Learning Task-Optimal Registration Cost Functions for Localizing Cytoarchitecture and Function in the Cerebral Cortex
Year: 2010
Type: article
Abstract: Image registration is typically formulated as an optimization problem with multiple tunable, manually set parameters. We present a principled framework for learning thousands of parameters of registration cost functions, such as a spatially-varying tradeoff between the image dissimilarity and regularization terms. Our approach belongs to the classic machine learning framework of model selection by optimization of cross-validation error. This second layer of optimization of cross-validation error over and above registration selects parameters in the registration cost function that result in good registration as measured by the performance of the specific application in a training data set. Much research effort has been devoted to developing generic registration algorithms, which are then specialized to particular imaging modalities, particular imaging targets and particular postregistration analyses. Our framework allows for a systematic adaptation of generic registration cost functions to specific applications by learning the "free" parameters in the cost functions. Here, we consider the application of localizing underlying cytoarchitecture and functional regions in the cerebral cortex by alignment of cortical folding. Most previous work assumes that perfectly registering the macro-anatomy also perfectly aligns the underlying cortical function even though macro-anatomy does not completely predict brain function. In contrast, we learn 1) optimal weights on different cortical folds or 2) optimal cortical folding template in the generic weighted sum of squared differences dissimilarity measure for the localization task. We demonstrate state-of-the-art localization results in both histological and functional magnetic resonance imaging data sets.
Institutions: MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Harvard University, Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, Mauna Kea Technologies (France), Forschungszentrum Jülich, RWTH Aachen University, Heinrich Heine University Düsseldorf
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Morphometry Biomedical Informatics Research Network, G349067127, Computational Modeling of Anatomical Shape Distributions, High Resol. Imaging and Modeling of Human Visual Cortex, Inferring in Vivo Cytoarchitectural Borders in the Medial Temporal Lobe, National Alliance for Medical Image Computing (NAMIC), The VETSA Longitudinal MRI Twin Study of Aging, Center for Functional Imaging Technologies, Neuroimaging Analysis Center, Automated Analysis of Healthy and Diseased Brain Tissue, G7203195112, Tools for Analyzing Cortical Structure and Connectivity, Multivariate Pattern Analysis Methods for Neuroimaging Genetics Studies
OpenAlex ID: W2138339175
