Abstract
Positron Emission Tomography (PET) imaging requires accurate attenuation correction (AC) to account for photon loss due to tissue density variations. In PET/MR systems, computed tomography (CT), which offers a straightforward estimation of AC is not available. This study presents a deep learning approach to generate synthetic CT (sCT) images directly from Time-of-Flight (TOF) non-attenuation corrected (NAC) PET images, enhancing AC for PET/MR. We first evaluated models pre-trained on large-scale natural image datasets for a CT-to-CT reconstruction task, finding that the pre-trained model outperformed those trained solely on medical datasets. The pre-trained model was then fine-tuned using an institutional dataset of 35 TOF NAC PET and CT volume pairs, achieving the lowest mean absolute error (MAE) of 74.49 HU and highest peak signal-to-noise ratio (PSNR) of 28.66 dB within the body contour region. Visual assessments demonstrated improved reconstruction of both bone and soft tissue structures from TOF NAC PET images. This work highlights the effectiveness of using pre-trained deep learning models for medical image translation tasks. Future work will assess the impact of sCT on PET attenuation correction and explore additional neural network architectures and datasets to further enhance performance and practical applications in PET imaging.
Abstract (translated)
正电子发射断层扫描（PET）成像需要准确的衰减校正（AC），以补偿由于组织密度变化引起的光子损失。在PET/MR系统中，提供直接衰减校正估计的计算机断层扫描（CT）不可用。这项研究提出了一种深度学习方法，可以从时间飞行（TOF）未校正衰减（NAC）PET图像生成合成CT（sCT）图像，从而增强PET/MR中的衰减校正。 首先，我们评估了在大规模自然图像数据集上预训练的模型，在CT到CT重建任务中进行测试。结果显示，这些预训练模型的表现优于仅在医学数据集上训练的模型。随后，通过使用一个包含35对TOF NAC PET和CT体体积配对的数据集对该预训练模型进行了微调。结果表明，该模型实现了最低均方绝对误差（MAE）74.49 HU以及最高的峰值信噪比（PSNR）28.66 dB的性能，在身体轮廓区域。 视觉评估显示，从TOF NAC PET图像中重建出的骨骼和软组织结构得到了显著改善。这项工作证明了使用预训练深度学习模型在医学图像转换任务中的有效性。未来的工作将评估sCT对PET衰减校正的影响，并探索其他神经网络架构和数据集以进一步提高性能和实际应用价值，特别是在PET成像领域。
URL
https://arxiv.org/abs/2504.07450
