DeepPET: A deep encoder-decoder network for directly solving the PET image reconstruction inverse problem
DeepPET: A deep encoder-decoder network for directly solving the PET image reconstruction inverse problem
复制标题
DOI：
10.1016/j.media.2019.03.013
复制
发表时间：
2019-05-01
影响因子：
10.9
通讯作者：
Fuchs, Thomas J.
中科院分区：
文献类型：
--
作者：
Haggstrom, Ida;Schmidtlein, C. Ross;Fuchs, Thomas J.
这项研究的目的是实现一个深度学习网络，以克服临床正电子发射断层扫描(PET)图像重建改进中的两个主要瓶颈。因此，我们提出了一种基于深度卷积编解码网络的端到端PET图像重建技术DeepPET，它以PET正弦图数据为输入，直接快速地输出高质量的定量PET图像。使用从全身数字体模获得的模拟数据，我们随机采样可配置的参数以生成逼真的图像，每个图像被放大到总共291,000多张参考图像。我们模拟了这些图像的真实PET采集，产生了噪声正弦图数据，用于训练、验证和测试DeepPET网络。我们表明，DeepPET生成的图像在相对均方误差(比有序子集期望最大化(OSEM)/滤波反投影(FBP)低11%/53%)、结构相似性指数(比OSEM/FBP高1%/11%)和峰值信噪比(比OSEM/FBP高1.1/3.8dB)方面比传统技术产生更高的质量。此外，我们还证明了DeepPET重建图像的速度分别是OSEM和FBP的108倍和3倍。最后，DeepPET被成功地应用于实际的临床数据。这项研究表明，与传统方法相比，端到端编解码器网络可以在很短的时间内生成高质量的PET图像。(C)2019爱思唯尔B.V.保留所有权利。
The purpose of this research was to implement a deep learning network to overcome two of the major bottlenecks in improved image reconstruction for clinical positron emission tomography (PET). These are the lack of an automated means for the optimization of advanced image reconstruction algorithms, and the computational expense associated with these state-of-the art methods.We thus present a novel end-to-end PET image reconstruction technique, called DeepPET, based on a deep convolutional encoder-decoder network, which takes PET sinogram data as input and directly and quickly outputs high quality, quantitative PET images. Using simulated data derived from a whole-body digital phantom, we randomly sampled the configurable parameters to generate realistic images, which were each augmented to a total of more than 291,000 reference images. Realistic PET acquisitions of these images were simulated, resulting in noisy sinogram data, used for training, validation, and testing the DeepPET network.We demonstrated that DeepPET generates higher quality images compared to conventional techniques, in terms of relative root mean squared error (11%/53% lower than ordered subset expectation maximization (OSEM)/filtered back-projection (FBP), structural similarity index (1%/11% higher than OSEM/FBP), and peak signal-to-noise ratio (1.1/3.8 dB higher than OSEM/FBP). In addition, we show that DeepPET reconstructs images 108 and 3 times faster than OSEM and FBP, respectively. Finally, DeepPET was successfully applied to real clinical data. This study shows that an end-to-end encoder-decoder network can produce high quality PET images at a fraction of the time compared to conventional methods. (C) 2019 Elsevier B.V. All rights reserved.