一种用于双时间窗协议全身动态PET成像的深度学习方法
本研究纳入70例肺部或乳腺结节患者,每例接受65分钟全身动态[18F]FDG PET/CT扫描,开发双向注意力序列到序列模型(Bi-AT-Seq2Seq)从双时间窗协议预测缺失帧以缩短扫描时间;该模型在MAE、Bias、PSNR和SSIM上显著优于单向或无注意力模型,双时间窗协议(10分钟早期扫描+5分钟晚期扫描)较15分钟早期停止协议使预测动态图像四项指标分别改善37.31%、36.24%、7.10%和0.014%。
要点
- Bi-AT-Seq2Seq模型在MAE、Bias、PSNR和SSIM上显著优于单向或无注意力模型。
- 双时间窗协议(10分钟+5分钟)较15分钟早期停止协议使四项指标分别改善37.31%、36.24%、7.10%和0.014%。
- 用恢复的完整时间-活度曲线估计的肿瘤动力学参数CCC高于用简化时间-活度曲线估计的CCC。
核心结论
- 所提出的算法能够从双时间窗协议(10+5分钟)准确生成完整的65分钟动态采集。
研究设计与样本
- 本研究纳入2022至2024年间诊断为肺部结节或乳腺结节的70例患者(平均年龄±标准差53.61±13.53岁;32例男性)。
- 每例患者接受65分钟全身动态[18F]FDG PET/CT扫描,并模拟早期停止协议和双时间窗协议以减少扫描时间。
- 开发了带注意力机制的双向序列到序列模型(Bi-AT-Seq2Seq)预测缺失帧,并与单向或无注意力模型比较预测帧的MAE、Bias、PSNR和SSIM。
- 报告了所提方法与传统方法估计的动力学参数一致性相关系数(CCC)比较。
主要发现
- Bi-AT-Seq2Seq在MAE、Bias、PSNR和SSIM上显著优于单向或无注意力模型。
- 采用双时间窗协议(含10分钟早期扫描后5分钟晚期扫描)较15分钟采集的早期停止协议使预测动态图像四项指标分别改善37.31%、36.24%、7.10%和0.014%。
- 用恢复的完整时间-活度曲线估计的肿瘤动力学参数CCC高于用简化时间-活度曲线估计的CCC。
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: Prolonged scanning durations are one of the primary barriers to the widespread clinical adoption of dynamic Positron Emission Tomography (PET). In this paper, we developed a deep learning algorithm that capable of predicting dynamic images from dual-time-window protocols, thereby shortening the scanning time. METHODS: This study includes 70 patients (mean age ± standard deviation, 53.61 ± 13.53 years; 32 males) diagnosed with pulmonary nodules or breast nodules between 2022 to 2024. Each patient underwent a 65-min dynamic total-body [18F]FDG PET/CT scan. Acquisitions using early-stop protocols and dual-time-window protocols were simulated to reduce the scanning time. To predict the missing frames, we developed a bidirectional sequence-to-sequence model with attention mechanism (Bi-AT-Seq2Seq); and then compared the model with unidirectional or non-attentional models in terms of Mean Absolute Error (MAE), Bias, Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity (SSIM) of predicted frames. Furthermore, we reported the comparison of concordance correlation coefficient (CCC) of the kinetic parameters between the proposed method and traditional methods. RESULTS: The Bi-AT-Seq2Seq significantly outperform unidirectional or non-attentional models in terms of MAE, Bias, PSNR, and SSIM. Using a dual-time-window protocol, which includes a 10-min early scan followed by a 5-min late scan, improves the four metrics of predicted dynamic images by 37.31%, 36.24%, 7.10%, and 0.014% respectively, compared to the early-stop protocol with a 15-min acquisition. The CCCs of tumor' kinetic parameters estimated with recovered full time-activity-curves (TACs) is higher than those with abbreviated TACs. CONCLUSION: The proposed algorithm can accurately generate a complete dynamic acquisition (65 min) from dual-time-window protocols (10 + 5 min).
引用
- Ding W, Wang H, Qiao X, et al. A deep learning method for total-body dynamic PET imaging with dual-time-window protocols. Eur J Nucl Med Mol Imaging. 2024. PMID: 39688700. doi:10.1007/s00259-024-07012-1
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。