{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T08:56:37Z","timestamp":1771059397827,"version":"3.50.1"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["WE 6405\/2-1"],"award-info":[{"award-number":["WE 6405\/2-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["TA 1438\/1-2"],"award-info":[{"award-number":["TA 1438\/1-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","award":["18UNPG34030172"],"award-info":[{"award-number":["18UNPG34030172"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["NIH\/NHLBI 5K24HL113128"],"award-info":[{"award-number":["NIH\/NHLBI 5K24HL113128"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["NIH\/NHLBI 5T32HL076136"],"award-info":[{"award-number":["NIH\/NHLBI 5T32HL076136"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["NIH 5R01-HL109711"],"award-info":[{"award-number":["NIH 5R01-HL109711"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["NIH\/NHLBI 5U01HL123339"],"award-info":[{"award-number":["NIH\/NHLBI 5U01HL123339"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Health & Human Services | National Institutes of Health"},{"name":"U.S. Department of Health & Human Services | National Institutes of Health"},{"name":"U.S. Department of Health & Human Services | National Institutes of Health"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans developed in cardiovascular radiology can optimize treatment planning in radiation oncology. The system was trained using multi-center data (<jats:italic>n<\/jats:italic>\u2009=\u2009858) with manual heart segmentations provided by cardiovascular radiologists. Validation of the system was performed in an independent real-world dataset of 5677 breast cancer patients treated with radiation therapy at the Dana-Farber\/Brigham and Women\u2019s Cancer Center between 2008\u20132018. In a subset of 20 patients, the performance of the system was compared to eight radiation oncology experts by assessing segmentation time, agreement between experts, and accuracy with and without deep-learning assistance. To compare the performance to segmentations used in the clinic, concordance and failures (defined as Dice\u2009&lt;\u20090.85) of the system were evaluated in the entire dataset. The system was successfully applied without retraining. With deep-learning assistance, segmentation time significantly decreased (4.0\u2009min [IQR 3.1\u20135.0] vs. 2.0\u2009min [IQR 1.3\u20133.5]; <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001), and agreement increased (Dice 0.95 [IQR\u2009=\u20090.02]; vs. 0.97 [IQR\u2009=\u20090.02], <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). Expert accuracy was similar with and without deep-learning assistance (Dice 0.92 [IQR\u2009=\u20090.02] vs. 0.92 [IQR\u2009=\u20090.02]; <jats:italic>p<\/jats:italic>\u2009=\u20090.48), and not significantly different from deep-learning-only segmentations (Dice 0.92 [IQR\u2009=\u20090.02]; <jats:italic>p<\/jats:italic>\u2009\u2265\u20090.1). In comparison to real-world data, the system showed high concordance (Dice 0.89 [IQR\u2009=\u20090.06]) across 5677 patients and a significantly lower failure rate (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). These results suggest that deep-learning algorithms can successfully be applied across medical specialties and improve clinical care beyond the original field of interest.<\/jats:p>","DOI":"10.1038\/s41746-021-00416-5","type":"journal-article","created":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T11:02:36Z","timestamp":1614942156000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2433-9151","authenticated-orcid":false,"given":"Roman","family":"Zeleznik","sequence":"first","affiliation":[]},{"given":"Jakob","family":"Weiss","sequence":"additional","affiliation":[]},{"given":"Jana","family":"Taron","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Guthier","sequence":"additional","affiliation":[]},{"given":"Danielle S.","family":"Bitterman","sequence":"additional","affiliation":[]},{"given":"Cindy","family":"Hancox","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4313-2754","authenticated-orcid":false,"given":"Benjamin H.","family":"Kann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0625-3466","authenticated-orcid":false,"given":"Daniel W.","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Rinaa S.","family":"Punglia","sequence":"additional","affiliation":[]},{"given":"Jeremy","family":"Bredfeldt","sequence":"additional","affiliation":[]},{"given":"Borek","family":"Foldyna","sequence":"additional","affiliation":[]},{"given":"Parastou","family":"Eslami","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4696-9610","authenticated-orcid":false,"given":"Michael T.","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Udo","family":"Hoffmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8754-0565","authenticated-orcid":false,"given":"Raymond","family":"Mak","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-2003","authenticated-orcid":false,"given":"Hugo J. W. L.","family":"Aerts","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"416_CR1","first-page":"48","volume":"122","author":"P Densen","year":"2011","unstructured":"Densen, P. Challenges and opportunities facing medical education. Trans. Am. Clin. Climatol. Assoc. 122, 48\u201358 (2011).","journal-title":"Trans. Am. Clin. Climatol. Assoc."},{"key":"416_CR2","doi-asserted-by":"publisher","first-page":"893","DOI":"10.12968\/bjon.2018.27.15.893","volume":"27","author":"L Craig","year":"2018","unstructured":"Craig, L. Service improvement in health care: a literature review. Br. J. Nurs. 27, 893\u2013896 (2018).","journal-title":"Br. J. Nurs."},{"key":"416_CR3","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1126\/science.aay5189","volume":"366","author":"A Hosny","year":"2019","unstructured":"Hosny, A. & Hugo, J. W. Artificial intelligence for global health. Science 366, 955\u2013956 (2019).","journal-title":"Science"},{"key":"416_CR4","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","volume":"2","author":"K-H Yu","year":"2018","unstructured":"Yu, K.-H., Beam, A. L. & Kohane, I. S. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2, 719\u2013731 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"416_CR5","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1016\/S0360-3016(98)90033-5","volume":"15","author":"R Mohan","year":"1988","unstructured":"Mohan, R. et al. A comprehensive three-dimensional radiation treatment planning system. Int. J. Radiat. Oncol.*Biol.*Phys. 15, 481\u2013495 (1988).","journal-title":"Int. J. Radiat. Oncol.*Biol.*Phys."},{"key":"416_CR6","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","volume":"25","author":"A Esteva","year":"2019","unstructured":"Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24\u201329 (2019).","journal-title":"Nat. Med."},{"key":"416_CR7","doi-asserted-by":"publisher","first-page":"S77","DOI":"10.1016\/j.ijrobp.2009.04.093","volume":"76","author":"G Gagliardi","year":"2010","unstructured":"Gagliardi, G. et al. Radiation dose\u2013volume effects in the heart. Int. J. Radiat. Oncol.*Biol.*Phys. 76, S77\u2013S85 (2010).","journal-title":"Int. J. Radiat. Oncol.*Biol.*Phys."},{"key":"416_CR8","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1056\/NEJMoa1209825","volume":"368","author":"SC Darby","year":"2013","unstructured":"Darby, S. C. et al. Risk of ischemic heart disease in women after radiotherapy for breast cancer. N. Engl. J. Med. 368, 987\u2013998 (2013).","journal-title":"N. Engl. J. Med."},{"key":"416_CR9","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1001\/jama.287.1.108-JMS0102-2-1","volume":"287","author":"J van Dis","year":"2002","unstructured":"van Dis, J. MSJAMA. Where we live: health care in rural vs urban America. JAMA 287, 108 (2002).","journal-title":"JAMA"},{"key":"416_CR10","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1038\/s41591-020-0942-0","volume":"26","author":"P Tschandl","year":"2020","unstructured":"Tschandl, P. et al. Human\u2013computer collaboration for skin cancer recognition. Nat. Med. 26, 1229\u20131234 (2020).","journal-title":"Nat. Med."},{"key":"416_CR11","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","volume":"18","author":"A Hosny","year":"2018","unstructured":"Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H. & Aerts, H. J. W. L. Artificial intelligence in radiology. Nat. Rev. Cancer 18, 500\u2013510 (2018).","journal-title":"Nat. Rev. Cancer"},{"key":"416_CR12","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1097\/RLI.0b013e3181c02ed5","volume":"45","author":"H-C Bauknecht","year":"2010","unstructured":"Bauknecht, H.-C. et al. Intra- and interobserver variability of linear and volumetric measurements of brain metastases using contrast-enhanced magnetic resonance imaging. Investigative Radiol. 45, 49\u201356 (2010).","journal-title":"Investigative Radiol."},{"key":"416_CR13","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1016\/j.ijrobp.2005.06.034","volume":"64","author":"RJHM Steenbakkers","year":"2006","unstructured":"Steenbakkers, R. J. H. M. et al. Reduction of observer variation using matched CT-PET for lung cancer delineation: a three-dimensional analysis. Int. J. Radiat. Oncol. Biol. Phys. 64, 435\u2013448 (2006).","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"416_CR14","first-page":"207","volume":"9","author":"C Huttin","year":"1997","unstructured":"Huttin, C. The use of clinical guidelines to improve medical practice: main issues in the United States. Int. J. Qual. Health Care 9, 207\u2013214 (1997).","journal-title":"Int. J. Qual. Health Care"},{"key":"416_CR15","unstructured":"RADCOMP Breast Atlas. https:\/\/www.nrgoncology.org\/About-Us\/Center-for-Innovation-in-Radiation-Oncology\/Breast\/RADCOMP-Breast-Atlas."},{"key":"416_CR16","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med."},{"key":"416_CR17","doi-asserted-by":"publisher","unstructured":"Paschali, M., Conjeti, S., Navarro, F. & Navab, N. Generalizability vs. Robustness: Investigating Medical Imaging Networks Using Adversarial Examples. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018 493\u2013501 (2018) https:\/\/doi.org\/10.1007\/978-3-030-00928-1_56 (2018).","DOI":"10.1007\/978-3-030-00928-1_56"},{"key":"416_CR18","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science 234\u2013241 (2015) https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"416_CR19","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L. R. Measures of the amount of ecologic association between species. Ecology 26, 297\u2013302 (1945).","journal-title":"Ecology"},{"key":"416_CR20","unstructured":"S\u00f8rensen, T. A Method of Establishing Groups of Equal Amplitude in Plant Sociology Based on Similarity of Species Content and Its Application to Analyses of the Vegetation on Danish Commons (K\u00f8benhavn, I kommission hos E. Munksgaard, 1948)."},{"key":"416_CR21","unstructured":"GNU General Public License v3.0. https:\/\/www.gnu.org\/licenses\/gpl-3.0.en.html (2007)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00416-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00416-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00416-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:46:23Z","timestamp":1670093183000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00416-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["416"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00416-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,5]]},"assertion":[{"value":"27 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"R.M. discloses research grants from ViewRay, Inc. as well as consulting fees from ViewRay, Inc; AstraZeneca. All unrelated to this work. MTL reports consulting fees with PQBypass, research funding from MedImmune, and a GPU donation from the Nvidia Corporation Academic Program, all unrelated to this research. U.H. reports grants from HeartFlow, MedImmune, Siemens, Genentech, and the American College of Radiology Imaging Network and personal fees from the American Heart Association. H.A. reports consultancy fees and stock from Onc.AI, unrelated to this research. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"43"}}