TAG-SPARK: Empowering High-Speed Volumetric Imaging With Deep Learning and Spatial Redundancy.
Yin-Tzu HsiehKai-Chun JhanJye-Chang LeeGuan-Jie HuangChang-Ling ChungWun-Ci ChenTing-Chen ChangBi-Chang ChenMing-Kai PanShun-Chi WuShi-Wei ChuPublished in: Advanced science (Weinheim, Baden-Wurttemberg, Germany) (2024)
Two-photon high-speed fluorescence calcium imaging stands as a mainstream technique in neuroscience for capturing neural activities with high spatiotemporal resolution. However, challenges arise from the inherent tradeoff between acquisition speed and image quality, grappling with a low signal-to-noise ratio (SNR) due to limited signal photon flux. Here, a contrast-enhanced video-rate volumetric system, integrating a tunable acoustic gradient (TAG) lens-based high-speed microscopy with a TAG-SPARK denoising algorithm is demonstrated. The former facilitates high-speed dense z-sampling at sub-micrometer-scale intervals, allowing the latter to exploit the spatial redundancy of z-slices for self-supervised model training. This spatial redundancy-based approach, tailored for 4D (xyzt) dataset, not only achieves >700% SNR enhancement but also retains fast-spiking functional profiles of neuronal activities. High-speed plus high-quality images are exemplified by in vivo Purkinje cells calcium observation, revealing intriguing dendritic-to-somatic signal convolution, i.e., similar dendritic signals lead to reverse somatic responses. This tailored technique allows for capturing neuronal activities with high SNR, thus advancing the fundamental comprehension of neuronal transduction pathways within 3D neuronal architecture.
Keyphrases
- high speed
- high resolution
- deep learning
- atomic force microscopy
- contrast enhanced
- computed tomography
- image quality
- machine learning
- convolutional neural network
- magnetic resonance imaging
- cerebral ischemia
- single molecule
- magnetic resonance
- induced apoptosis
- smoking cessation
- diffusion weighted
- copy number
- mass spectrometry
- cell cycle arrest
- dual energy
- living cells
- neural network
- gene expression
- air pollution
- diffusion weighted imaging
- cell death
- optical coherence tomography
- single cell
- quantum dots