{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T13:03:09Z","timestamp":1789131789593,"version":"build-2803163510"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"1145","license":[{"start":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T00:00:00Z","timestamp":1677801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,1]]},"abstract":"<jats:sec>\n                  <jats:title>Objective:<\/jats:title>\n                  <jats:p>In this proof-of-concept study, we aimed to develop deep-learning-based classifiers to identify rib fractures on frontal chest radiographs in children under 2 years of age.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods:<\/jats:title>\n                  <jats:p>This retrospective study included 1311 frontal chest radiographs (radiographs with rib fractures, n = 653) from 1231 unique patients (median age: 4 m). Patients with more than one radiograph were included only in the training set. A binary classification was performed to identify the presence or absence of rib fractures using transfer learning and Resnet-50 and DenseNet-121 architectures. The area under the receiver operating characteristic curve (AUC-ROC) was reported. Gradient-weighted class activation mapping was used to highlight the region most relevant to the deep learning models\u2019 predictions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results:<\/jats:title>\n                  <jats:p>On the validation set, the ResNet-50 and DenseNet-121 models obtained an AUC-ROC of 0.89 and 0.88, respectively. On the test set, the ResNet-50 model demonstrated an AUC-ROC of 0.84 with a sensitivity of 81% and specificity of 70%. The DenseNet-50 model obtained an AUC of 0.82 with 72% sensitivity and 79% specificity.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion:<\/jats:title>\n                  <jats:p>In this proof-of-concept study, a deep learning-based approach enabled the automatic detection of rib fractures in chest radiographs of young children with performances comparable to pediatric radiologists. Further evaluation of this approach on large multi-institutional data sets is needed to assess the generalizability of our results.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Advances in knowledge:<\/jats:title>\n                  <jats:p>In this proof-of-concept study, a deep learning-based approach performed well in identifying chest radiographs with rib fractures. These findings provide further impetus to develop deep learning algorithms for identifying rib fractures in children, especially those with suspected physical abuse or non-accidental trauma.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1259\/bjr.20220778","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T13:59:40Z","timestamp":1676901580000},"source":"Crossref","is-referenced-by-count":11,"title":["Deep learning-based prediction of rib fracture presence in frontal radiographs of children under two years of age: a proof-of-concept study"],"prefix":"10.1093","volume":"96","author":[{"given":"Adarsh","family":"Ghosh","sequence":"first","affiliation":[{"name":"Department of Radiology, Cincinnati Children\u2019s Hospital and Medical Center , Cincinnati, Ohio, USA"},{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurav","family":"Bose","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniella","family":"Patton","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ishaan","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vahid","family":"Khalkhali","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Katherine","family":"Henry","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Department of Pediatrics, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA"},{"name":"Center for Pediatric Clinical Effectiveness, Children\u2019s Hospital of Philadelphia , Philadelphia, Pennsylvania, United States"},{"name":"Safe Place: Center for Child Protection and Health, Division of General Pediatrics, Children\u2019s Hospital of Philadelphia , Philadelphia, PA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minhui","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arastoo","family":"Vossough","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond W","family":"Sze","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Sotardi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Francavilla","sequence":"additional","affiliation":[{"name":"Department of Radiology, Children\u2019s Hospital of Philadelphia , Philadelphia, PA, USA"},{"name":"Department of Radiology, Whiddon College of Medicine, University of South Alabama , Mobile, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,3,3]]},"reference":[{"issue":"4","key":"2024050709584925100_b1","doi-asserted-by":"crossref","DOI":"10.1542\/peds.105.4.e48","article-title":"Cause and clinical characteristics of rib fractures in infants","volume":"105","author":"Bulloch","year":"2000","journal-title":"Pediatrics"},{"key":"2024050709584925100_b2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.jacr.2010.09.008","article-title":"ACR appropriateness criteria(\u00ae) on suspected physical abuse-child","volume":"8","author":"Meyer","year":"2011","journal-title":"J Am Coll Radiol"},{"key":"2024050709584925100_b3","unstructured":"www.ACR.org\/-\/media\/ACR\/Files\/Practice-Parameters\/Skeletal-Survey.pdf."},{"key":"2024050709584925100_b4","unstructured":"(N.d.). clinical radiology census report. . Available from: https:\/\/www.rcr.ac.uk\/sites\/default\/files\/clinical_radiology_census_report_2021.pdf"},{"key":"2024050709584925100_b5","unstructured":"Available from: https:\/\/www.rcr.ac.uk\/system\/files\/publication\/field_publication_files\/bfcr174_suspected_physical_abuse (accessed \u00a02 Jan 2023)"},{"key":"2024050709584925100_b6","unstructured":"Global Radiologist Shortage\n          . Internet. RSNA. Available from: https:\/\/www.rsna.org\/news\/2022\/may\/Global-Radiologist-Shortage"},{"key":"2024050709584925100_b7","doi-asserted-by":"crossref","DOI":"10.1186\/s13244-021-00986-8","article-title":"Errors, discrepancies and underlying bias in radiology with case examples: a pictorial review","volume":"12","author":"Onder","year":"2021","journal-title":"Insights Imaging"},{"key":"2024050709584925100_b8","doi-asserted-by":"crossref","first-page":"561","DOI":"10.2214\/AJR.08.1220","article-title":"Biases in radiologic reasoning","volume":"192","author":"Gunderman","year":"2009","journal-title":"AJR Am J Roentgenol"},{"key":"2024050709584925100_b9","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1097\/PEC.0000000000000911","article-title":"Prevalence of abuse among young children with rib fractures: a systematic review","volume":"35","author":"Paine","year":"2019","journal-title":"Pediatr Emerg Care"},{"key":"2024050709584925100_b10","doi-asserted-by":"crossref","first-page":"e1451","DOI":"10.1097\/PEC.0000000000002071","article-title":"Prevalence of abuse and additional injury in young children with rib fractures as their presenting injury","volume":"37","author":"Brennan","year":"2021","journal-title":"Pediatr Emerg Care"},{"key":"2024050709584925100_b11","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1007\/s00247-019-04599-8","article-title":"Characteristics of rib fractures in young abused children","volume":"50","author":"Kriss","year":"2020","journal-title":"Pediatr Radiol"},{"key":"2024050709584925100_b12","doi-asserted-by":"crossref","first-page":"e477","DOI":"10.1542\/peds.2013-3793","article-title":"Evaluating children with fractures for child physical abuse","volume":"133","author":"Flaherty","year":"2014","journal-title":"Pediatrics"},{"key":"2024050709584925100_b13","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1097\/BPO.0b013e3181b2b3ee","article-title":"Child abuse and orthopaedic injury patterns: analysis at a level I pediatric trauma center","volume":"29","author":"Pandya","year":"2009","journal-title":"J Pediatr Orthop"},{"issue":"5","key":"2024050709584925100_b14","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2021200248","article-title":"Development and evaluation of a deep learning algorithm for rib segmentation and fracture detection from multicenter chest CT images","volume":"3","author":"Wu","year":"2021","journal-title":"Radiol Artif Intell"},{"key":"2024050709584925100_b15","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1007\/s00256-021-03709-8","article-title":"A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance","volume":"50","author":"Meng","year":"2021","journal-title":"Skeletal Radiol"},{"key":"2024050709584925100_b16","doi-asserted-by":"crossref","first-page":"869","DOI":"10.3348\/kjr.2019.0651","article-title":"Automatic detection and classification of rib fractures on thoracic CT using convolutional neural network: accuracy and feasibility","volume":"21","author":"Zhou","year":"2020","journal-title":"Korean J Radiol"},{"key":"2024050709584925100_b17","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1007\/s00256-022-04070-0","article-title":"Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning","volume":"51","author":"Hayashi","year":"2022","journal-title":"Skeletal Radiol"},{"key":"2024050709584925100_b18","doi-asserted-by":"crossref","first-page":"343","DOI":"10.3348\/kjr.2021.0449","article-title":"Deep learning-assisted diagnosis of pediatric skull fractures on plain radiographs","volume":"23","author":"Choi","year":"2022","journal-title":"Korean J Radiol"},{"key":"2024050709584925100_b19","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.diii.2021.10.007","article-title":"External validation of a commercially available deep learning algorithm for fracture detection in children","volume":"103","author":"Dupuis","year":"2022","journal-title":"Diagn Interv Imaging"},{"issue":"1","key":"2024050709584925100_b20","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2019190015","article-title":"The effect of image resolution on deep learning in radiography","volume":"2","author":"Sabottke","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"2024050709584925100_b21","unstructured":"PyTorch documentation \u2014 PyTorch 1.11.0 documentation\n          . Internet. Available from: https:\/\/pytorch.org\/docs\/stable\/index.html (accessed \u00a07 Jan 2022)"},{"key":"2024050709584925100_b22","first-page":"100916","volume-title":"Informatics in Medicine Unlocked","author":"Hossain","year":"2022"},{"key":"2024050709584925100_b23","doi-asserted-by":"crossref","first-page":"3462","DOI":"10.1109\/CVPR.2017.369","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR","author":"Wang","year":"2017"},{"key":"2024050709584925100_b24","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"2024050709584925100_b25","unstructured":"GitHub - jacobgil\/pytorch-grad-CAM: Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Examples for classification, object detection, segmentation, embedding networks and more. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM. Available from: https:\/\/github.com\/jacobgil\/pytorch-grad-cam"},{"key":"2024050709584925100_b26","volume-title":"PyTorch Computer Vision Cookbook","author":"GitHub - PacktPublishing\/PyTorch-Computer-Vision-Cookbook"},{"key":"2024050709584925100_b27","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2024050709584925100_b28","unstructured":"MedCalc\u2019s Diagnostic test evaluation calculator\n          . Internet. Available from: https:\/\/www.medcalc.org\/calc\/diagnostic_test.php (accessed \u00a07 Jan 2022)"},{"key":"2024050709584925100_b29","first-page":"1","volume-title":"2021 9th International Conference on Orange Technology (ICOT)","author":"Tsai","year":"2021"},{"key":"2024050709584925100_b30","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1007\/s00247-010-1953-7","article-title":"Value of postmortem thoracic CT over radiography in imaging of pediatric rib fractures","volume":"41","author":"Hong","year":"2011","journal-title":"Pediatr Radiol"},{"key":"2024050709584925100_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2020.103106","article-title":"Deep-learning-assisted detection and segmentation of rib fractures from CT scans: development and validation of fracnet","volume":"62","author":"Jin","year":"2020","journal-title":"EBioMedicine"},{"key":"2024050709584925100_b32","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1093\/aje\/kwj063","article-title":"The inconsistency of \u201coptimal\u201d cutpoints obtained using two criteria based on the receiver operating characteristic curve","volume":"163","author":"Perkins","year":"2006","journal-title":"Am J Epidemiol"},{"key":"2024050709584925100_b33","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/S0167-5877(00)00115-X","article-title":"Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests","volume":"45","author":"Greiner","year":"2000","journal-title":"Prev Vet Med"},{"key":"2024050709584925100_b34","unstructured":"Available from: https:\/\/www.acr.org\/-\/media\/ACR\/Files\/Practice-Parameters\/Skeletal-Survey.pdf (accessed \u00a0 Jul 2022)"}],"container-title":["The British Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjr\/article-pdf\/96\/1145\/20220778\/57431726\/bjr.20220778.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjr\/article-pdf\/96\/1145\/20220778\/57431726\/bjr.20220778.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T09:59:04Z","timestamp":1715075944000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjr\/article\/doi\/10.1259\/bjr.20220778\/7469090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,3]]},"references-count":34,"journal-issue":{"issue":"1145","published-online":{"date-parts":[[2023,3,3]]},"published-print":{"date-parts":[[2023,5,1]]}},"URL":"https:\/\/doi.org\/10.1259\/bjr.20220778","relation":{},"ISSN":["0007-1285","1748-880X"],"issn-type":[{"value":"0007-1285","type":"print"},{"value":"1748-880X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,5,1]]},"published":{"date-parts":[[2023,3,3]]},"article-number":"20220778"}}