A deep-learning approach for online cell identification and trace extraction in functional two-photon calcium imaging

• Published in: Nature communications 2022-03, Vol.13 (1), p.1529-22, Article 1529
• Main Authors: Sità, Luca, Brondi, Marco, Lagomarsino de Leon Roig, Pedro, Curreli, Sebastiano, Panniello, Mariangela, Vecchia, Dania, Fellin, Tommaso
• Format: Article
• Language: English
• Subjects: 14/69; 631/114/1305; 631/1647/245/2225; 631/1647/328/2235; Algorithms; Animals; Artificial neural networks; Calcium; Calcium imaging; Deep Learning; Field of view; Humanities and Social Sciences; Image analysis; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Internet; Machine learning; Mice; multidisciplinary; Nervous system; Neural networks; Neural Networks, Computer; Neuroimaging; Photons; Science; Science (multidisciplinary); Tracking
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-022-29180-0

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.