文献速递神经核医学肿瘤 PET/CT

条件生成对抗网络辅助动态18F-FDG脑PET运动校正

Conditional Generative Adversarial Networks Aided Motion Correction of Dynamic 18F-FDG PET Brain Studies.
PubMed 文献 · J Nucl Med · 2020-11-27

本研究开发并测试了一种基于条件生成对抗网络(cGAN)的全自动数据驱动运动校正方法,用于动态18F-FDG脑PET研究。10名健康志愿者完成20次18F-FDG PET/MRI检查,用70%数据训练cGAN并用MR导航校正,其余30%测试。结果显示,运动校正后图像导出输入函数与动脉血输入函数的AUC绝对百分比差异为1.2%±0.9%,灰质CMRGlc差异小于5%(2.4%±1.7%)。

要点

  • cGAN可从PET数据本身确定运动向量,实现全自动运动校正。
  • 运动校正后IDIF与AIF的AUC差异仅1.2%±0.9%。
  • 灰质CMRGlc在两种输入函数间差异2.4%±1.7%,小于5%。

核心结论

  • cGAN辅助运动校正可实现全自动、数据驱动的动态18F-FDG脑PET运动补偿,并支持从PET/MR向PET/CT转化无创临床绝对定量。

研究设计与样本

  • 10名健康志愿者(5男5女,平均年龄27±7岁,体重70±10kg)完成测试-再测试18F-FDG PET/MRI脑检查,共20次数据集。
  • 成像方案为60分钟PET列表模式采集并同期MRI,含MR导航和三维时间飞跃MR血管成像序列,采集动脉血样作为AIF参考标准。
  • cGAN训练使用随机选取的70%数据集(n=16),该部分用MR导航进行运动校正;测试使用剩余30%(n=6)。

主要发现

  • 将cGAN映射应用于测试数据集,从早期高噪声PET帧生成人工低噪声图像,再与参考帧配准得到三维运动向量。
  • 运动校正后IDIF与AIF的AUC绝对百分比差异为1.2%±0.9%。
  • 使用两种输入函数计算的灰质CMRGlc值差异小于5%(2.4%±1.7%)。

关键数值与推荐

  • cGAN训练集占70%(n=16),测试集占30%(n=6)。
  • 参考帧为注射后55-60分钟。
  • AUC绝对百分比差异为1.2%±0.9%,灰质CMRGlc差异为2.4%±1.7%。

临床怎么用

  • 该方法有望在不依赖MR导航的情况下,从PET数据本身确定运动向量,推动动态脑PET绝对定量在PET/CT临床环境中的应用。

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)。

原文

This work set out to develop a motion-correction approach aided by conditional generative adversarial network (cGAN) methodology that allows reliable, data-driven determination of involuntary subject motion during dynamic 18F-FDG brain studies. Methods: Ten healthy volunteers (5 men/5 women; mean age ± SD, 27 ± 7 y; weight, 70 ± 10 kg) underwent a test-retest 18F-FDG PET/MRI examination of the brain (n = 20). The imaging protocol consisted of a 60-min PET list-mode acquisition contemporaneously acquired with MRI, including MR navigators and a 3-dimensional time-of-flight MR angiography sequence. Arterial blood samples were collected as a reference standard representing the arterial input function (AIF). Training of the cGAN was performed using 70% of the total datasets (n = 16, randomly chosen), which was corrected for motion using MR navigators. The resulting cGAN mappings (between individual frames and the reference frame [55-60 min after injection]) were then applied to the test dataset (remaining 30%, n = 6), producing artificially generated low-noise images from early high-noise PET frames. These low-noise images were then coregistered to the reference frame, yielding 3-dimensional motion vectors. Performance of cGAN-aided motion correction was assessed by comparing the image-derived input function (IDIF) extracted from a cGAN-aided motion-corrected dynamic sequence with the AIF based on the areas under the curves (AUCs). Moreover, clinical relevance was assessed through direct comparison of the average cerebral metabolic rates of glucose (CMRGlc) values in gray matter calculated using the AIF and the IDIF. Results: The absolute percentage difference between AUCs derived using the motion-corrected IDIF and the AIF was (1.2% + 0.9%). The gray matter CMRGlc values determined using these 2 input functions differed by less than 5% (2.4% + 1.7%). Conclusion: A fully automated data-driven motion-compensation approach was established and tested for 18F-FDG PET brain imaging. cGAN-aided motion correction enables the translation of noninvasive clinical absolute quantification from PET/MR to PET/CT by allowing the accurate determination of motion vectors from the PET data itself.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Shiyam Sundar LK, Iommi D, Muzik O, et al. Conditional Generative Adversarial Networks Aided Motion Correction of Dynamic 18F-FDG PET Brain Studies. J Nucl Med. 2020. PMID: 33246982. doi:10.2967/jnumed.120.248856

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。