A deep-learning approach for online cell identification and trace extraction in functional two-photon calcium imaging.
A deep-learning approach for online cell identification and trace extraction in functional two-photon calcium imaging.
复制标题
DOI：
10.1038/s41467-022-29180-0
复制
发表时间：
2022-03-22
影响因子：
16.6
通讯作者：
Fellin T
中科院分区：
文献类型：
--
作者：
Sità L;Brondi M;Lagomarsino de Leon Roig P;Curreli S;Panniello M;Vecchia D;Fellin T
在体双光子钙成像是神经科学中的一种强有力的方法。然而，处理双光子钙成像数据是计算密集型和耗时的，使得在线逐帧分析具有挑战性。这对于大视场（FOV）成像尤其如此。在这里，我们提出了CITE-On（细胞识别和痕量提取在线），这是一种基于卷积神经网络的算法，用于快速自动细胞识别，分割，身份跟踪和双光子钙成像数据中的痕量提取。CITE-On在线处理数千个细胞，包括在介观双光子成像期间，并从FOV中的大多数神经元提取功能测量值。CITE-On的离线版本应用于公开数据集，其性能与最先进的离线分析方法相似。此外，CITE-On概括了麻醉和清醒头部固定小鼠的钙指标、脑区和采集参数。CITE-On是一个强大的工具，可以加速图像分析并促进闭环方法，例如在全光学成像和操作实验中。双光子钙成像数据的处理通常是耗时的，特别是对于大视场。在这里，作者介绍了CITE-On，这是一种基于卷积神经网络的工具，可以实现在线自动细胞识别、分割、身份跟踪和痕迹提取。
In vivo two-photon calcium imaging is a powerful approach in neuroscience. However, processing two-photon calcium imaging data is computationally intensive and time-consuming, making online frame-by-frame analysis challenging. This is especially true for large field-of-view (FOV) imaging. Here, we present CITE-On (Cell Identification and Trace Extraction Online), a convolutional neural network-based algorithm for fast automatic cell identification, segmentation, identity tracking, and trace extraction in two-photon calcium imaging data. CITE-On processes thousands of cells online, including during mesoscopic two-photon imaging, and extracts functional measurements from most neurons in the FOV. Applied to publicly available datasets, the offline version of CITE-On achieves performance similar to that of state-of-the-art methods for offline analysis. Moreover, CITE-On generalizes across calcium indicators, brain regions, and acquisition parameters in anesthetized and awake head-fixed mice. CITE-On represents a powerful tool to speed up image analysis and facilitate closed-loop approaches, for example in combined all-optical imaging and manipulation experiments. Processing of two-photon calcium imaging data is generally time-consuming, especially for large fields of view. Here, the authors present CITE-On, a tool based on a convolutional neural network, enabling online automatic cell identification, segmentation, identity tracking, and trace extraction.
登录
查看更多内容
DOI：
10.1016/j.cub.2020.09.067
发表时间：
2020-12-21
期刊：
Current biology : CB
影响因子：
--
作者：
Jacobs EAK;Steinmetz NA;Peters AJ;Carandini M;Harris KD
通讯作者：
Harris KD
提高神经元群体记录的数据质量。
影响因子：
25
作者：
Harris KD;Quiroga RQ;Freeman J;Smith SL
通讯作者：
Smith SL
影响因子：
7.7
作者：
Antonini A;Sattin A;Moroni M;Bovetti S;Moretti C;Succol F;Forli A;Vecchia D;Rajamanickam VP;Bertoncini A;Panzeri S;Liberale C;Fellin T
通讯作者：
Fellin T
影响因子：
25
作者：
Dombeck, Daniel A.;Harvey, Christopher D.;Tian, Lin;Looger, Loren L.;Tank, David W.
通讯作者：
Tank, David W.
影响因子：
64.8
作者：
Grewe BF;Gründemann J;Kitch LJ;Lecoq JA;Parker JG;Marshall JD;Larkin MC;Jercog PE;Grenier F;Li JZ;Lüthi A;Schnitzer MJ
通讯作者：
Schnitzer MJ