PresentationsFOCUSR: Fast Mesh Matching
FOCUSR is novel method for dense vertex-to-vertex correspondence between two surface meshes. This fast, accurate, and general method is applied on a broad variaty of meshes as well as in a clinical application.
November 2011, Ecole de Technologie Superieure, Montreal
Variability of the Human Cardiac Laminar Structure
The cardiac fibers are thought to be organized as laminar sheets. The diffusion tensor provides evidence of such secondary structure in humans, and its variability is studied along 17 myocardial segments of the left ventricle on 10 ex-vivo human hearts.
September 2011, Westin Harbour Conference Center, Toronto
Statistical Atlases and Computation Models of the Heart, MICCAI Worskhop
Statistical Atlases and Computation Models of the Heart, MICCAI Worskhop
FOCUSR: Fast Mesh Matching with Spectral Correspondence
Cortex matching is important in neuroimaging studies. We propose an approach based on spectral correspondence, where spectra of graphs derived from surface meshes are matched.
July 2011, CVPR group, Technische Universitat Munchen (TUM)
Brain Matching with Spectral Correspondence
Cortex matching is important in neuroimaging studies. We propose an approach based on spectral correspondence, where spectra of graphs derived from surface meshes are matched.
June 2011, Asclepios Team, INRIA Sophia-Antipolis
Statistical Analysis of the Human Cardiac Fiber Architecture from DT-MRI
The statistical atlas of the cardiac fiber architecture is build for the first time in Humans. The variability of the fiber architecture is studied in 10 ex-vivo human hearts.
May 2011, New York University
Functional Imaging and Modeling of the Heart
Best Student Paper Award
Functional Imaging and Modeling of the Heart
Best Student Paper Award
Human Statistical Atlas of Cardiac Fiber Architecture from DT-MRI
The statistical atlas of the cardiac fiber architecture is build for the first time in Humans. The construction of the atlas is automatic and the results provides the variability of the fiber architecture for 10 ex-vivo human hearts.
May 2011, Palais des Congres, Montreal
Int'l Society for Magnetic Resonance in Medicine
Int'l Society for Magnetic Resonance in Medicine
Landmark-based Non-rigid Registration via Graph Cuts
Graph cuts can be used to find an optimum deformation field between two images. The use of landmarks allows user interaction, leading the optimization to favor personalized solution, and to remove ambiguities.
August 2007, Polytechnique
Int'l Conf. Image Analysis and Recognition
Int'l Conf. Image Analysis and Recognition
Registration of ICE ultrasound with DynaCT, and 4D volume compounding.
In the first part, Samuel presented a ICE/CT registration framework. In the second part, using the ICE sequence, the reconstruction of a 4D volume is shown.
November 2006, Polytechnique
with Samuel Kadoury (LIV4D, Polytechnique)
with Samuel Kadoury (LIV4D, Polytechnique)
Registration using graph cut energy minimization
The graph cut method can be used to minimize an energy. This presentation shows how this can be used with image registration.
October 2006, Siemens Corporate Research
Localisation d'instruments médicaux en IRM utilisant leur signature magnétique
Introducing an original idea for localization of ferromagnetic objects in MR imaging.
April 2006, Polytechnique
with Arnaud Chanu (nanorobotic lab, Polytechnique)
with Arnaud Chanu (nanorobotic lab, Polytechnique)
Level sets: Introduction, implantation et exemples de segmentation
Basics of the level set method, from its motion equation to its implementation with applications to segmentation.
April 2006, University of Montreal
Graph cuts: Introduction et quelques méthodes de segmentation
Basics of the graph cut algorithm and explanation of 3 related algorithms: graph cuts based active contour, lazy snapping, and multi level banded graph cuts.
March 2006, University of Montreal
Recalage par maximisation de l'information mutuelle
Explanation and comparison of different voxel similarity measures such as cross-correlation, mutual information, and mutual information with gradient information.
December 2005, Polytechnique
with Jeremie Theriault
with Jeremie Theriault
Segmentation de structures cardiaques à l'aide de graphcuts
How the graph cut algorithm can efficiently be used to segment cardiac structures.
October 2005, Polytechnique
seminar of GRMSV
seminar of GRMSV
Segmentation à l'aide de graphcuts
Overview of the graph cut algorithm and showing some results in cardiac segmentation.
September 2005, Polytechnique