文献速递腹部技术与安全CT

利用人工智能从单能CT重建合成双能CT

Synthetic dual-energy CT reconstruction from single-energy CT Using artificial intelligence.
PubMed 文献 · Abdom Radiol (NY) · 2023-09-04

回顾性纳入734例胸腹盆增强双能CT患者,用Pix2PixHD和CycleGAN从70 keV单能图像生成50 keV、碘图和虚拟平扫图像。Pix2PixHD定量性能优于CycleGAN(碘图结构相似指数87%对46%,P<0.001),合成双能CT在消化道出血显示和虚拟平扫去碘上表现更好,放射科医师区分合成与真实双能CT的平均准确率为64.5%。

要点

  • Pix2PixHD合成碘图结构相似指数87%,CycleGAN为46%,P<0.001。
  • 放射科医师区分合成与真实双能CT平均准确率64.5%,定性难以区分。
  • Pix2PixHD合成双能CT显示消化道出血更清晰、虚拟平扫去碘更好。

核心结论

  • 使用Pix2PixHD从单能CT生成的合成双能CT可能提供双能CT的部分优势。

研究设计与样本

  • 回顾性研究纳入734例(389例女性,62.8岁±14.9)于2018年1月至2019年6月行胸腹盆增强双能CT的患者,以70 keV为输入(n=141,009),50 keV、碘图和虚拟平扫为输出,分别训练Pix2PixHD和CycleGAN模型,测试集n=17,839,用均方误差、结构相似指数和峰值信噪比评估。

关键影像表现/征象

  • Pix2PixHD和CycleGAN生成的合成双能CT在一位委员会认证放射科医师看来与真实双能CT定性无法区分(平均准确率64.5%)。
  • Pix2PixHD定量性能优于CycleGAN,如碘图结构相似指数87%对46%,P<0.001。
  • 使用Pix2PixHD的合成双能CT对消化道出血显示更清晰,合成虚拟平扫去碘效果优于CycleGAN。

诊断标准与关键数值

  • 以70 keV单能CT为输入,生成50 keV、碘图和虚拟平扫图像。
  • 定量评估指标包括均方误差、结构相似指数和峰值信噪比,Pix2PixHD碘图结构相似指数87%,CycleGAN为46%,P<0.001。
  • 定性评估由一位委员会认证放射科医师区分合成与真实双能CT,平均准确率64.5%。

临床应用与阅片要点

  • 合成双能CT图像在定性上与真实双能CT难以区分,阅片时需注意其来源。
  • Pix2PixHD生成的碘图和虚拟平扫在去碘和出血显示上表现更优。
  • 合成虚拟平扫可用于替代真实平扫评估碘去除效果,但需结合原始单能图像。

局限性

  • 原文未报告局限性

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

PURPOSE: To develop and assess the utility of synthetic dual-energy CT (sDECT) images generated from single-energy CT (SECT) using two state-of-the-art generative adversarial network (GAN) architectures for artificial intelligence-based image translation.

METHODS: In this retrospective study, 734 patients (389F; 62.8 years ± 14.9) who underwent enhanced DECT of the chest, abdomen, and pelvis between January 2018 and June 2019 were included. Using 70-keV as the input images (n = 141,009) and 50-keV, iodine, and virtual unenhanced (VUE) images as outputs, separate models were trained using Pix2PixHD and CycleGAN. Model performance on the test set (n = 17,839) was evaluated using mean squared error, structural similarity index, and peak signal-to-noise ratio. To objectively test the utility of these models, synthetic iodine material density and 50-keV images were generated from SECT images of 16 patients with gastrointestinal bleeding performed at another institution. The conspicuity of gastrointestinal bleeding using sDECT was compared to portal venous phase SECT. Synthetic VUE images were generated from 37 patients who underwent a CT urogram at another institution and model performance was compared to true unenhanced images.

RESULTS: sDECT from both Pix2PixHD and CycleGAN were qualitatively indistinguishable from true DECT by a board-certified radiologist (avg accuracy 64.5%). Pix2PixHD had better quantitative performance compared to CycleGAN (e.g., structural similarity index for iodine: 87% vs. 46%, p-value < 0.001). sDECT using Pix2PixHD showed increased bleeding conspicuity for gastrointestinal bleeding and better removal of iodine on synthetic VUE compared to CycleGAN.

CONCLUSIONS: sDECT from SECT using Pix2PixHD may afford some of the advantages of DECT.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Jeong J, Wentland A, Mastrodicasa D, et al. Synthetic dual-energy CT reconstruction from single-energy CT Using artificial intelligence. Abdom Radiol (NY). 2023. PMID: 37665385. doi:10.1007/s00261-023-04004-x

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。