{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:04:27Z","timestamp":1790269467646,"version":"4.1.0"},"reference-count":0,"publisher":"SPIE-Intl Soc Optical Eng","issue":"11","license":[{"start":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:00:00Z","timestamp":1667433600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Biomed. Opt."],"published-print":{"date-parts":[[2022,11,3]]},"abstract":"<jats:p>SignificanceOral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output.AimWe aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions.ApproachThis work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists.ResultsThe proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings.ConclusionsOur study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model\u2019s prediction can be improved.<\/jats:p>","DOI":"10.1117\/1.jbo.27.11.115001","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:56:01Z","timestamp":1667436961000},"page":"1-11","source":"Crossref","is-referenced-by-count":9,"title":["Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images"],"prefix":"10.1117","volume":"27","author":[{"given":"Bofan","family":"Song","sequence":"first","affiliation":[{"name":"Wyant College of Optical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaobai","family":"Li","sequence":"additional","affiliation":[{"name":"Wyant College of Optical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumsum","family":"Sunny","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Cancer Ctr."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4594-8674","authenticated-orcid":false,"given":"Keerthi","family":"Gurushanth","sequence":"additional","affiliation":[{"name":"KLE Society's Institute of Dental Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pramila","family":"Mendonca","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Cancer Ctr."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nirza","family":"Mukhia","sequence":"additional","affiliation":[{"name":"KLE Society's Institute of Dental Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjana","family":"Patrick","sequence":"additional","affiliation":[{"name":"Biocon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3637-9134","authenticated-orcid":false,"given":"Tyler","family":"Peterson","sequence":"additional","affiliation":[{"name":"Wyant College of Optical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubha","family":"Gurudath","sequence":"additional","affiliation":[{"name":"KLE Society's Institute of Dental Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhashini","family":"Raghavan","sequence":"additional","affiliation":[{"name":"KLE Society's Institute of Dental Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imchen","family":"Tsusennaro","sequence":"additional","affiliation":[{"name":"Christian Institute of Health Sciences and Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shirley T.","family":"Leivon","sequence":"additional","affiliation":[{"name":"Christian Institute of Health Sciences and Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trupti","family":"Kolur","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Medical Foundation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9171-7319","authenticated-orcid":false,"given":"Vivek","family":"Shetty","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Medical Foundation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-3207","authenticated-orcid":false,"given":"Vidya","family":"Bushan","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Medical Foundation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-6037","authenticated-orcid":false,"given":"Rohan","family":"Ramesh","sequence":"additional","affiliation":[{"name":"Christian Institute of Health Sciences and Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijay","family":"Pillai","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Medical Foundation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7580-2409","authenticated-orcid":false,"given":"Petra","family":"Wilder-Smith","sequence":"additional","affiliation":[{"name":"Univ. of California, Irvine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amritha","family":"Suresh","sequence":"additional","affiliation":[{"name":"Mazumdar Shaw Medical Ctr."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moni Abraham","family":"Kuriakose","sequence":"additional","affiliation":[{"name":"Cochin Cancer Research Ctr."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5287-8323","authenticated-orcid":false,"given":"Praveen","family":"Birur","sequence":"additional","affiliation":[{"name":"Biocon Foundation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongguang","family":"Liang","sequence":"additional","affiliation":[{"name":"Wyant College of Optical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","container-title":["Journal of Biomedical Optics"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-biomedical-optics\/volume-27\/issue-11\/115001\/Exploring-uncertainty-measures-in-convolutional-neural-network-for-semantic-segmentation\/10.1117\/1.JBO.27.11.115001.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:28:01Z","timestamp":1790267281000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-biomedical-optics\/volume-27\/issue-11\/115001\/Exploring-uncertainty-measures-in-convolutional-neural-network-for-semantic-segmentation\/10.1117\/1.JBO.27.11.115001.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,3]]},"references-count":0,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,11,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jbo.27.11.115001","relation":{},"ISSN":["1083-3668","1560-2281"],"issn-type":[{"value":"1083-3668","type":"print"},{"value":"1560-2281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,3]]}}}