Fukui Ryohei, Fujii Susumu, Ninomiya Hiroki, Fujiwara Yasuhiro, Ida Tomonobu
Division of Clinical Radiology, Tottori University Hospital(Current address: Department of Radiological Technology, Graduate School of Health Sciences, Okayama University).
Division of Clinical Radiology, Tottori University Hospital.
Nihon Hoshasen Gijutsu Gakkai Zasshi. 2020;76(11):1152-1162. doi: 10.6009/jjrt.2020_JSRT_76.11.1152.
Computed tomography (CT) is used for the attenuation correction (AC) of [F-18] fluoro-deoxy-glucose positron emission tomography (PET) image. However, acquisition of a CT image for this purpose requires increasing the radiation dose of the patient. To generate a pseudo-image, a generative adversarial network (GAN) based on deep learning is adopted. The purpose of this study was to generate a pseudo-CT image, using a GAN, for the AC of the PET image, with the aim of reducing the dose of the patient. A set of approximately 15,000 no-AC PET and CT images was used as the training sample, and the CycleGAN was employed as the image generation model. The training samples were inputted in the CycleGAN, and the hyperparameters, i.e., the learning rate, batch size, and number of epochs were set to 0.0001, 1, and 300, respectively. A pseudo-PET image was obtained using a pseudo-CT image, which was used for the AC of the no-AC PET image. The coefficient of similarity between the real and generated pseudo-images was estimated using the peak signal-to-noise ratio (PSNR) , the structural similarity (SSIM), and the dice similarity coefficient (DSC). The average values of PSNR, SSIM, and DSC of the pseudo-CT were 31.0 dB, 0.87, and 0.89, and those of the pseudo-PET were 35.9 dB, 0.90, and 0.95, respectively. The AC for the whole-body PET image could be accomplished using the pseudo-CT image generated via the GAN. The proposed method would be established as the CT-less PET/CT examination.
计算机断层扫描（CT）用于[F-18]氟脱氧葡萄糖正电子发射断层扫描（PET）图像的衰减校正（AC）。然而，为此目的获取CT图像需要增加患者的辐射剂量。为了生成伪图像，采用了基于深度学习的生成对抗网络（GAN）。本研究的目的是使用GAN生成用于PET图像AC的伪CT图像，以减少患者的剂量。一组约15000张无AC的PET和CT图像用作训练样本，CycleGAN用作图像生成模型。将训练样本输入CycleGAN，超参数，即学习率、批量和轮数分别设置为0.0001、1和300。使用伪CT图像获得伪PET图像，该伪PET图像用于无AC的PET图像的AC。使用峰值信噪比（PSNR）、结构相似性（SSIM）和骰子相似系数（DSC）估计真实图像和生成的伪图像之间的相似系数。伪CT的PSNR、SSIM和DSC的平均值分别为31.0 dB、0.87和0.89，伪PET的平均值分别为35.9 dB、0.90和0.95。可以使用通过GAN生成的伪CT图像完成全身PET图像的AC。所提出的方法将被确立为无CT的PET/CT检查。
