深度学习模型用于低计数PET图像增强的临床验证
本研究纳入120例接受18F-FDG PET/CT检查的患者(内部队列84例、外部队列36例),用OSEM算法重建120秒(G120)和30秒(G30)列表模式数据,并以深度学习模型RaDynPET从G30生成增强图像R30。内部队列中R30主观图像质量评分显著高于G30和G120,肝脏SNR与CNR超过G120;外部队列中R30病灶水平灵敏度95.45%、特异度98.41%,与G120病灶检出无统计学差异。
要点
- R30在内部队列的图像质量评分显著高于G30和G120。
- 外部队列R30病灶检出灵敏度95.45%、特异度98.41%,与G120无统计学差异。
- RaDynPET在深度学习方法中PSNR和SSIM最高。
核心结论
- RaDynPET模型能有效恢复高图像质量,并在以标准采集时间25%采集的18F-FDG PET扫描中保持SUV一致性。
研究设计与样本
- 共纳入120例接受18F-FDG PET/CT检查的患者,其中内部队列84例、外部队列36例。
- PET图像用OSEM算法重建120秒(G120)和30秒(G30)列表模式数据,RaDynPET由G30生成增强图像R30。
- 两名有经验的核医学科医师独立用5点李克特量表评价主观图像质量。
主要发现
- 内部队列中R30图像质量评分显著高于G30和G120。
- R30与G120在肝脏和病灶SUV值上高度一致,且肝脏SNR和CNR超过G120。
- 薄层组中R30的肝脏SNR和CNR与G120相当,年轻年龄组中R30的CNR与G120相当。
- 外部队列中R30与G120保持强SUV一致性,病灶水平灵敏度95.45%、特异度98.41%,R30与G120病灶检出无统计学差异。
- RaDynPET在深度学习方法中PSNR和SSIM最高。
关键数值与推荐
- 主观图像质量采用5点李克特量表评价。
- 外部队列病灶水平灵敏度95.45%、特异度98.41%。
- RaDynPET在深度学习方法中PSNR和SSIM最高。
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: To investigate the effects of the deep learning model RaDynPET on fourfold reduced-count whole-body PET examinations. METHODS: A total of 120 patients (84 internal cohorts and 36 external cohorts) undergoing 18F-FDG PET/CT examinations were enrolled. PET images were reconstructed using OSEM algorithm with 120-s (G120) and 30-s (G30) list-mode data. RaDynPET was developed to generate enhanced images (R30) from G30. Two experienced nuclear medicine physicians independently evaluated subjective image quality using a 5-point Likert scale. Standardized uptake values (SUV), standard deviations, liver signal-to-noise ratio (SNR), lesion tumor-to-background ratio (TBR), and contrast-to-noise ratio (CNR) were compared. Subgroup analyses evaluated performance across demographics, and lesion detectability were evaluated using external datasets. RaDynPET was also compared to other deep learning methods. RESULTS: In internal cohorts, R30 demonstrated significantly higher image quality scores than G30 and G120. R30 showed excellent agreement with G120 for liver and lesion SUV values and surpassed G120 in liver SNR and CNR. Liver SNR and CNR of R30 were comparable to G120 in thin group, and the CNR of R30 was comparable to G120 in young age group. In external cohorts, R30 maintained strong SUV agreement with G120, with lesion-level sensitivity and specificity of 95.45% and 98.41%, respectively. There was no statistical difference in lesion detection between R30 and G120. RaDynPET achieved the highest PSNR and SSIM among deep learning methods. CONCLUSION: The RaDynPET model effectively restored high image quality while maintaining SUV agreement for 18F-FDG PET scans acquired in 25% of the standard acquisition time.
引用
- Long Q, Tian Y, Pan B, et al. Clinical validation of a deep learning model for low-count PET image enhancement. Eur J Nucl Med Mol Imaging. 2025. PMID: 40471320. doi:10.1007/s00259-025-07370-4
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。