{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:04:58Z","timestamp":1768309498798,"version":"3.49.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>\n                    Accurate segmentation of polyps in colonoscopy images is essential for early colorectal cancer detection; however, it remains a challenging task due to reflections, occlusions, motion artifacts, inter- and intra-polyp appearance variability, and the presence of noisy or inconsistent ground-truth annotations. In this work, we introduce dynamic-Nu T-Loss (DNA-TLoss), a robust, adaptive loss function based on the heavy-tailed Student\u2019s \ud835\udc61-distribution that incorporates three novel extensions: (1) a per-image learnable degrees-of-freedom parameter\n                    <jats:italic>\u03bd<\/jats:italic>\n                    , predicted by a lightweight NuPredictor network to dynamically adjust robustness to outliers; (2) per-pixel precision weights\n                    <jats:italic>\u03bb<\/jats:italic>\n                    for spatially adaptive error sensitivity; and (3) a multi-scale aggregation scheme that computes and combines loss at multiple spatial resolutions to capture both coarse and fine details. Integrated into a U-Net with a ResNet-34 encoder, DNA-TLoss was evaluated on five public benchmarks: CVC-300, CVC-ClinicDB, ETIS-LaribPolypDB, Kvasir, and CVC-ColonDB. Our method achieves the lowest Hausdorff distance across all datasets, with an average reduction of 14.6% compared to T-Loss; notably, on CVC-300, it yields a significant decrease of 45.96%. It also obtains the lowest false discovery rate on all five datasets, improving over T-Loss by up to 38.7% on CVC-300 and 24.5% on Kvasir. Furthermore, DNA-TLoss provided best-in-class calibration, achieving expected calibration error as low as 0.44% on CVC-300 and outperforming all other baselines on four out of five datasets. These results highlight the promise of joint global and local uncertainty adaptation, coupled with multi-scale optimization, for advancing trustworthy, real-time computer-aided polyp detection in colonoscopy.\n                  <\/jats:p>","DOI":"10.3389\/fmed.2025.1657123","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T05:44:54Z","timestamp":1768196694000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust colonoscopy polyp segmentation using dynamic-Nu T-Loss with multi-scale and uncertainty-aware adaptation"],"prefix":"10.3389","volume":"12","author":[{"given":"Alireza","family":"Norouziazad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahan Najafpour Ghazvini","family":"Fardshad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatemeh","family":"Esmaeildoost","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehrdad Najafpour Ghazvini","family":"Fardshad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Razieh","family":"Salahandish","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1977","DOI":"10.1056\/NEJM199312303292701","article-title":"Prevention of colorectal cancer by colonoscopic polypectomy","volume":"329","author":"Winawer","year":"1993","journal-title":"N Engl J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat Commun"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10462-025-11173-2","article-title":"Polyp segmentation in medical imaging: challenges, approaches and future directions","volume":"58","author":"Qayoom","year":"2025","journal-title":"Artif Intell Rev"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"411","DOI":"10.5217\/ir.2017.15.3.411","article-title":"Miss rate of colorectal neoplastic polyps and risk factors for missed polyps in consecutive colonoscopies","volume":"15","author":"Kim","year":"2017","journal-title":"Intest Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfma.2024.12.022","article-title":"The optimal labelling method for artificial intelligence-assisted polyp detection in colonoscopy","author":"Wang","year":"2024","journal-title":"J Formos Med Assoc"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"5931","DOI":"10.3748\/wjg.v28.i41.5931","article-title":"Enhanced segmentation of gastrointestinal polyps from capsule endoscopy images with artifacts using ensemble learning","volume":"28","author":"Zhou","year":"2022","journal-title":"World J Gastroenterol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"5915","DOI":"10.1038\/s41467-021-26216-9","article-title":"Annotation-efficient deep learning for automatic medical image segmentation","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/SoutheastCon51012.2023.10115189","article-title":"Comparative study of decision tree, adaboost, random forest, na\u00efve bayes, KNN, and perceptron for heart disease prediction","volume-title":"SoutheastCon 2023","author":"Maydanchi","year":"2023"},{"key":"ref9","author":"Singh","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s41746-024-01424-x","article-title":"Efficiency and safety of automated label cleaning on multimodal retinal images","volume":"8","author":"Lin","year":"2025","journal-title":"NPJ Digit Med"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.01045","article-title":"Contrastive learning for label efficient semantic segmentation","author":"Zhao","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"101759","DOI":"10.1016\/j.media.2020.101759","article-title":"Deep learning with noisy labels: exploring techniques and remedies in medical image analysis","volume":"65","author":"Karimi","year":"2020","journal-title":"Med Image Anal"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s42256-023-00625-5","article-title":"Labelling instructions matter in biomedical image analysis","volume":"5","author":"R\u00e4dsch","year":"2023","journal-title":"Nat Mach Intell"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CSICC55295.2022.9780525","article-title":"A convolutional neuro-fuzzy network using fuzzy image segmentation for acute leukemia classification","author":"Boreiri","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e2103091118","DOI":"10.1073\/pnas.2103091118","article-title":"Exploring deep neural networks via layer-peeled model: minority collapse in imbalanced training","volume":"118","author":"Fang","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"5983","DOI":"10.1038\/s41598-023-33215-x","article-title":"Differences in learning characteristics between support vector machine and random forest models for compound classification revealed by Shapley value analysis","volume":"13","author":"Siemers","year":"2023","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"128","DOI":"10.5201\/ipol.2014.104","article-title":"An analysis of the Viola-Jones face detection algorithm","volume":"4","author":"Wang","year":"2014","journal-title":"Image Process On Line"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.182","article-title":"Accurate image super-resolution using very deep convolutional networks","author":"Kim","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"102026","DOI":"10.1016\/j.compmedimag.2021.102026","article-title":"Unified focal loss: generalising dice and cross entropy-based losses to handle class imbalanced medical image segmentation","volume":"95","author":"Yeung","year":"2022","journal-title":"Comput Med Imaging Graph"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.324","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00075","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00482","article-title":"Arcface: additive angular margin loss for deep face recognition","author":"Deng","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1038\/s41551-023-01049-7","article-title":"Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging","volume":"7","author":"Azizi","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"ref24","first-page":"8535","article-title":"Co-teaching: robust training of deep neural networks with extremely noisy labels","volume-title":"Adv Neural Inf Process Syst","author":"Han","year":"2018"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.240","article-title":"Making deep neural networks robust to label noise: a loss correction approach","author":"Patrini","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"7260","DOI":"10.48550\/arXiv.2006.07805","article-title":"Dual t: reducing estimation error for transition matrix in label-noise learning","volume":"33","author":"Yao","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"8792","DOI":"10.48550\/arXiv.1805.07836","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00041","article-title":"Symmetric cross entropy for robust learning with noisy labels","author":"Wang","year":"2019"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00446","article-title":"A general and adaptive robust loss function","author":"Barron","year":"2019"},{"key":"ref30","article-title":"Normalized loss functions for deep learning with noisy labels","author":"Ma","year":"2020"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-43898-1_68","article-title":"Robust T-loss for medical image segmentation","author":"Gonzalez-Jimenez","year":"2023"},{"key":"ref32","article-title":"Kvasir-seg: a segmented polyp dataset","author":"Jha","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","article-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians","volume":"43","author":"Bernal","year":"2015","journal-title":"Comput Med Imaging Graph"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","article-title":"Automated polyp detection in colonoscopy videos using shape and context information","volume":"35","author":"Tajbakhsh","year":"2015","journal-title":"IEEE Trans Med Imaging"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","article-title":"Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer","volume":"9","author":"Silva","year":"2014","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/4037190","article-title":"A benchmark for endoluminal scene segmentation of colonoscopy images","volume":"2017","author":"V\u00e1zquez","year":"2017","journal-title":"J Healthc Eng"},{"key":"ref37","article-title":"U-net: convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention\u2013MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3520","DOI":"10.1109\/TIP.2019.2962685","article-title":"Semantic segmentation with context encoding and multi-path decoding","volume":"29","author":"Ding","year":"2020","journal-title":"IEEE Trans Image Process"},{"key":"ref40","author":"Kingma","year":"2014"},{"key":"ref41","author":"Ghodousian","year":"2022"},{"key":"ref42","author":"Ghodousian","year":"2022"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1657123\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T05:45:23Z","timestamp":1768196723000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1657123\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":43,"alternative-id":["10.3389\/fmed.2025.1657123"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1657123","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1657123"}}