Radiograph Assessment with Artificial Intellegince Software

The investigators are targeting to study the accuracy of the AI algorithms which comprise IBL LAMA compared to the radiologists' estimation of diagnostic angles and lengths of standard AP standing lower extremity radiographs. Currently, radiologists make the measurement using manual annotations or using specialized semi-automated computerized tools implemented in radiological viewers. As part of this study, a panel of radiologists will create a clinical reference standard ("gold standard") by making measurements of diagnostic angles and lengths on a pool of standing lower extremity radiographs with the aid of clinical software such as TraumaCad (Brainlab, Westchester, IL, USA) and mediCAD (Hectec GmbH, Germany) . The measurements of IBL LAMA will be compared to the clinical reference standard. The investigators plan to use statistical tests of agreement based on Bland-Altman plots, as well as the inter-class correlation coefficient (ICC). Furthermore, the time needed to analyze the images manually should be compared to the time needed to check the result of the Artificial Intelligence algorithm.