DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data

Taehyo Kim, Hai Shu, Qiran Jia, Mony de Leon
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:946-954, 2024.

Abstract

Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer’s disease FDG-PET image analysis, demonstrate DeepFDR’s superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v238-kim24b, title = {{DeepFDR}: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data}, author = {Kim, Taehyo and Shu, Hai and Jia, Qiran and de Leon, Mony}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {946--954}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/kim24b/kim24b.pdf}, url = {https://proceedings.mlr.press/v238/kim24b.html}, abstract = {Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer’s disease FDG-PET image analysis, demonstrate DeepFDR’s superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.} }
Endnote
%0 Conference Paper %T DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data %A Taehyo Kim %A Hai Shu %A Qiran Jia %A Mony de Leon %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-kim24b %I PMLR %P 946--954 %U https://proceedings.mlr.press/v238/kim24b.html %V 238 %X Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer’s disease FDG-PET image analysis, demonstrate DeepFDR’s superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.
APA
Kim, T., Shu, H., Jia, Q. & de Leon, M.. (2024). DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:946-954 Available from https://proceedings.mlr.press/v238/kim24b.html.

Related Material