期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 41, 期 12, 页码 3587-3599出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2022.3189759
关键词
Low-dose CT; metal artifact reduction; dual-domain learning; progressive restoration network
类别
资金
- National Institutes of Health (NIH) [R01EB025468]
To reduce radiation risk, low-dose computed tomography (LDCT) has been widely used, but the image quality is often degraded by noise and metal artifacts. Previous methods focused on either denoising LDCT or reducing metal artifacts in full-dose CT, which may not work well for the simultaneous reduction of metal artifacts and low-dose CT (MARLD). In this study, a dual-domain under-to-fully-complete progressive restoration network (DuDoUFNet) is proposed to achieve high-quality reconstruction under various low-dose and metal settings, surpassing previous LDCT and MAR methods.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据