Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data

TL;DR

This paper introduces DEAR, a 3D deep encoder-decoder adversarial network that reconstructs high-quality 3D CT images from few-view data, reducing radiation exposure in clinical imaging.

Contribution

The paper presents a novel 3D deep learning framework that directly reconstructs 3D CT volumes from limited-view data, outperforming 2D methods by leveraging 3D information.

Findings

DEAR-3D outperforms 2D deep-learning methods in quality.

The method effectively reconstructs 3D volumes from sparse data.

Validated on Mayo Clinic abdominal CT dataset.

Abstract

X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizing X-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dose has been an important topic in recent years. Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper, we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT image reconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in 3D instead of 2D geometry, a 3D deep network has a great potential for improving the image quality in a data-driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publicly available abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other 2D deep-learning methods, the proposed DEAR-3D network can utilize 3D information to produce promising reconstruction results.