Improving the Quality of Synthetic FLAIR Images with Deep Learning Using a Conditional Generative Adversarial Network for Pixel-by-Pixel Image Translation
Improving the Quality of Synthetic FLAIR Images with Deep Learning Using a Conditional Generative Adversarial Network for Pixel-by-Pixel Image Translation
复制标题
DOI：
10.3174/ajnr.a5927
复制
发表时间：
2019-02-01
影响因子：
3.5
通讯作者：
Aoki, S.
中科院分区：
文献类型：
--
作者：
Hagiwara, A.;Otsuka, Y.;Aoki, S.
背景和目的：合成FLAIR图像的质量低于常规FLAIR图像。在这里，我们的目标是通过条件生成对抗网络训练，使用深度学习和逐像素翻译来提高合成FLAIR图像的质量。材料和方法：前瞻性纳入40例MS患者并进行扫描（3T），以获取合成MR成像和常规FLAIR图像。用SyMRI软件创建合成FLAIR图像。采集的数据分为30个训练数据集和10个测试数据集。训练条件生成对抗网络，以使用传统FLAIR图像作为目标，从原始合成MR成像数据生成改进的FLAIR图像。分别计算合成和深度学习FLAIR图像与传统FLAIR图像的峰值信噪比、归一化均方根误差和MS病变图的Dice指数。目视评估病变的显著性和伪影的存在。研究结果：峰值信噪比和标准化均方根误差分别显著高于和低于生成与合成FLAIR图像在聚集颅内组织和所有组织节段（所有P < .001）。生成的FLAIR图像和合成的FLAIR图像之间的病变图的Dice指数和视觉病变显著性相当（分别为P = 1和.59）。生成的FLAIR图像比合成FLAIR图像显示更少的颗粒伪影（P = 0.003）和肿胀伪影（在所有情况下）。结论：通过深度学习，我们通过生成对比度更接近传统FLAIR图像的FLAIR图像以及更少的颗粒和肿胀伪影，同时保留病变对比度，提高了合成FLAIR图像的质量。前瞻性纳入40例MS患者并进行扫描（3T），以获取合成MR成像和传统FLAIR图像。用SyMRI软件创建合成FLAIR图像。采集的数据分为30个训练数据集和10个测试数据集。训练条件生成对抗网络，以使用传统FLAIR图像作为目标，从原始合成MR成像数据生成改进的FLAIR图像。分别计算合成和深度学习FLAIR图像与传统FLAIR图像的峰值信噪比、归一化均方根误差和MS病变图的Dice指数。目视评估病变的显著性和伪影的存在。峰值信噪比和归一化均方根误差显着较高和较低，分别在生成与合成FLAIR图像在聚集颅内组织和所有组织段。生成的FLAIR图像和合成的FLAIR图像之间的病变图的Dice指数和视觉病变显著性相当。通过使用深度学习，作者得出结论，他们通过生成对比度更接近传统FLAIR图像的FLAIR图像以及更少的颗粒和肿胀伪影，同时保留病变对比度，提高了合成FLAIR图像的质量。
BACKGROUND AND PURPOSE: Synthetic FLAIR images are of lower quality than conventional FLAIR images. Here, we aimed to improve the synthetic FLAIR image quality using deep learning with pixel-by-pixel translation through conditional generative adversarial network training. MATERIALS AND METHODS: Forty patients with MS were prospectively included and scanned (3T) to acquire synthetic MR imaging and conventional FLAIR images. Synthetic FLAIR images were created with the SyMRI software. Acquired data were divided into 30 training and 10 test datasets. A conditional generative adversarial network was trained to generate improved FLAIR images from raw synthetic MR imaging data using conventional FLAIR images as targets. The peak signal-to-noise ratio, normalized root mean square error, and the Dice index of MS lesion maps were calculated for synthetic and deep learning FLAIR images against conventional FLAIR images, respectively. Lesion conspicuity and the existence of artifacts were visually assessed. RESULTS: The peak signal-to-noise ratio and normalized root mean square error were significantly higher and lower, respectively, in generated-versus-synthetic FLAIR images in aggregate intracranial tissues and all tissue segments (all P < .001). The Dice index of lesion maps and visual lesion conspicuity were comparable between generated and synthetic FLAIR images (P = 1 and .59, respectively). Generated FLAIR images showed fewer granular artifacts (P = .003) and swelling artifacts (in all cases) than synthetic FLAIR images. CONCLUSIONS: Using deep learning, we improved the synthetic FLAIR image quality by generating FLAIR images that have contrast closer to that of conventional FLAIR images and fewer granular and swelling artifacts, while preserving the lesion contrast.Forty patients with MS were prospectively included and scanned (3T) to acquire synthetic MR imaging and conventional FLAIR images. Synthetic FLAIR images were created with the SyMRI software. Acquired data were divided into 30 training and 10 test datasets. A conditional generative adversarial network was trained to generate improved FLAIR images from raw synthetic MR imaging data using conventional FLAIR images as targets. The peak signal-to-noise ratio, normalized root mean square error, and the Dice index of MS lesion maps were calculated for synthetic and deep learning FLAIR images against conventional FLAIR images, respectively. Lesion conspicuity and the existence of artifacts were visually assessed. The peak signal-to-noise ratio and normalized root mean square error were significantly higher and lower, respectively, in generated-versus-synthetic FLAIR images in aggregate intracranial tissues and all tissue segments. The Dice index of lesion maps and visual lesion conspicuity were comparable between generated and synthetic FLAIR images. Using deep learning, the authors conclude that they improved the synthetic FLAIR image quality by generating FLAIR images that have contrast closer to that of conventional FLAIR images and fewer granular and swelling artifacts, while preserving the lesion contrast.