Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines

作者：Varoquaux, Gael^*; Raamana, Pradeep Reddy; Engemann, Denis A.; Hoyos-Idrobo, Andres; Schwartz, Yannick; Thirion, Bertrand

来源：NeuroImage, 2017, 145: 166-179.

DOI：10.1016/j.neuroimage.2016.10.038

• Cross-validation
• Decoding
• FMRI
• Model selection
• Sparse
• Bagging
• MVPA

Decoding, i.e. prediction from brain images or signals, calls for empirical evaluation of its predictive power. Such evaluation is achieved via cross-validation, a method also used to tune decoders' hyper-parameters. This paper is a review on cross-validation procedures for decoding in neuroimaging. It includes a didactic overview of the relevant theoretical considerations. Practical aspects are highlighted with an extensive empirical study of the common decoders in within- and across-subject predictions, on multiple datasets anatomical and functional MRI and MEG- and simulations. Theory and experiments outline that the popular "leave-one-out" strategy leads to unstable and biased estimates, and a repeated random splits method should be preferred. Experiments outline the large error bars of cross-validation in neuroimaging settings: typical confidence intervals of 10%. Nested cross-validation can tune decoders' parameters while avoiding circularity bias. However we find that it can be favorable to use sane defaults, in particular for non-sparse decoders.

• 出版日期2017-1-15
• 单位中国地震局