X-ray Scatter Estimation Using Deep Splines

TL;DR

This paper introduces a physics-constrained neural network approach using B-splines for X-ray scatter estimation, which maintains smoothness, reduces complexity, and enhances robustness over traditional U-net methods.

Contribution

The novel integration of B-splines as a known operator into neural networks for X-ray scatter estimation improves robustness and efficiency compared to U-net based methods.

Findings

Performs comparably to U-net in accuracy

Reduces runtime and parameter complexity

More robust to unseen noise levels

Abstract

Algorithmic X-ray scatter compensation is a desirable technique in flat-panel X-ray imaging and cone-beam computed tomography. State-of-the-art U-net based image translation approaches yielded promising results. As there are no physics constraints applied to the output of the U-Net, it cannot be ruled out that it yields spurious results. Unfortunately, those may be misleading in the context of medical imaging. To overcome this problem, we propose to embed B-splines as a known operator into neural networks. This inherently limits their predictions to well-behaved and smooth functions. In a study using synthetic head and thorax data as well as real thorax phantom data, we found that our approach performed on par with U-net when comparing both algorithms based on quantitative performance metrics. However, our approach not only reduces runtime and parameter complexity, but we also found it much more robust to unseen noise levels. While the U-net responded with visible artifacts, our approach preserved the X-ray signal's frequency characteristics.