深度学习用于超低计数[18F]FDG PET图像恢复在痴呆诊断中的临床验证
研究训练基于CSBDeep工具箱的3D U-net深度学习模型,对208±10 MBq [18F]FDG注射后10分钟list-mode数据重建的2分钟至10秒缩短扫描进行图像恢复,并应用于阿尔茨海默病15例、额颞叶痴呆14例和健康对照13例。结果显示深度学习使所有恢复图像均可评估,诊断准确率保持在90%-93%,而未经深度学习处理的短扫描诊断准确率从90%降至4%。
要点
- 深度学习恢复使10秒超低计数[18F]FDG PET图像全部可评估。
- 深度学习恢复后诊断准确率保持90%-93%,10分钟扫描为90%。
- 深度学习可大幅缩短扫描时间或降低给药活度,如10分钟扫描3.5 MBq约60 µSv。
核心结论
- 研究证明深度学习在恢复超低计数脑[18F]FDG PET数据集方面表现突出,适用于定量区域、基于体素的组间和临床视觉分析。
- 深度学习使[18F]FDG PET在痴呆患者及可能其他适应症中大幅缩短扫描时间或降低给药活度成为可能,例如10分钟扫描3.5 MBq约60 µSv。
研究设计与样本
- 采用CSBDeep工具箱内容感知图像恢复方法的多种3D U-net深度学习模型,以1,000名随机受试者的子体积进行训练。
- 基于注射208±10 MBq [18F]FDG后的10分钟list-mode PET数据,重建2分钟、1分钟、30秒、20秒和10秒的缩短扫描时长。
- 模型应用于阿尔茨海默病(n=15)、额颞叶痴呆(n=14)和健康对照(n=13)的[18F]FDG PET扫描。
- 探索缩短扫描时间对诊断相关区域个体区域测量值和基于体素的组间对比的影响。
- 三位独立阅片者对所有数据集的可评估性、诊断和诊断信心进行评分。
主要发现
- 个体平均区域[18F]FDG摄取基本保持不变。
- 未应用深度学习时,标准差随扫描时间缩短而强烈增加(平均增加≤48%),而应用深度学习时标准差略微降低(≥-7%)。
- 组间对比中,未应用深度学习时显著体素数随扫描时间缩短而强烈减少(≥-41%),深度学习部分抵消了这一减少(≥-27%)。
- 视觉阅片方面,未应用深度学习时扫描时长低于2分钟的可评估图像比例骤降至仅4%(10秒扫描),而经深度学习恢复的每一张图像均可评估。
- 未应用深度学习时诊断信心随扫描时间缩短持续下降,而应用深度学习时诊断信心几乎无变化(中至高信心评分:0%-54% vs. 80%-84%;10分钟扫描为83%)。
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
Deep learning (DL) represents a promising technique for image restoration. We explored its ability to restore ultra-low-count [18F]FDG PET studies of the brain in subjects with dementia and in healthy subjects to allow for reduced scan durations or administered activities without compromising diagnostic performance. Methods: Various DL models using the content aware image restoration approach of CSBDeep toolbox (3D U-nets) were trained with subvolumes of 1,000 random subjects. On the basis of 10-min list-mode PET data after injection of 208 ± 10 MBq of [18F]FDG, we reconstructed reduced scan durations of 2 min, 1 min, 30 s, 20 s, and 10 s. The resulting models were applied to [18F]FDG PET scans of subjects with Alzheimer disease (n = 15), frontotemporal dementia (n = 14), and healthy controls (n = 13). We explored the effect of reduced scan times on individual regional measures in diagnostically relevant regions and on voxel-based group contrasts. Three independent readers rated all datasets with regard to assessability, diagnosis, and diagnostic confidence. Results: Individual mean regional [18F]FDG uptake remained largely unchanged. The SD strongly increased with shorter scan duration without application of DL (mean increase ≤ 48%), whereas it slightly decreased with DL (≥-7%). In group contrasts, the number of significant voxels strongly decreased with shorter scan time without DL (≥-41%), which was partially offset by DL (≥-27%). On visual reads, the fraction of assessable images steeply fell to only 4% (10-s scan) for scan durations below 2 min without DL, whereas every single image restored with DL was assessable. The diagnostic confidence continuously declined with shorter scan durations without DL, whereas diagnostic confidence only negligibly changed with DL (intermediate-to-high confidence ratings: 0%-54% vs. 80%-84%; 83% for the 10-min scan). The diagnostic accuracy of PET reads dropped from 90% to 4% without and remained high with DL (90%-93%; 90% for the 10-min scan). Conclusion: Our study demonstrates the compelling performance of DL to restore cerebral [18F]FDG PET datasets with ultra-low-count statistics for quantitative regional, voxel-based group, and clinical visual analyses. Consequently, DL enables a dramatic reduction of scan durations or administered activities (e.g., 10-min scan with 3.5 MBq, equivalent to ∼60 µSv) for [18F]FDG PET in patients with dementia and possibly other indications.
引用
- Schiller F, Brumberg J, Frings L, et al. Clinical Validation of Deep Learning for Image Restoration of Ultra-Low-Count [18F]FDG PET for Dementia Diagnostics. J Nucl Med. 2025. PMID: 40813236. doi:10.2967/jnumed.124.269234
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。