{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T07:00:04Z","timestamp":1773903604709,"version":"3.50.1"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Dendritic spines are the seat of most excitatory synapses in the brain, and a cellular structure considered central to learning, memory, and activity-dependent plasticity. The quantification of dendritic spines from light microscopy data is usually performed by humans in a painstaking and error-prone process. We found that human-to-human variability is substantial (inter-rater reliability 82.2\u00b16.4%), raising concerns about the reproducibility of experiments and the validity of using human-annotated \u2018ground truth\u2019 as an evaluation method for computational approaches of spine identification. To address this, we present DeepD3, an open deep learning-based framework to robustly quantify dendritic spines in microscopy data in a fully automated fashion. DeepD3\u2019s neural networks have been trained on data from different sources and experimental conditions, annotated and segmented by multiple experts and they offer precise quantification of dendrites and dendritic spines. Importantly, these networks were validated in a number of datasets on varying acquisition modalities, species, anatomical locations and fluorescent indicators. The entire DeepD3 open framework, including the fully segmented training data, a benchmark that multiple experts have annotated, and the DeepD3 model zoo is fully available, addressing the lack of openly available datasets of dendritic spines while offering a ready-to-use, flexible, transparent, and reproducible spine quantification method.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011774","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T13:52:37Z","timestamp":1709214757000},"page":"e1011774","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["DeepD3, an open framework for automated quantification of dendritic spines"],"prefix":"10.1371","volume":"20","author":[{"given":"Martin H. P.","family":"Fernholz","sequence":"first","affiliation":[]},{"given":"Drago A.","family":"Guggiana Nilo","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Bonhoeffer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3643-7776","authenticated-orcid":true,"given":"Andreas M.","family":"Kist","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"issue":"6533","key":"pcbi.1011774.ref001","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1038\/375682a0","article-title":"Dendritic spines as basic functional units of neuronal integration","volume":"375","author":"R Yuste","year":"1995","journal-title":"Nature"},{"issue":"4","key":"pcbi.1011774.ref002","doi-asserted-by":"crossref","first-page":"R157","DOI":"10.1016\/j.cub.2009.12.040","article-title":"Dendritic spines: the stuff that memories are made of?","volume":"20","author":"SB Hofer","year":"2010","journal-title":"Current biology"},{"issue":"1","key":"pcbi.1011774.ref003","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1146\/annurev.neuro.24.1.1071","article-title":"Morphological changes in dendritic spines associated with long-term synaptic plasticity","volume":"24","author":"R Yuste","year":"2001","journal-title":"Annual review of neuroscience"},{"key":"pcbi.1011774.ref004","doi-asserted-by":"crossref","first-page":"e34700","DOI":"10.7554\/eLife.34700","article-title":"Chronic 2P-STED imaging reveals high turnover of dendritic spines in the hippocampus in vivo","volume":"7","author":"T Pfeiffer","year":"2018","journal-title":"Elife"},{"issue":"7562","key":"pcbi.1011774.ref005","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1038\/nature14467","article-title":"Impermanence of dendritic spines in live adult CA1 hippocampus","volume":"523","author":"A Attardo","year":"2015","journal-title":"Nature"},{"key":"pcbi.1011774.ref006","doi-asserted-by":"crossref","first-page":"e66809","DOI":"10.7554\/eLife.66809","article-title":"Visualizing synaptic plasticity in vivo by large-scale imaging of endogenous AMPA receptors","volume":"10","author":"AR Graves","year":"2021","journal-title":"Elife"},{"issue":"4","key":"pcbi.1011774.ref007","doi-asserted-by":"crossref","first-page":"e1997","DOI":"10.1371\/journal.pone.0001997","article-title":"Automated three-dimensional detection and shape classification of dendritic spines from fluorescence microscopy images","volume":"3","author":"A Rodriguez","year":"2008","journal-title":"PloS one"},{"issue":"6","key":"pcbi.1011774.ref008","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1162\/089976602753712945","article-title":"An image analysis algorithm for dendritic spines","volume":"14","author":"IY Koh","year":"2002","journal-title":"Neural computation"},{"issue":"1","key":"pcbi.1011774.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/cpns.16","article-title":"Automatic dendritic spine quantification from confocal data with Neurolucida 360","volume":"77","author":"DL Dickstein","year":"2016","journal-title":"Current protocols in neuroscience"},{"key":"pcbi.1011774.ref010","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.jneumeth.2018.08.019","article-title":"Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes","volume":"309","author":"X Xiao","year":"2018","journal-title":"Journal of neuroscience methods"},{"key":"pcbi.1011774.ref011","doi-asserted-by":"crossref","first-page":"817903","DOI":"10.3389\/fnana.2022.817903","article-title":"A Deep Learning-Based Workflow for Dendritic Spine Segmentation","volume":"16","author":"I Vidaurre-Gallart","year":"2022","journal-title":"Frontiers in neuroanatomy"},{"key":"pcbi.1011774.ref012","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer; 2015. p. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"pcbi.1011774.ref013","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s12021-017-9332-2","article-title":"Automated 3-D detection of dendritic spines from in vivo two-photon image stacks","volume":"15","author":"PK Singh","year":"2017","journal-title":"Neuroinformatics"},{"issue":"8","key":"pcbi.1011774.ref014","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1038\/s41592-019-0493-9","article-title":"Kilohertz frame-rate two-photon tomography","volume":"16","author":"A Kazemipour","year":"2019","journal-title":"Nature methods"},{"issue":"1","key":"pcbi.1011774.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-017-02751-2","article-title":"Hotspots of dendritic spine turnover facilitate clustered spine addition and learning and memory","volume":"9","author":"AC Frank","year":"2018","journal-title":"Nature communications"},{"issue":"2","key":"pcbi.1011774.ref016","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.neuron.2015.06.036","article-title":"BigNeuron: large-scale 3D neuron reconstruction from optical microscopy images","volume":"87","author":"H Peng","year":"2015","journal-title":"Neuron"},{"issue":"9","key":"pcbi.1011774.ref017","doi-asserted-by":"crossref","first-page":"1281","DOI":"10.1038\/s41593-018-0209-y","article-title":"DeepLabCut: markerless pose estimation of user-defined body parts with deep learning","volume":"21","author":"A Mathis","year":"2018","journal-title":"Nature neuroscience"},{"key":"pcbi.1011774.ref018","article-title":"Engineering paralog-specific PSD-95 synthetic binders as potent and minimally invasive imaging probes","author":"C Rimbault","year":"2021","journal-title":"bioRxiv"},{"issue":"7","key":"pcbi.1011774.ref019","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1038\/s41592-019-0435-6","article-title":"High-performance calcium sensors for imaging activity in neuronal populations and microcompartments","volume":"16","author":"H Dana","year":"2019","journal-title":"Nature methods"},{"issue":"6","key":"pcbi.1011774.ref020","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1038\/nprot.2018.026","article-title":"High-yield in vitro recordings from neurons functionally characterized in vivo","volume":"13","author":"S Weiler","year":"2018","journal-title":"Nature protocols"},{"issue":"2","key":"pcbi.1011774.ref021","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/0165-0270(91)90128-M","article-title":"A simple method for organotypic cultures of nervous tissue","volume":"37","author":"L Stoppini","year":"1991","journal-title":"Journal of Neuroscience Methods"},{"issue":"6","key":"pcbi.1011774.ref022","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1038\/nprot.2009.56","article-title":"Targeted single-cell electroporation of mammalian neurons in vivo","volume":"4","author":"B Judkewitz","year":"2009","journal-title":"Nature protocols"},{"issue":"15","key":"pcbi.1011774.ref023","doi-asserted-by":"crossref","first-page":"2457","DOI":"10.1016\/j.neuron.2021.05.036","article-title":"Limited functional convergence of eye-specific inputs in the retinogeniculate pathway of the mouse","volume":"109","author":"J Bauer","year":"2021","journal-title":"Neuron"},{"issue":"4","key":"pcbi.1011774.ref024","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1038\/nn.4516","article-title":"Video-rate volumetric functional imaging of the brain at synaptic resolution","volume":"20","author":"R Lu","year":"2017","journal-title":"Nature neuroscience"},{"issue":"3","key":"pcbi.1011774.ref025","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s40708-017-0063-9","article-title":"Fast assembling of neuron fragments in serial 3D sections","volume":"4","author":"H Chen","year":"2017","journal-title":"Brain informatics"},{"key":"pcbi.1011774.ref026","article-title":"BigNeuron: A resource to benchmark and predict best-performing algorithms for automated reconstruction of neuronal morphology","author":"L Manubens-Gil","year":"2022","journal-title":"bioRxiv"},{"issue":"1","key":"pcbi.1011774.ref027","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TITB.2003.808506","article-title":"Nonrigid image registration in shared-memory multiprocessor environments with application to brains, breasts, and bees","volume":"7","author":"T Rohlfing","year":"2003","journal-title":"IEEE transactions on information technology in biomedicine"},{"issue":"1","key":"pcbi.1011774.ref028","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1038\/s41597-020-0526-3","article-title":"BAGLS, a multihospital benchmark for automatic glottis segmentation","volume":"7","author":"P G\u00f3mez","year":"2020","journal-title":"Scientific data"},{"key":"pcbi.1011774.ref029","unstructured":"Ranzuglia G, Callieri M, Dellepiane M, Cignoni P, Scopigno R. MeshLab as a complete tool for the integration of photos and color with high resolution 3D geometry data. In: CAA 2012 Conference Proceedings. Pallas Publications\u2014Amsterdam University Press (AUP); 2013. p. 406\u2013416. Available from: http:\/\/vcg.isti.cnr.it\/Publications\/2013\/RCDCS13."},{"key":"pcbi.1011774.ref030","doi-asserted-by":"crossref","unstructured":"Feng L, Zhao T, Kim J. neuTube 1.0: a new design for efficient neuron reconstruction software based on the SWC format. eneuro. 2015;2(1). doi: 10.1523\/ENEURO.0049-14.2014 26464967","DOI":"10.1523\/ENEURO.0049-14.2015"},{"issue":"1","key":"pcbi.1011774.ref031","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: deep learning for cell counting, detection, and morphometry","volume":"16","author":"T Falk","year":"2019","journal-title":"Nature methods"},{"issue":"2","key":"pcbi.1011774.ref032","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"F Isensee","year":"2021","journal-title":"Nature methods"},{"issue":"1","key":"pcbi.1011774.ref033","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1038\/s41592-020-01018-x","article-title":"Cellpose: a generalist algorithm for cellular segmentation","volume":"18","author":"C Stringer","year":"2021","journal-title":"Nature Methods"},{"key":"pcbi.1011774.ref034","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR; 2015. p. 448\u2013456."},{"key":"pcbi.1011774.ref035","unstructured":"Ramachandran P, Zoph B, Le QV. Searching for activation functions. arXiv preprint arXiv:171005941. 2017;."},{"key":"pcbi.1011774.ref036","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"10","key":"pcbi.1011774.ref037","doi-asserted-by":"crossref","first-page":"e3","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","volume":"1","author":"A Odena","year":"2016","journal-title":"Distill"},{"key":"pcbi.1011774.ref038","doi-asserted-by":"crossref","first-page":"139356","DOI":"10.1109\/ACCESS.2020.3012722","article-title":"Efficient biomedical image segmentation on EdgeTPUs at point of care","volume":"8","author":"AM Kist","year":"2020","journal-title":"IEEE Access"},{"key":"pcbi.1011774.ref039","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;."},{"key":"pcbi.1011774.ref040","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16); 2016. p. 265\u2013283."}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T13:53:01Z","timestamp":1709214781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011774"}},"subtitle":[],"editor":[{"given":"Matthias Helge","family":"Hennig","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011774","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.02.01.526476","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,29]]}}}