Deep learning based low-dose synchrotron radiation CT reconstruction

TL;DR

This paper introduces ResAttUnet, a deep learning model that enhances low-dose synchrotron radiation CT reconstruction by reducing sampling angles and mitigating artifacts, thus improving image quality efficiently.

Contribution

The paper proposes ResAttUnet, a novel U-shaped deep learning network combining ResNet and attention mechanisms for high-quality sparse data reconstruction in CT imaging.

Findings

ResAttUnet effectively reduces artifacts in low-dose CT images.

The model achieves high-quality reconstructions with less data and faster training due to mixed precision.

Significant reduction in sampling angles without compromising image detail.

Abstract

Synchrotron radiation sources are widely used in various fields, among which computed tomography (CT) is one of the most important. The amount of effort expended by the operator varies depending on the subject. If the number of angles needed to be used can be greatly reduced under the condition of similar imaging effects, the working time and workload of the experimentalists will be greatly reduced. However, decreasing the sampling angle can produce serious artifacts and blur the details. We try to use a deep learning model which can build high quality reconstruction sparse data sampling from the angle of the image and ResAttUnet are put forward. ResAttUnet is roughly a symmetrical U-shaped network that incorporates similar mechanisms to ResNet and attention. In addition, the mixed precision is adopted to reduce the demand for video memory of the model and training time.