文献速递肿瘤 PET/CT放射性药物与辐射防护

基于深度学习图像合成与配准消除双示踪剂全身PET/CT中的第二次CT扫描

Eliminating the second CT scan of dual-tracer total-body PET/CT via deep learning-based image synthesis and registration.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-02-11

本研究回顾性纳入247例接受双示踪剂全身PET/CT的患者,开发整合配准生成对抗网络(RegGAN)与非刚性配准的深度学习框架,将第一次扫描的衰减校正CT(ACCT)转换为第二次扫描的伪ACCT用于衰减与散射校正(ASC)。结果显示全身伪ACCT的MAE为97.64–112.59 HU,四种示踪剂SUV的MAE为0.05–0.08,正常器官SUV中位绝对百分比偏差<2.6%,病灶平均绝对百分比偏差<3.6%。

要点

  • 深度学习框架可将首次ACCT转换为二次扫描伪ACCT,替代第二次CT用于ASC。
  • 全身伪ACCT的MAE在四种示踪剂间为97.64–112.59 HU。
  • 四种示踪剂全身PET SUV的MAE为0.05–0.08,病灶SUV平均绝对百分比偏差<3.6%。

核心结论

  • 所提出的结合RegGAN与非刚性配准的深度学习框架在减少双示踪剂全身PET/CT成像CT辐射剂量方面显示出前景,并在多种示踪剂中获得成功验证。

研究设计与样本

  • 回顾性纳入三个队列共247例在两天分别接受双示踪剂全身PET/CT的患者,时间间隔1–11天。
  • 其中167例接受[68Ga]Ga-DOTATATE/[18F]FDG,50例接受[68Ga]Ga-PSMA-11/[18F]FDG,30例接受[68Ga]Ga-FAPI-04/[18F]FDG。
  • 开发整合配准生成对抗网络(RegGAN)与非刚性配准技术的深度学习框架,将第一次扫描的ACCT转换为第二次扫描的伪ACCT,用于第二次示踪剂PET图像的ASC。

主要发现

  • 全身伪ACCT图像的MAE在四种示踪剂间为97.64–112.59 HU。
  • 基于深度学习的ASC PET图像与真实PET图像高度相似。
  • 全身PET图像SUV的MAE分别为:[68Ga]Ga-DOTATATE 0.06、[68Ga]Ga-PSMA-11 0.08、[68Ga]Ga-FAPI-04 0.06、[18F]FDG 0.05。
  • 所有正常器官SUV的中位绝对百分比偏差<2.6%,四种示踪剂病灶SUV的平均绝对百分比偏差<3.6%。

关键数值与推荐

  • 全身伪ACCT图像MAE为97.64–112.59 HU(四种示踪剂)。
  • 全身PET SUV的MAE:[68Ga]Ga-DOTATATE 0.06、[68Ga]Ga-PSMA-11 0.08、[68Ga]Ga-FAPI-04 0.06、[18F]FDG 0.05。
  • 正常器官SUV中位绝对百分比偏差<2.6%,病灶SUV平均绝对百分比偏差<3.6%(四种示踪剂)。

临床怎么用

  • 原文未据此给出临床推荐。

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

PURPOSE: This study aims to develop and validate a deep learning framework designed to eliminate the second CT scan of dual-tracer total-body PET/CT imaging. METHODS: We retrospectively included three cohorts of 247 patients who underwent dual-tracer total-body PET/CT imaging on two separate days (time interval:1-11 days). Out of these, 167 underwent [68Ga]Ga-DOTATATE/[18F]FDG, 50 underwent [68Ga]Ga-PSMA-11/[18F]FDG, and 30 underwent [68Ga]Ga-FAPI-04/[18F]FDG. A deep learning framework was developed that integrates a registration generative adversarial network (RegGAN) with non-rigid registration techniques. This approach allows for the transformation of attenuation-correction CT (ACCT) images from the first scan into pseudo-ACCT images for the second scan, which are then used for attenuation and scatter correction (ASC) of the second tracer PET images. Additionally, the derived registration transform facilitates dual-tracer image fusion and analysis. The deep learning-based ASC PET images were evaluated using quantitative metrics, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) across the whole body and specific regions. Furthermore, the quantitative accuracy of PET images was assessed by calculating standardized uptake value (SUV) bias in normal organs and lesions. RESULTS: The MAE for whole-body pseudo-ACCT images ranged from 97.64 to 112.59 HU across four tracers. The deep learning-based ASC PET images demonstrated high similarity to the ground-truth PET images. The MAE of SUV for whole-body PET images was 0.06 for [68Ga]Ga-DOTATATE, 0.08 for [68Ga]Ga-PSMA-11, 0.06 for [68Ga]Ga-FAPI-04, and 0.05 for [18F]FDG, respectively. Additionally, the median absolute percent deviation of SUV was less than 2.6% for all normal organs, while the mean absolute percent deviation of SUV was less than 3.6% for lesions across four tracers. CONCLUSION: The proposed deep learning framework, combining RegGAN and non-rigid registration, shows promise in reducing CT radiation dose for dual-tracer total-body PET/CT imaging, with successful validation across multiple tracers.

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

引用

  1. Lin Y, Wang K, Zheng Z, et al. Eliminating the second CT scan of dual-tracer total-body PET/CT via deep learning-based image synthesis and registration. Eur J Nucl Med Mol Imaging. 2025. PMID: 39932542. doi:10.1007/s00259-025-07113-5

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。