inria – François Chung, Ph.D.

Tag: inria

CVIU 2013 – Artículo de revista científica

Mis publicaciones

François Chung | junio 2013

Publicación

François Chung, Hervé Delingette; Regional appearance modeling based on the clustering of intensity profiles; In: Computer Vision and Image Understanding (CVIU), 117 (6), pp. 705-717, 2013.

Abstract

Model-based image segmentation is a popular approach for the segmentation of anatomical structures from medical images because it includes prior knowledge about the shape and appearance of structures of interest. This paper focuses on the formulation of a novel appearance prior that can cope with large variability between subjects, for instance due to the presence of pathologies. Instead of relying on Principal Component Analysis (PCA) such as in Statistical Appearance Models (SAMs), our approach relies on a multimodal intensity profile atlas from which a point may be assigned to several profile modes consisting of a mean profile and its covariance matrix. These profile modes are first estimated without any intra-subject registration through a boosted Expectation-Maximization (EM) classification based on spectral clustering. Then, they are projected on a reference mesh whose role is to store the appearance information in a common geometric representation. We show that this prior leads to better performance than the classical monomodal PCA approach while relying on fewer profile modes.

Palabras clave

appearance modeling
medical imaging
model-based image segmentation
unsupervised clustering

Referencias

Publicación

Versión publicada (ScienceDirect)
Versión pre-print (PDF)
Referencia bibliográfica (BibTeX)

TVC 2011 – Artículo de revista científica

Mis publicaciones

François Chung | febrero 2011

Publicación

François Chung, Jérôme Schmid, Nadia Magnenat-Thalmann, Hervé Delingette; Comparison of statistical models performance in case of segmentation using a small amount of training datasets; In: The Visual Computer (TVC), 27 (2), pp. 141-151, 2011.

Abstract

Model-based image segmentation has been extensively used in medical imaging to learn both shape and appearance of anatomical structures from training datasets. The more training datasets are used, the more accurate is the segmented model as we account for more information about its variability. However, training datasets of large size with a proper sampling of the population may not always be available. In this paper, we compare the performance of statistical models in the context of lower limb bones segmentation using Magnetic Resonance (MR) images when only a small number of datasets is available for training. For shape, both priors based on Principal Component Analysis (PCA) and shape memory strategies are tested. For appearance, methods based on intensity profiles are tested, namely mean intensity profiles, multivariate Gaussian distributions of profiles and multimodal profiles from Expectation-Maximization (EM) clustering. Segmentation results show that local and simple methods perform the best when a small number of datasets is available for training. Conversely, statistical methods feature the best segmentation results when the number of training datasets is increased.

Palabras clave

clustering
model-based segmentation
principal component analysis
statistical models

Referencias

Publicación

Versión publicada (Springer)
Versión publicada (HAL)
Versión pre-print (PDF)
Referencia bibliográfica (BibTeX)

Ph.D. Thesis 2011 – Tesis doctoral

Mis publicaciones

François Chung | enero 2011

Publicación

François Chung; Regional appearance modeling for deformable model-based image segmentation; Tesis doctoral (Ph.D. Thesis), Mines ParisTech, Centre de Mathématiques Appliquées, 2011.

Abstract

This thesis presents a novel appearance prior for model-based image segmentation. This appearance prior, denoted as Multimodal Prior Appearance Model (MPAM), is built upon an Expectation-Maximization (EM) clustering of intensity profiles with model order selection to automatically select the number of profile classes. Unlike classical approaches based on Principal Component Analysis (PCA), the clustering is considered as regional because intensity profiles are classified for each mesh and not for each vertex.

First, we explain how to build a MPAM from a training set of meshes and images. The clustering of intensity profiles and the determination of the number of appearance regions by a novel model order selection criterion are explained. A spatial regularization approach to spatially smooth the clustering of profiles is presented and the projection of the appearance information from each dataset on a reference mesh is described.

Second, we present a boosted clustering based on spectral clustering, which optimizes the clustering of profiles for segmentation purposes. The representation of the similarity between data points in the spectral space is explained. Comparative results on liver profiles from Computed Tomography (CT) images show that our approach outperforms PCA-based appearance models.

Finally, we present methods for the analysis of lower limb structures from Magnetic Resonance (MR) images. In a first part, our technique to create subject-specific models for kinematic simulations of lower limbs is described. In a second part, the performance of statistical models is compared in the context of lower limb bones segmentation when only a small number of datasets is available for training.

Palabras clave

appearance modeling
liver
lower limbs
medical imaging
model-based image segmentation
unsupervised clustering

Referencias

Proyecto INRIA @Ginebra, Suiza (2010). El proyecto 3D Anatomical Human (3DAH) es una red europea de investigación de tipo Marie Curie. El objetivo del proyecto es incrementar el desarrollo de tecnologías y de conocimiento en torno a las representaciones virtuales del cuerpo humano para aplicaciones médicas interactivas. Más específicamente, la red tiene como objetivo desarrollar modelos 3D realistas y funcionales del sistema músculo-esquelético.

Las principales áreas de investigación son:

análisis del control motor: simulación del miembro inferior;
computación gráfica: simulación eficaz de los humanos;
biomecánica: caracterización tisular precisa y simulación mecánica;
procesamiento de imágenes: modelado de órganos a partir de imágenes;
ortopedia: resolución de determinados problemas patológicos.

Los socios de este proyecto son:

AAU - Aalborg Universitet (DK);
CRS4 - Centro di Ricerca, Sviluppo e Studi Superiori in Sardegna (IT);
EPFL - École Polytechnique Fédérale de Lausanne (CH);
INRIA Sophia-Antipolis - Institut National de Recherche en Informatique et en Automatique (FR);
UNIGE - Université de Genève (CH);
UCL - University College London (UK);
VUB - Vrije Universiteit Brussel (BE).

En este proyecto, mi trabajo consiste en segmentar las estructuras anatómicas del miembro inferior (p. ej. músculos, huesos y ligamentos) a partir de imágenes por resonancia magnética (IRM) estáticas y dinámicas. Debido a la variabilidad de estas estructuras, la segmentación se lleva a cabo mediante la combinación de un registro no rígido de la imagen con una segmentación basada en modelos deformables.

Referencias

Más información

3DAH – 3D Anatomical Human
INRIA Sophia-Antipolis – Institut National de Recherche en Informatique et en Automatique

CBM 2009 – Acta de conferencia

Mis publicaciones

François Chung | septiembre 2009

Publicación

Tobias Heimann, François Chung, Hans Lamecker, Hervé Delingette; Subject-specific ligament models: Towards real-time simulation of the knee joint; CBM 2009: Computational Biomechanics for Medicine IV, London, 2009.

Abstract

We present an efficient finite element method to simulate a transversely isotropic non-linear material for ligaments. The approach relies on tetrahedral elements and exploits the geometry to optimize computation of the derivatives of the strain energy. To better support incompressibilty, deviatoric and dilational responses are uncoupled and a penalty term controls volume preservation. We derive stress and elasticity tensors required for implicit solvers and verify our model against the FEBio software using a variety of load scenarios with synthetic shapes. The maximum node positioning error for ligament materials is < 5% for strains under physiological conditions. To generate subject-specific ligament models, we propose a novel technique to estimate fiber orientation from segmented ligament geometry. The approach is based on an automatic centerline extraction and generation of the corresponding diffusion field. We present results for a medial collateral ligament segmented from standard Magnetic Resonance Imaging (MRI) data. Results show the general viability of the method, but also the limitations of current MRI acquisitions. In the future, we hope to employ the presented techniques for real-time simulation of knee surgery.

Palabras clave

knee
ligament
real-time
simulation

Referencias

Publicación

Versión publicada (Springer)
Versión pre-print (PDF)
Referencia bibliográfica (BibTeX)

Artículo relacionado

3D Anatomical Human (proyecto INRIA)

François Chung, Ph.D.

Tag: inria

CVIU 2013 – Artículo de revista científica

Publicación

Artículos relacionados

TVC 2011 – Artículo de revista científica

Publicación

Artículos relacionados

Ph.D. Thesis 2011 – Tesis doctoral

Publicación

Artículos relacionados

Más información

3D Anatomical Human

Artículos relacionados

Más información

CBM 2009 – Acta de conferencia

Publicación

Artículo relacionado

Idiomas

Artículos recientes

Categorías

Noticias

Búsqueda