François Chung, Ph.D.

Tag: doctoral thesis

CVIU 2013 - Academic journal

CVIU 2013 – Academic journal article

Publication

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.

Keywords

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

References

Publication

Related articles

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

Mines 2018 – Magazine

Mines 2012 – Magazine article

Publication

François Chung; De l'imagerie médicale à la médecine du futur; Mines Revue des Ingénieurs, 458, pp. 53-56, 2012.

Abstract

Depuis ses débuts, l'imagerie médicale a pour objectif de fournir aux radiologues des images médicales afin de les aider dans leur diagnostic. Avec l'avancée des techniques d'acquisition, les radiologues se retrouvent à analyser des images de plus en plus complexes et dans des quantités de plus en plus importantes. Du côté de la recherche, cela se traduit par une collaboration entre physique médicale, radiologie et imagerie médicale. Les physiciens ont pour objectif d'améliorer la qualité et la résolution des images médicales. Ces améliorations permettent d'aider les radiologues dans leur diagnostic et à la communauté de l'imagerie médicale de pouvoir extraire des informations plus précises. Cette collaboration permet non seulement d'avancer dans les sciences médicales (ex. étude de l'anatomie et physiologie), mais également dans les applications cliniques (ex. détection de maladies et planification de thérapie).

References

Publication

Published version (PDF)
Bibliographic reference (BibTeX)
Online version (Ingénieurs Belges)

L'Ing. 2012 - Magazine

L’Ing. 2012 – Magazine article

Publication

François Chung; L'imagerie médicale: Un domaine d'ingénieurie et de recherche au service de la société; L'Ing., 17, pp. 10-12, 2012.

Abstract

Depuis ses débuts, l'imagerie médicale a pour objectif de fournir aux radiologues des images médicales afin de les aider dans leur diagnostic. Avec l'avancée des techniques d'acquisition, les radiologues se retrouvent à analyser des images de plus en plus complexes et dans des quantités de plus en plus importantes. Du côté de la recherche, cela se traduit par une collaboration entre physique médicale, radiologie et imagerie médicale. Les physiciens ont pour objectif d'améliorer la qualité et la résolution des images médicales. Ces améliorations permettent d'aider les radiologues dans leur diagnostic et à la communauté de l'imagerie médicale de pouvoir extraire des informations plus précises. Cette collaboration permet non seulement d'avancer dans les sciences médicales (ex. étude de l'anatomie et physiologie), mais également dans les applications cliniques (ex. détection de maladies et planification de thérapie).

References

Publication

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

Related articles

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