{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T20:38:13Z","timestamp":1790887093292,"version":"4.1.0"},"reference-count":30,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQ20H140007"],"award-info":[{"award-number":["LQ20H140007"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Oral Pathology Medicine"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early diagnosis in oral cancer is essential to reduce both morbidity and mortality. This study explores the use of uncertainty estimation in deep learning for early oral cancer diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We develop a Bayesian deep learning model termed \u2018Probabilistic HRNet\u2019, which utilizes the ensemble MC dropout method on HRNet. Additionally, two oral lesion datasets with distinct distributions are created. We conduct a retrospective study to assess the predictive performance and uncertainty of Probabilistic HRNet across these datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Probabilistic HRNet performs optimally on the In\u2010domain test set, achieving an F1 score of 95.3% and an AUC of 96.9% by excluding the top 30% high\u2010uncertainty samples. For evaluations on the Domain\u2010shift test set, the results show an F1 score of 64.9% and an AUC of 80.3%. After excluding 30% of the high\u2010uncertainty samples, these metrics improve to an F1 score of 74.4% and an AUC of 85.6%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Redirecting samples with high uncertainty to experts for subsequent diagnosis significantly decreases the rates of misdiagnosis, which highlights that uncertainty estimation is vital to ensure safe decision making for computer\u2010aided early oral cancer diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/jop.13536","type":"journal-article","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T00:24:00Z","timestamp":1713399840000},"page":"294-302","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep neural network uncertainty estimation for early oral cancer diagnosis"],"prefix":"10.1111","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4680-3189","authenticated-orcid":false,"given":"Huiping","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Stomatology The First Affiliated Hospital, Zhejiang University School of Medicine  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4080-134X","authenticated-orcid":false,"given":"Hanshen","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligent Transportation, Zhejiang Institute of Communications  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2431-0121","authenticated-orcid":false,"given":"Jun","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Stomatology The First Affiliated Hospital, Zhejiang University School of Medicine  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"issue":"1","key":"e_1_2_10_2_1","first-page":"29","article-title":"A clinico\u2010pathological study of oral cancers","volume":"27","author":"Ayaz B","year":"2011","journal-title":"Biomedica"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/jop.12625"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1097\/CEJ.0b013e32834fdb6d"},{"key":"e_1_2_10_6_1","first-page":"358","volume-title":"Contemporary Oral Oncology: Biology, Epidemiology, Etiology and Prevention","author":"Kuriakose MA","year":"2017"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oooo.2018.02.020"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tice.2018.06.004"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-018-1836-1"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.9.005318"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.26.8.086007"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"HeinM AndriushchenkoM BitterwolfJ.Why relu networks yield high\u2010confidence predictions far away from the training data and how to mitigate the problem. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2019: 41\u201350.","DOI":"10.1109\/CVPR.2019.00013"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34025-x"},{"issue":"1","key":"e_1_2_10_14_1","first-page":"1","article-title":"ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning","volume":"9","author":"R\u0105czkowski \u0141","year":"2019","journal-title":"Sci Rep"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104418"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"HuS WorrallD KnegtS et al.Supervised uncertainty quantification for segmentation with multiple annotations. In: International Conference on Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI); 2019: 137\u2013145.","DOI":"10.1007\/978-3-030-32245-8_16"},{"key":"e_1_2_10_17_1","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan B","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_10_18_1","unstructured":"GalY GhahramaniZ.Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning (PMLR); 2016: 1050\u20131059."},{"key":"e_1_2_10_19_1","article-title":"Transforming neural\u2010net output levels to probability distributions","volume":"3","author":"Denker J","year":"1990","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"issue":"1","key":"e_1_2_10_21_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2022.105737"},{"key":"e_1_2_10_23_1","unstructured":"Kaggle.Oral cancer (lips and tongue) images; 2020.https:\/\/www.kaggle.com\/datasets\/shivam17299\/oral-cancer-lips-and-tongue-images"},{"key":"e_1_2_10_24_1","unstructured":"ChandrashekarHS Geetha KiranA MuraliS et al.Oral images dataset. Mendeley Data V2; 2021."},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR et al.ImageNet: a large\u2010scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009: 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1974.tb00994.x"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS et al.Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016: 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101557"}],"container-title":["Journal of Oral Pathology &amp; Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jop.13536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T22:14:51Z","timestamp":1715724891000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jop.13536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1111\/jop.13536"],"URL":"https:\/\/doi.org\/10.1111\/jop.13536","archive":["Portico"],"relation":{},"ISSN":["0904-2512","1600-0714"],"issn-type":[{"value":"0904-2512","type":"print"},{"value":"1600-0714","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,17]]},"assertion":[{"value":"2023-10-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}