Journal Article

PreJuSER-10476

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Learning Task-Optimal Registration Cost Functions for Localizing Cytoarchitecture and Function in the Cerebral Cortex

Yeo, B. T. T. ; Sabuncu, M. R. ; Vercauteren, T. ; Holt, D. J. ; Amunts, K.FZJ* ; Zilles, K.FZJ* ; Golland, P. ; Fischl, B.

2010
Institute of Electrical and Electronics Engineers, New York, NY

This record in other databases:      

Please use a persistent id in citations: doi:10.1109/TMI.2010.2049497

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.

Keyword(s): Algorithms (MeSH) ; Brain: physiology (MeSH) ; Brain Mapping: methods (MeSH) ; Cerebral Cortex: physiology (MeSH) ; Humans (MeSH) ; Image Enhancement: methods (MeSH) ; Image Interpretation, Computer-Assisted: methods (MeSH) ; Information Storage and Retrieval: methods (MeSH) ; Magnetic Resonance Imaging: methods (MeSH) ; Pattern Recognition, Automated: methods (MeSH) ; Reproducibility of Results (MeSH) ; Sensitivity and Specificity (MeSH) ; J ; Cross validation error (auto) ; functional magnetic resonance imaging (fMRI) (auto) ; histology (auto) ; ill-posed (auto) ; leave one out error (auto) ; local maxima (auto) ; local minima (auto) ; model selection (auto) ; objective function (auto) ; parameter tuning (auto) ; registration parameters (auto) ; regularization (auto) ; space of local optima (auto) ; tradeoff (auto)

Note: Manuscript received October 24, 2009; revised April 21, 2010; accepted April 22, 2010. Date of publication June 07, 2010; date of current version June 30, 2010. This work was supported in part by the NAMIC (NIH NIBIB NAMIC U54-EB005149), in part by the NAC (NIH NCRR NAC P41-RR13218), in part by the mBIRN (NIH NCRR mBIRN U24-RR021382), in part by the NIH NINDS R01-NS051826 Grant, in part by the NSF CAREER 0642971 Grant, in part by the National Institute on Aging (AG02238), in part by the NCRR (P41-RR14075, R01 RR16594-01A1), in part by the NIBIB (R01 EB001550, R01EB006758), in part by the NINDS (R01 NS052585-01), and in part by the MIND Institute. Additional support was provided by The Autism & Dyslexia Project funded by the Ellison Medical Foundation. The work of B. T. Thomas Yeo was supported by the A*STAR, Singapore. Asterisk indicates corresponding author.

---

Contributing Institute(s):

1. Molekulare Organisation des Gehirns (INM-2)
2. Strukturelle und funktionelle Organisation des Gehirns (INM-1)
3. Jülich-Aachen Research Alliance - Translational Brain Medicine (JARA-BRAIN)

Research Program(s):

1. Funktion und Dysfunktion des Nervensystems (FUEK409) (FUEK409)
2. 89574 - Theory, modelling and simulation (POF2-89574) (POF2-89574)

Appears in the scientific report 2010

---