{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T11:05:25Z","timestamp":1776251125314,"version":"3.50.1"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e4tsklinikum Freiburg"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Optimal contrast agent dosing in computed tomography (CT) depends on accurate patient weight, yet manual measurements increase workload and self-reporting can introduce bias. We developed and tested a deep-learning-based algorithm to automate the approximation of contrast agent dosage directly from CT scout images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 817 patients undergoing thorax\/abdomen CT. Prior to examination, patient weight was collected via manual scale measurements and self-reporting. We developed an EfficientNet convolutional neural network pipeline to estimate weight from scout images and used in-context learning and dataset distillation to analyze body-weight-informative CT features. The model was used in a browser-based user interface to provide dosing estimates for various contrast agent compounds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Self-reported patient weights were statistically significantly lower than manual scale measurements (75.13\u2009kg vs. 77.06\u2009kg;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u200910\n                      <jats:sup>\u2212 5<\/jats:sup>\n                      , Wilcoxon signed-rank test). In 5-fold cross-validation, the pipeline predicted patient weight with a mean absolute error (MAE) of 3.90\u2009\u00b1\u20090.20\u2009kg. This error corresponds to a difference of roughly 4.48\u201311.70\u2009ml of contrast agent, depending on the specific agent. Interpretability analysis confirmed that both larger anatomical shape and higher overall attenuation were the predictive features of body weight.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This open-source deep learning pipeline enables automatic, accurate contrast agent dosing in routine CT workflows. The approach has the potential to improve patient safety and clinical efficiency by providing accurate weight estimates without requiring additional measurements or relying on potentially outdated records. Further validation on larger cohorts and across different clinical centers is required.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-026-02331-1","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T09:25:16Z","timestamp":1775899516000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated scout-image-based estimation of contrast agent dosing: a deep learning approach"],"prefix":"10.1186","volume":"26","author":[{"given":"Robin Tibor","family":"Schirrmeister","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laetitia","family":"Taleb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Friemel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Reisert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian","family":"Bamberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob","family":"Wei\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Rau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,11]]},"reference":[{"key":"2331_CR1","doi-asserted-by":"publisher","unstructured":"Bae KT. Intravenous contrast medium administration and scan timing at CT: considerations and approaches. Radiology. 2010, Juli;256(1):S. 32\u201361. https:\/\/doi.org\/10.1148\/radiol.10090908.","DOI":"10.1148\/radiol.10090908"},{"key":"2331_CR2","doi-asserted-by":"publisher","unstructured":"Boos J. Does body mass index outperform body weight as a surrogate parameter in the calculation of size-specific dose estimates in adult body CT? Br J Radiol. 2016;89(1059):S.20150734. https:\/\/doi.org\/10.1259\/bjr.20150734.","DOI":"10.1259\/bjr.20150734"},{"key":"2331_CR3","doi-asserted-by":"publisher","unstructured":"Fukunaga M, Matsubara K, Ichikawa S, Mitsui H, Yamamoto H, Miyati T. CT dose management of adult patients with unknown body weight using an effective diameter. Eur J Radiol. 2021, Feb;135:S.109483. https:\/\/doi.org\/10.1016\/j.ejrad.2020.109483.","DOI":"10.1016\/j.ejrad.2020.109483"},{"key":"2331_CR4","doi-asserted-by":"publisher","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, Nov;13(1):S.19010. https:\/\/doi.org\/10.1038\/s41598-023-46080-5.","DOI":"10.1038\/s41598-023-46080-5"},{"key":"2331_CR5","doi-asserted-by":"publisher","unstructured":"Ichikawa S, Hamada M, Sugimori H. A deep-learning method using computed tomography scout images for estimating patient body weight. Sci Rep. 2021 Aug;11(1):S.15627. https:\/\/doi.org\/10.1038\/s41598-021-95170-9.","DOI":"10.1038\/s41598-021-95170-9"},{"key":"2331_CR6","unstructured":"Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. International conference on machine learning. PMLR; 2019:S. 6105\u20136114."},{"key":"2331_CR7","doi-asserted-by":"publisher","unstructured":"Cardoso MJ. MONAI: an open-source framework for deep learning in healthcare. Python. November 2022. https:\/\/doi.org\/10.48550\/arXiv.2211.02701.","DOI":"10.48550\/arXiv.2211.02701"},{"key":"2331_CR8","doi-asserted-by":"publisher","unstructured":"Hollmann N. Accurate predictions on small data with a tabular foundation model. Nature. 2025, Jan;637(8045):S. 319\u2013326. https:\/\/doi.org\/10.1038\/s41586-024-08328-6.","DOI":"10.1038\/s41586-024-08328-6"},{"key":"2331_CR9","unstructured":"Feuer B. TuneTables: context optimization for scalable prior-data fitted Networks. Gehalten auf der the thirty-eighth annual conference on neural information processing Systems, Nov. 2024. Zugegriffen: 12. November. 2024. [Online]. Verf\u00fcgbar unter: https:\/\/openreview.net\/forum?id=FOfU3qhcIG%2526referrer=%255Bthe%2520profile%2520of%2520Colin%2520White%255D(%252Fprofile%253Fid%253D%257EColin_White1."},{"key":"2331_CR10","unstructured":"ONNX Runtime developers. ONNX Runtime. C++. November 2018. Available from: https:\/\/github.com\/microsoft\/onnxruntime."},{"key":"2331_CR11","doi-asserted-by":"publisher","unstructured":"Okabayashi T, Terazaki K, Sagawa H, Itagaki K, Matsuda A. Deep learning model for body weight estimation from computed tomography scout images incorporating sex and height. Radiol Phys Technol. 2026. https:\/\/doi.org\/10.1007\/s12194-026-01028-y.","DOI":"10.1007\/s12194-026-01028-y"},{"key":"2331_CR12","doi-asserted-by":"crossref","unstructured":"Ting Y-S. Why machine learning models systematically underestimate extreme Values. Open J Astrophys. 2025;8.","DOI":"10.33232\/001c.142224"},{"key":"2331_CR13","doi-asserted-by":"publisher","unstructured":"Barreto I. Impact of patient centering in CT on organ dose and the effect of using a positioning compensation system: evidence from OSLD measurements in postmortem subjects. J Appl Clin Med Phys. 2019;20(6):S.141\u2013151. https:\/\/doi.org\/10.1002\/acm2.12594.","DOI":"10.1002\/acm2.12594"},{"key":"2331_CR14","doi-asserted-by":"crossref","unstructured":"McCollough C. Use of water equivalent diameter for calculating patient size and size-specific dose estimates (SSDE) in CT. AAPM Rep. 2014, Sep;2014:S.6\u201323.","DOI":"10.37206\/146"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-026-02331-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02331-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02331-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:21:29Z","timestamp":1776248489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12880-026-02331-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,11]]},"references-count":14,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2331"],"URL":"https:\/\/doi.org\/10.1186\/s12880-026-02331-1","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,11]]},"assertion":[{"value":"22 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Institutional Review Board of the University of Freiburg (Ethic Committee Freiburg 24\u20131487-S1). All methods were performed in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki. Informed written consent was waived by the Ethic Committee Freiburg.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The manuscript contains de-identified CT scout images that do not include any individual person\u2019s data or identifying features. The use of these images is covered by the ethical waiver granted for this retrospective research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"190"}}