is represented by a graph, the nodes of which represent sulci and the edges the relations between sulci. It can also be considered a statistical model that describes the cortical topography as well as its variability.

Region-Based Active Contour with Noise and Shape Priors

In this paper, we propose to combine formally noise and shape priors in region-based active contours. On the one hand, we use the general framework of exponential family as a prior model for noise. On the other hand, translation and scale invariant Legendre moments are considered to incorporate the shape prior (e.g. fidelity to a reference shape). The combination of the two prior terms in the active contour functional yields the final evolution equation whose evolution speed is rigorously derived using shape derivative tools. Experimental results on both synthetic images and real life cardiac echography data clearly demonstrate the robustness to initialization and noise, flexibility and large potential applicability of our segmentation algorithm.

Knowledge-based segmentation and labeling of brain structures from MRI images

In this paper, we propose a new knowledge-based method illustrated in the context of segmentation, which labels internal brain structures viewed by magnetic resonance imaging (MRI). In order to improve the accuracy of the labeling, we introduce a fuzzy model of regions of interest (ROI) by analogy with the electrostatic potential distribution, to represent more appropriately the knowledge of distance, shape and relationship of structures. The knowledge is mainly derived from the Talairach stereotaxic atlas. The labeling is achieved by the regionwise labeling using genetic algorithms (GAs), followed by a voxelwise amendment using parallel region growing. The fuzzy model is used both to design the fitness function of GAs, and to guide the region growing. The performance of our proposed method has been quantitatively validated by six indices with respect to manually labeled images.

Shape variability and spatial relationships modeling in statistical pattern recognition

We focus on the problem of shape variability modeling in statistical pattern recognition. We present a nonlinear statistical model invariant to affine transformations. This model is learned on an ordinate set of points. The concept of relations between model components is also taken in account. This model is used to find curves and points partially occulted in the image. We present its application on medical imaging in cephalometry.