Deep-learning-based whole-brain imaging at single-neuron resolution

Kefu Ning; Xiaoyu Zhang; Xuefei Gao; Tao Jiang; He Wang; Siqi Chen; Anan Li; Jing Yuan

doi:10.1364/BOE.393081

Deep-learning-based whole-brain imaging at single-neuron resolution

Biomed Opt Express. 2020 Jun 8;11(7):3567-3584. doi: 10.1364/BOE.393081. eCollection 2020 Jul 1.

Authors

Kefu Ning^{1

2}, Xiaoyu Zhang^{1

2}, Xuefei Gao^{1

3}, Tao Jiang³, He Wang¹, Siqi Chen¹, Anan Li^{1

3}, Jing Yuan^{1

3}

Affiliations

¹ Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, MoE Key Laboratory for Biomedical Photonics, School of Engineering Sciences, Innovation Institute, Huazhong University of Science and Technology, Wuhan 430074, China.
² These authors contributed equally to this work.
³ HUST-Suzhou Institute for Brainsmatics, JITRI Institute for Brainsmatics, Suzhou 215000, China.

Abstract

Obtaining fine structures of neurons is necessary for understanding brain function. Simple and effective methods for large-scale 3D imaging at optical resolution are still lacking. Here, we proposed a deep-learning-based fluorescence micro-optical sectioning tomography (DL-fMOST) method for high-throughput, high-resolution whole-brain imaging. We utilized a wide-field microscope for imaging, a U-net convolutional neural network for real-time optical sectioning, and histological sectioning for exceeding the imaging depth limit. A 3D dataset of a mouse brain with a voxel size of 0.32 × 0.32 × 2 µm was acquired in 1.5 days. We demonstrated the robustness of DL-fMOST for mouse brains with labeling of different types of neurons.