{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:44:44Z","timestamp":1790696684357,"version":"4.1.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1007921","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Swiss Government Excellence Scholarship","award":["2017.0575"],"award-info":[{"award-number":["2017.0575"]}]},{"name":"NIH","award":["EY028219"],"award-info":[{"award-number":["EY028219"]}]},{"name":"Center for Computational Brain Research"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Spiking information of individual neurons is essential for functional and behavioral analysis in neuroscience research. Calcium imaging techniques are generally employed to obtain activities of neuronal populations. However, these techniques result in slowly-varying fluorescence signals with low temporal resolution. Estimating the temporal positions of the neuronal action potentials from these signals is a challenging problem. In the literature, several generative model-based and data-driven algorithms have been studied with varied levels of success. This article proposes a neural network-based signal-to-signal conversion approach, where it takes as input raw-fluorescence signal and learns to estimate the spike information in an end-to-end fashion. Theoretically, the proposed approach formulates the spike estimation as a single channel source separation problem with unknown mixing conditions. The source corresponding to the action potentials at a lower resolution is estimated at the output. Experimental studies on the spikefinder challenge dataset show that the proposed signal-to-signal conversion approach significantly outperforms state-of-the-art-methods in terms of Pearson\u2019s correlation coefficient, Spearman\u2019s rank correlation coefficient and yields comparable performance for the area under the receiver operating characteristics measure. We also show that the resulting system: (a) has low complexity with respect to existing supervised approaches and is reproducible; (b) is layer-wise interpretable, and (c) has the capability to generalize across different calcium indicators.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1007921","type":"journal-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T13:36:18Z","timestamp":1614605778000},"page":"e1007921","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":21,"title":["Signal-to-signal neural networks for improved spike estimation from calcium imaging data"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9780-7745","authenticated-orcid":true,"given":"Jilt","family":"Sebastian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2442-5671","authenticated-orcid":true,"given":"Mriganka","family":"Sur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3611-6550","authenticated-orcid":true,"given":"Hema A.","family":"Murthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-1409","authenticated-orcid":true,"given":"Mathew","family":"Magimai-Doss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,3,1]]},"reference":[{"issue":"3","key":"pcbi.1007921.ref001","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/nrn2338","article-title":"Imaging in vivo: watching the brain in action","volume":"9","author":"JN Kerr","year":"2008","journal-title":"Nature Reviews Neuroscience"},{"key":"pcbi.1007921.ref002","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3389\/fncir.2013.00151","article-title":"Three-dimensional mapping of microcircuit correlation structure","volume":"7","author":"RJ Cotton","year":"2013","journal-title":"Frontiers in neural circuits"},{"issue":"5","key":"pcbi.1007921.ref003","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1038\/nmeth.1453","article-title":"High-speed in vivo calcium imaging reveals neuronal network activity with near-millisecond precision","volume":"7","author":"BF Grewe","year":"2010","journal-title":"Nature methods"},{"key":"pcbi.1007921.ref004","first-page":"156786","article-title":"Robustness of spike deconvolution for calcium imaging of neural spiking","author":"M Pachitariu","year":"2017","journal-title":"bioRxiv"},{"issue":"2","key":"pcbi.1007921.ref005","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1016\/j.bpj.2008.08.005","article-title":"Spike inference from calcium imaging using sequential Monte Carlo methods","volume":"97","author":"JT Vogelstein","year":"2009","journal-title":"Biophysical journal"},{"issue":"7458","key":"pcbi.1007921.ref006","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1038\/nature12354","article-title":"Ultrasensitive fluorescent proteins for imaging neuronal activity","volume":"499","author":"TW Chen","year":"2013","journal-title":"Nature"},{"issue":"1","key":"pcbi.1007921.ref007","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.bpj.2012.07.058","article-title":"Photon shot noise limits on optical detection of neuronal spikes and estimation of spike timing","volume":"104","author":"B Wilt","year":"2013","journal-title":"Biophysical journal"},{"issue":"6","key":"pcbi.1007921.ref008","doi-asserted-by":"crossref","first-page":"3691","DOI":"10.1152\/jn.01073.2009","article-title":"Fast non-negative deconvolution for spike train inference from population calcium imaging","volume":"104","author":"JT Vogelstein","year":"2010","journal-title":"Journal of neurophysiology"},{"key":"pcbi.1007921.ref009","doi-asserted-by":"crossref","unstructured":"Jewell S, Hocking TD, Fearnhead P, Witten D. Fast nonconvex deconvolution of calcium imaging data. arXiv preprint arXiv:1802.07380. 2018 Feb 21.","DOI":"10.1093\/biostatistics\/kxy083"},{"issue":"2","key":"pcbi.1007921.ref010","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.neuron.2015.11.037","article-title":"Simultaneous Denoising, Deconvolution, and Demixing of calcium Imaging Data","volume":"89","author":"EA Pnevmatikakis","year":"2016","journal-title":"Neuron"},{"issue":"5","key":"pcbi.1007921.ref011","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1038\/nmeth874","article-title":"Reconstruction of firing rate changes across neuronal populations by temporally deconvolved Ca 2+ imaging","volume":"3","author":"E Yaksi","year":"2006","journal-title":"Nature methods"},{"key":"pcbi.1007921.ref012","doi-asserted-by":"crossref","first-page":"12190","DOI":"10.1038\/ncomms12190","article-title":"Accurate spike estimation from noisy calcium signals for ultrafast three-dimensional imaging of large neuronal populations in vivo","volume":"7","author":"T Deneux","year":"2016","journal-title":"Nature Communications"},{"issue":"7","key":"pcbi.1007921.ref013","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/nn.2140","article-title":"Population imaging of ongoing neuronal activity in the visual cortex of awake rats","volume":"11","author":"DS Greenberg","year":"2008","journal-title":"Nature neuroscience"},{"key":"pcbi.1007921.ref014","unstructured":"Friedrich J, Paninski L. Fast active set methods for online spike inference from calcium imaging. Advances In Neural Information Processing Systems; 2016. p. 1984\u20131992."},{"key":"pcbi.1007921.ref015","doi-asserted-by":"crossref","unstructured":"Pnevmatikakis EA, Merel J, Pakman A, Paninski L. Bayesian spike inference from calcium imaging data. InSignals, Systems and Computers, 2013 Asilomar Conference on 2013 Nov 3 (pp. 349-353). IEEE.","DOI":"10.1109\/ACSSC.2013.6810293"},{"issue":"11","key":"pcbi.1007921.ref016","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1109\/TSP.2019.2908913","article-title":"Spike Estimation From Fluorescence Signals Using High-Resolution Property of Group Delay","volume":"67","author":"J Sebastian","year":"2019","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"3","key":"pcbi.1007921.ref017","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.neuron.2016.04.014","article-title":"Benchmarking Spike Rate Inference in Population calcium Imaging","volume":"90","author":"L Theis","year":"2016","journal-title":"Neuron"},{"issue":"11","key":"pcbi.1007921.ref018","doi-asserted-by":"crossref","first-page":"e1003356","DOI":"10.1371\/journal.pcbi.1003356","article-title":"Beyond GLMs: a generative mixture modeling approach to neural system identification","volume":"9","author":"L Theis","year":"2013","journal-title":"PLoS computational biology"},{"issue":"5","key":"pcbi.1007921.ref019","doi-asserted-by":"crossref","first-page":"e1006157","DOI":"10.1371\/journal.pcbi.1006157","article-title":"Community-based benchmarking improves spike rate inference from two-photon calcium imaging data","volume":"14","author":"P Berens","year":"2018","journal-title":"PLoS computational biology"},{"key":"pcbi.1007921.ref020","doi-asserted-by":"crossref","unstructured":"Linsley D, Linsley JW, Sharma T, Meyers N, Serre T. Learning to predict action potentials end-to-end from calcium imaging data. IEEE 52nd Annual Conference on Information Sciences and Systems (CISS), 2018, pp. 1-6.","DOI":"10.1109\/CISS.2018.8362319"},{"key":"pcbi.1007921.ref021","unstructured":"Im DJ, Prakhya S, Yan J, Turaga S, Branson K. Importance Weighted Adversarial Variational Autoencoders for Spike Inference from calcium Imaging Data. arXiv preprint arXiv:1906.03214. 2019 Jun 7."},{"key":"pcbi.1007921.ref022","unstructured":"Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. Advances in neural information processing systems 2014 (pp. 3104-3112)."},{"key":"pcbi.1007921.ref023","doi-asserted-by":"crossref","unstructured":"Chan W, Jaitly N, Le Q, Vinyals O. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on 2016 Mar 20 (pp. 4960-4964). IEEE.","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"pcbi.1007921.ref024","doi-asserted-by":"crossref","unstructured":"Chiu CC, Sainath TN, Wu Y, Prabhavalkar R, Nguyen P, Chen Z, Kannan A, Weiss RJ, Rao K, Gonina K, Jaitly N. State-of-the-art speech recognition with sequence-to-sequence models. arXiv preprint arXiv:1712.01769. 2017 Dec 5.","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"pcbi.1007921.ref025","doi-asserted-by":"crossref","unstructured":"Nallapati R, Zhou B, Gulcehre C, Xiang B. Abstractive text summarization using sequence-to-sequence rnns and beyond. arXiv preprint arXiv:1602.06023. 2016 Feb 19.","DOI":"10.18653\/v1\/K16-1028"},{"key":"pcbi.1007921.ref026","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. 2018 Oct 11."},{"key":"pcbi.1007921.ref027","unstructured":"Venkataramani S, Casebeer J, Smaragdis P. Adaptive front-ends for end-to-end source separation. InProc. NIPS 2017."},{"key":"pcbi.1007921.ref028","doi-asserted-by":"crossref","unstructured":"Luo Y, Mesgarani N. TasNet: time-domain audio separation network for real-time, single-channel speech separation. arXiv preprint arXiv:1711.00541. 2017 Nov 1.","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"pcbi.1007921.ref029","doi-asserted-by":"crossref","unstructured":"Fu SW, Tsao Y, Lu X, Kawai H. Raw waveform-based speech enhancement by fully convolutional networks. arXiv preprint arXiv:1703.02205. 2017 Mar 7.","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"pcbi.1007921.ref030","doi-asserted-by":"crossref","unstructured":"Rethage D, Pons J, Serra X. A Wavenet for speech denoising. arXiv preprint arXiv:1706.07162. 2017 Jun 22.","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"pcbi.1007921.ref031","unstructured":"Svoboda K, Project G. Simultaneous imaging and loose-seal cell-attached electrical recordings from neurons expressing a variety of genetically encoded calcium indicators; 2015. Available from: http:\/\/dx.doi.org\/10.6080\/K02R3PMN."},{"key":"pcbi.1007921.ref032","unstructured":"GENIE project, Janelia Research Campus, HHMI; Karel Svoboda (contact). Simultaneous imaging and loose-seal cell-attached electrical recordings from neurons expressing a variety of genetically encoded calcium indicators. CRCNS.org; 2015. Available from: http:\/\/dx.doi.org\/10.6080\/K02R3PMN."},{"key":"pcbi.1007921.ref033","article-title":"Suite2p: beyond 10,000 neurons with standard two-photon microscopy","author":"M Pachitariu","year":"2016","journal-title":"bioRxiv"},{"key":"pcbi.1007921.ref034","unstructured":"Speiser A, Yan J, Archer E, Buesing L, Turaga SC, Macke JH. Fast amortized inference of neural activity from calcium imaging data with variational autoencoders. Advances in Neural Information Processing Systems. vol. 30; 2017"},{"key":"pcbi.1007921.ref035","doi-asserted-by":"crossref","unstructured":"K\u00fcmmerer M, Wallis TS, Bethge M. Saliency Benchmarking: Separating Models, Maps and Metrics. arXiv preprint arXiv:1704.08615. 2017 Apr 27.","DOI":"10.1007\/978-3-030-01270-0_47"},{"key":"pcbi.1007921.ref036","unstructured":"Chollet, Fran\u00e7ois and others. Keras (2015). https:\/\/keras.io"},{"key":"pcbi.1007921.ref037","unstructured":"Girija, SS. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org, 2015."},{"issue":"Oct","key":"pcbi.1007921.ref038","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of machine learning research"},{"issue":"3","key":"pcbi.1007921.ref039","doi-asserted-by":"crossref","DOI":"10.1109\/MCSE.2007.58","article-title":"Python for scientific computing","volume":"9","author":"TE Oliphant","year":"2007","journal-title":"Computing in Science & Engineering"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1007921","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1007921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T22:50:08Z","timestamp":1724539808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1007921"}},"subtitle":[],"editor":[{"given":"Renaud Blaise","family":"Jolivet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1007921","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.05.01.071993","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]}}}