当前位置: X-MOL 学术Neural Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
PET image super-resolution using generative adversarial networks.
Neural Networks ( IF 7.8 ) Pub Date : 2020-02-03 , DOI: 10.1016/j.neunet.2020.01.029
Tzu-An Song 1 , Samadrita Roy Chowdhury 1 , Fan Yang 1 , Joyita Dutta 2
Affiliation  

The intrinsically low spatial resolution of positron emission tomography (PET) leads to image quality degradation and inaccurate image-based quantitation. Recently developed supervised super-resolution (SR) approaches are of great relevance to PET but require paired low- and high-resolution images for training, which are usually unavailable for clinical datasets. In this paper, we present a self-supervised SR (SSSR) technique for PET based on dual generative adversarial networks (GANs), which precludes the need for paired training data, ensuring wider applicability and adoptability. The SSSR network receives as inputs a low-resolution PET image, a high-resolution anatomical magnetic resonance (MR) image, spatial information (axial and radial coordinates), and a high-dimensional feature set extracted from an auxiliary CNN which is separately-trained in a supervised manner using paired simulation datasets. The network is trained using a loss function which includes two adversarial loss terms, a cycle consistency term, and a total variation penalty on the SR image. We validate the SSSR technique using a clinical neuroimaging dataset. We demonstrate that SSSR is promising in terms of image quality, peak signal-to-noise ratio, structural similarity index, contrast-to-noise ratio, and an additional no-reference metric developed specifically for SR image quality assessment. Comparisons with other SSSR variants suggest that its high performance is largely attributable to simulation guidance.

中文翻译:

使用生成对抗网络的PET图像超分辨率。

正电子发射断层扫描(PET)固有的低空间分辨率会导致图像质量下降和基于图像的定量不准确。最近开发的监督超分辨率(SR)方法与PET息息相关,但需要成对的低分辨率和高分辨率图像进行训练,这通常不适用于临床数据集。在本文中,我们提出了一种基于双重生成对抗网络(GAN)的PET自我监督SR(SSSR)技术,该技术无需配对训练数据,从而确保了更广泛的适用性和可采用性。SSSR网络接收低分辨率PET图像,高分辨率解剖磁共振(MR)图像,空间信息(轴向和径向坐标)作为输入,以及从辅助CNN中提取的高维特征集,该辅助特征CNN使用配对的模拟数据集以有监督的方式分别进行了训练。使用损失函数训练网络,该函数包括两个对抗损失项,周期一致性项和SR图像上的总变化量。我们使用临床神经影像数据集验证了SSSR技术。我们证明SSSR在图像质量,峰值信噪比,结构相似性指数,对比度对噪声比以及专门为SR图像质量评估开发的其他无参考指标方面很有前途。与其他SSSR变体的比较表明,其高性能很大程度上归因于仿真指导。使用损失函数训练网络,该函数包括两个对抗损失项,周期一致性项和SR图像上的总变化量。我们使用临床神经影像数据集验证了SSSR技术。我们证明SSSR在图像质量,峰值信噪比,结构相似性指数,对比度对噪声比以及专门为SR图像质量评估开发的其他无参考指标方面很有前途。与其他SSSR变体的比较表明,其高性能很大程度上归因于仿真指导。使用损失函数训练网络,该函数包括两个对抗损失项,周期一致性项和SR图像上的总变化量。我们使用临床神经影像数据集验证了SSSR技术。我们证明SSSR在图像质量,峰值信噪比,结构相似性指数,对比度对噪声比以及专门为SR图像质量评估开发的其他无参考指标方面很有前途。与其他SSSR变体的比较表明,其高性能很大程度上归因于仿真指导。结构相似性指标,对比度和噪声比,以及专门为SR图像质量评估开发的其他无参考指标。与其他SSSR变体的比较表明,其高性能很大程度上归因于仿真指导。结构相似性指标,对比度和噪声比,以及专门为SR图像质量评估开发的其他无参考指标。与其他SSSR变体的比较表明,其高性能很大程度上归因于仿真指导。
更新日期:2020-02-03
down
wechat
bug