Scholarlink

Purpose <p>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.</p> Methods <p>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 [<sup>68</sup>Ga]Ga-DOTATATE/[<sup>18</sup>F]FDG, 50 underwent [<sup>68</sup>Ga]Ga-PSMA-11/[<sup>18</sup>F]FDG, and 30 underwent [<sup>68</sup>Ga]Ga-FAPI-04/[<sup>18</sup>F]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.</p> Results <p>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 [<sup>68</sup>Ga]Ga-DOTATATE, 0.08 for [<sup>68</sup>Ga]Ga-PSMA-11, 0.06 for [<sup>68</sup>Ga]Ga-FAPI-04, and 0.05 for [<sup>18</sup>F]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.</p> Conclusion <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Eliminating the second CT scan of dual-tracer total-body PET/CT via deep learning-based image synthesis and registration

  • 期刊论文

  • 发表日期：

    2025年2月11日

查看全文
  • Yu Lin,
  • Kang Wang,
  • Zhe Zheng,
  • Haojun Yu,
  • Shuguang Chen,
  • WenXin Tang,
  • Yibo He,
  • Huaping Gao,
  • Runjun Yang,
  • Yunzhe Xie,
  • Junjie Yang,
  • Xiaoguang Hou,
  • Shuo Wang,
  • Hongcheng Shi

摘要

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.