文献速递肿瘤 PET/CT放射性药物与辐射防护

基于深度学习的全身PET衰减校正:18F-FDG、68Ga-DOTATATE和18F-Fluciclovine的多示踪剂研究

Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2022-03-12

该研究将基于深度学习的衰减校正框架应用于18F-FDG、68Ga-DOTATATE和18F-Fluciclovine的临床全身肿瘤PET/CT数据集,训练示踪剂特异性神经网络预测衰减图(µ-DL),并与MLAA估计的衰减图(µ-MLAA)及CT衰减图(µ-CT)比较。结果显示µ-DL在所有示踪剂中图像质量优于µ-MLAA,基于µ-DL的OSEM重建(OSEMDL)在肿瘤SUVmax和体积测量上较OSEMMLAA更接近OSEMCT金标准。结论认为该框架为三种示踪剂提供准确稳健的衰减校正,临床质量与CT等效。

要点

  • µ-DL衰减图在所有示踪剂中质量优于µ-MLAA。
  • OSEMDL较OSEMMLAA在三种示踪剂中肿瘤SUVmax和体积测量更准确。
  • OSEMDL衰减校正质量在三种示踪剂中临床与CT等效。

核心结论

  • 所提框架为全身18F-FDG、68Ga-DOTATATE和18F-Fluciclovine的肿瘤SUV及肿瘤体积估计提供准确稳健的衰减校正。
  • 所提方法在三种示踪剂的衰减校正中提供与CT临床等效的质量。

研究设计与样本

  • 回顾性应用深度学习衰减校正框架于临床全身肿瘤PET/CT数据集,使用18F-FDG(N=113)、68Ga-DOTATATE(N=76)和18F-Fluciclovine(N=90)。
  • 框架以MLAA算法估计的活性图(λ-MLAA)和衰减图(µ-MLAA)为输入,采用改进U-net神经网络和基于成像物理的损失函数学习CT衍生衰减图(µ-CT)。
  • 每种示踪剂用40名受试者训练神经网络预测衰减图(µ-DL),µ-DL和µ-MLAA与金标准µ-CT比较。
  • 用OSEM算法分别结合µ-DL(OSEMDL)和µ-MLAA(OSEMMLAA)重建PET图像,与CT-based重建(OSEMCT)比较。
  • 肿瘤感兴趣区由两名放射科医生分割,报告肿瘤SUV和体积指标,并用常规图像分析指标评估。

主要发现

  • µ-DL在所有示踪剂的所有指标中图像质量优于µ-MLAA,高分辨率和细节恢复良好。
  • 以OSEMCT为金标准,OSEMDL较OSEMMLAA在三种示踪剂中提供更准确的肿瘤定量。
  • SUVmax误差:OSEMMLAA vs OSEMDL为18F-FDG(N=152)-3.6±4.4% vs -1.7±4.5%,68Ga-DOTATATE(N=70)-4.3±5.1% vs 0.4±2.8%,18F-Fluciclovine(N=44)-7.3±2.9% vs -2.8±2.3%。
  • 肿瘤体积误差:OSEMMLAA vs OSEMDL为18F-FDG -8.4±14.5% vs -3.0±15.0%,68Ga-DOTATATE -14.1±19.7% vs 1.8±11.6%,18F-Fluciclovine -15.9±9.1% vs -6.4±6.4%。

临床怎么用

  • 原文未据此给出推荐。

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)。

原文

UNLABELLED: A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT). METHODS: Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics. RESULTS: µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine. CONCLUSIONS: The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Toyonaga T, Shao D, Shi L, et al. Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. Eur J Nucl Med Mol Imaging. 2022. PMID: 35277742. doi:10.1007/s00259-022-05748-2

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。