{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T13:55:14Z","timestamp":1794491714051,"version":"4.9.1"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T00:00:00Z","timestamp":1610668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T00:00:00Z","timestamp":1610668800000},"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":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This study was performed to propose a method, the Feature Ambiguity Mitigate Operator (FAMO) model, to mitigate feature ambiguity in bone fracture detection on radiographs of various body parts. A total of 9040 radiographic studies were extracted. These images were classified into several body part types including 1651 hand, 1302 wrist, 406 elbow, 696 shoulder, 1580 pelvic, 948 knee, 1180 ankle, and 1277 foot images. Instance segmentation was annotated by radiologists. The ResNext-101+FPN was employed as the baseline network structure and the FAMO model for processing. The proposed FAMO model and other ablative models were tested on a test set of 20% total radiographs in a balanced body part distribution. To the per-fracture extent, an AP (average precision) analysis was performed. For per-image and per-case, the sensitivity, specificity, and AUC (area under the receiver operating characteristic curve) were analyzed. At the per-fracture level, the controlled experiment set the baseline AP to 76.8% (95% CI: 76.1%, 77.4%), and the major experiment using FAMO as a preprocessor improved the AP to 77.4% (95% CI: 76.6%, 78.2%). At the per-image level, the sensitivity, specificity, and AUC were 61.9% (95% CI: 58.7%, 65.0%), 91.5% (95% CI: 89.5%, 93.3%), and 74.9% (95% CI: 74.1%, 75.7%), respectively, for the controlled experiment, and 64.5% (95% CI: 61.3%, 67.5%), 92.9% (95% CI: 91.0%, 94.5%), and 77.5% (95% CI: 76.5%, 78.5%), respectively, for the experiment with FAMO. At the per-case level, the sensitivity, specificity, and AUC were 74.9% (95% CI: 70.6%, 78.7%), 91.7%% (95% CI: 88.8%, 93.9%), and 85.7% (95% CI: 84.8%, 86.5%), respectively, for the controlled experiment, and 77.5% (95% CI: 73.3%, 81.1%), 93.4% (95% CI: 90.7%, 95.4%), and 86.5% (95% CI: 85.6%, 87.4%), respectively, for the experiment with FAMO. In conclusion, in bone fracture detection, FAMO is an effective preprocessor to enhance model performance by mitigating feature ambiguity in the network.<\/jats:p>","DOI":"10.1038\/s41598-021-81236-1","type":"journal-article","created":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T11:02:30Z","timestamp":1610708550000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["The Feature Ambiguity Mitigate Operator model helps improve bone fracture detection on X-ray radiograph"],"prefix":"10.1038","volume":"11","author":[{"given":"Hui-Zhao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Feng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Qing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Zhou","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuo-Jun","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Juan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Qing","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Qin","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bu-Lang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,15]]},"reference":[{"key":"81236_CR1","volume-title":"Orthopedic Imaging A Practical Approach","author":"JB Adam Greenspan","year":"2019","unstructured":"Adam Greenspan, J. B. Orthopedic Imaging A Practical Approach 6th edn. (Science Press, Beijing, 2019).","edition":"6"},{"key":"81236_CR2","volume-title":"Clinical Epidemiology of Orthopaedic Trauma","author":"Z Yingze","year":"2016","unstructured":"Yingze, Z. Clinical Epidemiology of Orthopaedic Trauma 2nd edn. (Thieme, New York, 2016).","edition":"2"},{"key":"81236_CR3","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1080\/17453674.2017.1344459","volume":"88","author":"J Olczak","year":"2017","unstructured":"Olczak, J. et al. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 88, 581\u2013586. https:\/\/doi.org\/10.1080\/17453674.2017.1344459 (2017).","journal-title":"Acta Orthop"},{"key":"81236_CR4","unstructured":"Gale, W., Oakden-Rayner, L., Carneiro, G., Bradley, A. P. & Palmer, L. J. Detecting hip fractures with radiologist-level performance using deep neural networks. http:\/\/arxiv.org\/abs\/1711.06504 arXiv [cs.CV] (2017)."},{"key":"81236_CR5","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., van der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2261\u20132269 https:\/\/doi.org\/10.1109\/CVPR.2017.243 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"81236_CR6","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1007\/s10278-018-0167-7","volume":"32","author":"G Kitamura","year":"2019","unstructured":"Kitamura, G., Chung, C. Y. & Moore, B. E. II. Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, de novo training, and multiview incorporation. J. Digit Imaging 32, 672\u2013677. https:\/\/doi.org\/10.1007\/s10278-018-0167-7 (2019).","journal-title":"J. Digit Imaging"},{"key":"81236_CR7","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180001","author":"YL Thian","year":"2019","unstructured":"Thian, Y. L. et al. Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiol. Artif. Intell. https:\/\/doi.org\/10.1148\/ryai.2019180001 (2019).","journal-title":"Radiol. Artif. Intell."},{"key":"81236_CR8","doi-asserted-by":"publisher","first-page":"11591","DOI":"10.1073\/pnas.1806905115","volume":"115","author":"R Lindsey","year":"2018","unstructured":"Lindsey, R. et al. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci USA 115, 11591\u201311596. https:\/\/doi.org\/10.1073\/pnas.1806905115 (2018).","journal-title":"Proc Natl Acad Sci USA"},{"key":"81236_CR9","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z. & He, K. Aggregated residual transformations for deep neural networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 5987\u20135995. https:\/\/doi.org\/10.1109\/CVPR.2017.634 (2017).","DOI":"10.1109\/CVPR.2017.634"},{"key":"81236_CR10","doi-asserted-by":"publisher","unstructured":"Lin, T. Y. et al. Feature pyramid networks for object detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106 (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"81236_CR11","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1080\/00107514.2018.1515261","volume":"59","author":"NE Myridis","year":"2018","unstructured":"Myridis, N. E. Advances in imaging and electron physics. Contemp. Phys. 59, 411\u2013412 (2018).","journal-title":"Contemp. Phys."},{"key":"81236_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. Mask R-CNN. In 2017 IEEE International Conference on Computer Vision (ICCV) 2980\u20132988. https:\/\/doi.org\/10.1109\/ICCV.2017.322 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"key":"81236_CR13","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowsk, L., Kyrola, A. & He, K. Accurate, large minibatch SGD: Training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81236-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81236-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81236-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T02:12:01Z","timestamp":1670033521000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81236-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,15]]},"references-count":13,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["81236"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-81236-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,15]]},"assertion":[{"value":"28 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1589"}}