监督式深度学习在CT金属伪影减少中的进展:一项系统综述
该研究系统综述了监督式深度学习(DL)金属伪影减少(MAR)算法在CT中的性能,按正弦图、图像和双域三领域分类。检索四个数据库后纳入十四项研究,其中十三种算法相比未校正图像和非DL MAR算法显示更高的PSNR和SSIM值。一项研究基于CT值计算显示,在临床数据上DL MAR算法相比未校正图像和非DL MAR算法具有统计学显著更好的MAR性能。
要点
- 监督式DL MAR算法在正弦图、图像和双域均显示出降低金属伪影的潜力。
- 十三项研究报道DL MAR算法相比未校正图像和非DL MAR算法,PSNR和SSIM值更高。
- 一项研究基于CT值计算显示,临床数据上DL MAR算法相比未校正图像和非DL MAR算法性能显著更优。
核心结论
- DL MAR算法在减少金属伪影方面显示出有希望的结果,但需要标准化方法来评估临床数据上的DL-based MAR算法,以提高算法间的可比性。
研究设计与样本
- 系统综述;检索PubMed、EMBASE、Web of Science和Scopus数据库;纳入十四项比较DL-based MAR算法与未校正图像的研究;结局评估采用PSNR和SSIM或任何其他比较MAR性能与未校正图像的客观指标。
诊断标准与关键数值
- 十三种MAR算法相比未校正图像和非DL MAR算法具有更高的PSNR和SSIM值;一项研究基于CT值计算显示,在临床数据上DL MAR算法相比未校正图像和非DL MAR算法具有统计学显著更好的MAR性能。
局限性
- 需要标准化方法来评估临床数据上的DL-based MAR算法,以提高算法间的可比性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Metallic artefacts caused by metal implants, are a common problem in computed tomography (CT) imaging, degrading image quality and diagnostic accuracy. With advancements in artificial intelligence, novel deep learning (DL)-based metal artefact reduction (MAR) algorithms are entering clinical practice.
OBJECTIVE: This systematic review provides an overview of the performance of the current supervised DL-based MAR algorithms for CT, focusing on three different domains: sinogram, image, and dual domain.
METHODS: A literature search was conducted in PubMed, EMBASE, Web of Science, and Scopus. Outcomes were assessed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) or any other objective measure comparing MAR performance to uncorrected images.
RESULTS: After screening, fourteen studies were selected that compared DL-based MAR-algorithms with uncorrected images. MAR-algorithms were categorised into the three domains. Thirteen MAR-algorithms showed a higher PSNR and SSIM value compared to the uncorrected images and to non-DL MAR-algorithms. One study showed statistically significant better MAR performance on clinical data compared to the uncorrected images and non-DL MAR-algorithms based on Hounsfield unit calculations.
CONCLUSION: DL MAR-algorithms show promising results in reducing metal artefacts, but standardised methodologies are needed to evaluate DL-based MAR-algorithms on clinical data to improve comparability between algorithms.
CLINICAL RELEVANCE STATEMENT: Recent studies highlight the effectiveness of supervised Deep Learning-based MAR-algorithms in improving CT image quality by reducing metal artefacts in the sinogram, image and dual domain. A systematic review is needed to provide an overview of newly developed algorithms.
引用
- Kleber CEJ, Karius R, Naessens LE, et al. Advancements in supervised deep learning for metal artifact reduction in computed tomography: A systematic review. Eur J Radiol. 2024. PMID: 39265203. doi:10.1016/j.ejrad.2024.111732
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。