UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty

TL;DR

This paper introduces UNSCT-HRNet, a deep learning framework that models anatomical uncertainty and spatial relationships to improve landmark detection in radiographic images for total hip arthroplasty, especially under unstructured data conditions.

Contribution

It presents a novel deep learning model with SRF and UE modules that enhances accuracy and robustness in landmark detection for THA, handling unstructured data effectively.

Findings

Achieves over 60% improvement in unstructured data accuracy

Maintains strong performance on structured datasets

Provides a reliable automated solution for surgical planning

Abstract

Total hip arthroplasty (THA) relies on accurate landmark detection from radiographic images, but unstructured data caused by irregular patient postures or occluded anatomical markers pose significant challenges for existing methods. To address this, we propose UNSCT-HRNet (Unstructured CT - High-Resolution Net), a deep learning-based framework that integrates a Spatial Relationship Fusion (SRF) module and an Uncertainty Estimation (UE) module. The SRF module, utilizing coordinate convolution and polarized attention, enhances the model's ability to capture complex spatial relationships. Meanwhile, the UE module which based on entropy ensures predictions are anatomically relevant. For unstructured data, the proposed method can predict landmarks without relying on the fixed number of points, which shows higher accuracy and better robustness comparing with the existing methods. Our UNSCT-HRNet demonstrates over a 60% improvement across multiple metrics in unstructured data. The experimental results also reveal that our approach maintains good performance on the structured dataset. Overall, the proposed UNSCT-HRNet has the potential to be used as a new reliable, automated solution for THA surgical planning and postoperative monitoring.