文献速递腹部技术与安全CT

在实验动物研究中利用生成对抗网络深度学习降低腹部CT的对比剂用量

Contrast Media Reduction in Computed Tomography With Deep Learning Using a Generative Adversarial Network in an Experimental Animal Study.
PubMed 文献 · Invest Radiol · 2022-04-06

本可行性研究在20只健康哥廷根小型猪中行多期腹部低千伏CT,比较低对比剂剂量(105 mgl/kg)与正常剂量(350 mgl/kg),用生成对抗网络(GAN)将低剂量图像转换为虚拟对比剂增强图像;GAN增强后血管与实质对比噪声比显著提高且与正常剂量无显著差异,视觉图灵测试中放射科顾问医师中位数96.5%的检查认为两种图像病理一致,中位数91%的病例能识别出正常对比剂数据。

要点

  • GAN可将低对比剂剂量腹部CT图像转换为虚拟对比剂增强图像,血管与实质CNR较原始低剂量图像显著提高。
  • 虚拟对比剂增强图像的血管与实质CNR与正常对比剂剂量检查无显著差异。
  • 视觉图灵测试中,放射科顾问医师中位数96.5%的检查认为正常与虚拟对比剂图像病理一致。

核心结论

  • 在健康哥廷根小型猪实验模型中,基于GAN的对比剂增强可将腹部CT对比剂用量减少约70%,图像质量满意。

研究设计与样本

  • 可行性实验动物研究,20只健康哥廷根小型猪行多期腹部低千伏(90 kV)CT,低对比剂剂量105 mgl/kg与正常剂量350 mgl/kg,分3次共120次检查;1只因检查不完整被排除,19只中随机选3只(18次检查)留作验证,其余16只(96次检查)用于训练GAN进行低剂量到正常剂量的图像转换。

关键影像表现/征象

  • GAN增强后图像在各对比剂期相的血管与实质对比噪声比均较原始低对比剂剂量图像提高。
  • 虚拟对比剂增强图像与正常对比剂剂量图像在血管和实质对比噪声比上无显著差异。

诊断标准与关键数值

  • 血管对比噪声比:低对比剂剂量组6.9 ± 7.0 vs 虚拟对比剂组28.7 ± 23.8,P < 0.0001。
  • 实质对比噪声比:低对比剂剂量组1.5 ± 0.7 vs 虚拟对比剂组3.8 ± 2.0,P < 0.0001。
  • 血管对比噪声比:虚拟对比剂组28.7 ± 23.8 vs 正常对比剂组34.2 ± 28.8,无显著差异。
  • 实质对比噪声比:虚拟对比剂组3.8 ± 2.0 vs 正常对比剂组3.7 ± 2.6,无显著差异。
  • 视觉图灵测试中,放射科顾问医师中位数96.5%的检查认为正常与虚拟对比剂图像病理一致;中位数91%的病例能将正常对比剂数据识别为正常。

临床应用与阅片要点

  • 作者认为基于GAN的对比剂增强可在实验环境中将腹部CT对比剂用量减少约70%且图像质量满意;原文未据此给出临床推荐。

局限性

  • 原文标题与摘要明确为可行性研究。
  • 原文结论使用「could be demonstrated」的限定表述。

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

OBJECTIVE: This feasibility study aimed to use optimized virtual contrast enhancement through generative adversarial networks (GAN) to reduce the dose of iodine-based contrast medium (CM) during abdominal computed tomography (CT) in a large animal model.

METHODS: Multiphasic abdominal low-kilovolt CTs (90 kV) with low (low CM, 105 mgl/kg) and normal contrast media doses (normal CM, 350 mgl/kg) were performed with 20 healthy Göttingen minipigs on 3 separate occasions for a total of 120 examinations. These included an early arterial, late arterial, portal venous, and venous contrast phase. One animal had to be excluded because of incomplete examinations. Three of the 19 animals were randomly selected and withheld for validation (18 studies). Subsequently, the GAN was trained for image-to-image conversion from low CM to normal CM (virtual CM) with the remaining 16 animals (96 examinations). For validation, region of interest measurements were performed in the abdominal aorta, inferior vena cava, portal vein, liver parenchyma, and autochthonous back muscles, and the contrast-to-noise ratio (CNR) was calculated. In addition, the normal CM and virtual CM data were presented in a visual Turing test to 3 radiology consultants. On the one hand, they had to decide which images were derived from the normal CM examination. On the other hand, they had to evaluate whether both images are pathological consistent.

RESULTS: Average vascular CNR (low CM 6.9 ± 7.0 vs virtual CM 28.7 ± 23.8, P < 0.0001) and parenchymal (low CM 1.5 ± 0.7 vs virtual CM 3.8 ± 2.0, P < 0.0001) CNR increased significantly by GAN-based contrast enhancement in all contrast phases and was not significantly different from normal CM examinations (vascular: virtual CM 28.7 ± 23.8 vs normal CM 34.2 ± 28.8; parenchymal: virtual CM 3.8 ± 2.0 vs normal CM 3.7 ± 2.6). During the visual Turing testing, the radiology consultants reported that images from normal CM and virtual CM were pathologically consistent in median in 96.5% of the examinations. Furthermore, it was possible for the examiners to identify the normal CM data as such in median in 91% of the cases.

CONCLUSIONS: In this feasibility study, it could be demonstrated in an experimental setting with healthy Göttingen minipigs that the amount of CM for abdominal CT can be reduced by approximately 70% by GAN-based contrast enhancement with satisfactory image quality.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Haubold, Jost, Theysohn, et al. Contrast Media Reduction in Computed Tomography With Deep Learning Using a Generative Adversarial Network in an Experimental Animal Study. Invest Radiol. 2022. PMID: 35438659. doi:10.1097/RLI.0000000000000875

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。