无监督深度学习用于PET图像去噪
本研究提出一种基于无监督深度学习的PET图像去噪方法,无需训练配对,利用同一患者的高质量先验图像作为网络输入、噪声PET图像作为训练标签。在BrainWeb仿真、10例68Ga-PRGD2 PET/CT和30例18F-FDG PET/MR临床数据上验证,该方法在偏差-方差权衡和CNR提升比上均优于高斯、NLM、BM4D和Deep Decoder方法。
要点
- 无监督深度学习无需配对训练数据即可实现PET图像去噪
- 在仿真中偏差-方差权衡表现最佳
- 临床PET/CT和PET/MR数据集CNR提升比均高于参考方法
核心结论
- 所提出的无监督深度学习框架图像恢复效果优异,优于高斯、NLM、BM4D和Deep Decoder方法。
研究设计与样本
- 方法学研究:利用同一患者先验高质量图像作为网络输入、噪声PET图像作为训练标签的无监督深度学习。
- 仿真研究基于BrainWeb体模进行验证。
- 临床数据包括10例68Ga-PRGD2 PET/CT和30例18F-FDG PET/MR患者数据集。
- 参考方法包括高斯、以CT/MR为先验的NLM、BM4D和Deep Decoder方法。
主要发现
- 仿真研究中,所提方法的CRC vs. STD曲线在偏差-方差权衡上表现最佳。
- 临床PET/CT数据集:所提方法CNR提升比为53.35% ± 21.78%,高斯为12.64% ± 6.15%(P = 0.002),CT引导NLM为24.35% ± 16.30%(P = 0.002),BM4D为38.31% ± 20.26%(P = 0.002),Deep Decoder为41.67% ± 22.28%(P = 0.002)。
- 临床PET/MR数据集:所提方法CNR提升比为46.80% ± 25.23%,高斯为18.16% ± 10.02%(P < 0.0001),MR引导NLM为25.36% ± 19.48%(P < 0.0001),BM4D为37.02% ± 21.38%(P < 0.0001),Deep Decoder为30.03% ± 20.64%(P < 0.0001)。
- 所有数据集的恢复图像显示所提方法能有效平滑噪声同时恢复图像细节。
关键数值与推荐
- 以CNR提升比作为不同方法排序指标,基于Wilcoxon符号秩检验进行统计比较。
- 仿真研究采用CRC vs. STD曲线评估偏差-方差权衡。
临床怎么用
- 该无监督深度学习方法可利用同一患者先验图像对PET图像进行去噪,无需配对训练数据。
- 在68Ga-PRGD2 PET/CT和18F-FDG PET/MR临床数据中,该方法CNR提升比高于高斯、NLM、BM4D和Deep Decoder方法。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: 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. METHODS: 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 68Ga-PRGD2 PET/CT dataset containing 10 patients and a 18F-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. RESULTS: 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. CONCLUSION: The proposed unsupervised deep learning framework provides excellent image restoration effects, outperforming the Gaussian, NLM methods, BM4D, and Deep Decoder methods.
引用
- Cui J, Gong K, Guo N, et al. PET image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging. 2019. PMID: 31468181. doi:10.1007/s00259-019-04468-4
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。