Department of Medical Imaging, University of Saskatchewan, Saskatoon, SK, Canada.
Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, SK, Canada.
Int J Comput Assist Radiol Surg. 2023 Oct;18(10):1903-1914. doi: 10.1007/s11548-023-02862-w. Epub 2023 Mar 22.
The usage of iodinated contrast media (ICM) can improve the sensitivity and specificity of computed tomography (CT) for many clinical indications. However, the adverse effects of ICM administration can include renal injury, life-threatening allergic-like reactions, and environmental contamination. Deep learning (DL) models can generate full-dose ICM CT images from non-contrast or low-dose ICM administration or generate non-contrast CT from full-dose ICM CT. Eliminating the need for both contrast-enhanced and non-enhanced imaging or reducing the amount of required contrast while maintaining diagnostic capability may reduce overall patient risk, improve efficiency and minimize costs. We reviewed the current capabilities of DL to reduce the need for contrast administration in CT.
We conducted a systematic review of articles utilizing DL to reduce the amount of ICM required in CT, searching MEDLINE, Embase, Compendex, Inspec, and Scopus to identify papers published from 2016 to 2022. We classified the articles based on the DL model and ICM reduction.
Eighteen papers met the inclusion criteria for analysis. Of these, ten generated synthetic full-dose (100%) ICM from real non-contrast CT, while four augmented low-dose to full-dose ICM CT. Three used DL to create synthetic non-contrast CT from real 100% ICM CT, while one paper used DL to translate the 100% ICM to non-contrast CT and vice versa. DL models commonly used generative adversarial networks trained and tested by paired contrast-enhanced and non-contrast or low ICM CTs. Image quality metrics such as peak signal-to-noise ratio and structural similarity index were frequently used for comparing synthetic versus real CT image quality.
DL-generated contrast-enhanced or non-contrast CT may assist in diagnosis and radiation therapy planning; however, further work to optimize protocols to reduce or eliminate ICM for specific pathology is still needed along with a dedicated assessment of the clinical utility of these synthetic images.
碘造影剂（ICM）的使用可以提高 CT 对许多临床适应证的敏感性和特异性。然而，ICM 给药的不良反应包括肾损伤、危及生命的过敏样反应和环境污染。深度学习（DL）模型可以从非对比或低剂量 ICM 给药生成全剂量 ICM CT 图像，或从全剂量 ICM CT 生成非对比 CT。消除对对比增强和非增强成像的需求，或在保持诊断能力的同时减少所需对比剂的量，可能会降低整体患者风险、提高效率并最大限度地降低成本。我们回顾了 DL 减少 CT 中对比剂给药需求的现有能力。
我们对利用 DL 减少 CT 中 ICM 用量的文章进行了系统回顾，在 MEDLINE、Embase、Compendex、Inspec 和 Scopus 中搜索 2016 年至 2022 年发表的论文。我们根据 DL 模型和 ICM 减少对文章进行分类。
符合分析纳入标准的论文有 18 篇。其中，10 篇从真实非对比 CT 生成合成全剂量（100%）ICM，4 篇将低剂量增强至全剂量 ICM CT。3 篇使用 DL 从真实 100% ICM CT 生成合成非对比 CT，1 篇论文使用 DL 将 100% ICM 转换为非对比 CT，反之亦然。DL 模型通常使用基于配对对比增强和非对比或低 ICM CT 进行训练和测试的生成对抗网络。图像质量指标，如峰值信噪比和结构相似性指数，常用于比较合成与真实 CT 图像质量。
DL 生成的对比增强或非对比 CT 可能有助于诊断和放射治疗计划；然而，仍需要进一步优化协议以减少或消除特定病理学的 ICM，并专门评估这些合成图像的临床实用性。
