{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:29:13Z","timestamp":1773102553966,"version":"3.50.1"},"reference-count":25,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"vor","delay-in-days":18,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate structure contouring on computed tomography (CT) is critical for prostate cancer radiotherapy, but it remains labour intensive and prone to interobserver variability, particularly for small, low\u2010contrast organs such as the prostate, seminal vesicles (SV) and penile bulb (PB). Deep\u2010learning models can automate this task. However, they typically require large, fully labelled datasets that are often unavailable in clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study evaluated whether self\u2010supervised (label\u2010free) slice\u2010prediction pretraining could enhance segmentation performance, especially in scenarios with limited annotated data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We used 322 pelvic CT volumes (215 from UMMC, 107 from TCIA), split 80:20 into training and testing sets (258 training, 64 testing patients). A novel lightweight 2D U\u2010Net encoder was first pretrained on unlabelled data using a slice\u2010prediction task across axial, sagittal, and coronal planes. The pretrained model was then fine\u2010tuned for multi\u2010class segmentation using either the full dataset or a reduced subset of 60 labelled patients. Baselines trained from scratch with 1\u2010channel or 3\u2010channel input were included for comparison. Segmentation accuracy was assessed using mean distance agreement (MDA) and Dice similarity coefficient (DSC). Paired\n                      <jats:italic>t<\/jats:italic>\n                      \u2010tests with Bonferroni correction were applied to assess statistical significance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Models with self\u2010supervised pretraining achieved consistently lower MDA across all major pelvic structures. Notable improvements included reductions in bladder MDA from 0.600 mm to 0.547 mm, femoral heads from 1.370 mm to 0.994 mm, PB from 1.470 mm to 1.283 mm, rectum from 0.792 mm to 0.669 mm, prostate from 1.281 mm to 1.183 mm, and SV from 1.175 mm to 0.893 mm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Self\u2010supervised pretraining via slice prediction enables anatomically informed feature learning and improves segmentation robustness under limited data conditions. This strategy enhances accuracy without reliance on manual labels during pretraining and is compatible with computationally lightweight architectures, making it well\u2010suited in resource\u2010constrained clinical environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70357","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:20:22Z","timestamp":1771518022000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning anatomy from unlabelled CT volumes: A self\u2010supervised framework for improving prostate radiotherapy segmentation"],"prefix":"10.1002","volume":"53","author":[{"given":"Diyana Afrina","family":"Hizam","sequence":"first","affiliation":[{"name":"Department of Clinical Oncology Faculty of Medicine Universiti Malaya  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngie Min","family":"Ung","sequence":"additional","affiliation":[{"name":"Department of Clinical Oncology Faculty of Medicine Universiti Malaya  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marniza","family":"Saad","sequence":"additional","affiliation":[{"name":"Department of Clinical Oncology Faculty of Medicine Universiti Malaya  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Firdaus Mohd","family":"Salleh","sequence":"additional","affiliation":[{"name":"Department of Clinical Oncology Faculty of Medicine Universiti Malaya  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asyraf","family":"Muaadz","sequence":"additional","affiliation":[{"name":"Department of Clinical Oncology Faculty of Medicine Universiti Malaya  Kuala Lumpur Malaysia"},{"name":"Department of Clinical Oncology Universiti Malaya Medical Centre  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li Kuo","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Imaging Universiti Malaya  Kuala Lumpur Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2015.33.7_suppl.94"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.06.007"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.4236\/ijmpcero.2021.102005"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13246\u2010024\u201001411\u20102"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880\u2010023\u201000974\u2010y"},{"key":"e_1_2_8_7_1","first-page":"234","volume-title":"U\u2010net: Convolutional networks for biomedical image segmentation","author":"Ronneberger O","year":"2015"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TTS.2023.3234203"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2023.100413"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.980312"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3167384"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010023\u201046433\u20100"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2012.01.023"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.02.019"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360-3016(02)02805-5"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101840"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2023.100092"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103150"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10020207"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129199"},{"key":"e_1_2_8_23_1","unstructured":"AliY TalebA H\u00f6hneMM\u2010C LippertC.Self\u2010supervised learning for 3d medical image analysis using 3d simclr and monte carlo dropout. arXiv preprint arXiv:210914288.2021;"},{"key":"e_1_2_8_24_1","first-page":"472","volume-title":"Self\u2010supervised pretraining for 2d medical image segmentation","author":"Kalapos A","year":"2022"},{"key":"e_1_2_8_25_1","first-page":"21271","article-title":"Bootstrap your own latent\u2010a new approach to self\u2010supervised learning","volume":"33","author":"Grill J\u2010B","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230477"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70357","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70357","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T13:34:18Z","timestamp":1773063258000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/mp.70357"],"URL":"https:\/\/doi.org\/10.1002\/mp.70357","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"2025-10-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70357"}}