2nd International MICCAI Workshop on Spatiotemporal Image Analysis for Longitudinal and Time-Series Image Data (STIA'12)
Monday October 1st, 2012, Nice Acropolis, Room Gallieni 4
Lecture Notes in Computer Science
Volume 7570, 2012, DOI: 10.1007/978-3-642-33555-6
The STIA'12 organizers are excited to announce two distinguished guest speakers who will discuss spatio-temporal imaging based on its underlying fundamental mathematical problems and its central and vital role in biological imaging, respectively.
Alain Trouvé, ENS de Cachan, France, professeur à l'ENS de Cachan, et Directeur du département de Mathématiques
Alexandre Dufour, UNITÉ D'ANALYSE D'IMAGES QUANTITATIVES INSTITUT PASTEUR, Bioimage Analysis Team (http://www.bioimageanalysis.org/) lead by Jean-Christoph Olivo Marin
Rationale:This workshop aims to be the follow-up of the first international workshop on Spatiotemporal Image Analysis (STIA'10) for Longitudinal and Time-Series Image Data held in conjunction with MICCAI 2010 in Beijing. The previous STIA'10 workshop was a success with 58 full paying attendees in the advanced registrations, 8 podium speakers and 8 poster presentations selected from a total of about 25 submitted papers. Papers were sent from a large variety of institutions from all geographic regions.
The obviously increasing interest of the MICCAI community in a methodology-oriented workshop on longitudinal image data analysis supports, in our view, the organization of a second workshop on the same topic. There seems a clear need for information exchange and brainstorming with respect to this new and rapidly evolving image analysis subdiscipline. Such a workshop focusing more on theoretical and methodological aspects rather than application-driven research would also complement and augment previous workshops dedicated to very specific applications such as "early brain development". A large numbers of papers have been published in the main journals and conference proceedings over the last two years (for instance, last MICCAI meeting in 2011 had a session dedicated to this topic). The organization of such a workshop on a regular basis would help to establish the MICCAI meetings as a key forum to discuss novel theoretical and methodological advances, to foster collaborations among the specialists in the field, and to provide profound education and information about the state-of-the-art to researchers novel to this topic.
Target Audience:There is a rapidly growing interest in the analysis of time-series data. Recent examples are the very successful MICCAI 2008, 2009 and 2011 workshops on image analysis of the early developing brain, where a modeling of brain growth and brain maturation were key topics but with the main focus on a very specific application domain. Our objective is to move beyond such a specific application domain with the proposed workshop by focusing on common underlying methodologies to analyze time-series data. The increased focus on personalized medicine or subject-specific analysis includes processing of time-series data such as pre-/post-therapy or modeling of lesion evolution via parameterized models. Clinical studies of aging, e.g., include series of follow-up scans to stage and model the effect of aging and to determine the onset of accelerated degeneration. Rapidly evolving advanced imaging technology can routinely measure volumetric data in short time intervals, creating 4D datasets that require new, efficient processing, visualization, and quantitative analysis techniques.
The target audience will therefore be researchers interested in or already involved in research and development of methods for studying growth or change patterns in longitudinal and time-series image data. This workshop aims at contributing to a fundamental understanding of data, processing methodology and statistical concepts but also to a review and discussion of existing methods, procedures and problem solutions. We expect to create discussions between researchers, developers and potential users in order to inform about existing technology, image databases for testing and comparison, and to lay the ground for future research.
Sponsorship:We are thankful to ICM (Hôpital Pitié Salpêtrière, Brain and Spine Institute, Paris www.icm-institute.org) and SCI (Scientific Computing and Imaging Institute, Utah (www.sci.utah.edu) for sponsoring this workshop.The NA-MIC consortium (www.na-mic.org) funded by NIH is acknowledged for providing scientific and engineering support.
Scientific FocusClinical imaging increasingly makes use of longitudinal image studies to examine subject-specific changes due to pathology, intervention, therapy, neurodevelopment, or neurodegeneration. Moreover, dynamic organ changes as seen in cardiac imaging or functional changes as measured in perfusion imaging, just to name a few, by definition result in time-series image data presenting volumetric image data over time. Expressions such as development, degeneration, disease progress, recovery, monitoring or heart cycle inherently carry the aspect of a dynamic process – suggesting that imaging at multiple time points may be applied. The detection and characterization of changes from baseline due to disease, trauma, or treatment require novel image processing and visualization tools for qualitative and quantitative assessment of change trajectories. Whereas longitudinal analysis of scalar data is well known in the statistics community, its extension to high-dimensional image data, shapes or functional changes poses significant challenges. Cross-sectional analysis of longitudinal data does not provide a model of growth or change that considers the inherent correlation of repeated images of individuals, nor does it tell us how an individual patient changes relative to a change over time of a comparable healthy or disease-specific population, an aspect which is highly relevant to decision making and therapy planning. Although successful early results were presented for image regression in aging studies, such standard regression is not optimal for longitudinal data because repeated observations from the same individual would ignore the correlation between repeated measurements and thus violate the Gauss-Markov assumption of independence. Moreover, individual change trajectories often need to be interpreted in relationship to a population growth model, which in turn is the hidden group model given a representative set of individual trajectories, and require a common framework based on the use of hierarchical linear (or nonlinear) models (HLM). Other typical driving applications are concerned with registration of serial data of the cardiac cycle, sampled at different time points, or measuring object shape changes via shape regression, both requiring new image registration and modeling approaches.
The special nature of longitudinal or repeated, time-series data of individual subjects, with the inherent correlation of structure and function across the sequence of images, resulted in the development of a variety of new image processing and analysis approaches tackling the challenging issues of registration, segmentation and analysis in the presence of geometric and contrast changes over time. New methodologies are rapidly evolving, often focusing on the specific application at hand.
This workshop will cover a comprehensive discussion of multiple approaches and new advances for spatio-temporal image processing of longitudinal image data but also aims at a dialogue to define the generic nature of algorithms, methods, modeling approaches, and statistical analysis for optimal analysis of such data. This in turn will lead to a discussion on solutions achieved so far, summary of the state-of-the-art and open issues to be tackled in future research.
The primary focus of this workshop will be on the generic nature of algorithms, methods, modeling approaches and statistical analysis. We are specifically looking for papers that introduce novel and innovative methodology for spatiotemporal analysis of images, with methods driven by challenging applications. We will invite paper submissions related to the following topics:
List of topics:
- Regression of sequences of time-series image data
- Modeling of shape changes due to development, degeneration, pathology, or evolution
- Modeling of growth and change trajectories, predictive modeling of "disease"
- Modeling of space occupying and infiltration patterns as seen in tumor staging
- Physiological modeling of pathology evolution to extract model parameters characterizing
- Joint segmentation of time-series image data
- Joint registration of time-series data
- Group discrimination via multi-dimensional longitudinal statistical data analysis
Paper submissions on novel methodology development for spatiotemporal analysis might be driven by typical challenging applications as listed below.
Novel image analysis approaches driven by:
- Analysis of heart shape across heart cycle
- Study of early brain growth trajectory
- Study of healthy aging and/or aging in disease
- Study of perfusion changes in time-series image data
- Monitoring of therapeutic intervention (baseline and multiple follow-up measures)
- Staging of disease, e.g., MS lesion and brain atrophy evolution or tumor growth
|8:40-9:00||Workshop opening||G. Gerig, T. Fletcher, S. Durrleman, M. Niethammer|
|9:00-9:50||Plenary talk||Alain Trouvé, ENS de Cachan, France|
|Longitudinal Registration and Transport:|
|9:50-10:10||Spatio-temporal regularization for longitudinal registration to an unbiased 3D individual template||Nicolas Guizard, Vladimir Fonov, Daniel Garca-Lorenzo, Brengre Aubert-Broche, Simon Eskilden, D. Louis Collins|
|10:10-10:30||Local versus global descriptors of hippocampus shape evolution for Alzheimers longitudinal population analysis||Jean-Baptiste Fiot, Laurent Risser, Laurent Cohen, Jurgen Fripp, Franois-Xavier Vialard|
|Spatio-temporal Analysis of Shapes:|
|11:00-11:20||Mixed-Effects Shape Models for Estimating Longitudinal Changes in Anatomy||Manasi Datar, Prasanna Muralidharan, Abhishek Kumar, Sylvain Gouttard, Joseph Piven, Guido Gerig, Ross Whitaker, P. Thomas Fletcher|
|11:20-11:40||Unsupervised Learning of Shape Complexity: Application to Brain Development||Ahmed Serag, Ioannis Gousias, Antonios Makropoulos, Paul Aljabar, Joseph Hajnal, James Boardman, Serena Counsell, Daniel Rueckert|
|Spatio-temporal Analysis under Appearance Changes:|
|11:40-12:00||Spatial-temporal pharmacokinetic model based registration of 4D brain PET data||Jieqing Jiao, Graham Searle, Andri Tziortzi, Cristian Salinas, Roger Gunn, Julia Schnabel|
|12:00-12:20||Predicting the Location of Glioma Recurrence After a Resection Surgery||Erin Stretton, Emmanuel Mandonnet, Ezequiel Geremia, Bjoern H. Menze, Herve Delingette, Nicholas Ayache|
|14:30-15:30||Plenary talk||Alexandre Dufour, UNITÉ D'ANALYSE D'IMAGES QUANTITATIVES INSTITUT PASTEUR, Bioimage Analysis Team, Paris, France|
|Spatio-temporal Imaging for Biology:|
|16:00-16:20||Motion-Based Segmentation for Cardiomyocyte Characterization||Xiaofeng Liu, Dirk Padfield|
|16:20-16:40||Multi-temporal Globally-Optimal Dense 3-D Cell Segmentation & Tracking from Multi-photon Time-lapse Movies of Live Tissue Microenvironments||Arunachalam Narayanaswamy, Amine Merouane, Antonio Peixoto, Ena Ladi, Paul Herzmark, Ulrich von Andrian, Ellen Robey, Badrinath Roysam|
|16:40-17:30||Discussions and Conclusion|
|Elastic Demons: Characterizing Cortical Development in Neonates Using an Implicit Surface Registration||Paul Pearlman, Ivana Isgum, Karina Kersbergen, Manon Benders, Max Viergever, Josien Pluim|
|Which reorientation framework for the atlas-based comparison of cardiac image sequences?||Nicolas Duchateau, Mathieu De Craene, Xavier Pennec, Beatriz Merino, Marta Sitges, Bart Bijnens|
|A new framework for analyzing structural volume changes of longitudinal brain MRI data||Berengere Aubert-Broche, Vladimir Fonov, Daniel Garcia Lorenzo, Abderazzak Mouiha, Nicolas Guizard, Pierrick Coupe, Simon Eskildsen, D. Louis Collins|
|4D Segmentation of Longitudinal Brain MR Images with Consistent Cortical Thickness Measurement||Li Wang, Feng Shi, Gang Li, Dinggang Shen|
|Tracking Metastic Brain Tumors In Longitudinal Scans via Joint Image Registration and Labeling||Nicha Chitphakdithai, Veronica Chiang, James Duncan|
- Guido Gerig, University of Utah (gerig*at*sci.utah.edu)
- Stanley Durrleman, INRIA (stanley.durrleman*at*inria.fr)
- Thomas Fletcher, University of Utah (fletcher*at*sci.utah.edu)
- Marc Niethammer, University of North Carolina at Chapel Hill (mn*at*cs.unc.edu)
- Paul Aljabar, Imperial College
- Stephanie Allassonniere, Ecole Polytechnique, Palaisau, France
- D. Louis Collins, MNI, Montreal
- Roman Filipovych, University of Pennsylvania, USA
- Jan Ehrhardt, Universitaet zu Luebeck, Germany
- Jim Gee, University of Pennsylvania, USA
- Julien Lefebre, Universitee de la Mediterranee, Marseille, France
- Jan Modersitzki, McMaster University, Canada
- Sebastien Ourselin, Imperial College London, UK
- Kilian Pohl, University of Pennsylvania, USA
- Marcel Prastawa, University of Utah, USA
- Anqi Qiu, National Univerity of Singapore, Singapore
- Daniel Rueckert, Imperial College London, UK
- Laurent Risser, CNRS Toulouse, France
- Maurico Reyes, Universitaet Bern, Switzerland
- Dinggang Shen, University of North Carolina at Chapel Hill, USA
- Julia Schnabel, Oxford University, UK
- Martin Styner, University of North Carolina at Chapel Hill, USA
- Fedde van der Lijn, Erasmus MC, NL
- Koen Van Leemput, Aalto University, Finland
- Carl-Fredrik Westin, Harvard University, USA
- Prasanna Muralidharan, University of Utah, USA
- Sandy Wells, Harvard University, USA
- Simon Warfield, Harvard University, USA
- Hongtu Zhu, University of North Carolina at Chapel Hill, USA