392 Artificial Intelligence Approach in Hip Prosthesis Identification and Assessing Radiographic Outcome Measures

Aim Radiographic assessment is crucial for the success of a hip replacement procedure as an accurately positioned prosthesis indicates favourable long-term outcomes. This project aims to develop a novel artificial intelligence (AI)-based method that can: (1) automatically identify the presence of a hip resurfacing prosthesis in radiographs and (2) calculate the radiographic neck-shaft angle (NSA) of the prosthesis from two-dimensional plane images using both anterior-posterior (AP) and lateral x-rays with high accuracy. Method Using a computer vision and pattern recognition algorithm, the femur shaft and prosthesis regions were identified, and their respective angles were extracted for NSA calculation. A neural network (NN) was then trained using clinician-generated AP radiograph NSAs as ground truths and AI-generated AP and lateral NSAs as features. Spearman's correlation and Kruskal-Wallis tests were calculated to explore any significant association between the final AI-generated and clinician-generated AP x-ray NSAs. Mean absolute error (MAE) and R-squared values were calculated with and without the NN model to identify the model's accuracy and variability. Results There was a statistically significant correlation between the final AI-generated AP x-ray NSAs and the clinician-generated AP x-ray NSAs (rs=0.83,p=0.00). MAE and R2 without the NN were 3.09 and 0.37 respectively. MAE and R2 with the NN were 1.94 and 0.53 respectively. Conclusions The results of this study demonstrate that the identification of hip resurfacing prostheses using artificial intelligence is feasible. By incorporating additional features such as the lateral NSA, the model can provide an accurate prediction of the AP radiographic NSA, closely approximating the ground truth.