Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital, 55 Fruit St, White 427, Boston, MA, 02114, USA.
State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, 38 Zheda Road, No.3 Teaching Building, 405, Hangzhou, 310027, China.
Eur J Nucl Med Mol Imaging. 2019 Dec;46(13):2780-2789. doi: 10.1007/s00259-019-04468-4. Epub 2019 Aug 29.
Image quality of positron emission tomography (PET) is limited by various physical degradation factors. Our study aims to perform PET image denoising by utilizing prior information from the same patient. The proposed method is based on unsupervised deep learning, where no training pairs are needed.
In this method, the prior high-quality image from the patient was employed as the network input and the noisy PET image itself was treated as the training label. Constrained by the network structure and the prior image input, the network was trained to learn the intrinsic structure information from the noisy image and output a restored PET image. To validate the performance of the proposed method, a computer simulation study based on the BrainWeb phantom was first performed. A Ga-PRGD2 PET/CT dataset containing 10 patients and a F-FDG PET/MR dataset containing 30 patients were later on used for clinical data evaluation. The Gaussian, non-local mean (NLM) using CT/MR image as priors, BM4D, and Deep Decoder methods were included as reference methods. The contrast-to-noise ratio (CNR) improvements were used to rank different methods based on Wilcoxon signed-rank test.
For the simulation study, contrast recovery coefficient (CRC) vs. standard deviation (STD) curves showed that the proposed method achieved the best performance regarding the bias-variance tradeoff. For the clinical PET/CT dataset, the proposed method achieved the highest CNR improvement ratio (53.35% ± 21.78%), compared with the Gaussian (12.64% ± 6.15%, P = 0.002), NLM guided by CT (24.35% ± 16.30%, P = 0.002), BM4D (38.31% ± 20.26%, P = 0.002), and Deep Decoder (41.67% ± 22.28%, P = 0.002) methods. For the clinical PET/MR dataset, the CNR improvement ratio of the proposed method achieved 46.80% ± 25.23%, higher than the Gaussian (18.16% ± 10.02%, P < 0.0001), NLM guided by MR (25.36% ± 19.48%, P < 0.0001), BM4D (37.02% ± 21.38%, P < 0.0001), and Deep Decoder (30.03% ± 20.64%, P < 0.0001) methods. Restored images for all the datasets demonstrate that the proposed method can effectively smooth out the noise while recovering image details.
The proposed unsupervised deep learning framework provides excellent image restoration effects, outperforming the Gaussian, NLM methods, BM4D, and Deep Decoder methods.
正电子发射断层扫描（PET）的图像质量受到各种物理退化因素的限制。本研究旨在利用同一患者的先验信息对 PET 图像进行去噪。所提出的方法基于无监督深度学习，不需要训练对。
在该方法中，将来自患者的高质量先验图像用作网络输入，将噪声 PET 图像本身用作训练标签。在网络结构和先验图像输入的约束下，网络被训练以从噪声图像中学习内在结构信息，并输出恢复的 PET 图像。为了验证所提出方法的性能，首先进行了基于 BrainWeb 体模的计算机模拟研究。随后，使用包含 10 名患者的 Ga-PRGD2 PET/CT 数据集和包含 30 名患者的 F-FDG PET/MR 数据集进行临床数据评估。高斯、基于 CT/MR 图像的非局部均值（NLM）、BM4D 和 Deep Decoder 方法被用作参考方法。使用 Wilcoxon 符号秩检验基于对比噪声比（CNR）的提高来对不同方法进行排名。
对于模拟研究，对比恢复系数（CRC）与标准偏差（STD）曲线表明，所提出的方法在偏倚-方差权衡方面表现出最佳性能。对于临床 PET/CT 数据集，与高斯（12.64%±6.15%，P=0.002）、CT 引导的 NLM（24.35%±16.30%，P=0.002）、BM4D（38.31%±20.26%，P=0.002）和 Deep Decoder（41.67%±22.28%，P=0.002）方法相比，所提出的方法实现了最高的 CNR 提高比（53.35%±21.78%）。对于临床 PET/MR 数据集，所提出的方法的 CNR 提高比达到 46.80%±25.23%，高于高斯（18.16%±10.02%，P<0.0001）、MR 引导的 NLM（25.36%±19.48%，P<0.0001）、BM4D（37.02%±21.38%，P<0.0001）和 Deep Decoder（30.03%±20.64%，P<0.0001）方法。所有数据集的重建图像表明，所提出的方法可以有效地平滑噪声，同时恢复图像细节。
所提出的无监督深度学习框架提供了出色的图像恢复效果，优于高斯、NLM 方法、BM4D 和 Deep Decoder 方法。
