{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:51:10Z","timestamp":1781826670808,"version":"3.54.5"},"reference-count":32,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2022,9,4]],"date-time":"2022-09-04T00:00:00Z","timestamp":1662249600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Acta Radiol"],"published-print":{"date-parts":[[2023,4]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Radial head fractures are often evaluated in emergency departments and can easily be missed. Automated or semi-automated detection methods that help physicians may be valuable regarding the high miss rate.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To evaluate the accuracy of combined deep, transfer, and classical machine learning approaches on a small dataset for determination of radial head fractures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and Methods<\/jats:title>\n                    <jats:p>A total of 48 patients with radial head fracture and 56 patients without fracture on elbow radiographs were retrospectively evaluated. The input images were obtained by cropping anteroposterior elbow radiographs around a center-point on the radial head. For fracture determination, an algorithm based on feature extraction using distinct prototypes of pretrained networks (VGG16, ResNet50, InceptionV3, MobileNetV2) representing four different approaches was developed. Reduction of feature space dimensions, feeding the most relevant features, and development of ensemble of classifiers were utilized.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The algorithm with the best performance consisted of preprocessing the input, computation of global maximum and global mean outputs of four distinct pretrained networks, dimensionality reduction by applying univariate and ensemble feature selectors, and applying Support Vector Machines and Random Forest classifiers to the transformed and reduced dataset. A maximum accuracy of 90% with MobileNetV2 pretrained features was reached for fracture determination with a small sample size.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Radial head fractures can be determined with a combined approach and limitations of the small sample size can be overcome by utilizing pretrained deep networks with classical machine learning methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/02841851221122424","type":"journal-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T02:10:03Z","timestamp":1662343803000},"page":"1476-1483","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":5,"title":["All-star approach to a small medical imaging dataset: combined deep, transfer, and classical machine learning approaches for the determination of radial head fractures"],"prefix":"10.1177","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0971-3827","authenticated-orcid":false,"given":"Ozgur I","family":"Koska","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Dokuz Eyl\u00fcl University Engineering Faculty, \u0130zmir, Turkey"},{"name":"ETHZ Computer Vision Laboratory, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4073-9665","authenticated-orcid":false,"given":"Atilla Hikmet","family":"\u00c7ilengir","sequence":"additional","affiliation":[{"name":"Department of Radiology, Izmir Demokrasi University, Izmir, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhsin Engin","family":"Ulu\u00e7","sequence":"additional","affiliation":[{"name":"Department of Radiology, Izmir Katip Celebi University Ataturk Training and Research Hospital, Izmir, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aylin","family":"Y\u00fccel","sequence":"additional","affiliation":[{"name":"Department of Radiology, Afyonkarahisar Health Sciences University, Afyonkarahisar, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6755-2131","authenticated-orcid":false,"given":"\u00d6zg\u00fcr","family":"Tosun","sequence":"additional","affiliation":[{"name":"Department of Radiology, Izmir Katip Celebi University Ataturk Training and Research Hospital, Izmir, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2022,9,4]]},"reference":[{"key":"bibr1-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/s11999-009-1183-1"},{"key":"bibr2-02841851221122424","first-page":"22","volume-title":"Shoulder and Elbow Trauma","author":"Roidis NT","year":"2004"},{"key":"bibr3-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1016\/j.injury.2015.10.050"},{"key":"bibr4-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180001"},{"key":"bibr5-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180066"},{"key":"bibr6-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-019-03284-z"},{"key":"bibr7-02841851221122424","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2015. arXiv:1409.1556v6 cs.CV. Available at: https:\/\/arxiv.org\/abs\/1409.1556v6 (last accessed December 2019)."},{"key":"bibr8-02841851221122424","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems \u2013 Volume 1, 2012, pp. 1097\u20131105. Red Hook, NY: Curran Associates Inc."},{"key":"bibr9-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"bibr10-02841851221122424","unstructured":"Howard AG, Zhu M, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017. arXiv:1704.04861v1 cs.CV. Available at: https:\/\/arxiv.org\/abs\/1704.04861 (last accessed December 2019)."},{"key":"bibr11-02841851221122424","unstructured":"Rajpurkar P, Irvin J, Bagul A, et al. MURA: large dataset for abnormality detection in musculoskeletal radiographs. 2018. arXiv:1712.06957v4 physics.med-ph. Available at: https:\/\/arxiv.org\/abs\/1712.06957 (last accessed December 2019)."},{"key":"bibr12-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2017.11.015"},{"key":"bibr13-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.05.011"},{"key":"bibr14-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806905115"},{"key":"bibr15-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1080\/17453674.2017.1344459"},{"key":"bibr16-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-018-3016-3"},{"key":"bibr17-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06167-y"},{"key":"bibr18-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000000848"},{"key":"bibr19-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-018-0167-7"},{"key":"bibr20-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"bibr21-02841851221122424","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, et al. Imagenet: a large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2019:248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"bibr22-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1007\/b95439"},{"key":"bibr23-02841851221122424","first-page":"18","volume":"2","author":"Liaw A","year":"2002","journal-title":"R News"},{"key":"bibr24-02841851221122424","unstructured":"Hernandez-Garcia A, Konig P. Data augmentation instead of explicit regularization. 2019. arXiv:1806.03852v4 cs.CV. Available at: https:\/\/arxiv.org\/abs\/1806.03852 (last accessed December 2019)."},{"key":"bibr25-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1080\/17453674.2019.1600125"},{"key":"bibr26-02841851221122424","unstructured":"Anu TC, Mallikarjunaswamy MS, Raman R. Detection of bone fracture using image processing methods. IJCA Proceedings on National Conference on Power Systems and Industrial Automation NCPSIA, 2015, pp. 6\u20139."},{"key":"bibr27-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180015"},{"key":"bibr28-02841851221122424","doi-asserted-by":"publisher","DOI":"10.3390\/reports2040026"},{"key":"bibr29-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2015.7163993"},{"key":"bibr30-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1080\/17453674.2018.1453714"},{"key":"bibr31-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1177\/0165551515613226"},{"key":"bibr32-02841851221122424","doi-asserted-by":"publisher","DOI":"10.1177\/0165551516677911"}],"container-title":["Acta Radiologica"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851221122424","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02841851221122424","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851221122424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:28:10Z","timestamp":1777390090000},"score":1,"resource":{"primary":{"URL":"http:\/\/journals.sagepub.com\/doi\/10.1177\/02841851221122424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,4]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["10.1177\/02841851221122424"],"URL":"https:\/\/doi.org\/10.1177\/02841851221122424","relation":{},"ISSN":["0284-1851","1600-0455"],"issn-type":[{"value":"0284-1851","type":"print"},{"value":"1600-0455","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,4]]}}}