Maximin Designs for Ultra-Fast Functional Brain Imaging
Functional brain imaging experiments allow researchers to study the inner workings of the human brain, and are widely conducted in many fields. An important experimental design issue for such an experiment is the selection of a sequence of mental stimuli that allows us to collect informative data for making precise and valid statistical inferences. However, obtaining a good stimulus sequence can be challenging, especially when brain mapping technology with a high temporal resolution is employed. In this work, we focus on such ultra-fast functional brain imaging studies, and propose an efficient approach for obtaining high-quality stimulus sequences by taking the uncertainty of the autocorrelation of the response into account. The performance of our proposed approach is demonstrated via case studies.
The research of Ming-Hung Kao was in part supported by the National Science Foundation grants DMS-13-52213, and CMMI-17-26445.
- Kao, M.-H., Stufken, J.: Optimal design for event-related fMRI studies. In: Dean, A., Morris M., Stufken, J., Bingham, D. (eds.) Handbook of Design and Analysis of Experiments, pp. 895–924 CRC Press, Boca Raton (2015)Google Scholar
- Kao, M.-H., Mandal, A., Stufken, J.: Constrained multi-objective designs for functional MRI experiments via a modified nondominated sorting genetic algorithm. J. R. Stat. Soc. Ser. C (Appl. Stat.) 61(4), 515–534 (2012)Google Scholar