000K utf8 1100 2022$c2022-03-07 1500 eng 2050 urn:nbn:de:hbz:465-20240220-093907-1 2051 10.1038/s41598-022-08020-7 3000 Quinsten, Anton S. 3010 Demircioğlu, Aydin 3010 Forsting, Michael 3010 Nassenstein, Kai 3010 Umutlu, Lale 4000 Determining the anatomical site in knee radiographs using deep learning [Quinsten, Anton S.] 4209 An important quality criterion for radiographs is the correct anatomical side marking. A deep neural network is evaluated to predict the correct anatomical side in radiographs of the knee acquired in anterior–posterior direction. In this retrospective study, a ResNet-34 network was trained on 2892 radiographs from 2540 patients to predict the anatomical side of knees in radiographs. The network was evaluated in an internal validation cohort of 932 radiographs of 816 patients and in an external validation cohort of 490 radiographs from 462 patients. The network showed an accuracy of 99.8% and 99.9% on the internal and external validation cohort, respectively, which is comparable to the accuracy of radiographers. Anatomical side in radiographs of the knee in anterior–posterior direction can be deduced from radiographs with high accuracy using deep learning. 4950 https://doi.org/10.1038/s41598-022-08020-7$xR$3Volltext$534 4950 https://nbn-resolving.org/urn:nbn:de:hbz:465-20240220-093907-1$xR$3Volltext$534 4961 https://duepublico2.uni-due.de/receive/duepublico_mods_00078808 5051 610