Scholarlink

Purpose <p>This study aims to develop a two-stage 3D denoising diffusion implicit model (DDIM) framework for CT-free attenuation correction in cardiac PET imaging, enabling direct generation of attenuation-corrected (AC) images from non-attenuation-corrected (NAC) PET scans. The method is comprehensively validated using both [<sup>18</sup>F]FDG PET and [<sup>13</sup>N]ammonia cardiac PET datasets to demonstrate its clinical applicability across different perfusion and metabolic imaging protocols.</p> Methods <p>The framework employs a two-stage approach: (1) a noise-to-image DDIM was first pretrained on all available AC images (i.e., no need of paired NACs) to learn a diverse AC distributions, enabling the high-fidelity generation of AC images with varying appearances; (2) the pretrained model was fine-tuned with a limited set of paired NAC-AC images to form a conditional DDIM, ensuring anatomically aligned, controllable generation. The model architecture uses a 3D U-Net, trained on 224 paired NAC-AC and 396 unpaired AC images for [<sup>18</sup>F]FDG, and 608 paired NAC-AC images and 885 unpaired AC images for [<sup>13</sup>N]ammonia. Performance was evaluated through quantitative metrics (including NMAE, NRMSE, SSIM and PSNR) and visual assessment.</p> Results <p>The proposed two-stage DDIM framework achieved excellent agreement with clinical CT-based attenuation correction (CT-AC), demonstrating superior correlation (slope = 0.78, <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:{R}^{2}\)</EquationSource> </InlineEquation> = 0.95 for [<sup>18</sup>F]FDG; slope = 0.99, <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\:{R}^{2}\)</EquationSource> </InlineEquation>= 0.91 for [<sup>13</sup>N]ammonia) and lower errors compared to existing approaches. Ablation studies confirmed the benefits of both the two-stage training strategy and the incorporation of unpaired AC images, as evidenced by narrower confidence intervals in Bland-Altman analysis and reduced percentage errors.</p> Conclusion <p>The two-stage 3D DDIM framework achieves performance comparable to clinical CT-AC while effectively leveraging unpaired data, demonstrating significant potential for robust cardiac PET attenuation correction.</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

Generative restoration for cardiac PET attenuation correction: a two-stage 3D DDIM framework optimizing fidelity and clinical controllability

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月2日

查看全文
  • Junhang Deng,
  • Hao Sun,
  • Haifeng Wang,
  • Xiaotong Hong,
  • Weiping Xu,
  • Fan Wang,
  • Jianhua Ma,
  • Chunfeng Lian,
  • Lijun Lu

摘要

Purpose

This study aims to develop a two-stage 3D denoising diffusion implicit model (DDIM) framework for CT-free attenuation correction in cardiac PET imaging, enabling direct generation of attenuation-corrected (AC) images from non-attenuation-corrected (NAC) PET scans. The method is comprehensively validated using both [18F]FDG PET and [13N]ammonia cardiac PET datasets to demonstrate its clinical applicability across different perfusion and metabolic imaging protocols.

Methods

The framework employs a two-stage approach: (1) a noise-to-image DDIM was first pretrained on all available AC images (i.e., no need of paired NACs) to learn a diverse AC distributions, enabling the high-fidelity generation of AC images with varying appearances; (2) the pretrained model was fine-tuned with a limited set of paired NAC-AC images to form a conditional DDIM, ensuring anatomically aligned, controllable generation. The model architecture uses a 3D U-Net, trained on 224 paired NAC-AC and 396 unpaired AC images for [18F]FDG, and 608 paired NAC-AC images and 885 unpaired AC images for [13N]ammonia. Performance was evaluated through quantitative metrics (including NMAE, NRMSE, SSIM and PSNR) and visual assessment.

Results

The proposed two-stage DDIM framework achieved excellent agreement with clinical CT-based attenuation correction (CT-AC), demonstrating superior correlation (slope = 0.78, \(\:{R}^{2}\) = 0.95 for [18F]FDG; slope = 0.99, \(\:{R}^{2}\) = 0.91 for [13N]ammonia) and lower errors compared to existing approaches. Ablation studies confirmed the benefits of both the two-stage training strategy and the incorporation of unpaired AC images, as evidenced by narrower confidence intervals in Bland-Altman analysis and reduced percentage errors.

Conclusion

The two-stage 3D DDIM framework achieves performance comparable to clinical CT-AC while effectively leveraging unpaired data, demonstrating significant potential for robust cardiac PET attenuation correction.