A Lightweight Dual-Domain Attention Framework for Sparse-View CT Reconstruction

TL;DR

This paper introduces CAGAN, a lightweight dual-domain neural network for sparse-view CT reconstruction, effectively reducing artifacts and preserving image quality while maintaining low complexity suitable for mobile devices.

Contribution

The paper proposes a novel dual-domain reconstruction pipeline with a lightweight adversarial auto-encoder, combining coordinate attention and shuffle blocks for efficient sparse-view CT image reconstruction.

Findings

Outperforms DD-Net and DuDoNet in quality and efficiency

Balances model complexity with high reconstruction performance

Reduces parameters significantly without performance loss

Abstract

Computed Tomography (CT) plays an essential role in clinical diagnosis. Due to the adverse effects of radiation on patients, the radiation dose is expected to be reduced as low as possible. Sparse sampling is an effective way, but it will lead to severe artifacts on the reconstructed CT image, thus sparse-view CT image reconstruction has been a prevailing and challenging research area. With the popularity of mobile devices, the requirements for lightweight and real-time networks are increasing rapidly. In this paper, we design a novel lightweight network called CAGAN, and propose a dual-domain reconstruction pipeline for parallel beam sparse-view CT. CAGAN is an adversarial auto-encoder, combining the Coordinate Attention unit, which preserves the spatial information of features. Also, the application of Shuffle Blocks reduces the parameters by a quarter without sacrificing its performance. In the Radon domain, the CAGAN learns the mapping between the interpolated data and fringe-free projection data. After the restored Radon data is reconstructed to an image, the image is sent into the second CAGAN trained for recovering the details, so that a high-quality image is obtained. Experiments indicate that the CAGAN strikes an excellent balance between model complexity and performance, and our pipeline outperforms the DD-Net and the DuDoNet.