{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:06:58Z","timestamp":1766138818623,"version":"3.41.2"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000},"content-version":"vor","delay-in-days":212,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012095","name":"Scottish Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012095","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Teleost fish scales form distinct growth rings deposited in proportion to somatic growth in length, and are routinely used in fish ageing and growth analyses. Extraction of incremental growth data from scales is labour intensive. We present a fully automated method to retrieve this data from fish scale images using Convolutional Neural Networks (CNNs). Our pipeline of two CNNs automatically detects the centre of the scale and individual growth rings (circuli) along multiple radial transect emanating from the centre. The focus detector was trained on 725 scale images and achieved an average precision of 99%; the circuli detector was trained on 40\u00a0678 circuli annotations and achieved an average precision of 95.1%. Circuli detections were made with less confidence in the freshwater zone of the scale image where the growth bands are most narrowly spaced. However, the performance of the circuli detector was similar to that of another human labeller, highlighting the inherent ambiguity of the labelling process. The system predicts the location of scale growth rings rapidly and with high accuracy, enabling the calculation of spacings and thereby growth inferences from salmon scales. The success of our method suggests its potential for expansion to other species.<\/jats:p>","DOI":"10.1093\/biomethods\/bpae056","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T02:54:41Z","timestamp":1722480881000},"source":"Crossref","is-referenced-by-count":6,"title":["Automatic detection of fish scale circuli using deep learning"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0017-8963","authenticated-orcid":false,"given":"Nora N","family":"Hanson","sequence":"first","affiliation":[{"name":"Freshwater Fisheries Laboratory, Marine Directorate, Scottish Government , Pitlochry PH16 5LB, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8397-0659","authenticated-orcid":false,"given":"James P","family":"Ounsley","sequence":"additional","affiliation":[{"name":"Freshwater Fisheries Laboratory, Marine Directorate, Scottish Government , Pitlochry PH16 5LB, United Kingdom"}]},{"given":"Jason","family":"Henry","sequence":"additional","affiliation":[{"name":"Freshwater Fisheries Laboratory, Marine Directorate, Scottish Government , Pitlochry PH16 5LB, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6692-209X","authenticated-orcid":false,"given":"Kasim","family":"Terzi\u0107","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of St Andrews , St Andrews KY16 9SX, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0124-7156","authenticated-orcid":false,"given":"Bruno","family":"Caneco","sequence":"additional","affiliation":[{"name":"Freshwater Fisheries Laboratory, Marine Directorate, Scottish Government , Pitlochry PH16 5LB, United Kingdom"}]}],"member":"286","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"2024081721212222800_bpae056-B1","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1577\/1548-8659(1990)119<0673:GARSOC>2.3.CO;2","article-title":"Growth and relative size of calcified structures of fish","volume":"119","author":"Casselman","year":"1990","journal-title":"Trans Am Fish Soc"},{"key":"2024081721212222800_bpae056-B2","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1139\/f96-307","article-title":"Scale analyses to estimate somatic growth in sockeye salmon, Oncorhynchus nerka","volume":"54","author":"Fukuwaka","year":"1997","journal-title":"Can J Fish Aquat Sci"},{"key":"2024081721212222800_bpae056-B3","first-page":"34","article-title":"Seasonal changes in growth of coho salmon (Oncorhynchus kisutch) off Oregon and Washington and concurrent changes in the spacing of scale circuli","volume":"103","author":"Fisher","year":"2005","journal-title":"Fish Bull"},{"key":"2024081721212222800_bpae056-B4","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1111\/jfb.13971","article-title":"Experimental investigation of the effects of temperature and feeding regime on scale growth in Atlantic salmon Salmo salar post-smolts","volume":"94","author":"Thomas","year":"2019","journal-title":"J Fish Biol"},{"key":"2024081721212222800_bpae056-B5","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1111\/j.1095-8649.2007.01538.x","article-title":"Links between patterns of marine growth and survival of Atlantic salmon Salmo salar, L","volume":"71","author":"Peyronnet","year":"2007","journal-title":"J Fish Biol"},{"key":"2024081721212222800_bpae056-B6","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1111\/jfb.14552","article-title":"Variation in the post-smolt growth pattern of wild one sea-winter salmon (Salmo salar L.), and its linkage to surface warming in the eastern North Atlantic Ocean","volume":"98","author":"Todd","year":"2021","journal-title":"J Fish Biol"},{"key":"2024081721212222800_bpae056-B7","doi-asserted-by":"crossref","first-page":"eabk2542","DOI":"10.1126\/sciadv.abk2542","article-title":"Ecological regime shift in the Northeast Atlantic Ocean revealed from the unprecedented reduction in marine growth of Atlantic salmon","volume":"8","author":"Vollset","year":"2022","journal-title":"Sci Adv"},{"key":"2024081721212222800_bpae056-B8","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1111\/jfb.15567","article-title":"A multi-population approach supports common patterns in marine growth and maturation decision in Atlantic salmon (Salmo salar L.) from Southern Europe","volume":"104","author":"Tr\u00e9hin","year":"2023","journal-title":"J Fish Biol"},{"key":"2024081721212222800_bpae056-B9","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1139\/cjfas-2021-0142","article-title":"Retrospective analysis of marine growth and relationships to return rates of Penobscot River Atlantic salmon","volume":"79","author":"Barajas","year":"2021","journal-title":"Can J Fish Aquat Sci"},{"key":"2024081721212222800_bpae056-B10","doi-asserted-by":"crossref","first-page":"213","DOI":"10.3354\/meps12531","article-title":"Digital imaging techniques in otolith data capture, analysis and interpretation","volume":"598","author":"Fisher","year":"2018","journal-title":"Mar Ecol Prog Ser"},{"key":"2024081721212222800_bpae056-B11","doi-asserted-by":"crossref","first-page":"bpae018","DOI":"10.1093\/biomethods\/bpae018","article-title":"A semi-automated spectral approach to analyzing cyclical growth patterns using fish scales","volume":"9","author":"Chaput","year":"2024","journal-title":"Biol Methods Protoc"},{"key":"2024081721212222800_bpae056-B12","doi-asserted-by":"crossref","first-page":"101322","DOI":"10.1016\/j.ecoinf.2021.101322","article-title":"Automatic interpretation of salmon scales using deep learning","volume":"63","author":"Vab\u00f8","year":"2021","journal-title":"Ecological Informatics"},{"key":"2024081721212222800_bpae056-B13","doi-asserted-by":"crossref","first-page":"121","DOI":"10.3390\/fishes7030121","article-title":"DeepOtolith v1.0: an open-source AI platform for automating fish age reading from otolith or scale images","volume":"7","author":"Politikos","year":"2022","journal-title":"Fishes"},{"key":"2024081721212222800_bpae056-B14","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2024081721212222800_bpae056-B15","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"first-page":"779","year":"2016","author":"Redmon","key":"2024081721212222800_bpae056-B16"},{"key":"2024081721212222800_bpae056-B17","doi-asserted-by":"crossref","first-page":"53040","DOI":"10.1109\/ACCESS.2019.2912200","article-title":"Review of deep learning algorithms and architectures","volume":"7","author":"Shrestha","year":"2019","journal-title":"IEEE Access"},{"key":"2024081721212222800_bpae056-B18","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"year":"2018","author":"Redmon","key":"2024081721212222800_bpae056-B19"},{"year":"2015","author":"Tzutalin","key":"2024081721212222800_bpae056-B20"},{"key":"2024081721212222800_bpae056-B21","doi-asserted-by":"crossref","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","article-title":"Object detection using YOLO: challenges, architectural successors, datasets and applications","volume":"82","author":"Diwan","year":"2023","journal-title":"Multimed Tools Appl"},{"first-page":"248","year":"2009","author":"Deng","key":"2024081721212222800_bpae056-B22"},{"year":"2019","author":"Zhang","key":"2024081721212222800_bpae056-B23"},{"year":"2015","author":"Abadi","key":"2024081721212222800_bpae056-B24"},{"year":"2015","author":"Chollet","key":"2024081721212222800_bpae056-B25"},{"year":"2020","author":"Vingelmann","key":"2024081721212222800_bpae056-B26"},{"year":"2017","author":"Kingma","key":"2024081721212222800_bpae056-B27"},{"volume-title":"Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems","year":"2019","author":"G\u00e9ron","key":"2024081721212222800_bpae056-B28"},{"key":"2024081721212222800_bpae056-B29","doi-asserted-by":"publisher","first-page":"279","DOI":"10.3390\/electronics10030279","article-title":"A comparative analysis of object detection metrics with a companion open-source toolkit","volume":"10","author":"Padilla","year":"2021","journal-title":"Electronics (Switzerland)"},{"year":"1992","author":"Shearer","key":"2024081721212222800_bpae056-B30"},{"key":"2024081721212222800_bpae056-B31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5324\/fn.v36i0.1954","article-title":"Increased precision of growth data gained by reading multiple scales from each individual of Atlantic salmon (Salmo salar)","volume":"36","author":"Haraldstad","year":"2016","journal-title":"Fauna Norv"},{"key":"2024081721212222800_bpae056-B32","first-page":"1085","article-title":"Inferring ground truth from subjective labelling of venus images","author":"Smyth","year":"1994","journal-title":"Adv Neural Inf Proc Syst"},{"key":"2024081721212222800_bpae056-B33","first-page":"42","volume-title":"Communications in Computer and Information Science","author":"Rizos","year":"2020"},{"key":"2024081721212222800_bpae056-B34","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/j.1467-9868.2010.00749.x","article-title":"Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models","volume":"73","author":"Wood","year":"2011","journal-title":"J Royal Stat Soc (B)"}],"container-title":["Biology Methods and Protocols"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomethods\/advance-article-pdf\/doi\/10.1093\/biomethods\/bpae056\/58703613\/bpae056.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomethods\/advance-article-pdf\/doi\/10.1093\/biomethods\/bpae056\/58844083\/bpae056.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomethods\/advance-article-pdf\/doi\/10.1093\/biomethods\/bpae056\/58844083\/bpae056.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T21:21:45Z","timestamp":1723929705000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomethods\/article\/doi\/10.1093\/biomethods\/bpae056\/7724799"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,11]]}},"URL":"https:\/\/doi.org\/10.1093\/biomethods\/bpae056","relation":{},"ISSN":["2396-8923"],"issn-type":[{"type":"electronic","value":"2396-8923"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]},"article-number":"bpae056"}}