Affiliation:
1. Department of Orthopaedics, Wangjing Hospital China Academy of Chinese Medical Sciences Beijing China
2. Department of Industrial & Manufacturing Systems Engineering, School of Mechanical Engineering & Automation Beihang University Beijing China
3. Department of General Surgery The Third Affiliated Hospital of Sun Yat‐sen University Guangzhou China
4. Department of Orthopaedics Weifang Hospital of Traditional Chinese Medicine Weifang Shandong China
Abstract
AbstractPurposePreoperative prudent patient selection plays a crucial role in knee osteoarthritis management but faces challenges in appropriate referrals such as total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA) and nonoperative intervention. Deep learning (DL) techniques can build prediction models for treatment decision‐making. The aim is to develop and evaluate a knee arthroplasty prediction pipeline using three‐view X‐rays to determine the suitable candidates for TKA, UKA or are not arthroplasty candidates.MethodsA study was conducted using three‐view (anterior‐posterior, lateral and patellar) X‐rays and surgical data of patients undergoing TKA, UKA or nonarthroplasty interventions from sites A and B. Data from site A were used to derive and validate models. Data from site B were used as external test set. A DL pipeline combining YOLOv3 and ResNet‐18 with confident learning (CL) was developed. Multiview Convolutional Neural Network, EfficientNet‐b4, ResNet‐101 and the proposed model without CL were also trained and tested. The models were evaluated using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivity and F1 score.ResultsThe data set comprised a total of 1779 knees. Of which 1645 knees were from site A as a derivation set and an internal validation cohort. The external validation cohort consisted of 134 knees. The internal validation cohort demonstrated superior performance for the proposed model augmented with CL, achieving an AUC of 0.94 and an accuracy of 85.9%. External validation further confirmed the model's generalisation, with an AUC of 0.93 and an accuracy of 82.1%. Comparative analysis with other neural network models showed the proposed model's superiority.ConclusionsThe proposed DL pipeline, integrating YOLOv3, ResNet‐18 and CL, provides accurate predictions for knee arthroplasty candidates based on three‐view X‐rays. This prediction model could be useful in performing decision making for the type of arthroplasty procedure in an automated fashion.Level of EvidenceLevel III, diagnostic study.