MFCA is a MICCAI
workshop devoted to statistical and geometrical methods for modeling the variability of biological shapes. The goal is to foster the interactions between the mathematical community around shapes and the MICCAI community around computational anatomy applications. The workshop aims at being a forum for the exchange of the theoretical ideas and a source of inspiration for new methodological developments in computational anatomy.
- First MFCA workshop, held in Copenhagen (Denmark) in October 2006,
- Second MFCA workshop, held in New-York (USA) in September 2008,
- Third MFCA workshop, held in Toronto (CA) on September 22, 2011,
- Forth MFCA workshop, held in Nagoya (JP) on September 22, 2013,
the fifth MFCA workshop
will be held in Munich, Germany, Friday October 9th, 2015, in conjunction with MICCAI 2015
The goal of computational anatomy is to analyze and to statistically model the anatomy of organs in
different subjects. Computational anatomic methods are generally based on the
extraction of anatomical features or manifolds which are then statistically
analyzed, often through a non-linear registration. There are nowadays a growing
number of methods that can faithfully deal with the underlying biomechanical
behavior of intra-subject deformations. However, it is more difficult to relate
the anatomies of different subjects. In the absence of any justified physical
model, diffeomorphisms provide the most general mathematical framework that
enforce topological consistency. However, working with this infinite dimensional
space raises some deep computational and mathematical problems, in particular
for doing statistics. Likewise, modeling the variability of surfaces leads to
rely on shape spaces that are much more complex than for curves. To cope with
these, different methodological and computational frameworks have been proposed
(e.g. smooth left-invariant metrics, focus on well-behaved subspaces of
diffeomorphisms, modeling surfaces using currents, etc.) The goal of the
workshop is to foster interactions between researchers investigating the
combination of geometry and statistics in non-linear image and surface
registration in the context of computational anatomy from different points of
view. A special emphasis will be put on theoretical developments, applications
and results being welcomed as illustrations.
Workshop format and topics
The program will be composed of oral presentations selected by the peer-reviewed contributions of the participants. To foster interactions, a large amount of time will be reserved for discussions after each presentation. Contributions are solicited in (but not limited to) the areas of:
- Riemannian sub-Riemannian and group theoretical methods
- Statistical models for manifold-valued data, including surfaces, deformations and shapes
- Metrics for computational anatomy
- Statistics of surfaces
- Time-evolving geometric processes
- Stratified spaces
- Optimal transport in registration problems
- Approximation methods in statistical learning (e.g. variational Bayes, importance sampling, Monte Carlo methods)
- Paper Submission: June 8, 2015 (11:59 PM Pacific time)
- Notification of Acceptance: July 17, 2015
- Camera Ready Paper Submission: August 10th, 2015
- Workshop: Friday October 9th, 2015.
Authors are invited to submit papers of about 10 to 12 pages in the LNCS format on the MFCA'15 CMT submission portal https://cmt.research.microsoft.com/MFCA2015
before the submission deadline. The file format for submissions is Adobe Portable Document Format (PDF). Other formats will not be accepted. Please create an account on your first login on the CMT system.
Papers accepted at the MICCAI conference cannot be submitted. Notice that the workshop submission deadline will be after the MICCAI decision. Double submissions are NOT allowed with any other MICCAI workshop. If you hesitate between several workshops, please contact the workshop chairs beforehand.
Program and Proceedings
Proceedings are available here.
The proceedings of the workshop will be available as a collection of open archive papers
, along with the proceedings of the previous editions.
Selected publications will be invited for a special issue of SIAM Journal on Imaging Sciences (SIIMS)
08:30 - 10:30 - Session 1 : diffeomorphisms and matching of densities and shape
- 08:30 - 08:40: Welcome announcements. Workshop chairs.
- 08:40 - 09:15 (Long) Weighted Diffeomorphic Density Matching with Applications to Thoracic Image Registration. Caleb Rottman*, Martin Bauer, Klas Modin, Sarang Joshi.
- 09:15 - 09:35 (Short) Stochastic EPDiff Landmark Dynamics. Tomasz Tyranowski*, Darryl Holm.
- 09:35 - 10:10 (Long) Reconstructing Karcher Means of Shapes on a Riemannian Manifold of Metrics and Curvatures. Boris Gutman*, Tom Fletcher, Greg Fleishman, Paul Thompson.
- 10:10 - 10:30 (Short) Adaptive time-stepping in diffeomorphic image registration with bounded inverse consistency error. Akshay Pai*, Stefan Klein, Stefan Sommer, Sune Darkner, Jon Sporring, Mads Nielsen.
10:30 - 11:00 - Coffe break
11:00 - 12:30 - Session 2 : Longitudinal and multivariate analysis on manifolds
12:30 - 13:30 - Lunch
13:30 - 15:35 - Session 3 : Matching the shape of curves and signals
- 13:30 - 14:05 (Long) Curve Matching with Applications in Medical Imaging. Martin Bauer*, Martins Bruveris, Philipp Harms, Jakob Møller-Andersen.
- 14:05 - 14:40 (Long) Covariant un-reduction for curve matching. Alexis Arnaudon*, Marco Castrillon-Lopez, Darryl Holm.
- 14:40 - 15:15 (Long) Kernel Metrics on Normal Cycles and Application to Curve Matching. Pierre Roussillon*, Joan Alexis Glaunès.
- 15:15 - 15:35 (Short) Efficient Metamorphosis Computation for Classifying Embryonic Cardiac Action Potentials. Giann Gorospe*, Renjun Zhu, Jia-Qiang He, Leslie Tung, Rene Vidal, Laurent Younes.
15:35 - 16:00 - Coffe break
16:00 - 17:30 - Session 3 : Fréchet mean on manifolds and quotient spaces
- 16:00 - 16:35 (Long) Estimating the Template in the Total Space with the Fréchet Mean on Quotient Spaces may have a Bias: a Case Study on Vector Spaces Quotiented by the Group of Translations. Loïc Devilliers*, Stéphanie Allassonnière, Xavier Pennec.
- 16:35 - 17:10 (Long) An efficient recursive estimator of the Fréchet mean on hypersphere with applications to Medical Image Analysis. Hesamoddin Salehian, Rudrasis Chakraborty*, Edward Ofori, David Vaillancourt, Baba Vemuri.
- 17:10 - 17:30 (Short) An efficient recursive algorithm for atlas construction. Rudrasis Chakraborty*, Monami Banerjee, Dohyung Seo, Sara Turner, David Fuller, John Forder, Baba Vemuri.
Follow the instructions at the official Miccai 2015
website to register for this workshop.
- Stéphanie Allassonière (Ecole Polytechnique, FR)
- Rachid Deriche (INRIA, FR)
- Ian Dryden(U. of Nottingham, UK)
- Aasa Feragen (U. of Copenhagen, DK)
- Luc Florac(Eindhoven U. of Technology, NL)
- James Gee (University of Pennsylvania, USA)
- Guido Gerig (SCI, U. of Utah, USA)
- Polina Golland (MIT, USA)
- Darryl Holm (Imperial College London, UK)
- Susan Holmes (Stanford U., USA)
- Steve Marron (UNC Chapel Hill, USA)
- Stephen Marsland (Massey U., NZ)
- Yoshitaka Masutani (U. of Tokyo Hosp, JP)
- Michael Miller (Johns Hopkins U., USA)
- Marc Niethammer (UNC Chapel Hill, USA)
- Salvador Olmos (U. of Saragossa, SP)
- Jerry Prince (Johns Hopkins U., USA)
- Anand Rangarajan (U. of Florida, USA)
- Daniel Rueckert (Imperial Coll. London, UK)
- Kaleem Siddiqi (McGill U., CA)
- Martin Styner (UNC Chapel Hill, USA)
- Hemant D Tagare (Yale University, USA)
- Paul Thompson (U. Southern California, USA)
- Alain Trouvé (ENS Cachan, FR)
- Carole Twining (U. of Manchester, UK)
- Baba Vemuri (U. of Florida, USA)
- Francois Xavier Vialard (Dauphine U., FR)
- Rene Vidal (Johns Hopkins U., USA)
- Laurent Younes (Johns Hopkins U., USA)
- William M. Wells III (MIT & Harvard, USA)