To reduce the potential risk of radiation to the patient, low-dose computed tomography (LDCT) has been widely adopted in clinical practice for reconstructing cross-sectional images using sinograms with reduced x-ray flux. The LDCT image quality is often degraded by different levels of noise depending on the low-dose protocols. The image quality will be further degraded when the patient has metallic implants, where the image suffers from additional streak artifacts along with further amplified noise levels, thus affecting the medical diagnosis and other CT-related applications. Previous studies mainly focused either on denoising LDCT without considering metallic implants or full-dose CT metal artifact reduction (MAR). Directly applying previous LDCT or MAR approaches to the issue of simultaneous metal artifact reduction and low-dose CT (MARLD) may yield sub-optimal reconstruction results. In this work, we develop a dual-domain under-to-fully-complete progressive restoration network, called DuDoUFNet, for MARLD. Our DuDoUFNet aims to reconstruct images with substantially reduced noise and artifact by progressive sinogram to image domain restoration with a two-stage progressive restoration network design. Our experimental results demonstrate that our method can provide high-quality reconstruction, superior to previous LDCT and MAR methods under various low-dose and metal settings.

中文翻译：

---

DuDoUFNet：双域未完全完成渐进式恢复网络，用于同时金属伪影减少和低剂量 CT 重建


为了减少对患者的潜在辐射风险，低剂量计算机断层扫描 (LDCT) 已在临床实践中广泛采用，使用减少 X 射线通量的正弦图重建横截面图像。根据低剂量方案的不同，LDCT 图像质量通常会因不同级别的噪声而降低。当患者有金属植入物时，图像质量将进一步下降，图像会出现额外的条纹伪影以及进一步放大的噪声水平，从而影响医疗诊断和其他 CT 相关应用。先前的研究主要集中在不考虑金属植入物的 LDCT 降噪或全剂量 CT 金属伪影减少 (MAR) 上。直接应用以前的 LDCT 或 MAR 方法来解决同时金属伪影减少和低剂量 CT (MARLD) 的问题可能会产生次优的重建结果。在这项工作中，我们为 MARLD 开发了一个双域欠完全渐进恢复网络，称为 DuDoUFNet。我们的 DuDoUFNet 旨在通过两阶段渐进恢复网络设计，通过渐进正弦图到图像域恢复来重建图像，从而显着减少噪声和伪影。我们的实验结果表明，我们的方法可以提供高质量的重建，在各种低剂量和金属设置下优于以前的 LDCT 和 MAR 方法。