Back to all papers

Patient-Specific Instrumentation Improves Technical Execution Accuracy After Artificial Intelligence-Assisted Preoperative Planning in Medial Unicompartmental Knee Arthroplasty.

July 21, 2026pubmed logopapers

Authors

Liu D,Zhao Y,Gao Z,Niu J,Zhang Y,Liu X,Ji G,Liu G

Affiliations (7)

  • Department of Orthopaedics, The First Hospital of Hebei Medical University, Shijiazhuang, China.
  • Department of Orthopaedics, Handan First Hospital, Handan, China.
  • Longwood Valley Medical Technology Co Ltd, Beijing, China.
  • Longwood Valley Medical Technology Co Ltd, Beijing, China. [email protected].
  • Tsinghua University, Beijing, China. [email protected].
  • Department of Orthopaedics, The First Hospital of Hebei Medical University, Shijiazhuang, China. [email protected].
  • Department of Orthopaedics, The First Hospital of Hebei Medical University, Shijiazhuang, China. [email protected].

Abstract

Artificial intelligence (AI)-assisted preoperative planning may improve anatomic characterization and implant-size prediction in unicompartmental knee arthroplasty (UKA). However, whether patient-specific instrumentation (PSI) provides additional technical benefit when added to AI-assisted planning remains unclear. We developed and validated an AI-assisted preoperative planning workflow combined with PSI for medial UKA and evaluated its effect on implant positioning accuracy. A hybrid architecture combining a convolutional neural network-based U-Net with a Transformer-based deep learning module (C-T Module) was developed to automate CT processing for AI-assisted preoperative planning and PSI design in UKA. Segmentation performance of the C-T Module was compared with that of a conventional 3D U-Net. PSI feasibility was validated using synthetic bone models. In a prospective randomized clinical study, 24 patients underwent AI-assisted planning plus PSI-assisted medial UKA (PSI group) and 24 patients underwent the same AI-assisted planning workflow followed by conventionally instrumented medial UKA (control group). Surgical accuracy, perioperative outcomes, short-term outcomes and implant-size prediction accuracy were compared. The C-T Module demonstrated superior image segmentation accuracy compared to the conventional 3D U-Net. Compared with the control group, the PSI group significantly improved surgical accuracy, including more accurate tibial component positioning, greater tibial coverage, and less deviation in proximal tibial resection (all P < 0.001). Except for the significantly longer skin incision in the PSI group (P < 0.001), no other perioperative parameters differed significantly between groups. Case-sequence analysis showed no consistent changes in operative efficiency or most accuracy parameters across sequential PSI cases. The AI-based planning system demonstrated significantly higher accuracy in prosthesis size prediction than conventional templating (P < 0.001). Short-term follow-up showed no significant between-group differences in OKS, VAS pain score, or patient satisfaction. The AI-assisted planning system accurately predicted implant size, and PSI improved technical execution accuracy in medial UKA. However, short-term exploratory clinical outcomes did not differ between groups, and whether these technical gains translate into durable clinical benefit remains uncertain.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.