A Realistic Collimated X-Ray Image Simulation Pipeline

TL;DR

This paper introduces a physically motivated simulation pipeline for X-ray collimator shadows, improving dataset diversity and model generalization in collimator detection tasks.

Contribution

The novel pipeline simulates realistic collimator shadows with randomized labels and noise, aiding deep learning training without relying solely on real data.

Findings

Simulated data closely matches real collimator shadows.

Using simulated data improves deep learning model generalization.

Pipeline enables expansion of limited X-ray datasets.

Abstract

Collimator detection remains a challenging task in X-ray systems with unreliable or non-available information about the detectors position relative to the source. This paper presents a physically motivated image processing pipeline for simulating the characteristics of collimator shadows in X-ray images. By generating randomized labels for collimator shapes and locations, incorporating scattered radiation simulation, and including Poisson noise, the pipeline enables the expansion of limited datasets for training deep neural networks. We validate the proposed pipeline by a qualitative and quantitative comparison against real collimator shadows. Furthermore, it is demonstrated that utilizing simulated data within our deep learning framework not only serves as a suitable substitute for actual collimators but also enhances the generalization performance when applied to real-world data.