Abstract
A method that provides the ability to accurately classify trochlea dysplasia would be a valuable tool in treating patients with unstable patellas and anterior knee pain. In this study, a reference frame and a standardised femoral parameter measurement method for three-dimensional models were established to measure key femoral parameters. An artificial neural network was then trained with these parameters and the matching output from qualitative classifications by three orthopaedic surgeons for each knee. The neural network was then evaluated to test its ability for quantitative classification of normal and dysplastic knees. The maximum agreement between the qualitative and quantitative classification methods was found to be 80.6%, whereas agreement between the surgeons was 69.44%.This was achieved for a neural network with 8 input parameters and 19 hidden-layer neurons. The study shows that there is merit in making use of a trained artificial neural network as an additional tool for classification of trochlear dysplasia.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
