Fully automated workflow for designing patient-specific orthopaedic implants: application to total knee arthroplasty

2024-03-22

AI Summary

To address the low efficiency and heavy manual dependency in personalized prosthetic design for total knee arthroplasty (TKA), this study proposes the first end-to-end, fully automated CT-driven prosthetic design pipeline. Methodologically, we integrate a deep learning–based segmentation network with an enhanced statistical shape model (SSM) to establish a 77-dimensional parametric morphological modeling framework guided by anatomical landmark points, enabling fully unsupervised generation of highly patient-specific prostheses directly from CT scans. Our key contribution is the first clinically viable, real-time closed-loop design system—achieving an average processing time of 15 minutes—with segmentation accuracy of 0.4 ± 0.2 mm, whole-bone reconstruction error of 1.0 ± 0.3 mm, and prosthetic fit error of 0.9 ± 0.5 mm. This significantly improves preoperative planning efficiency and enhances the level of patient-specific customization.

Technology Category

• Computer Vision: Segmentation
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Data transparency and provenance

Abstract

Background. Osteoarthritis affects about 528 million people worldwide, causing pain and stiffness in the joints. Arthroplasty is commonly performed to treat joint osteoarthritis, reducing pain and improving mobility. Nevertheless, a significant share of patients remain unsatisfied with their surgery. Personalised arthroplasty was introduced to improve surgical outcomes however current solutions require delays, making it difficult to integrate in clinical routine. We propose a fully automated workflow to design patient-specific implants for total knee arthroplasty. Methods. The proposed pipeline first uses artificial neural networks to segment the femur and tibia proximal and distal extremities. Then the full bones are reconstructed using augmented statistical shape models, combining shape and landmarks information. Finally, 77 morphological parameters are computed to design patient-specific implants. The developed workflow has been trained on 91 CT scans and evaluated on 41 CT scans, in terms of accuracy and execution time. Results. The workflow accuracy was $0.4pm0.2mm$ for segmentation, $1.0pm0.3mm$ for full bone reconstruction, and $2.2pm1.5mm$ for anatomical landmarks determination. The custom implants fitted the patients' anatomy with $0.9pm0.5mm$ accuracy. The whole process from segmentation to implants' design lasted about 15 minutes. Conclusion. The proposed workflow performs a fast and reliable personalisation of knee implants, directly from a CT image without requiring any manual intervention. It allows the establishment of a patient-specific pre-operative planning in a very short time, making it easily available for all patients. Combined with efficient implant manufacturing techniques, this solution could help answer the growing number of arthroplasties while reducing complications and improving patients' satisfaction.

Problem

• Rapid Prototyping
• Orthopedic Implant Customization
• Total Knee Arthroplasty

Innovation

• Automated Workflow
• Personalized Implant Design
• Efficiency in Knee Replacement Surgery