François Chung, Ph.D.

Tag: 3dah

LAP 2011 - Book

LAP 2011 – Book

|

Publication

François Chung; Regional appearance modeling for model-based image segmentation: Methodological approaches to improve the accuracy of model-based image segmentation; Lambert Academic Publishing (LAP), Saarbrücken, 2011; ISBN: 978-3844322095.

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. Comparative results on liver profiles from Computed Tomography (CT) images show that MPAM outperforms PCA-based appearance models. Finally, methods for the analysis of lower limb structures from Magnetic Resonance (MR) images are presented. A first part deals with the creation of subject-specific models for kinematic simulations of the lower limbs. In a second part, the performance of statistical models is compared in the context of lower limb bone segmentation when only a small number of datasets is available for training.

References

Publication

Book (Amazon)
Book (MoreBooks)
Bibliographic reference (BibTeX)

Related articles

3D Anatomical Human (INRIA project)
Ph.D. Thesis 2011 (doctoral thesis)

Learn more

LAP – Lambert Academic Publishing

TVC 2011 - Academic journal

TVC 2011 – Academic journal article

|

Publication

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.

Keywords

  • clustering
  • model-based segmentation
  • principal component analysis
  • statistical models

References

Publication

Published version (Springer)
Published version (HAL)
Preprint version (PDF)
Bibliographic reference (BibTeX)

Related articles

3D Anatomical Human (INRIA project)
Ph.D. Thesis 2011 (doctoral thesis)

Ph.D. Thesis 2011 - Doctoral thesis

Ph.D. Thesis 2011 – Doctoral thesis

|

Publication

François Chung; Regional appearance modeling for deformable model-based image segmentation; Doctoral thesis (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.

Keywords

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

References

Publication

Published version (PDF)
Presentation (PDF)
Bibliographic reference (BibTeX)
Hard copy (Amazon)
Hard copy (MoreBooks)

Related articles

3D Anatomical Human (INRIA project)
CVIU 2013 (academic journal article)
LAP 2011 (book)

Learn more

PASTEL
Mines ParisTech

3D Anatomical Human

3D Anatomical Human

|

INRIA project @Geneva, Switzerland (2010). The 3D Anatomical Human (3DAH) project is a EU Marie Curie Research and Training Network (RTN). The objective is to increase the development of technologies and knowledge around virtual representations of the human body for interactive medical applications. More specifically, the network aims at developing realistic functional 3D models of the musculoskeletal system, the methodology being demonstrated on the lower limb.

The main areas of research are:

  • motor control analysis: simulation of the lower limb;
  • computer graphics: efficient simulation of humans;
  • biomechanics: accurate tissue characterization and mechanical simulation;
  • image processing: modelling of organs from images;
  • orthopaedics: resolution of particular pathological problems.

Partners of this project include:

  • 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).

In this project, my work consists in segmenting anatomical structures of the lower limb (e.g. muscles, bones and ligaments) from static and dynamic Magnetic Resonance (MR) images. Because of the variability of these structures, the segmentation is performed by combining non-rigid image registration with segmentation based on deformable models.

References

Related articles

TVC 2011 (academic journal article)
CBM 2009 (conference proceeding)
MICCAI 2009 (conference proceeding)

Learn more

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

CBM 2009 - Conference

CBM 2009 – Conference proceeding

|

Publication

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.

Keywords

  • knee
  • ligament
  • real-time
  • simulation

References

Publication

Published version (Springer)
Preprint version (PDF)
Bibliographic reference (BibTeX)

Related article

3D Anatomical Human (INRIA project)

Languages

Recent articles

Categories

News

Recent news & Popular news

Search