{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:26:30Z","timestamp":1793917590876,"version":"4.8.0"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Monash Health","id":[{"id":"https:\/\/ror.org\/02t1bej08","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Radiol Phys Technol"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    A measurable fraction of examinations in retrospective imaging archives lack a recorded body weight, limiting metadata completeness for tasks such as cohort auditing, weight-stratified analysis, and the assembly of machine-learning training datasets. We developed and compared three approaches for body-weight prediction from a single middle-slice CT image: a LightGBM model on 19 CT-derived tabular features (water equivalent diameter, effective diameter, body composition, scanner parameters), an ImageNet-pretrained ResNet-18 on images alone, and a ResNet-18 with late fusion of the same 19 tabular features into the 512-dimensional image embedding. Models were trained with 5-fold patient-disjoint cross-validation on a combined train+validation development pool of 30,857 examinations from 16,169 patients; the best-performing fold of each model family was selected by within-fold validation mean absolute error (MAE) and evaluated, without further tuning, on a held-out test partition of 3,479 examinations from 1,796 patients (patient-disjoint from training and validation). On the test set, the fusion ResNet-18 achieved MAE 4.06\u00a0kg (95% CI 3.90\u20134.23;\n                    <jats:italic>R\u00b2<\/jats:italic>\n                    = 0.92), with 69.5% of predictions within \u00b1\u20095\u00a0kg and 93.8% within \u00b1\u200910\u00a0kg. A weighted ensemble of the fusion ResNet and LightGBM produced a small further reduction in MAE to 3.99\u00a0kg (paired bootstrap\n                    <jats:italic>p<\/jats:italic>\n                    &lt; .001), but the 0.07\u00a0kg difference is below practically meaningful thresholds. The simpler single-model ResNet-18 with metadata fusion may be useful for retrospective missing-weight imputation, with split-conformal 90% and 95% prediction intervals (empirical test coverage 89% and 94%) available for case-level uncertainty quantification.\n                  <\/jats:p>","DOI":"10.1007\/s12194-026-01122-1","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T10:22:35Z","timestamp":1787134955000},"page":"1588-1601","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Single-slice ct body-weight prediction with image and metadata fusion: a multi-model comparison"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7564-8210","authenticated-orcid":false,"given":"Daniel","family":"Carrion","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8029-9951","authenticated-orcid":false,"given":"M. K.","family":"Badawy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"issue":"3","key":"1122_CR1","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1148\/radiol.12121919","volume":"265","author":"JA Brink","year":"2012","unstructured":"Brink JA, Morin RL. Size-specific dose estimation for CT: how should it be used and what does it mean? Radiology. 2012;265(3):666\u20138. https:\/\/doi.org\/10.1148\/radiol.12121919.","journal-title":"Radiology"},{"key":"1122_CR2","unstructured":"American Association of Physicists in Medicine. Use of Water Equivalent Diameter for Calculating Patient Size and Size-Specific Dose Estimates (SSDE) in CT. AAPM Report 220. AAPM; 2014."},{"key":"1122_CR3","unstructured":"American Association of Physicists in Medicine. Size-Specific Dose Estimates (SSDE) in Pediatric and Adult Body CT Examinations. AAPM Report 204. AAPM; 2011."},{"issue":"1076","key":"1122_CR4","doi-asserted-by":"publisher","first-page":"20170079","DOI":"10.1259\/bjr.20170079","volume":"90","author":"AJ Aschoff","year":"2017","unstructured":"Aschoff AJ, Catalano C, Kirchin MA, Krix M, Albrecht T. Low radiation dose in computed tomography: the role of iodine. Br J Radiol. 2017;90(1076):20170079. https:\/\/doi.org\/10.1259\/bjr.20170079.","journal-title":"Br J Radiol"},{"issue":"3","key":"1122_CR5","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1148\/rg.313105138","volume":"31","author":"MJ Modica","year":"2011","unstructured":"Modica MJ, Kanal KM, Gunn ML. The obese emergency patient: imaging challenges and solutions. Radiographics. 2011;31(3):811\u201323. https:\/\/doi.org\/10.1148\/rg.313105138.","journal-title":"Radiographics"},{"issue":"2","key":"1122_CR6","doi-asserted-by":"publisher","first-page":"433","DOI":"10.2214\/AJR.06.0409","volume":"188","author":"RN Uppot","year":"2007","unstructured":"Uppot RN, Sahani DV, Hahn PF, Gervais D, Mueller PR. Impact of obesity on medical imaging and image-guided intervention. AJR Am J Roentgenol. 2007;188(2):433\u201340. https:\/\/doi.org\/10.2214\/AJR.06.0409.","journal-title":"AJR Am J Roentgenol"},{"issue":"5","key":"1122_CR7","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1139\/H08-075","volume":"33","author":"M Mourtzakis","year":"2008","unstructured":"Mourtzakis M, Prado CMM, Lieffers JR, Reiman T, McCargar LJ, Baracos VE. A practical and precise approach to quantification of body composition in cancer patients using computed tomography images acquired during routine care. Appl Physiol Nutr Metab. 2008;33(5):997\u20131006. https:\/\/doi.org\/10.1139\/H08-075.","journal-title":"Appl Physiol Nutr Metab"},{"issue":"9","key":"1122_CR8","doi-asserted-by":"publisher","first-page":"e14467","DOI":"10.1002\/acm2.14467","volume":"25","author":"H Ichikawa","year":"2024","unstructured":"Ichikawa H, Ichikawa S, Sawane Y. Machine learning-based estimation of patient body weight from radiation dose metrics in computed tomography. J Appl Clin Med Phys. 2024;25(9):e14467. https:\/\/doi.org\/10.1002\/acm2.14467.","journal-title":"J Appl Clin Med Phys"},{"issue":"1","key":"1122_CR9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s12194-023-00697-3","volume":"16","author":"S Ichikawa","year":"2023","unstructured":"Ichikawa S, Itadani H, Sugimori H. Prediction of body weight from chest radiographs using deep learning with a convolutional neural network. Radiol Phys Technol. 2023;16(1):127\u201334. https:\/\/doi.org\/10.1007\/s12194-023-00697-3.","journal-title":"Radiol Phys Technol"},{"key":"1122_CR10","doi-asserted-by":"publisher","first-page":"19010","DOI":"10.1038\/s41598-023-46080-5","volume":"13","author":"A Demircio\u011flu","year":"2023","unstructured":"Demircio\u011flu A, Quinsten AS, Umutlu L, Forsting M, Nassenstein K, Bos D. Determining body height and weight from thoracic and abdominal CT localizers in pediatric and young adult patients using deep learning. Sci Rep. 2023;13:19010. https:\/\/doi.org\/10.1038\/s41598-023-46080-5.","journal-title":"Sci Rep"},{"key":"1122_CR11","first-page":"3149","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017;30:3149\u201357.","journal-title":"Adv Neural Inf Process Syst"},{"key":"1122_CR12","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016:770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"1122_CR13","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin HC, Roth HR, Gao M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging. 2016;35(5):1285\u201398. https:\/\/doi.org\/10.1109\/TMI.2016.2528162.","journal-title":"IEEE Trans Med Imaging"},{"key":"1122_CR14","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","volume":"3","author":"SC Huang","year":"2020","unstructured":"Huang SC, Pareek A, Seyyedi S, Banerjee I, Lungren MP. Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digit Med. 2020;3:136. https:\/\/doi.org\/10.1038\/s41746-020-00341-z.","journal-title":"NPJ Digit Med"},{"key":"1122_CR15","doi-asserted-by":"crossref","unstructured":"Dietterich TG. Ensemble methods in machine learning. In: International Workshop on Multiple Classifier Systems. Berlin: Springer; 2000:1\u201315.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"1122_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9326-7","volume-title":"Ensemble Machine Learning: Methods and Applications","author":"C Zhang","year":"2012","unstructured":"Zhang C, Ma Y. Ensemble Machine Learning: Methods and Applications. New York: Springer; 2012."},{"key":"1122_CR17","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. In: International Conference on Learning Representations. 2015."}],"container-title":["Radiological Physics and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12194-026-01122-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12194-026-01122-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12194-026-01122-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:05:04Z","timestamp":1793916304000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12194-026-01122-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":17,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["1122"],"URL":"https:\/\/doi.org\/10.1007\/s12194-026-01122-1","relation":{},"ISSN":["1865-0333","1865-0341"],"issn-type":[{"value":"1865-0333","type":"print"},{"value":"1865-0341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"assertion":[{"value":"19 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This research study was conducted retrospectively from de-identified imaging data obtained for clinical purposes. The Monash Health Human Research Ethics Committee determined that the study was exempt from formal Research Ethics Committee review as a retrospective quality improvement project, consistent with the\n                      Ethical Considerations in Quality Assurance and Evaluation Activities\n                      guideline (National Health and Medical Research Council, 2014). The study adheres to the principles of the Declaration of Helsinki (1964, and subsequent amendments).","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The study used existing, de-identified clinical imaging archives; no individual participant was contacted or recruited for this work.","order":3,"name":"Ethics","label":"Consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The manuscript reports aggregate model-performance statistics; no identifiable patient images or data are reproduced.","order":4,"name":"Ethics","label":"Consent to publish","group":{"name":"EthicsHeading","label":"Declarations"}}]}}