Oops! It seems that you are using an outdated version of Internet Explorer!

This website (and the rest of the internet as well) works best in the latest browsers. Websites look better, do load faster and browsing the web is less unsafe. Please upgrade your Internet Explorer or install an alternative browser.

Browser selection
  • Join us in Delémont where shape models are in focus !





    Newsletter

    twitter    facebook

Invited Speakers

 

Martin Styner

University of North Carolina

Associate Professor,
Co-Director of Neuro Image Research and Analysis Laboratories (NIRAL)


Talk : Structural Shape Analysis via the NA-MIC Shape Toolkit

Structural shape analysis has become an important tool for local quantification of shape differences between groups of subjects, shape changes across time or for the discrimination of patient groups. This presentation will focus on methods available within the NA-MIC shape toolkit that encompasses object-specific spherical harmonic descriptions, derived medial descriptions, and group-based particle descriptions. Extensions for longitudinal data and complex surface data are presented as well.
 

Tobias Heimann

Siemens AG, Corporate Technology

Research Scientist, Imaging and Computer Vision


Talk : Statistical Shape Models from A to Z

This talk gives an overview of the different components required for a fully automated 3D segmentation pipeline based on statistical shape models (SSMs) and machine learning. Starting from the construction of mesh-based statistical shape models, over initialization and appearance modeling, up to the local adaptation strategy, different approaches are presented and discussed. The focus is on practical applicability of all techniques and should enable newcomers to get a good starting point for a first SSM pipeline, as well as give more experienced participants ideas for further optimizations and refinements.
 

Guido Gerig

University of Utah

Professor. School of Computing, University of Utah, USA


Talk : Spatio-Temporal Shape Modeling and Analysis

Rapid advances in image acquisition and shape capturing technology provide continuous or time-discrete 3D volumetric images and/or surfaces, motivated by the notion that dynamic spatiotemporal changes may provide information not available from snapshots in time. Capturing properties of time-varying 3D objects requires novel methods to make use of the inherent correlation and causality of repeated measurements. This talk will discuss development of advanced 4D analysis methodologies that carry the notion of linear and nonlinear regression, now applied to complex, high-dimensional data such as image-derived shapes and structures. We will address concepts for regression of 4D shapes from time-discrete data, enforcing temporal smoothness, and will discuss work in progress towards statistical analysis of 4D shape trajectories. Comparison of shape change trajectories will also include the notion of time warp for accommodating variations in time-change functions. The proposed methodology is based on the framework of “currents” and thus overcomes limitations of common point-to-point correspondence. Our research is driven by challenging medical image analysis problems, where clinical assessment routinely uses terms such as development, growth trajectory, aging, degeneration, disease progress, recovery or prediction. This terminology inherently carries the aspect of dynamic processes, suggesting that snapshots in time and cross-sectional analysis in populations are not sufficient. We will show examples from ongoing clinical studies such as analysis of early brain growth in healthy and at-risk subjects, of modeling neurodegeneration, and of modelling bone shape developments after surgery.
 

Cristian Lorenz

Philips Research

Principal Scientist at Philips Technologie GmbH, Hamburg.


Talk : Deformable shape models – Aspects and applications in medical image analysis

Deformable shape model based methods serve meanwhile as a standard approach for medical image analysis problems. Strength and challenges of the approach are discussed in the context of a variety of medical imaging modalities and respective applications. Robust and efficient solutions can be realized by combining implicit and explicit modeling, tailoring the general approach to meet the requirements of a specific application.
 

Yoshinobu Sato

Nara Institute of Science and Technology, Japan

Associate Professor.

Talk : Computational anatomy modelling of abdominal organs and musculoskeletal structures

In human anatomy, multiple structures are interrelated and hierarchically organized. We present computational anatomy modelling approaches which incorporate these interrelations and hierarchization to perform automated segmentation and identification of patient-specific anatomy of abdominal organs and musculoskeletal structures from 3D data. Further, the approaches are extended so as to address automated surgical planning and diagnostic assistance.
 

Xavier Pennec

INRIA Sophia Antipolis

Senior Research Scientist (Directeur de Recherche), INRIA, Asclepios team


Talk : Geometric Structures for Statistics on Shapes and Deformations in Computational Anatomy

Computational anatomy is an emerging discipline at the interface of geometry, statistics, image analysis and medicine that aims at analysing and modelling the biological variability of the organs shapes at the population level. The goal is to model the mean anatomy and its normal variation among a population and to discover morphological differences between normal and pathological populations. For instance, the analysis of population-wise structural brain changes with aging in Alzheimer's disease requires first the analysis of longitudinal morphological changes for a specific subject. This can be evaluated through the non-rigid registration. Second, To perform a longitudinal group-wise analysis, the subject-specific longitudinal trajectories need to be transported in a common reference (using some parallel transport). To reach this goal, one needs to design a consistent statistical framework on manifolds and Lie groups. The geometric structure considered so far was that of metric and more specially Riemannian geometry. Roughly speaking, the main steps are to redefine the mean as the minimizer of an intrinsic quantity: the Riemannian squared distance to the data points. When the Fréchet mean is determined, one can pull back the distribution on the tangent space at the mean to define higher order moments like the covariance matrix. In the context of medical shape analysis, the powerful framework of Riemannian (right) invariant metric on groups of diffeomorphisms (aka LDDMM) has often been investigated for such analyses in computational anatomy. In parallel, efficient image registration methods and discrete parallel transport methods based on diffeomorphisms parameterized by stationary velocity fields (SVF) (DARTEL, log-demons, Schild's ladder etc) have been developed with a great success from the practical point of view but with less theoretical support. In this talk, I will detail the Riemannian framework for geometric statistics and partially extend if to affine connection spaces and more particularly to Lie groups provided with the canonical Cartan-Schouten connection (a non-metric connection). In finite dimension, this provides strong theoretical bases for the use of one-parameter subgroups. The generalization to infinite dimensions would grounds the SVF-framework. From the practical point of view, we show that it leads to quite simple and very efficient models of atrophy of the brain in Alzheimer's disease.

Program chairs and organizers

Pictures of the Event

We have uploaded the pictures we took during the event. They are hosted on Lirdy.com which is an easy way to unite all photos from all participants in one album. Feel free to contribute your pics!

See all pictures

Awards

Three awards will be delivered during the event, subject to a vote from the Symposium participants :

  • The best oral presentation award with an amount of 300 CHF will be sponsored by   research

    This award was won by Sandro Schönborn from the University of Basel for his presentation on : Robust Image Analysis by Fitting a 3d Morphable Face Model for Portrait Manipulation

  • The best poster award with an amount of 300 CHF will be sponsored by   research

    This award was won by Max Hermann from the University of Bonn for the poster on : Anatomic Segmentation of Statistical Shape Models

  • The winner of the Shape 2014 Grand Challenge award with an amount of 300 CHF will be sponsored by   Corporate Technology

    This award was equally won by two contenders Thomas Gerig from the University of Basel and Guoyan Zheng from the University of Bern

Grand Challenge in Statistical Shape Modeling

As part of the Shape Symposium we are hosting the first Grand Challenge in Statistical Shape Modeling. The task is to build a model of the liver from a set of segmented training datasets provided as courtesy of www.visceral.eu .

Training datasets and more information about the challenge can be found on the challenge webpage.

Shape 2014 - Grand Challenge

Program

Wednesday

12:30 - 12:45

Opening of the Symposium

12:45 - 13:45

Keynote : Tobias Heimann

Statistical Shape Models from A to Z

This talk gives an overview of the different components required for a fully automated 3D segmentation pipeline based on statistical shape models (SSMs) and machine learning. Starting from the construction of mesh-based statistical shape models, over initialization and appearance modeling, up to the local adaptation strategy, different approaches are presented and discussed. The focus is on practical applicability of all techniques and should enable newcomers to get a good starting point for a first SSM pipeline, as well as give more experienced participants ideas for further optimizations and refinements.

13:45 - 15:00

Podium Presentation Session 1

Selected oral presentations:

  • Construction of Statistical Shape Models Using a Probabilistic Point-based Shape Representation (J. Keustermans, D. Vandermeulen, W. Mollemans, F. Schutyser, P. Suetens)

  • Robust Image Analysis by Fitting a 3d Morphable Face Model for Portrait Manipulation (S. Schönborn, A. Forster, B. Egger, A. Schneider. T. Vetter)

  • Relative Statistical Performance of S-reps with Principal Nested Spheres vs. PDMs (S. Pizer, J. Hong, S. Jung, J. Marron, J. Schulz, J. Vicor)

  • Consistent Dense Correspondences from Pair-Wise Non-Rigid Registration (T. Gass, G. Szekely, O. Goksel)

  • A Bilinear Model for Temporally Coherent Respiratory Motion (F. Preiswerk, P. Cattin)

15:30 - 16:30

Keynote : Guido Gerig

Spatio-Temporal Shape Modeling and Analysis

Rapid advances in image acquisition and shape capturing technology provide continuous or time-discrete 3D volumetric images and/or surfaces, motivated by the notion that dynamic spatiotemporal changes may provide information not available from snapshots in time. Capturing properties of time-varying 3D objects requires novel methods to make use of the inherent correlation and causality of repeated measurements. This talk will discuss development of advanced 4D analysis methodologies that carry the notion of linear and nonlinear regression, now applied to complex, high-dimensional data such as image-derived shapes and structures. We will address concepts for regression of 4D shapes from time-discrete data, enforcing temporal smoothness, and will discuss work in progress towards statistical analysis of 4D shape trajectories. Comparison of shape change trajectories will also include the notion of time warp for accommodating variations in time-change functions. The proposed methodology is based on the framework of “currents” and thus overcomes limitations of common point-to-point correspondence. Our research is driven by challenging medical image analysis problems, where clinical assessment routinely uses terms such as development, growth trajectory, aging, degeneration, disease progress, recovery or prediction. This terminology inherently carries the aspect of dynamic processes, suggesting that snapshots in time and cross-sectional analysis in populations are not sufficient. We will show examples from ongoing clinical studies such as analysis of early brain growth in healthy and at-risk subjects, of modeling neurodegeneration, and of modelling bone shape developments after surgery.

16:30 - 18:15

Shape Challenge

Methods & Results presentations

Networking Apero
Thursday

09:00 - 10:00

Panel Discussion

Leading representatives from different MedTech companies and academia will discuss current and future industrial uses of statistical shape modelling as well as the diverse scientific challenges needed to bring statistical shape modelling into focus for the development of future healthcare technologies.

10:30 - 11:45

Podium Presentation Session 2

Selected oral presentations :

  • 3D-Regression Voting on CT-Volumes of the Human Liver for SSM Surface Appearance Modeling (T. Norajitra, H.P. Meinzer, K. Maier-Hein)

  • Geodesically Damped Shape Models (C. Jud, T. Vetter)

  • Towards a Practical Clinical Workflow for Cardiac Shape Modeling, with Application to Atrial Fibrillation and Stroke (J. Cates, A. Morris, E. Bieging, E. Kholmovski, S. Bengali, R. MacLeod, C. McGann)

  • Detection of Ribs in MR Images (G. Samei, C. Tanner, G. Szekely)

  • Automatic extraction of hand-bone shapes using Random Forest regression-voting in the Constrained Local Model framework (C. Lindner, T. Cootes)

11:45 - 12:45

Keynote : Yoshinobu Sato

Computational anatomy modelling of abdominal organs and musculoskeletal structures

In human anatomy, multiple structures are interrelated and hierarchically organized. We present computational anatomy modelling approaches which incorporate these interrelations and hierarchization to perform automated segmentation and identification of patient-specific anatomy of abdominal organs and musculoskeletal structures from 3D data. Further, the approaches are extended so as to address automated surgical planning and diagnostic assistance.

Lunch

13:30 - 14:30

Poster Teasers

Each poster presenter will shortly introduce his work to all of the audience.

14:30 - 16:00

Poster Session

Poster discussion with authors and coffee

16:00 - 17:00

Keynote : Christian Lorenz

Deformable shape models – Aspects and applications in medical image analysis

Deformable shape model based methods serve meanwhile as a standard approach for medical image analysis problems. Strength and challenges of the approach are discussed in the context of a variety of medical imaging modalities and respective applications. Robust and efficient solutions can be realized by combining implicit and explicit modeling, tailoring the general approach to meet the requirements of a specific application.

Sicas introduction
Social Event, until 23:00
Friday

09:00 - 10:00

Keynote : Martin Styner

Structural Shape Analysis via the NA-MIC Shape Toolkit

Structural shape analysis has become an important tool for local quantification of shape differences between groups of subjects, shape changes across time or for the discrimination of patient groups. This presentation will focus on methods available within the NA-MIC shape toolkit that encompasses object-specific spherical harmonic descriptions, derived medial descriptions, and group-based particle descriptions. Extensions for longitudinal data and complex surface data are presented as well.

10:30 - 11:30

Keynote : Xavier Pennec

Geometric Structures for Statistics on Shapes and Deformations in Computational Anatomy

Computational anatomy is an emerging discipline at the interface of geometry, statistics, image analysis and medicine that aims at analysing and modelling the biological variability of the organs shapes at the population level. The goal is to model the mean anatomy and its normal variation among a population and to discover morphological differences between normal and pathological populations. For instance, the analysis of population-wise structural brain changes with aging in Alzheimer's disease requires first the analysis of longitudinal morphological changes for a specific subject. This can be evaluated through the non-rigid registration. Second, To perform a longitudinal group-wise analysis, the subject-specific longitudinal trajectories need to be transported in a common reference (using some parallel transport). To reach this goal, one needs to design a consistent statistical framework on manifolds and Lie groups. The geometric structure considered so far was that of metric and more specially Riemannian geometry. Roughly speaking, the main steps are to redefine the mean as the minimizer of an intrinsic quantity: the Riemannian squared distance to the data points. When the Fréchet mean is determined, one can pull back the distribution on the tangent space at the mean to define higher order moments like the covariance matrix. In the context of medical shape analysis, the powerful framework of Riemannian (right) invariant metric on groups of diffeomorphisms (aka LDDMM) has often been investigated for such analyses in computational anatomy. In parallel, efficient image registration methods and discrete parallel transport methods based on diffeomorphisms parameterized by stationary velocity fields (SVF) (DARTEL, log-demons, Schild's ladder etc) have been developed with a great success from the practical point of view but with less theoretical support. In this talk, I will detail the Riemannian framework for geometric statistics and partially extend if to affine connection spaces and more particularly to Lie groups provided with the canonical Cartan-Schouten connection (a non-metric connection). In finite dimension, this provides strong theoretical bases for the use of one-parameter subgroups. The generalization to infinite dimensions would grounds the SVF-framework. From the practical point of view, we show that it leads to quite simple and very efficient models of atrophy of the brain in Alzheimer's disease.

Awards and Closing
Lunch

12:45 - 13:45

Tutorial : Marcel Lüthi

Tutorial on statistical shape modeling software Statismo

Statismo is an open source framework for statistical shape modeling. It provides functionality for all shape modeling tasks, from model-building to shape analysis. This tutorial will introduce the basic principles behind statismo and shows on concrete examples how it can be used in practical applications. In a first part, we will introduce the basic philosophy and design principles of statismo. The second part shows with concrete code examples of how statismo can be used for building shape models and model fitting. In the last part we show how the concept of Gaussian process models in statismo can be used to formulate shape priors that are far more powerful than standard PCA models.

13:45 - 14:45

Tutorial : Martin Styner

The NA-MIC Shape Analysis toolkit

This tutorial will cover the major tools in the NA-MIC Shape Analysis toolkit and how they are used to perform statistical shape analysis. The tutorial of the toolkit will include shape parametrization, SPHARM-PDM and medial axis computation, as well as computation and interpretation of the statistical analysis for both SPHARM PDM and the medial axis/thickness results.

Venue Delémont, Switzerland

The congress venue is located 40 km from Basel in Delémont/Switzerland, the capital of the canton of Jura.

A shuttle bus will take visitors from the train station in Delémont to the conference venue.
Taxis and public buses are available (Bus 11 or 18, stop Zard).
More information


MedTech Lab
Place des Sciences 1
2822 Courroux, Switzerland

phone: +41 32 422 58 20
contact@si-cas.com
si-cas.com