Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, China Academy of Sciences, Shenzhen 518055, People's Republic of China.
National Innovation Center for Advanced Medical Devices, Shenzhen 518131, People's Republic of China.
Phys Med Biol. 2021 Jun 24;66(13). doi: 10.1088/1361-6560/ac08b2.
Positron emission tomography (PET) imaging can be used for early detection, diagnosis and postoperative patient monitoring of many diseases. Traditional PET imaging requires not only additional computed tomography (CT) imaging or magnetic resonance imaging (MR) to provide anatomical information but also attenuation correction (AC) map calculation based on CT images or MR images for accurate quantitative estimation. During a patient's treatment, PET/CT or PET/MR scans are inevitably repeated many times, leading to additional doses of ionizing radiation (CT scans) and additional economic and time costs (MR scans). To reduce adverse effects while obtaining high-quality PET/MR images in the course of a patient's treatment, especially in the stage of evaluating the effect of postoperative treatment, in this work, we propose a new method based on deep learning, which can directly obtain synthetic attenuation-corrected PET (sAC PET) and synthetic T1-weighted MR (sMR) images based only on non-attenuation-corrected PET (NAC PET) images. Our model, based on the Wasserstein generative adversarial network, first removes noise and artifacts from the NAC PET images to generate sAC PET images and then generates sMR images from the obtained sAC PET images. To evaluate the performance of this generative model, we evaluated it on paired PET/MR images from a total of eighty clinical patients. Based on qualitative and quantitative analysis, the generated sAC PET and sMR images showed a high degree of similarity to the real AC PET and real MR images. These results indicated that our proposed method can reduce the frequency of additional anatomical imaging scans during PET imaging and has great potential in improving doctors' clinical diagnosis efficiency, saving patients' economic expenditure and reducing the radiation risk brought by CT scanning.
正电子发射断层扫描（PET）成像可用于许多疾病的早期检测、诊断和术后患者监测。传统的 PET 成像不仅需要额外的计算机断层扫描（CT）或磁共振成像（MR）来提供解剖信息，还需要基于 CT 或 MR 图像计算衰减校正（AC）图，以进行准确的定量估计。在患者治疗过程中，不可避免地要多次重复进行 PET/CT 或 PET/MR 扫描，这会导致额外的电离辐射剂量（CT 扫描）和额外的经济和时间成本（MR 扫描）。为了在治疗过程中获得高质量的 PET/MR 图像的同时减少不良影响，特别是在评估术后治疗效果的阶段，在这项工作中，我们提出了一种基于深度学习的新方法，可以仅基于未校正衰减 PET（NAC PET）图像直接获得合成衰减校正 PET（sAC PET）和合成 T1 加权磁共振（sMR）图像。我们的模型基于 Wasserstein 生成对抗网络，首先从 NAC PET 图像中去除噪声和伪影，生成 sAC PET 图像，然后从获得的 sAC PET 图像生成 sMR 图像。为了评估这个生成模型的性能，我们在总共 80 名临床患者的 PET/MR 图像对上进行了评估。通过定性和定量分析，生成的 sAC PET 和 sMR 图像与真实的 AC PET 和真实的 MR 图像具有高度的相似性。这些结果表明，我们提出的方法可以减少 PET 成像过程中额外解剖成像扫描的频率，在提高医生的临床诊断效率、节省患者的经济支出和降低 CT 扫描带来的辐射风险方面具有巨大潜力。
