Development and Validation of an Artificial Intelligence Preoperative Planning and Patient-Specific Instrumentation System for Total Knee Arthroplasty

Abstract

Background: Accurate preoperative planning for total knee arthroplasty (TKA) is crucial. Computed tomography (CT)-based preoperative planning offers more comprehensive information and can also be used to design patient-specific instrumentation (PSI), but it requires well-reconstructed and segmented images, and the process is complex and time-consuming. This study aimed to develop an artificial intelligence (AI) preoperative planning and PSI system for TKA and to validate its time savings and accuracy in clinical applications.

Methods: The 3D-UNet and modified HRNet neural network structures were used to develop the AI preoperative planning and PSI system (AIJOINT). Forty-two patients who were scheduled for TKA underwent both AI and manual CT processing and planning for component sizing, 20 of whom had their PSIs designed and applied intraoperatively. The time consumed and the size and orientation of the postoperative component were recorded.

Results: The Dice similarity coefficient (DSC) and loss function indicated excellent performance of the neural network structure in CT image segmentation. AIJOINT was faster than conventional methods for CT segmentation (3.74 ± 0.82 vs. 128.88 ± 17.31 min, p < 0.05) and PSI design (35.10 ± 3.98 vs. 159.52 ± 17.14 min, p < 0.05) without increasing the time for size planning. The accuracy of AIJOINT in planning the size of both femoral and tibial components was 92.9%, while the accuracy of the conventional method in planning the size of the femoral and tibial components was 42.9% and 47.6%, respectively (p < 0.05). In addition, AI-based PSI improved the accuracy of the hip-knee-ankle angle and reduced postoperative blood loss (p < 0.05).

Conclusion: AIJOINT significantly reduces the time needed for CT processing and PSI design without increasing the time for size planning, accurately predicts the component size, and improves the accuracy of lower limb alignment in TKA patients, providing a meaningful supplement to the application of AI in orthopaedics.

Keywords: artificial intelligence; knee arthroplasty; machine learning; patient-specific instrumentation.

Figure 1

Development of artificial intelligence preoperative planning and patient-specific instrumentation system for total knee arthroplasty (AIJOINT). (A) Network structure for image segmentation. (B) Segmentation of the femur and tibia. From left to right: images of original computed tomography (CT), manual segmentation, and automatic segmentation with AIJOINT in osteoarthritis. (C) Performance of AIJOINT in automatic segmentation. Dice similarity coefficient (DSC) of the training set and validation set. Loss of the training set and validation set. (D) Modified HRNet neural network structure used to identify featured anatomic landmarks. The red points represent the following automatic identification: the centres of the femoral head and intercondylar fossa and the medullary midpoints of the femur and tibia.

Figure 2

Prosthesis planning module for artificial intelligence preoperative planning and patient-specific instrumentation system for total knee arthroplasty (AIJOINT). (A) 3D reconstructed femur, tibia, and fibula. (B) Preoperative planning of the femoral component. (C) Preoperative planning of the tibial component. (D) 3D reconstruction for postoperative implantation.

Figure 3

Patient-specific instrumentation design module for artificial intelligence preoperative planning and patient-specific instrumentation system for total knee arthroplasty (AIJOINT). (A) Design of the femoral patient-specific instrumentation. The patient-specific instrumentation-guided groove is automatically parallel to the planned osteotomy plane (yellow planes and lines), and the unique fit and shape can be automatically determined. (B) Design of the tibial patient-specific instrumentation. The patient-specific instrumentation-guided groove is automatically parallel to the planned osteotomy plane (yellow planes and lines), and the unique fit and shape can be automatically determined.

Figure 4

Surgical procedure of artificial intelligence preoperative planning and patient-specific instrumentation system for total knee arthroplasty (AIJOINT). (A) Identification of the fitting zones of the custom cutting guides on the femoral bone model. (B) Identification of fitting zones of the custom cutting guides on the tibial bone model. (C) Intraoperative view of the application of the patient-specific instrumentation on the femoral side. (D) Intraoperative view of the application of the patient-specific instrumentation on the tibial side.

Figure 5

Time comparison between artificial intelligence (AI) processing and manual processing. AI was faster than conventional methods for CT segmentation and PSI design (p < 0.05) without increasing the time for size planning. * p < 0.001.