小柯机器人

近日，清华大学戴琼海等研究人员合作利用合成数据训练后，快速检测宽视场钙成像数据集中的神经元。相关论文于2023年4月1日发表在《自然—方法学》杂志上。

研究人员提出了基于深度学习的宽场神经元发现器（DeepWonder），它通过模拟功能记录进行训练，并有效地在实验数据上工作，以实现高保真的神经元提取。与其他方法相比，DeepWonder配备了系统的背景贡献预设，以快一个数量级的速度进行神经元推断，并提高了准确性。DeepWonder可以去除背景污染，并且计算效率高。具体来说，DeepWonder在处理TB级皮层范围内的功能记录时，完成了50倍的信噪比提升，并在17小时内提取了超过14000个神经元。

据介绍，宽视场显微镜可以提供对哺乳动物大脑中多毫米视场和数以千计的神经元进行光学访问的视频速率。然而，组织散射和背景污染导致信号恶化，使得神经元活动的提取具有挑战性、费力和耗时。

附：英文原文

Title: Rapid detection of neurons in widefield calcium imaging datasets after training with synthetic data

Author: Zhang, Yuanlong, Zhang, Guoxun, Han, Xiaofei, Wu, Jiamin, Li, Ziwei, Li, Xinyang, Xiao, Guihua, Xie, Hao, Fang, Lu, Dai, Qionghai

Issue&Volume: 2023-04-01

Abstract: Widefield microscopy can provide optical access to multi-millimeter fields of view and thousands of neurons in mammalian brains at video rate. However, tissue scattering and background contamination results in signal deterioration, making the extraction of neuronal activity challenging, laborious and time consuming. Here we present our deep-learning-based widefield neuron finder (DeepWonder), which is trained by simulated functional recordings and effectively works on experimental data to achieve high-fidelity neuronal extraction. Equipped with systematic background contribution priors, DeepWonder conducts neuronal inference with an order-of-magnitude-faster speed and improved accuracy compared with alternative approaches. DeepWonder removes background contaminations and is computationally efficient. Specifically, DeepWonder accomplishes 50-fold signal-to-background ratio enhancement when processing terabytes-scale cortex-wide functional recordings, with over 14,000 neurons extracted in 17h.

DOI: 10.1038/s41592-023-01838-7

Source: https://www.nature.com/articles/s41592-023-01838-7

Nature Methods：《自然—方法学》，创刊于2004年。隶属于施普林格·自然出版集团，最新IF：47.99
官方网址：https://www.nature.com/nmeth/
投稿链接：https://mts-nmeth.nature.com/cgi-bin/main.plex