Patrick H. Luckett¹*, John J. Lee², Ki Yun Park¹, Ryan V. Raut³˒⁴, Karin L. Meeker⁵, Evan M. Gordon⁵, Abraham Z. Snyder²˒⁵, Beau M. Ances⁵, Eric C. Leuthardt¹˒⁶˒⁷˒⁸˒⁹˒¹⁰˒¹¹, Joshua S. Shimony²

¹ Division of Neurotechnology, Department of Neurological Surgery, Washington University School of Medicine, St. Louis, MO, United States

² Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO, United States

³ Department of Physiology and Biophysics, University of Washington, Seattle, WA, United States

⁴ MindScope Program, Allen Institute, Seattle, WA, United States

⁵ Department of Neurology, Washington University School of Medicine, St. Louis, MO, United States

⁶ Department of Neuroscience, Washington University School of Medicine, St. Louis, MO, United States

⁷ Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO, United States

⁸ Department of Mechanical Engineering and Materials Science, Washington University in St. Louis, St. Louis, MO, United States

⁹ Center for Innovation in Neuroscience and Technology, Division of Neurotechnology, Washington University School of Medicine, St. Louis, MO, United States

¹⁰ Brain Laser Center, Washington University School of Medicine, St. Louis, MO, United States

¹¹ National Center for Adaptive Neurotechnologies, Albany, NY, United States

Abstract

Introduction: Resting state functional MRI (RS-fMRI) is currently used in numerous clinical and research settings. The localization of resting state networks (RSNs) has been utilized in applications ranging from group analysis of neurodegenerative diseases to individual network mapping for pre-surgical planning of tumor resections. Reproducibility of these results has been shown to require a substantial amount of high-quality data, which is not often available in clinical or research settings.

Methods: In this work, we report voxelwise mapping of a standard set of RSNs using a novel deep 3D convolutional neural network (3DCNN). The 3DCNN was trained on publicly available functional MRI data acquired in n = 2010 healthy participants. After training, maps that represent the probability of a voxel belonging to a particular RSN were generated for each participant, and then used to calculate mean and standard deviation (STD) probability maps, which are made publicly available. Further, we compared our results to previously published resting state and task-based functional mappings.

Results: Our results indicate this method can be applied in individual subjects and is highly resistant to both noisy data and fewer RS-fMRI time points than are typically acquired. Further, our results show core regions within each network that exhibit high average probability and low STD.

Discussion: The 3DCNN algorithm can generate individual RSN localization maps, which are necessary for clinical applications. The similarity between 3DCNN mapping results and task-based fMRI responses supports the association of specific functional tasks with RSNs.