{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T03:29:37Z","timestamp":1787887777532,"version":"build-2784847793"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"DOI":"10.13039\/100000053","name":"NATIONAL EYE INSTITUTE","doi-asserted-by":"crossref","award":["5R01HD107493-12"],"award-info":[{"award-number":["5R01HD107493-12"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"crossref","award":["5R21EY031883-02"],"award-info":[{"award-number":["5R21EY031883-02"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100001818","name":"Research to Prevent Blindness","doi-asserted-by":"publisher","award":["P30 EY10572"],"award-info":[{"award-number":["P30 EY10572"]}],"id":[{"id":"10.13039\/100001818","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Cancer Insitute","award":["U01CA242879"],"award-info":[{"award-number":["U01CA242879"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>In clinical medicine, variables like disease severity are often categorized into discrete ordinal labels such as normal\/mild\/moderate\/severe. However, these labels, commonly used to train and evaluate disease severity prediction models, simplify an underlying continuous severity spectrum. Using continuous scores can aid in detecting small severity changes more sensitively over time. We introduce a deep learning based approach that predicts continuously valued variables from medical images using only discrete ordinal labels during model development. We evaluated this approach using three medical imaging datasets: disease severity prediction for retinopathy of prematurity and knee osteoarthritis, and breast density prediction from mammograms. Deep learning models were trained with discrete labels, and model outputs were transformed into continuous scores. These were then compared against detailed expert severity assessments, which exceeded the granularity of training labels. Our study explored conventional and Monte Carlo dropout multi-class classification, ordinal classification, regression, and twin models. We found that models incorporating the ordinal nature of training labels significantly outperformed conventional multi-class classification. Notably, continuous scores from ordinal classification and regression models demonstrated a higher correlation with expert severity rankings and lower mean squared errors than multi-class models. The application of Monte Carlo dropout further enhanced the prediction accuracy of continuously valued scores, aligning closely with the continuous target variable. Our findings confirm that accurate continuous scores can be learned from discrete ordinal labels using deep learning, offering a robust method that effectively bridges the gap between discrete and continuous data across various image analysis tasks.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001248","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:54:17Z","timestamp":1776448457000},"page":"e0001248","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging deep learning to infer continuous predictions from ordinal labels in medical imaging"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1881-7065","authenticated-orcid":true,"given":"Katharina V.","family":"Hoebel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9anne","family":"Lemay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John Peter","family":"Campbell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Ostmo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael F.","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher P.","family":"Bridge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew D.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveer","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron S.","family":"Coyner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-9618","authenticated-orcid":true,"given":"Jayashree","family":"Kalpathy-Cramer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"11","key":"pdig.0001248.ref001","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1016\/j.ophtha.2016.07.026","article-title":"Plus disease in retinopathy of prematurity: a continuous spectrum of vascular abnormality as a basis of diagnostic variability","volume":"123","author":"JP Campbell","year":"2016","journal-title":"Ophthalmology"},{"issue":"11","key":"pdig.0001248.ref002","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: a review","volume":"42","author":"SM Anwar","year":"2018","journal-title":"J Med Syst"},{"issue":"22","key":"pdig.0001248.ref003","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"7","key":"pdig.0001248.ref004","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1001\/jamaophthalmol.2018.1934","article-title":"Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks","volume":"136","author":"JM Brown","year":"2018","journal-title":"JAMA Ophthalmol"},{"issue":"1","key":"pdig.0001248.ref005","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-018-20132-7","article-title":"Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach","volume":"8","author":"A Tiulpin","year":"2018","journal-title":"Sci Rep"},{"issue":"5","key":"pdig.0001248.ref006","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.3963","article-title":"Performance of a deep learning model vs human reviewers in grading endoscopic disease severity of patients with ulcerative colitis","volume":"2","author":"RW Stidham","year":"2019","journal-title":"JAMA Netw Open"},{"issue":"9","key":"pdig.0001248.ref007","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"J De Fauw","year":"2018","journal-title":"Nat Med"},{"issue":"1","key":"pdig.0001248.ref008","doi-asserted-by":"crossref","first-page":"17816","DOI":"10.1038\/s41598-017-17876-z","article-title":"Leveraging uncertainty information from deep neural networks for disease detection","volume":"7","author":"C Leibig","year":"2017","journal-title":"Sci Rep"},{"key":"pdig.0001248.ref009","doi-asserted-by":"crossref","unstructured":"Antony J, McGuinness K, O\u2019Connor NE, Moran K. Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR). 2016. p. 1195\u2013200. https:\/\/doi.org\/10.1109\/icpr.2016.7899799","DOI":"10.1109\/ICPR.2016.7899799"},{"key":"pdig.0001248.ref010","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-020-0255-1","article-title":"Siamese neural networks for continuous disease severity evaluation and change detection in medical imaging","volume":"3","author":"MD Li","year":"2020","journal-title":"NPJ Digit Med"},{"key":"pdig.0001248.ref011","doi-asserted-by":"crossref","unstructured":"Brown JM, Kalpathy-Cramer J, Campbell JP, Beers A, Chang K, Ostmo S, et al. Fully automated disease severity assessment and treatment monitoring in retinopathy of prematurity using deep learning. In: Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 2018. p. 22. https:\/\/doi.org\/10.1117\/12.2295942","DOI":"10.1117\/12.2295942"},{"key":"pdig.0001248.ref012","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.ajo.2016.12.025","article-title":"Plus disease in retinopathy of prematurity: diagnostic trends in 2016 versus 2007","volume":"176","author":"C Moleta","year":"2017","journal-title":"Am J Ophthalmol"},{"key":"pdig.0001248.ref013","doi-asserted-by":"crossref","unstructured":"Dwork C, Hardt M, Pitassi T, Reingold O, Zemel R. Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference. 2012. p. 214\u201326. https:\/\/doi.org\/10.1145\/2090236.2090255","DOI":"10.1145\/2090236.2090255"},{"key":"pdig.0001248.ref014","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L. Seeing stars. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL \u201905, 2005. p. 115\u201324. https:\/\/doi.org\/10.3115\/1219840.1219855","DOI":"10.3115\/1219840.1219855"},{"issue":"4","key":"pdig.0001248.ref015","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1162\/003465303772815754","article-title":"The Effects of Mandatory Seat Belt Laws on Driving Behavior and Traffic Fatalities","volume":"85","author":"A Cohen","year":"2003","journal-title":"Review of Economics and Statistics"},{"issue":"10","key":"pdig.0001248.ref016","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.3390\/jcm8101578","article-title":"Insights into Amyotrophic Lateral Sclerosis from a Machine Learning Perspective","volume":"8","author":"J Gordon","year":"2019","journal-title":"J Clin Med"},{"issue":"12","key":"pdig.0001248.ref017","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.1016\/j.jacr.2020.05.015","article-title":"Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density","volume":"17","author":"K Chang","year":"2020","journal-title":"J Am Coll Radiol"},{"key":"pdig.0001248.ref018","article-title":"An ordinal regression framework for a deep learning based severity assessment for Chest Radiographs","author":"P Wienholt","year":"2024","journal-title":"arXiv preprint"},{"issue":"7","key":"pdig.0001248.ref019","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1109\/JAS.2022.105668","article-title":"Meta ordinal regression forest for medical image classification with ordinal labels","volume":"9","author":"Y Lei","year":"2022","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"pdig.0001248.ref020","first-page":"7867","article-title":"Ordinal classification with distance regularization for robust brain age prediction","volume":"2024","author":"J Shah","year":"2024","journal-title":"IEEE Winter Conf Appl Comput Vis"},{"key":"pdig.0001248.ref021","doi-asserted-by":"crossref","unstructured":"Lu C, Angelopoulos AN, Pomerantz S. Improving trustworthiness of AI disease severity rating in medical imaging with ordinal conformal prediction sets. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part VIII. Berlin, Heidelberg: Springer, p. 545\u201354. https:\/\/doi.org\/10.1007\/978-3-031-16452-1_52","DOI":"10.1007\/978-3-031-16452-1_52"},{"key":"pdig.0001248.ref022","article-title":"Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity","author":"TK Redd","year":"2018","journal-title":"Br J Ophthalmol"},{"key":"pdig.0001248.ref023","unstructured":"Gal Y, Ghahramani Z. Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning. 2016. p. 1050\u20139."},{"issue":"1","key":"pdig.0001248.ref024","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1038\/s41746-022-00709-3","article-title":"Improving the repeatability of deep learning models with Monte Carlo dropout","volume":"5","author":"A Lemay","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"1","key":"pdig.0001248.ref025","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5409\/wjcp.v5.i1.35","article-title":"Retinopathy of prematurity: past, present and future","volume":"5","author":"PK Shah","year":"2016","journal-title":"World J Clin Pediatr"},{"issue":"7","key":"pdig.0001248.ref026","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1001\/archopht.123.7.991","article-title":"The international classification of retinopathy of prematurity revisited","volume":"123","author":"GE Quinn","year":"2005","journal-title":"Arch Ophthalmol"},{"issue":"9","key":"pdig.0001248.ref027","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1001\/jamaophthalmol.2019.2433","article-title":"Monitoring disease progression with a quantitative severity scale for retinopathy of prematurity using deep learning","volume":"137","author":"S Taylor","year":"2019","journal-title":"JAMA Ophthalmol"},{"key":"pdig.0001248.ref028","doi-asserted-by":"crossref","first-page":"100587","DOI":"10.1016\/j.eclinm.2020.100587","article-title":"Global, regional prevalence, incidence and risk factors of knee osteoarthritis in population-based studies","author":"A Cui","year":"2020","journal-title":"EClinicalMedicine"},{"issue":"4","key":"pdig.0001248.ref029","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological assessment of osteo-arthrosis","volume":"16","author":"JH Kellgren","year":"1957","journal-title":"Ann Rheum Dis"},{"key":"pdig.0001248.ref030","unstructured":"Liberman L, Menell JH. Breast imaging reporting and data system (BI-RADS). Radiol Clin North Am. https:\/\/pubmed.ncbi.nlm.nih.gov\/12117184\/"},{"issue":"9","key":"pdig.0001248.ref031","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1093\/jnci\/87.9.670","article-title":"Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study","volume":"87","author":"NF Boyd","year":"1995","journal-title":"J Natl Cancer Inst"},{"issue":"22","key":"pdig.0001248.ref032","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1056\/NEJMoa1903986","article-title":"Supplemental MRI screening for women with extremely dense breast tissue","volume":"381","author":"MF Bakker","year":"2019","journal-title":"N Engl J Med"},{"issue":"17","key":"pdig.0001248.ref033","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1056\/NEJMoa052911","article-title":"Diagnostic performance of digital versus film mammography for breast-cancer screening","volume":"353","author":"ED Pisano","year":"2005","journal-title":"N Engl J Med"},{"key":"pdig.0001248.ref034","doi-asserted-by":"crossref","unstructured":"Highnam R, Brady M, Yaffe MJ, Karssemeijer N, Harvey J. In: International workshop on digital mammography, 2010. 342\u20139.","DOI":"10.1007\/978-3-642-13666-5_46"},{"issue":"1","key":"pdig.0001248.ref035","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s10549-016-4090-7","article-title":"Volumetric breast density affects performance of digital screening mammography","volume":"162","author":"JOP Wanders","year":"2017","journal-title":"Breast Cancer Res Treat"},{"key":"pdig.0001248.ref036","doi-asserted-by":"crossref","unstructured":"Li L, Lin Ht. Ordinal regression by extended binary classification. Advances in Neural Information Processing Systems. 2006.","DOI":"10.7551\/mitpress\/7503.003.0113"},{"key":"pdig.0001248.ref037","doi-asserted-by":"crossref","unstructured":"Niu Z, Zhou M, Wang L, Gao X, Hua G. Ordinal regression with multiple output CNN for age estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 4920\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.532","DOI":"10.1109\/CVPR.2016.532"},{"key":"pdig.0001248.ref038","doi-asserted-by":"crossref","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E d, Shah R. Signature verification using a \u201cSiamese\u201d time delay neural network. In: Proceeding of Advances in Neural Information Processing Systems. 1993. p. 737\u201344.","DOI":"10.1142\/9789812797926_0003"},{"key":"pdig.0001248.ref039","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.patrec.2020.11.008","article-title":"Rank consistent ordinal regression for neural networks with application to age estimation","volume":"140","author":"W Cao","year":"2020","journal-title":"Pattern Recognition Letters"},{"key":"pdig.0001248.ref040","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5108","key":"pdig.0001248.ref041","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1136\/bmj.2.5108.1355-c","article-title":"Detection of Ovulation","volume":"2","author":"VB Green-Armytage","year":"1958","journal-title":"BMJ"},{"key":"pdig.0001248.ref042","doi-asserted-by":"crossref","unstructured":"Takezaki S, Tanaka K, Uchida S, Kadota T. Disease severity regression with continuous data augmentation. In: 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023, 2023. https:\/\/doi.org\/10.1109\/ISBI53787.2023.10230453","DOI":"10.1109\/ISBI53787.2023.10230453"},{"issue":"11","key":"pdig.0001248.ref043","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1016\/j.ophtha.2016.07.020","article-title":"Plus disease in retinopathy of prematurity: improving diagnosis by ranking disease severity and using quantitative image analysis","volume":"123","author":"J Kalpathy-Cramer","year":"2016","journal-title":"Ophthalmology"},{"issue":"11","key":"pdig.0001248.ref044","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1136\/ard.2003.016477","article-title":"Validity and reliability of three definitions of hip osteoarthritis: cross sectional and longitudinal approach","volume":"63","author":"M Reijman","year":"2004","journal-title":"Ann Rheum Dis"},{"issue":"1019","key":"pdig.0001248.ref045","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1259\/bjr\/21256379","article-title":"Inter- and intraradiologist variability in the BI-RADS assessment and breast density categories for screening mammograms","volume":"85","author":"A Redondo","year":"2012","journal-title":"Br J Radiol"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:54:28Z","timestamp":1776448468000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001248"}},"subtitle":[],"editor":[{"given":"Peter H.","family":"Charlton","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001248","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]}}}