Accuracy verification of the CT-based navigation system ‘OTS’ for severe hip dysplasia: A simulation using 3D bone models of Crowe types II, III, and IV

Introduction : Ortoma Treatment Solution (OTS) is a computer-assisted artificial intelligence (AI)-based orthopedic surgical platform. However, its application in severe hip dysplasia has not been reported. This study aimed to evaluate the accuracy of OTS in patients with severe hip dysplasia using three-dimensional (3D) bone models. Materials and Methods : 3D bone models of severe hip dysplasia (Crowe type II, 10 hips; type III, 10 hips; and type IV, 10 hips) were constructed. The accuracy of automatic AI segmentation, success rate, point matching accuracy across different matching methods, and deviation values at reference points after matching were assessed. Results : The overlap accuracy of segmentation was 1.00 ± 0 in the Crowe II group, 0.99 ± 0.02 in the Crowe III group, and 0.96 ± 0.06 in the Crowe IV group. The "Matching with true and false acetabulum + iliac crest" method achieved a 100% success rate across all groups, with mean deviations of 0.08 ± 0.27 mm in the Crowe II group, 0.12 ± 0.33 mm in the Crowe III group, and 0.14 ± 0.50 mm in the Crowe IV group ( P = 0.572). In the Crowe IV group, the anterior superior iliac spine deviation was significantly lower using the "Matching with true and false acetabulum + iliac crest" method compared to the "Matching with true and false acetabulum" method (0.28 ± 0.49 mm vs. 3.29 ± 2.56 mm, P = 0.030). Conclusions : Segmentation accuracy for severe hip dysplasia was very high. The matching success rate was 100%, with additional points on the iliac crest, which improved matching accuracy and reduced deviations, depending on the case.