First Deep Learning Approach to Hammering Acoustics for Stem Stability Assessment in Total Hip Arthroplasty

TL;DR

This paper introduces the first deep learning method using audio analysis to assess femoral stem stability during hip replacement surgery, achieving over 91% accuracy on intra-operative recordings.

Contribution

It presents a novel deep learning framework employing TimeMIL and pseudo-labeling for intra-operative acoustic assessment in THA, addressing variability issues.

Findings

Achieved 91.17% accuracy in stability estimation.

Reducing femoral stem brand diversity improves performance.

Dataset size limits model generalization.

Abstract

Audio event classification has recently emerged as a promising approach in medical applications. In total hip arthroplasty (THA), intra-operative hammering acoustics provide critical cues for assessing the initial stability of the femoral stem, yet variability due to femoral morphology, implant size, and surgical technique constrains conventional assessment methods. We propose the first deep learning framework for this task, employing a TimeMIL model trained on Log-Mel Spectrogram features and enhanced with pseudo-labeling. On intra-operative recordings, the method achieved 91.17 % +/- 2.79 % accuracy, demonstrating reliable estimation of stem stability. Comparative experiments further show that reducing the diversity of femoral stem brands improves model performance, although limited dataset size remains a bottleneck. These results establish deep learning-based audio event classification as a feasible approach for intra-operative stability assessment in THA.