Showing papers by "Francoise Preteux published in 2003"

3D Automated Lung Nodule Segmentation in HRCT

Abstract: A fully-automated 3D image analysis method is proposed to segment lung nodules in HRCT. A specific gray-level mathematical morphology operator, the SMDC-connection cost, acting in the 3D space of the thorax volume is defined in order to discriminate lung nodules from other dense (vascular) structures. Applied to clinical data concerning patients with pulmonary carcinoma, the proposed method detects isolated, juxtavascular and peripheral nodules with sizes ranging from 2 to 20 mm diameter. The segmentation accuracy was objectively evaluated on real and simulated nodules. The method showed a sensitivity and a specificity ranging from 85% to 97% and from 90% to 98%, respectively.

Variational non rigid image registration using exclusive F-information

Abstract: We address the problem of robust non rigid image registration and focus our interest on similarity criteria based on generalized information measures within the Ali-Silvey class. We introduce exclusive f-information as a novel class of similarity functionals, and develop a generic variational framework for their optimization over nonparametric and parametric transform spaces. This approach is applied to blind nonrigid alignment of face images with arbitrary lighting conditions and complex deformations.

Exploring MPEG-4 BIFS features for creating multimedia games

Abstract: This paper explores the new features of the recent MPEG- 4 standard, namely the description and the composition of an interactive multimedia scene. Providing with such advanced facilities, the MPEG-4 standard is no longer considered only as an efficient compression tool for conventional video / audio application. It is now granted the power of computing mechanism as any other programming languages to facilitate the creation of high interactive multimedia contents. Game-applications therefore can be also considered as a new output-feature of the MPEG-4 standard. The work describes in detail how game can be created within the MPEG-4 framework. The process of making game with MPEG-4 is studied comprehensively to demonstrate the compatibility as well as the advantages of the MPEG-4 standard regarding to Flash technology, a well-known tool for making games over the Internet.

Measuring myocardial deformations in tagged MR image sequences using informational non-rigid registration

Abstract: We address the problem of quantifying myocardial deformations from tagged MRI sequences. We develop a two-step method comprising (i) a motion estimation step using a novel variational non rigid registration technique based on generalized information measures, and (ii) a measurement step, yielding local and segmental deformation parameters over the whole myocardium. Experiments performed on healthy and pathological data originating from various imaging devices demonstrate that this method delivers, within a reasonable computation time and in a robust and fully unsupervised way, reliable measurements for normal subjects and provide quantitative pathology-specific information.

Measuring myocardial deformations from MR data using information-theoretic nonrigid registration

Abstract: Magnetic resonance imaging (MRI) is recognized as a relevant modality for dynamically imaging the heart anatomy and function, and achieving satisfying qualitative diagnosis. Reliable methods for quantitatively analyzing cardiac MR images remain, however, to be elaborated. This paper presents a novel approach for measuring myocardial and wall motion from MRI sequences. Based on efficient voxel-based statistical nonrigid registration (NRR), it allows for automatically extracting local/global deformation parameters at the voxel, myocardial segment and whole myocardium scales. Its performances for assessing the myocardial contractile function are illustrated both for the normal heart and for dilated cardiomyopathies (DCM).

Descripteurs de forme pour l'indexation de maillages 3D

Abstract: Cet article traite de l'indexation d'objets 3D mailles a l'aide de descripteurs de forme (DF), sous contraintes d'invariance geometrique et de robustesse topologique. Le spectre de forme 3D (SF3D), propose par les auteurs et retenu comme DF dans MPEG-7, est tout d'abord introduit. Intrinsequement invariant aux transformations geometriques, le SF3D n'est pas robuste vis-a-vis des representations topologiques multiples. C'est pourquoi un nouveau DF (DH3D), intrinsequement stable topologiquement, est propose. Derive de la transformee de Hough 3D, le DH3D n'est pas invariant aux transformees geometriques. Nous montrons mathematiquement comment il peut etre associe de facon optimale en termes de compacite de representation et de complexite de calcul a une procedure d'alignement spatial lui conferant alors un comportement d'invariance geometrique. Cela conduit a definir le DH3D optimal (DH3DO). Apres avoir specifie les mesures de similarite utilisees lors des applications de requete et avoir decrit la base de 1300 modeles utilisee, les deux DF sont evalues et compares objectivement en termes de score Bull-Eye, ce critere etablissant une nette superiorite du DH3DO.