Muller Florence M, Li Elizabeth J, Daube-Witherspoon Margaret E, Pantel Austin R, Wiers Corinde E, Dubroff Jacob G, Vanhove Christian, Vandenberghe Stefaan, Karp Joel S
Medical Image and Signal Processing, Faculty of Engineering and Architecture, Ghent University, Ghent, Belgium.
Physics and Instrumentation, Department of Radiology, University of Pennsylvania, Philadelphia, PA, US.
Eur J Nucl Med Mol Imaging. 2025 Mar 12. doi: 10.1007/s00259-025-07182-6.
Long-axial field-of-view PET scanners capture multi-organ tracer distribution with high sensitivity, enabling lower dose dynamic protocols and dual-tracer imaging for comprehensive disease characterization. However, reducing dose may compromise data quality and time-activity curve (TAC) fitting, leading to higher bias in kinetic parameters. Parametric imaging poses further challenges due to noise amplification in voxel-based modelling. We explore the potential of deep learning denoising (DL-DN) to improve quantification for low-dose dynamic PET.
Using 16 [F]FDG PET studies from the PennPET Explorer, we trained a DL framework on 10-min images from late-phase uptake (static data) that were sub-sampled from 1/2 to 1/300 of the counts. This model was used to denoise early-to-late dynamic frame images. Its impact on quantification was evaluated using compartmental modelling and voxel-based graphical analysis for parametric imaging for single- and dual-tracer dynamic studies with [F]FDG and [F]FGln at original (injected) and reduced (sub-sampled) doses. Quantification differences were evaluated for the area under the curve of TACs, K for [F]FDG and V for [F]FGln, and parametric images.
DL-DN consistently improved image quality across all dynamic frames, systematically enhancing TAC consistency and reducing tissue-dependent bias and variability in K and V down to 40 MBq doses. DL-DN preserved tumor heterogeneity in Logan V images and delineation of high-flux regions in Patlak K maps. In a /[F]FDG dual-tracer study, bias trends aligned with single-tracer results but showed reduced accuracy for [¹⁸F]FGln in breast lesions at very low doses (4 MBq).
This study demonstrates that applying DL-DN trained on static [F]FDG PET images to dynamic [F]FDG and [F]FGln PET can permit significantly reduced doses, preserving accurate FDG K and FGln V measurements, and enhancing parametric image quality. DL-DN shows promise for improving dynamic PET quantification at reduced doses, including novel dual-tracer studies.
长轴视野PET扫描仪能够以高灵敏度捕获多器官示踪剂分布，从而实现更低剂量的动态扫描方案以及双示踪剂成像，以全面表征疾病。然而，降低剂量可能会影响数据质量和时间-活性曲线（TAC）拟合，导致动力学参数出现更高的偏差。由于基于体素的建模中存在噪声放大问题，参数成像面临着进一步的挑战。我们探讨了深度学习去噪（DL-DN）在改善低剂量动态PET定量分析方面的潜力。
我们使用来自宾夕法尼亚PET探索者的16项[F]FDG PET研究，在晚期摄取的10分钟图像（静态数据）上训练了一个DL框架，这些图像的计数从1/2下采样到1/300。该模型用于对早期到晚期的动态帧图像进行去噪。使用房室模型和基于体素的图形分析对其对定量分析的影响进行评估，用于[F]FDG和[F]FGln在原始（注射）和降低（下采样）剂量下的单示踪剂和双示踪剂动态研究的参数成像。对TAC曲线下面积、[F]FDG的K值和[F]FGln的V值以及参数图像的定量差异进行了评估。
DL-DN在所有动态帧中持续改善图像质量，系统地增强了TAC的一致性，并将K值和V值中与组织相关的偏差和变异性降低至40 MBq剂量。DL-DN在Logan V图像中保留了肿瘤异质性，并在Patlak K图中清晰显示了高通量区域。在一项/[F]FDG双示踪剂研究中，偏差趋势与单示踪剂结果一致，但在非常低的剂量（4 MBq）下，[¹⁸F]FGln在乳腺病变中的准确性有所降低。
本研究表明，将基于静态[F]FDG PET图像训练的DL-DN应用于动态[F]FDG和[F]FGln PET，可以显著降低剂量，保留准确的FDG K值和FGln V值测量，并提高参数图像质量。DL-DN在降低剂量的情况下改善动态PET定量分析方面显示出前景，包括新型双示踪剂研究。
