{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:09:02Z","timestamp":1783573742147,"version":"3.55.0"},"reference-count":22,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":349,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Healthcare Tech Letters"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Polyps are abnormal tissue growths in the colon that may develop into colorectal cancer if left undetected. Accurate segmentation in medical imaging is essential for early diagnosis and treatment. Although deep learning has greatly improved polyp segmentation, its dependence on large annotated datasets and substantial computational resources hampers generalization across diverse clinical settings. To overcome these challenges, we propose PRISM, a momentum\u2010based self\u2010distillation method that improves segmentation performance without introducing additional inference cost. Instead of storing or reusing past predictions, PRISM constructs a temporally smoothed teacher model by applying an exponential moving average (EMA) to the model's weights throughout training. This momentum\u2010based teacher provides stable and adaptive supervision signals that co\u2010evolve with the student model. We evaluate PRISM on colonoscopy datasets collected from five distinct medical centres and validate its generalization on an unseen independent dataset. PRISM achieves a Dice score of 0.81 and an IoU of 0.75, outperforming baseline and conventional self\u2010distillation methods. Ablation studies confirm the effectiveness of the EMA\u2010based teacher model in improving segmentation accuracy. PRISM offers a computationally efficient and generalizable solution for polyp segmentation tasks. The code is available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/TugberkErol\/PRISM\">https:\/\/github.com\/TugberkErol\/PRISM<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1049\/htl2.70050","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T09:31:53Z","timestamp":1765877513000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PRISM: Past\u2010Regularized Iterative Self\u2010Distillation With Momentum for Polyp Segmentation"],"prefix":"10.1049","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0831-7307","authenticated-orcid":false,"given":"Tugberk","family":"Erol","sequence":"first","affiliation":[{"name":"Graduate School of Natural and Applied Sciences Gazi University Ankara Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuba","family":"Caglikantar","sequence":"additional","affiliation":[{"name":"Department of Software Engineering Faculty of Engineering and Natural Sciences Ankara Yildirim Beyazit University Ankara Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2083-4999","authenticated-orcid":false,"given":"Duygu","family":"Sarikaya","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Leeds Leeds UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"crossref","unstructured":"Y.Shen L.Xu Y.Yang Y.Li andY.Guo \u201cSelf\u2010Distillation From the Last Mini\u2010Batch for Consistency Regularization \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 11943\u201311952.","DOI":"10.1109\/CVPR52688.2022.01164"},{"key":"e_1_2_10_3_1","unstructured":"A.Romero N.Ballas S. E.Kahou A.Chassang C.Gatta andY.Bengio \u201cFitNets: Hints for Thin Deep Nets \u201dpreprint arXiv December 21 2014 https:\/\/arxiv.org\/abs\/1412.6550."},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"L.Zhang J.Song A.Gao J.Chen C.Bao andK.Ma \u201cBe Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 3713\u20133722.","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_2_10_5_1","unstructured":"T.Furlanello Z.Lipton M.Tschannen L.Itti andA.Anandkumar \u201cBorn again neural networks \u201d inProceedings of the International Conference on Machine Learning (ICML)(PMLR 2018) 1607\u20131616."},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","unstructured":"W.Park D.Kim Y.Lu andM.Cho \u201cRelational Knowledge Distillation \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2019) 3967\u20133976.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_8_1","unstructured":"C.\u2010H.Huang H.\u2010Y.Wu and Y.\u2010L.Lin \u201cHardNet\u2010MSEG: A Simple Encoder\u2010Decoder Polyp Segmentation Neural Network That Achieves Over 0.9 Mean Dice and 86 FPS \u201dpreprint arXiv January 18 2021 https:\/\/arxiv.org\/abs\/2101.07172."},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"e_1_2_10_11_1","first-page":"1372","volume-title":"Proceedings of the Medical Imaging With Deep Learning (MIDL)","author":"Jha D.","year":"2023"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"L.\u2010C.Chen Y.Zhu G.Papandreou F.Schroff andH.Adam \u201cEncoder\u2010Decoder With Atrous Separable Convolution for Semantic Image Segmentation \u201d inProceedings of the European Conference on Computer Vision (ECCV)(Springer 2018) 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_10_14_1","unstructured":"G.Hinton \u201cDistilling the Knowledge in a Neural Network \u201dpreprint arXiv March 9 2015 https:\/\/arxiv.org\/abs\/1503.02531."},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3098703"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16440-8_52"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"K.He H.Fan Y.Wu S.Xie andR.Girshick \u201cMomentum Contrast for Unsupervised Visual Representation Learning \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_28"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01981-y"},{"key":"e_1_2_10_20_1","unstructured":"I. Loshchilov andF.Hutter \u201cDecoupled weight decay regularization \u201dpreprint arXiv November 14 2017 https:\/\/arxiv.org\/abs\/1711.05101."},{"key":"e_1_2_10_21_1","doi-asserted-by":"crossref","unstructured":"J.Long E.Shelhamer andT.Darrell \u201cFully Convolutional Networks for Semantic Segmentation \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2015) 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","unstructured":"H.Zhao J.Shi X.Qi X.Wang andJ.Jia \u201cPyramid Scene Parsing Network \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2017) 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"K.He X.Zhang S.Ren andJ.Sun \u201cDeep Residual Learning for Image Recognition \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2016) 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Healthcare Technology Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl2.70050","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/htl2.70050","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl2.70050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T12:10:20Z","timestamp":1772971820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/htl2.70050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/htl2.70050"],"URL":"https:\/\/doi.org\/10.1049\/htl2.70050","archive":["Portico"],"relation":{},"ISSN":["2053-3713","2053-3713"],"issn-type":[{"value":"2053-3713","type":"print"},{"value":"2053-3713","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70050"}}