Analysis of Functional Medical Images

Data driven methods such as independent component analysis (ICA) have proven quite effective for the analysis of fMRI data and for discovering associations between fMRI and other medical imaging data types. Without imposing strong modeling assumptions, these methods efficiently take advantage of the multivariate nature of the fMRI data and are particularly attractive for use in cognitive paradigms where detailed a priori models of brain activity are not available. In this talk, we review three data-driven methods that have been successfully applied to fMRI: principal component analysis, ICA, and canonical correlation analysis. In particular, we discuss different algorithms that can be used to achieve ICA, their mutual relationships, their advantages and disadvantages as well as recent results in complex-valued ICA and its promise for the analysis of fMRI data in its native complex form. We provide examples of the application of all three data-driven approaches to fMRI data analysis and the fusion of fMRI data with other medical data types, such as EEG and structural MRI data. Biography: TÜLAY ADALI received the Ph.D. degree in electrical engineering from North Carolina State University, Raleigh, in 1992 and joined the faculty at the University of Maryland Baltimore County (UMBC), Baltimore, the same year. She is currently a Professor in the Department of Computer Science and Electrical Engineering at UMBC. She has held visiting positions at Technical University of Denmark, Lyngby, Denmark, Katholieke Universiteit, Leuven, Belgium, University of Campinas, Brazil, and École Supérieure de Physique et de Chimie Industrielles, Paris, France. Prof. Adali assisted in the organization of a number of international conferences and workshops including the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), the IEEE International Workshop on Neural Networks for Signal Processing (NNSP), and the IEEE International Workshop on Machine Learning for Signal Processing (MLSP). She was the General Co-Chair, NNSP (2001-2003); Technical Chair, MLSP (2004-2006); Publicity Chair, ICASSP (2000 and 2005); and Publications Co-Chair, ICASSP 2008. She is currently the Technical Chair, 2008 MLSP and Program Co-Chair, 2008 Workshop on Cognitive Information Processing and 2009 ICA Conference. Prof. Adali chaired the IEEE SPS Machine Learning for Signal Processing Technical Committee (2003-2005); Member, SPS Conference Board (1998-2006); Member, Bio Imaging and Signal Processing Technical Committee (2004-2007); and Associate Editor, IEEE Transactions on Signal Processing (2003-2006). She is currently a Member, Machine Learning for Signal Processing Technical Committee and an Associate Editor, IEEE Transactions on Biomedical Engineering, Signal Processing Journal, Research Letters in Signal Processing, and Journal of Signal Processing Systems for Signal, Image, and Video Technology. Prof. Adali is a Fellow of the AIMBE. Her research interests are in the areas of statistical signal processing, machine learning for signal processing, biomedical data analysis (functional MRI, MRI, PET, CR, ECG, and EEG), bioinformatics, and signal processing for optical communications. She is the recipient of a 1997 National Science Foundation (NSF) CAREER Award with more recent support from the National Institutes of Health, NSF, NASA, the US Army, and industry. The multiple comparison problem in fMRI a new method based on anatomical priors G. Lohmann, J. Neumann, K. Müller, J. Lepsien, R. Turner Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany Abstract. The multiple comparison problem arises in the statistical analysis of functional magnetic resonance images (fMRI) because independent statistical The multiple comparison problem arises in the statistical analysis of functional magnetic resonance images (fMRI) because independent statistical tests are performed at each voxel of an image. As there are typically many thousands of voxels in an image a standard significance threshold of p < 0.05 would lead to many false positive classifications. Several methods for multiple comparison correction have been proposed in the past but they all ignore anatomical information resulting in a bias against small anatomical structures. Here, we propose a new approach based on Monte Carlo simulations that explicitly incorporates anatomical priors, namely hemispheric symmetry. Applications to fMRI data show that this method is indeed more sensitive to small activations provided they are bilateral.