{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T20:04:59Z","timestamp":1789070699769,"version":"build-2803163510"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Leverhulme Early Career Fellowship","award":["ECF-2018-101"],"award-info":[{"award-number":["ECF-2018-101"]}]},{"name":"Natural Environment Research Council Independent Research Fellowship","award":["NE\/T01105X\/1"],"award-info":[{"award-number":["NE\/T01105X\/1"]}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["615709"],"award-info":[{"award-number":["615709"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Royal Society University Research Fellowship","award":["UF120016"],"award-info":[{"award-number":["UF120016"]}]},{"name":"Royal Society University Research Fellowship","award":["URF\\R\\180006"],"award-info":[{"award-number":["URF\\R\\180006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The digitization of natural history specimens has unlocked opportunities for large-scale phenotypic trait analysis. In recent years, deep learning has shown significant results in accurately predicting annotations on 2D specimen photographs. However, it can be challenging for biologists without extensive related expertise to easily use deep learning. Here, we introduce PhenoLearn, a toolkit developed for biologists to generate annotations on 2D specimen images using deep learning. PhenoLearn integrates graphical user interfaces (GUIs) within its two main modules, PhenoLabel for image annotation and PhenoTrain for model training and prediction. GUIs increase accessibility and reduce the need for computational expertise, allowing biologists to intuitively go through a workflow of labelling training sets, using deep learning, and reviewing predictions in the same tool. We demonstrate PhenoLearn\u2019s capabilities through a case study involving the segmentation of plumage areas on bird images, showcasing prediction accuracy and the running time with and without graphics processing unit, highlighting its potential to generate annotations with minimal computational cost and time. The toolkit\u2019s modular design and flexibility ensure adaptability, allowing for integration with other tools amidst rapidly evolving deep learning approaches. PhenoLearn bridges the gap between specimen digitization and downstream analysis, providing biologists with broader access to deep learning. The source code, installation guides, tutorials with screenshots, and a small demo dataset for PhenoLearn can be found at https:\/\/github.com\/echanhe\/phenolearn.<\/jats:p>","DOI":"10.1093\/jeb\/voaf058","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T12:11:29Z","timestamp":1747224689000},"page":"1152-1162","source":"Crossref","is-referenced-by-count":2,"title":["PhenoLearn: a user-friendly toolkit for image annotation and deep learning-based phenotyping for biological datasets"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3464-7526","authenticated-orcid":false,"given":"Yichen","family":"He","sequence":"first","affiliation":[{"name":"Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield , Sheffield ,","place":["United Kingdom"]},{"name":"Natural History Museum Department of Life Sciences, , London ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4872-9146","authenticated-orcid":false,"given":"Christopher R","family":"Cooney","sequence":"additional","affiliation":[{"name":"Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield , Sheffield ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3179-0263","authenticated-orcid":false,"given":"Steve","family":"Maddock","sequence":"additional","affiliation":[{"name":"University of Sheffield Department of Computer Science, , Sheffield ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6051","authenticated-orcid":false,"given":"Gavin H","family":"Thomas","sequence":"additional","affiliation":[{"name":"Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield , Sheffield ,","place":["United Kingdom"]},{"name":"Bird Group , Department of Life Sciences, Natural History Museum, Tring ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"2025090603071269700_bib1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"issue":"4","key":"2025090603071269700_bib2","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1111\/2041-210X.12035","article-title":"Geomorph: An R package for the collection and analysis of geometric morphometric shape data","volume":"4","author":"Adams","year":"2013","journal-title":"Methods in Ecology and Evolution"},{"key":"2025090603071269700_bib3","doi-asserted-by":"publisher","first-page":"133","DOI":"10.3897\/zookeys.209.3178","article-title":"No specimen left behind: Industrial scale digitization of natural history collections","volume":"209","author":"Blagoderov","year":"2012","journal-title":"ZooKeys"},{"key":"2025090603071269700_bib4","first-page":"122","article-title":"The OpenCV library","volume":"120","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s Journal of Software Tools"},{"issue":"4","key":"2025090603071269700_bib5","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1111\/2041-210X.12508","article-title":"Crowdsourced geometric morphometrics enable rapid large-scale collection and analysis of phenotypic data","volume":"7","author":"Chang","year":"2016","journal-title":"Methods in Ecology and Evolution"},{"key":"2025090603071269700_bib6","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"issue":"5","key":"2025090603071269700_bib7","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1038\/s41559-022-01714-1","article-title":"Latitudinal gradients in avian colourfulness","volume":"6","author":"Cooney","year":"2022","journal-title":"Nature Ecology & Evolution"},{"key":"2025090603071269700_bib8","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"2025090603071269700_bib9","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/ICCV.2017.322","article-title":"Mask R-CNN","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV)","author":"He","year":"2017"},{"issue":"2","key":"2025090603071269700_bib10","doi-asserted-by":"publisher","first-page":"e1010933","DOI":"10.1371\/journal.pcbi.1010933","article-title":"Using pose estimation to identify regions and points on natural history specimens","volume":"19","author":"He","year":"2023","journal-title":"PLOS Computational Biology"},{"issue":"1","key":"2025090603071269700_bib11","doi-asserted-by":"publisher","first-page":"5068","DOI":"10.1038\/s41467-022-32586-5","article-title":"Deep learning image segmentation reveals patterns of UV reflectance evolution in passerine birds","volume":"13","author":"He","year":"2022","journal-title":"Nature Communications"},{"key":"2025090603071269700_bib12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.08614","article-title":"What makes imagenet good for transfer learning?","author":"Huh","year":"2016"},{"issue":"4","key":"2025090603071269700_bib13","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/rse2.382","article-title":"Using photographs and deep neural networks to understand flowering phenology and diversity in mountain meadows","volume":"10","author":"John","year":"2024","journal-title":"Remote Sensing in Ecology and Conservation"},{"key":"2025090603071269700_bib14","first-page":"4015","article-title":"Segment anything","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Kirillov","year":"2023"},{"key":"2025090603071269700_bib15","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft COCO: Common objects in context","volume-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part v 13","author":"Lin","year":"2014"},{"issue":"3","key":"2025090603071269700_bib16","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1111\/2041-210X.13771","article-title":"Phenopype: A phenotyping pipeline for python","volume":"13","author":"L\u00fcrig","year":"2022","journal-title":"Methods in Ecology and Evolution"},{"issue":"7","key":"2025090603071269700_bib17","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1111\/2041-210X.13174","article-title":"Pavo 2: New tools for the spectral and spatial analysis of colour in R","volume":"10","author":"Maia","year":"2019","journal-title":"Methods in Ecology and Evolution"},{"issue":"9","key":"2025090603071269700_bib18","doi-asserted-by":"publisher","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":"Mathis","year":"2018","journal-title":"Nature Neuroscience"},{"issue":"6","key":"2025090603071269700_bib19","doi-asserted-by":"publisher","first-page":"rsos.240113","DOI":"10.1098\/rsos.240113","article-title":"How many specimens make a sufficient training set for automated three-dimensional feature extraction?","volume":"11","author":"Mulqueeney","year":"2024","journal-title":"Royal Society Open Science"},{"key":"2025090603071269700_bib20","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"33rd Conference on Neural Information Processing Systems (NeurIPS 2019)"},{"issue":"5","key":"2025090603071269700_bib21","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1111\/2041-210X.12036","article-title":"Implementing image analysis in laboratory-based experimental systems for ecology and evolution: A hands-on guide","volume":"4","author":"Pennekamp","year":"2013","journal-title":"Methods in Ecology and Evolution"},{"issue":"4","key":"2025090603071269700_bib22","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1111\/2041-210X.13373","article-title":"ML-morph: A fast, accurate and general approach for automated detection and landmarking of biological structures in images","volume":"11","author":"Porto","year":"2020","journal-title":"Methods in Ecology and Evolution"},{"issue":"1","key":"2025090603071269700_bib23","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1111\/mec.13332","article-title":"Shared and nonshared genomic divergence in parallel ecotypes of L ittorina saxatilis at a local scale","volume":"25","author":"Ravinet","year":"2016","journal-title":"Molecular Ecology"},{"issue":"3","key":"2025090603071269700_bib24","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1111\/2041-210X.13776","article-title":"Argos: A toolkit for tracking multiple animals in complex visual environments","volume":"13","author":"Ray","year":"2022","journal-title":"Methods in Ecology and Evolution"},{"key":"2025090603071269700_bib25","article-title":"tpsDig, Digitize Landmarks and Outlines (Version 2.05)","author":"Rohlf","year":"2006"},{"issue":"12","key":"2025090603071269700_bib26","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1111\/2041-210X.13712","article-title":"Sashimi: A toolkit for facilitating high-throughput organismal image segmentation using deep learning","volume":"12","author":"Schwartz","year":"2021","journal-title":"Methods in Ecology and Evolution"},{"issue":"1","key":"2025090603071269700_bib27","doi-asserted-by":"publisher","first-page":"20915","DOI":"10.1038\/s41598-024-71763-y","article-title":"Leveraging deep learning and computer vision technologies to enhance management of coastal fisheries in the Pacific region","volume":"14","author":"Shedrawi","year":"2024","journal-title":"Scientific Reports"},{"key":"2025090603071269700_bib28","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","article-title":"A survey on deep transfer learning","volume-title":"Artificial neural networks and machine learning\u2014ICANN 2018","author":"Tan","year":"2018"},{"key":"2025090603071269700_bib29","first-page":"8026","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025090603071269700_bib30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-386903-6.00001-0","volume-title":"Geometric morphometrics for biologists: A primer","author":"Zelditch","year":"2004","edition":"2nd\u00a0Edition"}],"container-title":["Journal of Evolutionary Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jeb\/advance-article-pdf\/doi\/10.1093\/jeb\/voaf058\/63181243\/voaf058.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jeb\/article-pdf\/38\/8\/1152\/63181243\/voaf058.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jeb\/article-pdf\/38\/8\/1152\/63181243\/voaf058.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T07:07:22Z","timestamp":1757142442000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jeb\/article\/38\/8\/1152\/8131513"}},"subtitle":[],"editor":[{"given":"Max","family":"Reuter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]},{"given":"Carmelo","family":"Fruciano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,14]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,9,6]]}},"URL":"https:\/\/doi.org\/10.1093\/jeb\/voaf058","relation":{},"ISSN":["1420-9101"],"issn-type":[{"value":"1420-9101","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,8]]},"published":{"date-parts":[[2025,5,14]]}}}