{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:46:31Z","timestamp":1767339991105,"version":"3.40.4"},"reference-count":49,"publisher":"IOP Publishing","issue":"8","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"tdm","delay-in-days":2,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"International Alliance for Cancer Early Detection","award":["C28070\/A30912"],"award-info":[{"award-number":["C28070\/A30912"]}]},{"DOI":"10.13039\/501100000770","name":"University of Manchester","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000770","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Research Grant Council of Hong Kong Special Administrative Region, China","award":["General Research Fund\/CityU 11205421"],"award-info":[{"award-number":["General Research Fund\/CityU 11205421"]}]},{"name":"Canary Center at Standford University"},{"DOI":"10.13039\/501100000735","name":"University of Cambridge","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000735","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018071","name":"OHSU Knight Cancer Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018071","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000765","name":"University College London","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000765","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2025,4,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective.<\/jats:italic> Prostate lesion segmentation from multiparametric magnetic resonance images is particularly challenging due to the limited availability of labeled data. This scarcity of annotated images makes it difficult for supervised models to learn the complex features necessary for accurate lesion detection and segmentation. <jats:italic>Approach.<\/jats:italic> We proposed a novel semi-supervised algorithm that embeds prototype learning into mean-teacher (MT) training to improve the feature representation for unlabeled data. In this method, pseudo-labels generated by the teacher network simultaneously serve as supervision for unlabeled prototype-based segmentation. By enabling prototype segmentation to operate across labeled and unlabeled data, the network enriches the pool of \u201clesion representative prototypes\u201d, and allows prototypes to flow bidirectionally\u2014from support-to-query and query-to-support paths. This intersected, bidirectional information flow strengthens the model\u2019s generalization ability. This approach is distinct from the MT algorithm as it involves few-shot training and differs from prototypical learning for adopting unlabeled data for training. <jats:italic>Main results.<\/jats:italic> This study evaluated multiple datasets with 767 patients from three different institutions, including the publicly available PROSTATEx\/PROSTATEx2 datasets as the holdout institute for reproducibility. The experimental results showed that the proposed algorithm outperformed state-of-the-art semi-supervised methods with limited labeled data, observing an improvement in Dice similarity coefficient with increasing labeled data, ranging from 0.04 to 0.09. <jats:italic>Significance.<\/jats:italic> Our method shows promise in improving segmentation outcomes with limited labeled data and potentially aiding clinicians in making informed patient treatment and management decisions<jats:sup>8<\/jats:sup>\n                  <jats:fn id=\"pmbadc182fn2\">\n                     <jats:label>8<\/jats:label>\n                     <jats:p>The algorithm implementation has been made available on GitHub via git@github.com:yanwenCi\/semi-proto-seg.git.<\/jats:p>\n                  <\/jats:fn>.<\/jats:p>","DOI":"10.1088\/1361-6560\/adc182","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T22:55:42Z","timestamp":1742252142000},"page":"085020","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A semi-supervised prototypical network for prostate lesion segmentation from multimodality MRI"],"prefix":"10.1088","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3962-5994","authenticated-orcid":true,"given":"Wen","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-0486","authenticated-orcid":false,"given":"Yipeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4401-5311","authenticated-orcid":false,"given":"Qianye","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1184-7421","authenticated-orcid":false,"given":"Yunguan","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9594-9638","authenticated-orcid":true,"given":"Tom","family":"Syer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8903-1561","authenticated-orcid":false,"given":"Zhe","family":"Min","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1014-0870","authenticated-orcid":false,"given":"Shonit","family":"Punwani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4230-0338","authenticated-orcid":false,"given":"Mark","family":"Emberton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2916-655X","authenticated-orcid":false,"given":"Dean C","family":"Barratt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carmen C M","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5237-2410","authenticated-orcid":true,"given":"Bernard","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"pmbadc182bib1","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1016\/S0140-6736(16)32401-1","article-title":"Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study","volume":"389","author":"Ahmed","year":"2017","journal-title":"Lancet"},{"key":"pmbadc182bib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ejrad.2018.02.006","article-title":"Prospective evaluation of fluciclovine (18F) PET-CT and MRI in detection of recurrent prostate cancer in non-prostatectomy patients","volume":"102","author":"Akin-Akintayo","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"pmbadc182bib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107624","article-title":"Automatic detection of prostate cancer grades and chronic prostatitis in biparametric MRI","volume":"239","author":"Bashkanov","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbadc182bib4","first-page":"pp 205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"pmbadc182bib5","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TMI.2022.3184675","article-title":"Generative consistency for semi-supervised cerebrovascular segmentation from TOF-MRA","volume":"42","author":"Chen","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"pmbadc182bib6"},{"key":"pmbadc182bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108511","article-title":"SIAM: spatial and intensity awareness module for cerebrovascular segmentation","volume":"260","author":"Chen","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbadc182bib8","first-page":"pp 1","article-title":"Are 3D better than 2D convolutional neural networks for medical imaging semantic segmentation?","author":"Crespi","year":"2022"},{"key":"pmbadc182bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109647","article-title":"Quality control and whole-gland, zonal and lesion annotations for the PROSTATEx challenge public dataset","volume":"138","author":"Cuocolo","year":"2021","journal-title":"Eur. J. Radiol."},{"key":"pmbadc182bib10","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.eururo.2010.12.009","article-title":"Magnetic resonance imaging for the detection, localisation and characterisation of prostate cancer: recommendations from a European consensus meeting","volume":"59","author":"Dickinson","year":"2011","journal-title":"Eur. Urology"},{"article-title":"An image is worth 16x16 words: transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"pmbadc182bib11"},{"key":"pmbadc182bib12","doi-asserted-by":"publisher","first-page":"5216","DOI":"10.1002\/mp.15687","article-title":"MRI-based prostate and dominant lesion segmentation using cascaded scoring convolutional neural network","volume":"49","author":"Eidex","year":"2022","journal-title":"Med. Phys."},{"key":"pmbadc182bib13","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1001\/jama.1994.03510290050036","article-title":"Pathologic and clinical findings to predict tumor extent of nonpalpable (Stage T1 c) prostate cancer","volume":"271","author":"Epstein","year":"1994","journal-title":"JAMA"},{"key":"pmbadc182bib14","first-page":"pp 8334","article-title":"Adaptive prototype learning and allocation for few-shot segmentation","author":"Gen","year":"2021"},{"key":"pmbadc182bib15","first-page":"pp 26007","article-title":"Semi-supervised semantic segmentation with prototype-based consistency regularization","volume":"vol 35","author":"Haiming","year":"2022"},{"key":"pmbadc182bib16","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1016\/j.bbe.2020.07.011","article-title":"Prostate lesion segmentation in MR images using radiomics based deeply supervised U-Net","volume":"40","author":"Hambarde","year":"2020","journal-title":"Biocybern. Biomed. Eng."},{"key":"pmbadc182bib17","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1016\/j.eururo.2018.08.007","article-title":"The SmartTarget biopsy trial: a prospective, within-person randomised, blinded trial comparing the accuracy of visual-registration and magnetic resonance imaging\/ultrasound image-fusion targeted biopsies for prostate cancer risk stratification","volume":"75","author":"Hamid","year":"2019","journal-title":"Eur. Urology"},{"key":"pmbadc182bib18","first-page":"pp 120","article-title":"Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features","author":"Isensee","year":"2018"},{"key":"pmbadc182bib19","doi-asserted-by":"publisher","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":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbadc182bib20","doi-asserted-by":"publisher","first-page":"5489","DOI":"10.1002\/mp.16374","article-title":"Prostate cancer segmentation from MRI by a multistream fusion encoder","volume":"50","author":"Jiang","year":"2023","journal-title":"Med. Phys."},{"key":"pmbadc182bib21","first-page":"pp 36","article-title":"Prototypical contrast adaptation for domain adaptive semantic segmentation","author":"Jiang","year":"2022"},{"key":"pmbadc182bib22","first-page":"pp 770","article-title":"Deep residual learning for image recognition","author":"Kaiming","year":"2016"},{"key":"pmbadc182bib23","first-page":"pp 4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"pmbadc182bib24","first-page":"pp 1205","article-title":"Semi-supervised semantic segmentation with directional context-aware consistency","author":"Lai","year":"2021"},{"key":"pmbadc182bib25","first-page":"p 896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"vol 3","author":"Lee","year":"2013"},{"key":"pmbadc182bib26","first-page":"pp 5267","article-title":"Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference","author":"Lee","year":"2019"},{"key":"pmbadc182bib27","doi-asserted-by":"publisher","DOI":"10.7937\/K9TCIA.2017.MURS5CL","article-title":"PROSTATEx challenge data","author":"Litjens","year":"2017","journal-title":"Cancer Imaging Arch."},{"key":"pmbadc182bib28","first-page":"pp 12674","article-title":"Semi-supervised semantic segmentation with cross-consistency training","author":"Ouali","year":"2020"},{"key":"pmbadc182bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106018","article-title":"Semi-supervised GAN-based radiomics model for data augmentation in breast ultrasound mass classification","volume":"203","author":"Pang","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbadc182bib30","first-page":"p 32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"pmbadc182bib31","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.inffus.2020.09.006","article-title":"A survey on deep learning in medicine: Why, how and when?","volume":"66","author":"Piccialli","year":"2021","journal-title":"Inf. Fusion"},{"key":"pmbadc182bib32","first-page":"pp 262","article-title":"A location-sensitive local prototype network for few-shot medical image segmentation","author":"Qinji","year":"2021"},{"key":"pmbadc182bib33","first-page":"pp 234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"pmbadc182bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"pmbadc182bib35","first-page":"pp 552","article-title":"Shape-aware semi-supervised 3D semantic segmentation for medical images","author":"Shuailin","year":"2020"},{"key":"pmbadc182bib36","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1038\/bjc.2017.57","article-title":"The PICTURE study: diagnostic accuracy of multiparametric MRI in men requiring a repeat prostate biopsy","volume":"116","author":"Simmons","year":"2017","journal-title":"Br. J. Cancer"},{"key":"pmbadc182bib37","first-page":"p 30","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017"},{"key":"pmbadc182bib38","first-page":"pp 1","article-title":"Semantic segmentation using generative adversarial networks with a feature reconstruction loss","author":"Sohaliya","year":"2021"},{"key":"pmbadc182bib39","first-page":"p 30","article-title":"Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017"},{"key":"pmbadc182bib40","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.2.021208","article-title":"PSNet: prostate segmentation on MRI based on a convolutional neural network","volume":"5","author":"Tian","year":"2018","journal-title":"J. Med. Imaging"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"pmbadc182bib41"},{"key":"pmbadc182bib42","first-page":"pp 9197","article-title":"Panet: few-shot image semantic segmentation with prototype alignment","author":"Wang","year":"2019"},{"key":"pmbadc182bib43","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.eururo.2015.08.052","article-title":"PI-RADS prostate imaging\u2013reporting and data system: 2015, version 2","volume":"69","author":"Weinreb","year":"2016","journal-title":"Eur. Urology"},{"key":"pmbadc182bib44","first-page":"pp 128","article-title":"The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation","author":"Yan","year":"2022"},{"key":"pmbadc182bib45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108161","article-title":"ProDiv: prototype-driven consistent pseudo-bag division for whole-slide image classification","volume":"249","author":"Yang","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbadc182bib46","first-page":"pp 6023","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"article-title":"Comparison of 2D vs. 3D u-net organ segmentation in abdominal 3D ct images","year":"2021","author":"Zettler","key":"pmbadc182bib47"},{"key":"pmbadc182bib48","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"pmbadc182bib49","first-page":"pp 2079","article-title":"Collaborative learning of semi-supervised segmentation and classification for medical images","author":"Zhou","year":"2019"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T12:57:06Z","timestamp":1745326626000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adc182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,20]]},"references-count":49,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,4,22]]},"published-print":{"date-parts":[[2025,4,20]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/adc182","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"type":"print","value":"0031-9155"},{"type":"electronic","value":"1361-6560"}],"subject":[],"published":{"date-parts":[[2025,4,20]]},"assertion":[{"value":"A semi-supervised prototypical network for prostate lesion segmentation from multimodality MRI","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-11-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-03-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}