Noninvasive brain imaging techniques including structural MRI, diffusion MRI (DMRI), perfusion MRI, functional MRI (FMRI), EEG, MEG, PET, SPECT, and CT are playing increasingly important roles in elucidating structural and functional properties in normal and diseased brains. It is widely believed that these different imaging modalities provide distinctive yet complementary information that is conducive to the understanding of the working dynamics of the brain. Effective processing, fusion, analysis, and visualization of images from multiple sources, however, pose as new challenging problems due to variations in imaging resolutions, spatial-temporal dynamics, as well as the fundamental biophysical mechanisms that are involved in determining the character of the images.
The objective of this MICCAI workshop is to move forward the state of the art in multimodal brain image analysis, in terms of analysis methodologies, algorithms, software systems, validation approaches, benchmark datasets, neuroscience, and clinical applications. MBIA is a forum for researchers to exchange ideas, data, and software, in order to speed up the development of innovative technologies for hypothesis testing and data-driven discovery in brain science.
Topics include but are not limited to:
- Multimodal brain data fusion methodologies – fusion of DMRI and FMRI data, fusion of FMRI and EEG data, and fusion of MRI and PET data.
- Methods for modeling temporal brain dynamics – modeling brain states via FMRI and/or EEG data.
- Structural and functional brain network construction methods – identification and optimization of network nodes, assessment of network properties, and creation of graph models for description of structural and functional brain networks.
- Brain connectivity analysis methods – joint modeling of structural and functional brain connectivity, relationship between structural and functional connectivity, and dynamics of connectivity.
- Multimodal brain image pattern classification methods – classification of brain diseases via multimodal features, feature extraction and dimension reduction using multimodal images, and multimodal image predictors of clinical measures.
- Multimodal brain image visualization and data management methods – visual analytics of multimodal image data and visualization of large-volume, dynamical multimodal image data.
- Registration, segmentation, shape analysis, and signal processing methods – multimodal image registration, multi-parametric image segmentation, and multi-resolution signal processing.
- Validation approaches and benchmark data generation – cross-validation via multiple image modalities and generation of benchmark data via reproducibility studies.
- Clinical applications – computer aided diagnosis and follow-up of brain diseases via multimodal images, early diagnosis of brain diseases via multimodal images, and differential diagnosis of brain diseases via multimodal images.
Accepted papers are published as a volume in the Springer LNCS.
Best Paper Award
A “Best Paper Award” (inclusive of a USD500 cash award, sponsored by the UNC IDEA Group) will be given at the end of the workshop. The winner will be chosen by the organizers based on relevance, novelty, and scientific contribution.
Congratulations to Suyash Awate, Peihong Zhu, and Ross Whitaker, from the University of Utah, whose work “How Many Templates Does it Take for a Good Segmentation? – Error Analysis in Multiatlas Segmentation as a Function of Database Size” won the MBIA 2012 Best Paper Award!