{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:17:08Z","timestamp":1784614628430,"version":"3.55.0"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T00:00:00Z","timestamp":1569196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T00:00:00Z","timestamp":1569196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"published-print":{"date-parts":[[2019,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n              <jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Structured reports have been shown to improve communication between radiologists and providers. However, some radiologists are concerned about resultant decreased workflow efficiency. We tested a machine learning-based algorithm designed to convert unstructured computed tomography pulmonary angiography (CTPA) reports into structured reports.<\/jats:p>\n              <\/jats:sec>\n              <jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>A self-supervised convolutional neural network-based algorithm was trained on a dataset of 475 manually structured CTPA reports. Labels for individual statements included \u201cpulmonary arteries,\u201d \u201clungs and airways,\u201d \u201cpleura,\u201d \u201cmediastinum and lymph nodes,\u201d \u201ccardiovascular,\u201d \u201csoft tissues and bones,\u201d \u201cupper abdomen,\u201d and \u201clines\/tubes.\u201d The algorithm was applied to a test set of 400 unstructured CTPA reports, generating a predicted label for each statement, which was evaluated by two independent observers. Per-statement accuracy was calculated based on strict criteria (algorithm label counted as correct if the statement unequivocally contained content only related to that particular label) and a modified criteria, accounting for problematic statements, including typographical errors, statements that did not fit well into the classification scheme, statements containing content for multiple labels, etc.<\/jats:p>\n              <\/jats:sec>\n              <jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Of the 4,157 statements, 3,806 (91.6%) and 3,986 (95.9%) were correctly labeled by the algorithm using strict and modified criteria, respectively, while 274 (6.6%) were problematic for the manual observers to label, the majority of which (<jats:italic>n<\/jats:italic>\u2009=\u2009173) were due to more than one section being included in one statement.<\/jats:p>\n              <\/jats:sec>\n              <jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>This algorithm showed high accuracy in converting free-text findings into structured reports, which could improve communication between radiologists and clinicians without loss of productivity and provide more structured data for research\/data mining applications.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s41747-019-0118-1","type":"journal-article","created":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T12:02:46Z","timestamp":1569240166000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Deep learning to convert unstructured CT pulmonary angiography reports into structured reports"],"prefix":"10.1186","volume":"3","author":[{"given":"Adam","family":"Spandorfer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody","family":"Branch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooyan","family":"Sahbaee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"U. Joseph","family":"Schoepf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James G.","family":"Ravenel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-4570","authenticated-orcid":false,"given":"John W.","family":"Nance","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,9,23]]},"reference":[{"key":"118_CR1","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.1007\/s00261-015-0420-1","volume":"40","author":"LP Marcal","year":"2015","unstructured":"Marcal LP, Fox PS, Evans DB et al (2015) Analysis of free-form radiology dictations for completeness and clarity for pancreatic cancer staging. Abdom Imaging 40:2391. \n                    https:\/\/doi.org\/10.1007\/s00261-015-0420-1","journal-title":"Abdom Imaging"},{"issue":"1","key":"118_CR2","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1148\/radiol.11101913","volume":"260","author":"Lawrence H. Schwartz","year":"2011","unstructured":"Schwartz LH, Panicek DM, Berk AR, Li Y, Hricak H (2011) Improving communication of diagnostic radiology findings through structured reporting. Radiology 260:174\u2013181. \n                    https:\/\/doi.org\/10.1148\/radiol.11101913","journal-title":"Radiology"},{"issue":"7","key":"118_CR3","doi-asserted-by":"publisher","first-page":"3009","DOI":"10.1007\/s00330-017-5161-9","volume":"28","author":"Andrea Franconeri","year":"2017","unstructured":"Franconeri, A, Fang J, Camey B et al (2017) Structured vs narrative reporting of pelvic MRI for fibroids: clarity and impact on treatment planning. Eur Radiol 28:3009\u20133017. \n                    https:\/\/doi.org\/10.1007\/s00330-017-5161-9","journal-title":"European Radiology"},{"issue":"2","key":"118_CR4","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.jcct.2017.02.011","volume":"11","author":"Harvey S. Hecht","year":"2017","unstructured":"Hecht HS, Cronin P, Blaha MJ et al (2017) 2016 SCCT\/STR guidelines for coronary artery calcium scoring of noncontrast noncardiac chest CT scans: a report of the Society of Cardiovascular Computed Tomography and Society of Thoracic Radiology. J Thorac Imaging 11:74\u201384. \n                    https:\/\/doi.org\/10.1016\/j.jcct.2017.02.011","journal-title":"Journal of Cardiovascular Computed Tomography"},{"issue":"1","key":"118_CR5","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1097\/RTI.0000000000000165","volume":"31","author":"Eduardo J. Mortani Barbosa","year":"2016","unstructured":"Mortani Barbosa EJ Jr, Lynch MC, Langlotz CP, Gefter WB (2016) Optimization of radiology reports for intensive care unit portable chest radiographs: perceptions and preferences of radiologists and ICU practitioners. J Thorac Imaging 31:43\u201348. \n                    https:\/\/doi.org\/10.1097\/RTI.0000000000000165","journal-title":"Journal of Thoracic Imaging"},{"issue":"10","key":"118_CR6","doi-asserted-by":"publisher","first-page":"4110","DOI":"10.1007\/s00330-017-4778-z","volume":"27","author":"Sebastian Gassenmaier","year":"2017","unstructured":"Gassenmaier S, Armbruster M, Haasters F et al (2017) Structured reporting of MRI of the shoulder - improvement of report quality? Eur Radiol 27:4110\u20134119. \n                    https:\/\/doi.org\/10.1007\/s00330-017-4778-z","journal-title":"European Radiology"},{"key":"118_CR7","doi-asserted-by":"publisher","unstructured":"Buckley BW, Daly L, Allen GN, Ridge CA (2017) Recall of structured radiology reports is significantly superior to that of unstructured reports. Br J Radiol 91:20170670. \n                    https:\/\/doi.org\/10.1259\/bjr.20170670","DOI":"10.1259\/bjr.20170670"},{"issue":"5","key":"118_CR8","doi-asserted-by":"publisher","first-page":"1934","DOI":"10.1007\/s00330-016-4553-6","volume":"27","author":"Lorenzo Faggioni","year":"2016","unstructured":"Faggioni L, Coppola F, Ferrari R, Neri E, Regge D (2017) Usage of structured reporting in radiological practice: results from an Italian online survey. Eur Radiol 27:1934\u20131943. \n                    https:\/\/doi.org\/10.1007\/s00330-016-4553-6","journal-title":"European Radiology"},{"issue":"12","key":"118_CR9","doi-asserted-by":"publisher","first-page":"1779","DOI":"10.1016\/j.jvir.2016.07.016","volume":"27","author":"Justin P. McWilliams","year":"2016","unstructured":"McWilliams JP, Shah RP, Quirk M et al (2016) Standardized reporting in IR: a prospective multi-institutional pilot study. J Vasc Interv Radiol 27:1779\u20131785. \n                    https:\/\/doi.org\/10.1016\/j.jvir.2016.07.016","journal-title":"Journal of Vascular and Interventional Radiology"},{"issue":"2","key":"118_CR10","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.acra.2014.08.014","volume":"22","author":"Daniel K. Powell","year":"2015","unstructured":"Powell DK, Silberzweig JE (2015) State of structured reporting in radiology, a survey. Acad Radiol 22:226\u2013233. \n                    https:\/\/doi.org\/10.1016\/j.acra.2014.08.014","journal-title":"Academic Radiology"},{"issue":"2","key":"118_CR11","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1148\/radiol.2341040049","volume":"234","author":"Keith J. Dreyer","year":"2005","unstructured":"Dreyer KJ, Kalra MK, Maher MM et al (2005) Application of recently developed computer algorithm for automatic classification of unstructured radiology reports: validation study. Radiology 234:323\u2013329. \n                    https:\/\/doi.org\/10.1148\/radiol.2341040049","journal-title":"Radiology"},{"issue":"5","key":"118_CR12","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1136\/amiajnl-2013-002516","volume":"21","author":"D. H. M. Nguyen","year":"2014","unstructured":"Nguyen DH, Patrick JD (2014) Supervised machine learning and active learning in classification of radiology reports. J Am Med Inform Assoc 21:893\u2013901. \n                    https:\/\/doi.org\/10.1136\/amiajnl-2013-002516","journal-title":"Journal of the American Medical Informatics Association"},{"issue":"3","key":"118_CR13","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1148\/radiol.2493080988","volume":"249","author":"David L. Weiss","year":"2008","unstructured":"Weiss DL, Langlotz CP (2008) Structured reporting: patient care enhancement or productivity nightmare? Radiology 249:739\u2013747. \n                    https:\/\/doi.org\/10.1148\/radiol.2493080988","journal-title":"Radiology"},{"key":"118_CR14","doi-asserted-by":"publisher","unstructured":"Masino AJ, Grundmeier RW, Pennington JW, Germiller JA, Crenshaw ED 3rd (2016) Temporal bone radiology report classification using open source machine learning and natural language processing libraries. BMC Med Inform Decis Mal 16:65. \n                    https:\/\/doi.org\/10.1186\/s12911-016-0306-3","DOI":"10.1186\/s12911-016-0306-3"},{"key":"118_CR15","doi-asserted-by":"publisher","unstructured":"Pathak S, Rossen JV, Vijlbrief O, Geerdink J, Seifert C, van Keulen M (2019) Post-structuring radiology reports of breast cancer patients for clinical quality assurance. IEEE\/ACM Trans Comput Biol Bioinform. \n                    https:\/\/doi.org\/10.1109\/TCBB.2019.2914678","DOI":"10.1109\/TCBB.2019.2914678"},{"key":"118_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.artmed.2015.09.007","volume":"66","author":"S Hassanpour","year":"2016","unstructured":"Hassanpour S, Langlotz CP (2016) Information extraction from multi-institutional radiology reports. Artif Intell Med 66:29\u201339. \n                    https:\/\/doi.org\/10.1016\/j.artmed.2015.09.007","journal-title":"Artif Intell Med"},{"key":"118_CR17","doi-asserted-by":"publisher","unstructured":"He T, Puppala M, Ezeana CF et al (2019) A deep learning-based decision support tool for precision risk assessment of breast cancer. JCO Clin Cancer Inform 3:1-12. \n                    https:\/\/doi.org\/10.1200\/CCI.18.00121","DOI":"10.1200\/CCI.18.00121"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-019-0118-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s41747-019-0118-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-019-0118-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,21]],"date-time":"2020-09-21T23:10:42Z","timestamp":1600729842000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurradiolexp.springeropen.com\/articles\/10.1186\/s41747-019-0118-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,23]]},"references-count":17,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["118"],"URL":"https:\/\/doi.org\/10.1186\/s41747-019-0118-1","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,23]]},"assertion":[{"value":"15 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was approved by the local institutional review board.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Puneet Sharma and Pooyan Sahbaee are employees of Siemens Healthineers. Dr. Schoepf receives institutional research support from Astellas, Bayer Healthcare, General Electric Healthcare, and Siemens Healthineers and has received consulting or speaking fees from Bayer, Guerbet, HeartFlow, and Siemens Healthineers. Dr. Nance is a speaker for Genentech and Boehringer Ingelheim. The other authors have no competing interest to disclose.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"37"}}