Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs

2026-06-13

AI Summary

This work proposes an end-to-end framework for lower-limb alignment assessment that eliminates the need for explicit anatomical landmark annotation, which is traditionally time-consuming and inflexible to evolving clinical standards. By leveraging Implicit Neural Shape Functions (INSF), the method encodes bone structures from knee radiographs into a compact latent space, from which clinical alignment parameters are directly regressed. Evaluated on both an internal dataset and the external MRKR dataset, the approach achieves accuracy comparable to state-of-the-art landmark-based methods and manual measurements. Moreover, the learned latent representation enables flexible adaptation to new measurement tasks without requiring re-annotation when clinical definitions change, thereby significantly enhancing both efficiency and adaptability in clinical alignment evaluation.

Abstract

Radiographic assessment of lower-limb alignment (LLA) is important for predicting joint health and surgical outcomes in total knee arthroplasty. Traditional measurement methods are manual and time-consuming, while recent machine learning approaches typically rely on locating a fixed set of anatomical landmarks. This dependence limits flexibility and may require re-annotation when clinical definitions change. To address this, we propose an automated workflow using Implicit Neural Shape Functions (INSF). Rather than relying on explicit landmark coordinates, we encode the anatomy into a compact latent space and regress clinical alignment measurements directly from these latent codes. This architecture allows for rapid extendability to new tasks without altering the backbone representation. We trained our method on an internal dataset of 566 knee radiographs, each annotated with the outline of the femur and tibia. We evaluated it on both an internal test dataset of 50 patients and a separate external set of 402 preoperative cases from the MRKR dataset. Manual clinical measurements are available for these data, and the MRKR measurements will be made publicly accessible. Performance was comparable to state-of-the-art landmark-based methods and manual agreement, while offering a flexible shape representation that can be extended to additional measurement tasks.

Problem

• lower-limb alignment
• radiographic assessment
• anatomical landmarks
• clinical measurement
• knee radiographs

Innovation

• Implicit Neural Shape Functions
• landmark-free
• lower-limb alignment
• latent shape representation
• knee radiographs