Learned denoising with simulated and experimental low-dose CT data

TL;DR

This paper investigates how convolutional neural networks perform in low-dose CT image denoising when trained on simulated versus real noisy data, highlighting the importance of training data quality and domain matching.

Contribution

It provides a comprehensive comparison of CNN performance on simulated and experimental noisy CT data, emphasizing end-to-end training and the need for better noise simulation methods.

Findings

Training on experimental data yields better denoising in real-world scenarios.

End-to-end sinogram-to-reconstruction training improves model performance.

Simulated data may not fully capture real noise characteristics, affecting generalization.

Abstract

Like in many other research fields, recent developments in computational imaging have focused on developing machine learning (ML) approaches to tackle its main challenges. To improve the performance of computational imaging algorithms, machine learning methods are used for image processing tasks such as noise reduction. Generally, these ML methods heavily rely on the availability of high-quality data on which they are trained. This work explores the application of ML methods, specifically convolutional neural networks (CNNs), in the context of noise reduction for computed tomography (CT) imaging. We utilize a large 2D computed tomography dataset for machine learning to carry out for the first time a comprehensive study on the differences between the observed performances of algorithms trained on simulated noisy data and on real-world experimental noisy data. The study compares the performance of two common CNN architectures, U-Net and MSD-Net, that are trained and evaluated on both simulated and experimental noisy data. The results show that while sinogram denoising performed better with simulated noisy data if evaluated in the sinogram domain, the performance did not carry over to the reconstruction domain where training on experimental noisy data shows a higher performance in denoising experimental noisy data. Training the algorithms in an end-to-end fashion from sinogram to reconstruction significantly improved model performance, emphasizing the importance of matching raw measurement data to high-quality CT reconstructions. The study furthermore suggests the need for more sophisticated noise simulation approaches to bridge the gap between simulated and real-world data in CT image denoising applications and gives insights into the challenges and opportunities in leveraging simulated data for machine learning in computational imaging.