Self-Supervised Multiview Xray Matching

TL;DR

This paper introduces a self-supervised method for establishing accurate correspondences between multi-view X-ray images using synthetic data, improving fracture detection without manual annotations.

Contribution

It proposes a novel self-supervised pipeline utilizing digitally reconstructed radiographs and transformer models to learn multi-view correspondences for X-ray analysis.

Findings

Improved multi-view fracture classification accuracy.

Effective pretraining strategy enhances real-world X-ray analysis.

Robust correspondence prediction across synthetic and real images.

Abstract

Accurate interpretation of multi-view radiographs is crucial for diagnosing fractures, muscular injuries, and other anomalies. While significant advances have been made in AI-based analysis of single images, current methods often struggle to establish robust correspondences between different X-ray views, an essential capability for precise clinical evaluations. In this work, we present a novel self-supervised pipeline that eliminates the need for manual annotation by automatically generating a many-to-many correspondence matrix between synthetic X-ray views. This is achieved using digitally reconstructed radiographs (DRR), which are automatically derived from unannotated CT volumes. Our approach incorporates a transformer-based training phase to accurately predict correspondences across two or more X-ray views. Furthermore, we demonstrate that learning correspondences among synthetic X-ray views can be leveraged as a pretraining strategy to enhance automatic multi-view fracture detection on real data. Extensive evaluations on both synthetic and real X-ray datasets show that incorporating correspondences improves performance in multi-view fracture classification.