- 20.07.2018: We extended the deadline for abstract submissions to 27th July!
- 12.06.2018: Our 2nd Keynote Speaker will be Prof. Dimitri Van de Ville talking about graph signal processing for human brain imaging.
- 06.06.2018: Deadline for complete papers is extended until 18th June!
- 21.05.2018: CMT System is open for submissions of both, complete and abstract papers! Click here to submit your manuscript
- 21.05.2018: PC Members are online! (More TBA)
- 09.04.2018: This year we will accept papers in two modalities: Complete papers (8-10 pages) and Abstract papers (2-3 pages). Read more about it in the section "Submit a paper"
- 09.04.2018: GRAIL accepted papers will be invited to submit an extended version to a Special Issue on Graphs in Biomedical Image Analysis that we will organize in a top-tier journal of the area.
- 09.04.2018: The GRAIL Best Paper Award will include a cash price sponsored by EntelAI !
- 30.03.2018: The GRAIL Website is up and running!
GRAIL 2018 is the second international workshop on GRaphs in biomedicAl Image anaLysis, organised as a satellite event of MICCAI 20178 in Granada, Spain.
Graph-based models have been developed for a wide variety of problems in computer vision and biomedical image analysis. Applications ranging from segmentation, registration, classification, and shape modelling, to population analysis have been successfully encoded through graph structures, demonstrating the versatile and principled nature of the graph based approaches.
Graphs are powerful mathematical structures which provide a flexible and scalable framework to model objects and their interactions in a readily interpretable fashion. As a consequence, an important body of work has been developed around different methodological aspects of graph including, but not limited to, graphical models, graph-theoretical algorithms, spectral graph analysis, graph dimensionality reduction, and graph-based network analysis. However, new topics are also emerging as the outcome of interdisciplinary studies, shedding light on areas like deep structured models and signal processing on graphs.
With this workshop we aim to highlight the potential of using graph-based models for biomedical image analysis. Our goal is to bring together scientists that use and develop graph-based models for the analysis of biomedical images and encourage the exploration of graph-based models for difficult clinical problems within a variety of biomedical imaging contexts.
The covered topics include but are not limited to:
- Probabilistic graphical models for biomedical image analysis
- Discrete and continuous optimization for graphical models
- Signal processing on graphs for biomedical image analysis
- Deep/machine learning on structured and unstructured graphs
- Convolutional neural networks on graphs
- Graphs for large scale population analysis
- Graph-based shape modeling and dimensionality reduction
- Combining imaging and non-imaging data through graph structures
- Graph-based generative models for biomedical image analysis
- Graph spectral methods
- Algorithms on graphs
- Graphs in neuroimaging
- Applications of graph-based models and algorithms to biomedical image analysis tasks (segmentation, registration, classification, etc.)
Prof. Michael Bronstein
University of Lugano / Tel Aviv University / Intel Perceptual Computing
Deep Learning on Graphs
Bio : Michael Bronstein is a full professor of Informatics at USI Lugano in Switzerland, associate professor of Applied Mathematics at Tel Aviv University in Israel, and a Principal Engineer at the Intel Perceptual Computing group. He got his Ph.D. with distinction in Computer Science from the Technion in 2007. He holds or has previously held visiting appointments at Politecnico di Milano, Stanford, Harvard, and MIT. His research appeared in the international media such as CNN and was recognized by numerous prestigious awards, including several best paper awards, the Hershel Rich Innovation Award (2003), three ERC grants (Starting Grant 2012, Proof of Concept Grant 2016, and Consolidator Grant 2016), two Google Faculty Research Awards (2015, 2017), Radcliffe Fellowship from the Institute for Advanced Study at Harvard University (2017), and Rudolf Diesel Industrial Fellowship from TU Munich (2017). Michael is the author of the first book on deformable 3D shape analysis, editor of four books, more than 150 papers in top scientific journals and conferences, and inventor of 25 granted patents. He has chaired more than a dozen of conferences and workshops in his field, and has served as area chair at ECCV 2016 and ICCV 2017 and as associate editor of four top journals is his field (IJCV, SIAM J. Imaging Sciences, CVIU and IJVC). He has given over 100 invited and keynote talks during his career.
During the last years, Michel has published several works about deep learning on graphs, contributing to the development of this incipient research area.
Prof. Dimitri Van De Ville
EPFL / University of Geneva
Graph Signal Processing Opens New Perspectives for Human Brain Imaging
Abstract: State-of-the-art magnetic resonance imaging (MRI) provides unprecedented opportunities to study brain structure (anatomy) and function (physiology). Based on such data, graph representations can be built where nodes are associated to brain regions and edge weights to strengths of structural or functional connections. In particular, structural graphs capture major neural pathways in white matter, while functional graphs map out statistical interdependencies between pairs of regional activity traces. Network analysis of these graphs has revealed emergent system-level properties of brain structure or function, such as efficiency of communication and modular organization. In this talk, graph signal processing (GSP) will be presented as a novel framework to integrate brain structure, contained in the structural graph, with brain function, characterized by activity traces that can be considered as time-dependent graph signals. Such a perspective allows to define novel meaningful graph-filtering operations of brain activity that take into account the anatomical backbone. For instance, we will show how activity can be analyzed in terms of being aligned versus liberal with respect to brain structure, or how additional prior information about cognitive systems can be incorporated. The well-known Fourier phase randomization method to generate surrogate data can also be adapted to this new setting. Finally, recent work will highlight how the spatial resolution of this type of analyses can be increased to the voxel level, representing a few ten thousands of nodes.
Bio: Dimitri Van De Ville (Senior Member, IEEE) received the M.S. degree in engineering and computer sciences and the Ph.D. degree from Ghent University, Ghent, Belgium, in 1998, and 2002, respectively. After a postdoctoral stay (2002-2005) at the lab of Prof. M. Unser at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland, he became responsible for the Signal Processing Unit at the University Hospital of Geneva, Geneva, Switzerland, as part of the Centre d'Imagerie Biomédicale (CIBM). In 2009, he received a Swiss National Science Foundation professorship and since 2015 became Professor of Bioengineering at the EPFL and the University of Geneva, Geneva, Switzerland. His research interests include wavelets, sparsity, graphs, pattern recognition, and their applications in computational neuroimaging.
Dr. Van De Ville served as an Associate Editor for the IEEE Transactions on Image Processing from 2006 to 2009 and the IEEE Signal Processing Letters from 2004 to 2006, as well as Guest Editor for several special issues. He was the Chair of the Bio Imaging and Signal Processing (BISP) Technical Committee of the IEEE Signal Processing Society (2012-2013) and is the Founding Chair of the EURASIP Biomedical Image & Signal Analytics SAT. He is Co-Chair of the biennial Wavelets & Sparsity series conferences, together with V. Goyal, Y. Lu, and M. Papadakis. He was a recipient of the Pfizer Research Award 2012, the NARSAD Independent Investigator Award 2014, and the Leenaards Foundation Award 2016.
Submissions should be done through the GRAIL CMT portal. The submission system will open on May 20th.
This year we will accept papers in 2 formats:
- Complete papers: Papers describing original research with length of 8-10 pages. These papers are eligible for the "Best Paper Award" and will be published in the GRAIL Open Proceedings and Lecture Notes in Computer Sciences (LNCS) series. Submissions should be anonymous, and formatted following the LNCS Style. All complete papers will be peer-reviewed by 3 members of the program committee, with double-blinded review process. The selection of the papers will be based on significance of results, technical merit, relevance and clarity of presentation.
- Abstracts: In order to encourage interesting discussions within the community, this year we are also inviting papers describing on-going, recently published or original research in a short paper of 2-3 pages. Depending on the number of submissions, we will organize a poster or oral session during GRAIL, where accepted short papers will be invited to present. The selection of the short abstracts will be made by members of the program committee and/or organizers. Submissions should be anonymous, and formatted following the LNCS Style.
The authors of the best paper of the workshop will receive a cash price (sponsored by EntelAI).
Accepted papers will be invited to submit an extended version to a Special Issue on Graphs in Biomedical Image Analysis in a top-tier journal of the area, that we will organize after the event.
|20 May 2018||Submission system opens.|
|Complete Paper submission deadline.|
|10 July 2018||Reviews due.|
|Notification of acceptance.|
|20 July 2018||Camera-ready papers (Complete papers).|
|Abstract Paper submission deadline.|
|3rd August 2018||Notification of acceptance for Abstract Paper submission.|