Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Pre- and post-operative radiographs of patients undergoing joint arthroplasty are often examined for a variety of purposes including preoperative planning and patient assessment. This work examines the feasibility of using active shape models (ASM) to semi-automate measurements from post-operative radiographs for the specific case of the Oxford™ Unicompartmental Knee. Measurements of the proximal tibia and the position of the tibial tray were made using the ASM model and manually. Data were obtained by four observers and one observer took four sets of measurements to allow assessment of the inter- and intra-observer reliability, respectively. The parameters measured were the tibial tray angle, the tray overhang, the tray size, the sagittal cut position, the resection level and the tibial width. Results demonstrated improved reliability (average of 27% and 11.2% increase for intra- and inter-reliability, respectively) and equivalent accuracy (p>0.05 for compared data values) for all of the measurements using the ASM model, with the exception of the tray overhang (p=0.0001). Less time (15s) was required to take measurements using the ASM model compared with manual measurements, which was significant. These encouraging results indicate that semi-automated measurement techniques could improve the reliability of radiographic measurements.

Original publication




Journal article


Eur j radiol

Publication Date





2585 - 2591


Algorithms, Artificial Intelligence, Computer Simulation, Data Interpretation, Statistical, Female, Humans, Male, Models, Anatomic, Models, Statistical, Observer Variation, Radiographic Image Enhancement, Reproducibility of Results, Sensitivity and Specificity, Tibia