School of Chemical & Biomolecular Engineering, Georgia Institute of Technology, Atlanta, GA, USA.
Petit Institute for Bioengineering and Bioscience, Georgia Institute of Technology, Atlanta, GA, USA.
Nat Commun. 2022 Sep 2;13(1):5165. doi: 10.1038/s41467-022-32886-w.
Volumetric functional imaging is widely used for recording neuron activities in vivo, but there exist tradeoffs between the quality of the extracted calcium traces, imaging speed, and laser power. While deep-learning methods have recently been applied to denoise images, their applications to downstream analyses, such as recovering high-SNR calcium traces, have been limited. Further, these methods require temporally-sequential pre-registered data acquired at ultrafast rates. Here, we demonstrate a supervised deep-denoising method to circumvent these tradeoffs for several applications, including whole-brain imaging, large-field-of-view imaging in freely moving animals, and recovering complex neurite structures in C. elegans. Our framework has 30× smaller memory footprint, and is fast in training and inference (50-70 ms); it is highly accurate and generalizable, and further, trained with only small, non-temporally-sequential, independently-acquired training datasets (∼500 pairs of images). We envision that the framework will enable faster and long-term imaging experiments necessary to study neuronal mechanisms of many behaviors.
容积功能成像被广泛用于在体记录神经元活动，但在提取钙迹的质量、成像速度和激光功率之间存在权衡。虽然深度学习方法最近已被应用于图像去噪，但它们在下游分析中的应用，如恢复高信噪比钙迹，受到了限制。此外，这些方法需要在超快率下获取具有时间顺序的预注册数据。在这里，我们展示了一种有监督的深度去噪方法，可以规避这些权衡，适用于多种应用，包括全脑成像、自由活动动物的大视场成像以及恢复秀丽隐杆线虫中的复杂神经突结构。我们的框架具有 30 倍更小的内存占用，并且在训练和推理方面速度很快（50-70ms）；它具有高度的准确性和通用性，并且仅使用小的、非时间顺序的、独立采集的训练数据集（约 500 对图像）进行训练。我们设想，该框架将能够实现更快和长期的成像实验，这对于研究许多行为的神经元机制是必要的。
