{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T05:29:15Z","timestamp":1769837355168,"version":"3.49.0"},"reference-count":38,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"crossref","award":["169005"],"award-info":[{"award-number":["169005"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Purpose<\/jats:italic>\n                    . Mammographic density is associated with the risk of developing breast cancer and can be predicted using deep learning methods. Model uncertainty estimates are not produced by standard regression approaches but would be valuable for clinical and research purposes. Our objective is to produce deep learning models with in-built uncertainty estimates without degrading predictive performance.\n                    <jats:italic>Approach<\/jats:italic>\n                    . We analysed data from over 150,000 mammogram images with associated continuous density scores from expert readers in the Predicting Risk Of Cancer At Screening (PROCAS) study. We re-designated the continuous density scores to 100 density classes then trained classification and ordinal deep learning models. Distributions and distribution-free methods were applied to extract predictions and uncertainties. A deep learning regression model was trained on the continuous density scores to act as a direct comparison.\n                    <jats:italic>Results<\/jats:italic>\n                    . The root mean squared error (RMSE) between expert assigned density labels and predictions of the standard regression model were 8.42 (8.34\u20138.51) while the RMSE for the classification and ordinal classification were 8.37 (8.28\u20138.46) and 8.44 (8.35\u20138.53) respectively. The average uncertainties produced by the models were higher when the density scores from pairs of expert readers density scores differ more, when different mammogram views of the same views are more variable, and when two separately trained models show higher variation.\n                    <jats:italic>Conclusions<\/jats:italic>\n                    . Using either a classification or ordinal approach we can produce model uncertainty estimates without loss of predictive performance.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae39e2","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T22:47:47Z","timestamp":1768862867000},"page":"015055","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3681-1342","authenticated-orcid":true,"given":"Steven","family":"Squires","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grey","family":"Kuling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D Gareth","family":"Evans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne L","family":"Martel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susan M","family":"Astley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"bpexae39e2bib1","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1186\/bcr2942","type":"journal-article","article-title":"Mammographic density and breast cancer risk: current understanding and future prospects","volume":"13","author":"Boyd","year":"2011","journal-title":"Breast Cancer Research"},{"key":"bpexae39e2bib2","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.breast.2022.09.007","type":"journal-article","article-title":"Mammographic breast density and the risk of breast cancer: a systematic review and meta-analysis","volume":"66","author":"Bodewes","year":"2022","journal-title":"The Breast"},{"key":"bpexae39e2bib3","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1158\/1055-9965.EPI-06-0034","type":"journal-article","article-title":"Silva. Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis","volume":"15","author":"Valerie","year":"2006","journal-title":"Cancer Epidemiology Biomarkers & Prevention"},{"key":"bpexae39e2bib4","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1186\/s13058-015-0626-8","type":"journal-article","article-title":"Preliminary evaluation of the publicly available laboratory for breast radiodensity assessment (libra) software tool: comparison of fully automated area and volumetric density measures in a case\u2013control study with digital mammography","volume":"17","author":"Keller","year":"2015","journal-title":"Breast Cancer Research"},{"key":"bpexae39e2bib5","doi-asserted-by":"publisher","first-page":"109019","DOI":"10.1016\/j.ejrad.2020.109019","type":"journal-article","article-title":"Impact of adding breast density to breast cancer risk models: a systematic review","volume":"127","author":"Vilmun","year":"2020","journal-title":"Eur. J. Radiol."},{"key":"bpexae39e2bib6","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1186\/s13058-014-0439-1","type":"journal-article","article-title":"and Isabel dos Santos-Silva. Digital mammographic density and breast cancer risk: a case\u2013control study of six alternative density assessment methods","volume":"16","author":"Eng","year":"2014","journal-title":"Breast cancer research"},{"key":"bpexae39e2bib7","first-page":"33","type":"book","article-title":"Volumetric assessment of breast tissue composition from FFDM images","author":"Hartman","year":"2008"},{"key":"bpexae39e2bib8","first-page":"342","type":"book","article-title":"Robust breast composition measurement - VolparaTM","author":"Highnam","year":"2010"},{"key":"bpexae39e2bib9","volume":"4","author":"D\u2019orsi","year":"2003","type":"book"},{"key":"bpexae39e2bib10","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.2214\/AJR.16.16561","type":"journal-article","article-title":"Effects of changes in bi-rads density assessment guidelines (fourth versus fifth edition) on breast density assessment: intra-and interreader agreements and density distribution","volume":"207","author":"Irshad","year":"2016","journal-title":"American Journal of Roentgenology"},{"key":"bpexae39e2bib11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13058-018-0932-z","type":"journal-article","article-title":"A comparison of five methods of measuring mammographic density: a case-control study","volume":"20","author":"Astley","year":"2018","journal-title":"Breast Cancer Research"},{"key":"bpexae39e2bib12","doi-asserted-by":"publisher","first-page":"031405","DOI":"10.1117\/1.JMI.6.3.031405","type":"journal-article","article-title":"Prediction of reader estimates of mammographic density using convolutional neural networks","volume":"6","author":"Ionescu","year":"2019","journal-title":"Journal of Medical Imaging"},{"key":"bpexae39e2bib13","doi-asserted-by":"publisher","first-page":"24502","DOI":"10.1117\/1.JMI.10.2.024502","type":"journal-article","article-title":"Automatic assessment of mammographic density using a deep transfer learning method","volume":"10","author":"Squires","year":"2023","journal-title":"Journal of Medical Imaging"},{"key":"bpexae39e2bib14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s42256-018-0004-1","type":"journal-article","article-title":"The need for uncertainty quantification in machine-assisted medical decision making","volume":"1","author":"Begoli","year":"2019","journal-title":"Nature Machine Intelligence"},{"key":"bpexae39e2bib15","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-080749","type":"journal-article","article-title":"Uncertainty of risk estimates from clinical prediction models: rationale, challenges, and approaches","volume":"388","author":"Riley","year":"2025","journal-title":"bmj"},{"key":"bpexae39e2bib16","doi-asserted-by":"publisher","first-page":"102830","DOI":"10.1016\/j.artmed.2024.102830","type":"journal-article","article-title":"Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis","volume":"150","author":"Lambert","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"bpexae39e2bib17","doi-asserted-by":"publisher","first-page":"100003","DOI":"10.1016\/j.metrad.2023.100003","type":"journal-article","article-title":"A review of uncertainty estimation and its application in medical imaging","volume":"1","author":"Zou","year":"2023","journal-title":"Meta-Radiology"},{"key":"bpexae39e2bib18","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1017\/cts.2016.9","type":"journal-article","article-title":"Uncertainty quantification in breast cancer risk prediction models using self-reported family health history","volume":"1","author":"Pflieger","year":"2017","journal-title":"Journal of Clinical and Translational Science"},{"key":"bpexae39e2bib19","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.ejor.2023.09.009","type":"journal-article","article-title":"Benoit. Explainability through uncertainty: Trustworthy decision-making with neural networks","volume":"317","author":"Thuy","year":"2024","journal-title":"Eur. J. Oper. Res."},{"key":"bpexae39e2bib20","doi-asserted-by":"publisher","first-page":"102861","DOI":"10.1016\/j.media.2023.102861","type":"journal-article","article-title":"Uncertainty aware training to improve deep learning model calibration for classification of cardiac mr images","volume":"88","author":"Dawood","year":"2023","journal-title":"Med. Image Anal."},{"key":"bpexae39e2bib21","first-page":"197","type":"book","article-title":"Same task, same observers, different values: the problem with visual assessment of breast density","volume":"8673","author":"Sergeant","year":"2013"},{"key":"bpexae39e2bib22","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1111\/j.1524-4741.2012.01250.x","type":"journal-article","article-title":"Reproducibility of bi-rads breast density measures among community radiologists: a prospective cohort study","volume":"18","author":"Spayne","year":"2012","journal-title":"The Breast Journal"},{"key":"bpexae39e2bib23","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1016\/j.acra.2013.01.003","type":"journal-article","article-title":"Reader variability in breast density estimation from full-field digital mammograms: the effect of image postprocessing on relative and absolute measures","volume":"20","author":"Keller","year":"2013","journal-title":"Acad. Radiol."},{"key":"bpexae39e2bib24","doi-asserted-by":"publisher","first-page":"4666","DOI":"10.1002\/sim.5848","type":"journal-article","article-title":"Correcting for rater bias in scores on a continuous scale, with application to breast density","volume":"32","author":"Sperrin","year":"2013","journal-title":"Statistics in Medicine"},{"key":"bpexae39e2bib25","doi-asserted-by":"publisher","first-page":"44506","DOI":"10.1117\/1.JMI.11.4.044506","type":"journal-article","article-title":"Capability and reliability of deep learning models to make density predictions on low-dose mammograms","volume":"11","author":"Squires","year":"2024","journal-title":"Journal of Medical Imaging"},{"key":"bpexae39e2bib26","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1158\/1940-6207.CAPR-11-0458","type":"journal-article","article-title":"Assessing individual breast cancer risk within the uk national health service breast screening program: a new paradigm for cancer prevention","volume":"5","author":"Evans","year":"2012","journal-title":"Cancer Prevention Research"},{"key":"bpexae39e2bib27","first-page":"770","type":"other","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"bpexae39e2bib28","first-page":"1","type":"journal-article","article-title":"Enhancing brain tumor detection in MRI images through explainable AI using Grad-CAM with Resnet 50","volume":"24","author":"Guluwadi","year":"2024","journal-title":"BMC Med. Imaging"},{"key":"bpexae39e2bib29","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1016\/j.ajpath.2019.05.007","type":"journal-article","article-title":"Pathology image analysis using segmentation deep learning algorithms","volume":"189","author":"Wang","year":"2019","journal-title":"The American Journal of Pathology"},{"key":"bpexae39e2bib30","doi-asserted-by":"publisher","first-page":"102125","DOI":"10.1016\/j.media.2021.102125","type":"journal-article","article-title":"Deep learning for chest x-ray analysis: A survey","volume":"72","author":"\u00c7alli","year":"2021","journal-title":"Med. Image Anal."},{"key":"bpexae39e2bib31","first-page":"4700","type":"book","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"bpexae39e2bib32","first-page":"3347","type":"journal-article","article-title":"Transfusion: Understanding transfer learning for medical imaging","volume":"32","author":"Raghu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bpexae39e2bib33","first-page":"248","type":"book","article-title":"Imagenet: A large-scale hierarchical image database","volume":"2009","author":"Deng","year":"2009"},{"key":"bpexae39e2bib34","author":"Kingma","year":"2014","type":"preprint"},{"key":"bpexae39e2bib35","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/1754-9485.13261","type":"journal-article","article-title":"A review of medical image data augmentation techniques for deep learning applications","volume":"65","author":"Chlap","year":"2021","journal-title":"Journal of Medical Imaging and Radiation Oncology"},{"key":"bpexae39e2bib36","first-page":"979","type":"book","article-title":"Differential data augmentation techniques for medical imaging classification tasks","volume":"2017","author":"Hussain"},{"key":"bpexae39e2bib37","first-page":"1279","type":"book","article-title":"A neural network approach to ordinal regression","volume":"2008","author":"Cheng","year":"2008"},{"key":"bpexae39e2bib38","doi-asserted-by":"publisher","first-page":"035030","DOI":"10.1088\/2057-1976\/accaea","type":"journal-article","article-title":"The effect of variable labels on deep learning models trained to predict breast density","volume":"9","author":"Squires","year":"2023","journal-title":"Biomed. Phys. Eng. Express"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T15:47:16Z","timestamp":1769788036000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae39e2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,30]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae39e2","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-04-28","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}