{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:43:54Z","timestamp":1791395034579,"version":"4.3.3"},"reference-count":51,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271337"],"award-info":[{"award-number":["62271337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371326"],"award-info":[{"award-number":["62371326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371328"],"award-info":[{"award-number":["62371328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20231310"],"award-info":[{"award-number":["BK20231310"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742568"],"award-info":[{"award-number":["2023M742568"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Deep learning\u2010based segmentation methods for optical coherence tomography (OCT) have demonstrated outstanding performance. However, the stochastic distribution of training data and the inherent limitations of deep neural networks introduce uncertainty into the segmentation process. Accurately estimating this uncertainty is essential for generating reliable confidence assessments and improving model predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To address these challenges, we propose a novel uncertainty\u2010guided cross\u2010layer fusion network (UGCFNet) for retinal OCT segmentation. UGCFNet integrates uncertainty quantification into the training process of deep neural networks and leverages this uncertainty to enhance segmentation accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Our model employs an encoder\u2013decoder architecture that quantitatively assesses uncertainty at multiple stages, directing the network's focus toward regions with higher uncertainty. By facilitating cross\u2010layer feature fusion, UGCFNet enhances the comprehensive understanding of both semantic information and morphological details. Additionally, we incorporate an improved Bayesian neural network loss function alongside an uncertainty\u2010aware loss function, enabling the network to effectively utilize these mechanisms for better uncertainty modeling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We conducted extensive experiments on the publicly available AI\u2010Challenger and OIMHS OCT segmentation datasets. The training, validation, and testing sets of the AI\u2010Challenger dataset are comprised of 32, 8, and 43 OCT volumes, yielding a total of 4096, 1024, and 5504 B\u2010scans, respectively. The training, validation, and testing sets of the OIMHS dataset consist of 100, 25, and 25 OCT volumes, resulting in 2,310, 798, and 751 B\u2010scans, respectively. The results demonstrate that UGCFNet achieves state\u2010of\u2010the\u2010art performance, with average Dice similarity coefficients of 79.47% and 93.22% on the respective datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our proposed UGCFNet significantly advances retinal OCT segmentation by integrating uncertainty guidance and cross\u2010level feature fusion, offering more reliable and accurate segmentation outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.18102","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T06:57:31Z","timestamp":1756796251000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Uncertainty\u2010guided cross\u2010level fusion network for retinal OCT image segmentation"],"prefix":"10.1002","volume":"52","author":[{"given":"Jiaxin","family":"Wang","sequence":"first","affiliation":[{"name":"MIPAV Lab School of Electronics and Information Engineering Soochow University Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifang","family":"Zhu","sequence":"additional","affiliation":[{"name":"MIPAV Lab School of Electronics and Information Engineering Soochow University Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dehui","family":"Xiang","sequence":"additional","affiliation":[{"name":"MIPAV Lab School of Electronics and Information Engineering Soochow University Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjian","family":"Chen","sequence":"additional","affiliation":[{"name":"MIPAV Lab School of Electronics and Information Engineering Soochow University Suzhou China"},{"name":"The State Key Laboratory of Radiation Medicine and Protection Soochow University  Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering Soochow University  Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology Shanghai Tenth People's Hospital, Tongji University School of Medicine  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"The Institute of High Performance Computing (IHPC) Agency for Science, Technology and Research (A*STAR)  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Shi","sequence":"additional","affiliation":[{"name":"MIPAV Lab School of Electronics and Information Engineering Soochow University Suzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,9]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1957169"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0039\u20106257(97)00132\u2010x"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1159\/000360461"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.05.002"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2004.06.002"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3112716"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2983721"},{"key":"e_1_2_9_9_1","doi-asserted-by":"crossref","unstructured":"YangZ FarsiuS Directional connectivity\u2010based segmentation of medical images.IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2023:11525\u201011535. doi:10.1109\/CVPR52729.2023.01109","DOI":"10.1109\/CVPR52729.2023.01109"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.538959"},{"key":"e_1_2_9_11_1","unstructured":"KendallA GalY What uncertainties do we need in bayesian deep learning for computer vision? Neural Inform Process Syst.2017:5580\u20105590. doi:10.5555\/3295222.3295309"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102539"},{"key":"e_1_2_9_13_1","unstructured":"YarinG ZoubinG Dropout as a bayesian approximation: representing model uncertainty in deep learning.International Conference on Machine Learning.2016:1050\u20101059. doi:10.5555\/3045390.3045502"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.103"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010031\u201016452\u20101_48"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602610"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010031\u201016452\u20101_51"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"YangF ZhaiQ LiX et\u00a0al.Uncertainty\u2010guided transformer reasoning for camouflaged object detection.IEEE\/CVF International Conference on Computer Vision.2021:4126\u20104135. doi:10.1109\/ICCV48922.2021.00411","DOI":"10.1109\/ICCV48922.2021.00411"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370685"},{"key":"e_1_2_9_20_1","first-page":"6965","article-title":"A probabilistic U\u2010net for segmentation of ambiguous images","author":"Kohl S","year":"2018","journal-title":"Neural Inf Process Syst"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2919951"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103104"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108458"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"KendallA GalY CipollaR Multi\u2010task learning using uncertainty to weigh losses for scene geometry and semantics.IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2018:7482\u20107491. doi:10.1109\/CVPR.2018.00781","DOI":"10.1109\/CVPR.2018.00781"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"PengY ChenH LinC et\u00a0al.Uncertainty\u2010aware explainable recommendation with large language models.International Joint Conference on Neural Networks (IJCNN).2024:1\u20108. doi:10.1109\/ijcnn60899.2024.10651104","DOI":"10.1109\/IJCNN60899.2024.10651104"},{"key":"e_1_2_9_26_1","unstructured":"TsaiTY LinL HuS et\u00a0al.UU\u2010Mamba: Uncertainty\u2010aware U\u2010Mamba for cardiovascular segmentation.2024.http:\/\/arxiv.org\/abs\/2409.14305"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201042444\u20107"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102719"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597\u2010023\u201002675\u20101"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010319\u201024574\u2010428"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.02.011"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3228285"},{"key":"e_1_2_9_33_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et\u00a0al. An Image is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale.2021.http:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103223"},{"key":"e_1_2_9_35_1","first-page":"282","article-title":"Uncertainty guided semi\u2010supervised segmentation of retinal layers in OCT images","author":"Sedai S","year":"2019","journal-title":"Med. Image Comput. Computer Assist Interven"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ Deep residual learning for image recognition.IEEE Conference on Computer Vision and Pattern Recognition.2016:770\u2010778. doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"RahmanMM MunirM MarculescuR EMCAD: efficient multi\u2010Scale convolutional attention decoding for medical image segmentation.IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2024:11769\u201011779. doi:10.1109\/CVPR52733.2024.01118","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"YuT LiD YangY HospedalesT XiangT Robust person re\u2010Identification by modelling feature uncertainty.IEEE\/CVF International Conference on Computer Vision.2019:552\u2010561. doi:10.1109\/ICCV.2019.00064","DOI":"10.1109\/ICCV.2019.00064"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28418"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11090940"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201032239\u20107_80"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2903562"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201000889\u20105_1"},{"key":"e_1_2_9_44_1","unstructured":"OktayO SchlemperJ FolgocLL et\u00a0al.Attention U\u2010Net: Learning where to look for the pancreas.2018.http:\/\/arxiv.org\/abs\/1804.03999"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_9_47_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT Fully convolutional networks for semantic segmentation.IEEE Conference on Computer Vision and Pattern Recognition.2015:3431\u20103440. doi:10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010031\u201016452\u20101_47"},{"key":"e_1_2_9_49_1","article-title":"Uncertainty evaluation metric for brain tumour segmentation","author":"Mehta R","year":"2020","journal-title":"Med Imaging Deep Learning (MIDL)"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101732"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201000949\u20106_26"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201032245\u20108_16"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.18102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:01:44Z","timestamp":1765339304000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.18102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":51,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1002\/mp.18102"],"URL":"https:\/\/doi.org\/10.1002\/mp.18102","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"2024-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e18102"}}