François Chung, Ph.D.

Tag: lower limb

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

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

Related articles

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

Learn more

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

ORASIS 2009 - Conference

ORASIS 2009 – Conference proceeding

Publication

François Chung, Jérôme Schmid, Olivier Clatz, Nadia Magnenat-Thalmann, Hervé Delingette; Reconstruction 3D des structures anatomiques des membres inférieurs; ORASIS'09: Congrès des jeunes chercheurs en vision par ordinateur, Association Française pour la Reconnaissance et l'Interprétation des Formes (AFRIF), Trégastel, 2009.

Abstract

Dans cet article, nous nous intéressons à la modélisation des structures anatomiques des membres inférieurs telles que les os, les muscles et les tendons. La méthode proposée commence par une acquisition d'images par résonance magnétique (IRM) durant laquelle les membres inférieurs d'un sujet sont scannés. Des modèles 3D sont ensuite générés après une segmentation manuelle des structures anatomiques. Cependant, la surface des modèles générés n'est pas lisse. De plus, les modèles ne sont pas attachés alors qu'ils devraient l'être anatomiquement. Nous décrivons donc les différentes étapes pour contraindre les modèles à être corrects au niveau anatomique et nous discutons de leur validation. L'objectif de cette méthode est de pouvoir réutiliser ces modèles dans des méthodes de segmentation automatique.

Keywords

  • IRM
  • segmentation
  • modélisation 3D
  • membres inférieurs

References

Publication

Related articles

3D reconstruction (INRIA project)
3D Anatomical Human (INRIA project)

Learn more

ORASIS’09
AFRIF – Association Française pour la Reconnaissance et l’Interprétation des Formes

3D reconstruction

3D reconstruction

INRIA project @Geneva, Switzerland (2009). We are interested in the 3D reconstruction of the lower limb anatomical structures. The proposed method starts with a Magnetic Resonance (MR) image acquisition during which the lower limb of a subject is scanned. 3D models are generated after a manual segmentation of the anatomical structures. However, the surface of the models appears not to be smooth and the models are not attached whereas they should be anatomically.

Various consecutive steps are needed to constrain the models to be correct at the anatomical level. The aim of our method is to reuse these models with automatic segmentation methods.

This work is a collaboration between:

  • INRIA Sophia-Antipolis - Institut National de Recherche en Informatique et en Automatique (FR);
  • UNIGE - Université de Genève (CH).

Our modeling approach allowed us to generate most of the anatomical structures of the lower limb, such as bones, muscles and tendons. We were able to create a total of 109 models including the bones, muscles, tendons and skin. Regarding the bones, we modeled 6 in total. More specifically, the hip, femur, patella, tibia, fibula and foot bone. Finally, we modeled 34 muscles in total. For each muscle, we modeled a pair of tendons (proximal and distal) whose role is to attach muscles to bones. The generated models were evaluated and validated by a medical expert.

References

Related articles

ORASIS 2009 (conference proceeding)
3D Anatomical Human (INRIA project)

Learn more

INRIA Sophia-Antipolis – Institut National de Recherche en Informatique et en Automatique