TY  - JOUR
AU  - Yeo, B.T.T.
AU  - Sabuncu, M.R.
AU  - Vercauteren, T.
AU  - Holt, D.J.
AU  - Amunts, K.
AU  - Zilles, K.
AU  - Golland, P.
AU  - Fischl, B.
TI  - Learning Task-Optimal Registration Cost Functions for Localizing Cytoarchitecture and Function in the Cerebral Cortex
JO  - IEEE transactions on medical imaging
VL  - 29
SN  - 0278-0062
CY  - New York, NY
PB  - Institute of Electrical and Electronics Engineers,
M1  - PreJuSER-10476
SP  - 1424 - 1441
PY  - 2010
N1  - 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.
AB  - 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.
KW  - Algorithms
KW  - Brain: physiology
KW  - Brain Mapping: methods
KW  - Cerebral Cortex: physiology
KW  - Humans
KW  - Image Enhancement: methods
KW  - Image Interpretation, Computer-Assisted: methods
KW  - Information Storage and Retrieval: methods
KW  - Magnetic Resonance Imaging: methods
KW  - Pattern Recognition, Automated: methods
KW  - Reproducibility of Results
KW  - Sensitivity and Specificity
KW  - J (WoSType)
LB  - PUB:(DE-HGF)16
C6  - pmid:20529736
UR  - <Go to ISI:>//WOS:000281925700008
DO  - DOI:10.1109/TMI.2010.2049497
UR  - https://juser.fz-juelich.de/record/10476
ER  -