Laurent Baptiste, Bousse Alexandre, Merlin Thibaut, Rominger Axel, Shi Kuangyu, Visvikis Dimitris
LaTIM, Inserm UMR 1101, University of Brest, Brest, France.
Department Nuclear Medicine, Bern University Hospital, University of Bern, Bern, Switzerland.
Eur J Nucl Med Mol Imaging. 2025 Jun;52(7):2563-2576. doi: 10.1007/s00259-025-07120-6. Epub 2025 Feb 7.
Long-axial field-of-view (LAFOV) positron emission tomography (PET) systems allow higher sensitivity, with an increased number of detected lines of response induced by a larger angle of acceptance. However this extended angle increases the number of multiple scatters and the scatter contribution within oblique planes. As scattering affects both quality and quantification of the reconstructed image, it is crucial to correct this effect with more accurate methods than the state-of-the-art single scatter simulation (SSS) that can reach its limits with such an extended field-of-view (FOV). In this work, which is an extension of our previous assessment of deep learning-based scatter estimation (DLSE) carried out on a conventional PET system, we aim to evaluate the DLSE method performance on LAFOV total-body PET.
The proposed DLSE method based on an convolutional neural network (CNN) U-Net architecture uses emission and attenuation sinograms to estimate scatter sinogram. The network was trained from Monte-Carlo (MC) simulations of XCAT phantoms [ F]-FDG PET acquisitions using a Siemens Biograph Vision Quadra scanner model, with multiple morphologies and dose distributions. We firstly evaluated the method performance on simulated data in both sinogram and image domain by comparing it to the MC ground truth and SSS scatter sinograms. We then tested the method on seven [ F]-FDG and [ F]-PSMA clinical datasets, and compare it to SSS estimations.
DLSE showed superior accuracy on phantom data, greater robustness to patient size and dose variations compared to SSS, and better lesion contrast recovery. It also yielded promising clinical results, improving lesion contrasts in [ F]-FDG datasets and performing consistently with [ F]-PSMA datasets despite no training with [ F]-PSMA.
LAFOV PET scatter can be accurately estimated from raw data using the proposed DLSE method.
长轴视野（LAFOV）正电子发射断层扫描（PET）系统具有更高的灵敏度，更大的接受角会增加检测到的响应线数量。然而，这种扩展角度会增加多次散射的数量以及斜平面内的散射贡献。由于散射会影响重建图像的质量和定量分析，因此使用比当前最先进的单散射模拟（SSS）更准确的方法来校正这种影响至关重要，因为在如此扩展的视野（FOV）下，SSS可能会达到其极限。在这项工作中，这是我们之前对传统PET系统进行的基于深度学习的散射估计（DLSE）评估的扩展，我们旨在评估DLSE方法在LAFOV全身PET上的性能。
所提出的基于卷积神经网络（CNN）U-Net架构的DLSE方法使用发射和衰减正弦图来估计散射正弦图。该网络通过使用西门子Biograph Vision Quadra扫描仪模型对XCAT体模的[F] - FDG PET采集进行蒙特卡罗（MC）模拟进行训练，具有多种形态和剂量分布。我们首先通过将其与MC真实值和SSS散射正弦图进行比较，在正弦图和图像域的模拟数据上评估该方法的性能。然后我们在七个[F] - FDG和[F] - PSMA临床数据集上测试该方法，并将其与SSS估计进行比较。
DLSE在体模数据上显示出更高的准确性，与SSS相比，对患者大小和剂量变化具有更强的鲁棒性，并且具有更好的病变对比度恢复。它还产生了有前景的临床结果，改善了[F] - FDG数据集中的病变对比度，并且在[F] - PSMA数据集中表现一致，尽管没有使用[F] - PSMA进行训练。
使用所提出的DLSE方法可以从原始数据中准确估计LAFOV PET散射。
