IntroductionAcquisition and pre-processing pipelines for diffusion-weighted imaging (DWI) volumes are resource- and time-consuming. Generating synthetic DWI scalar maps from commonly acquired brain MRI sequences such as fluid-attenuated inversion recovery (FLAIR) could be useful for supplementing datasets. In this work we design and compare GAN-based image translation models for generating DWI scalar maps from FLAIR MRI for the first time.MethodsWe evaluate a pix2pix model, two modified CycleGANs using paired and unpaired data, and a convolutional autoencoder in synthesizing DWI fractional anisotropy (FA) and mean diffusivity (MD) from whole FLAIR volumes. In total, 420 FLAIR and DWI volumes (11,957 images) from multi-center dementia and vascular disease cohorts were used for training/testing. Generated images were evaluated using two groups of metrics: (1) human perception metrics including peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), (2) structural metrics including a newly proposed histogram similarity (Hist-KL) metric and mean squared error (MSE).ResultsPix2pix demonstrated the best performance both quantitatively and qualitatively with mean PSNR, SSIM, and MSE metrics of 23.41 dB, 0.8, 0.004, respectively for MD generation, and 24.05 dB, 0.78, 0.004, respectively for FA generation. The new histogram similarity metric demonstrated sensitivity to differences in fine details between generated and real images with mean pix2pix MD and FA Hist-KL metrics of 11.73 and 3.74, respectively. Detailed analysis of clinically relevant regions of white matter (WM) and gray matter (GM) in the pix2pix images also showed strong significant (p < 0.001) correlations between real and synthetic FA values in both tissue types (R = 0.714 for GM, R = 0.877 for WM).Discussion/conclusionOur results show that pix2pix’s FA and MD models had significantly better structural similarity of tissue structures and fine details than other models, including WM tracts and CSF spaces, between real and generated images. Regional analysis of synthetic volumes showed that synthetic DWI images can not only be used to supplement clinical datasets, but demonstrates potential utility in bypassing or correcting registration in data pre-processing.

中文翻译：

---

使用生成对抗网络从 FLAIR 体积合成扩散加权 MRI 标量图

简介扩散加权成像 (DWI) 体积的采集和预处理流程非常消耗资源和时间。从常见的脑 MRI 序列（例如流体衰减反转恢复 (FLAIR)）生成合成 DWI 标量图可能有助于补充数据集。在这项工作中，我们首次设计并比较了基于 GAN 的图像转换模型，用于从 FLAIR MRI 生成 DWI 标量图。方法我们评估 pix2pix 模型、使用配对和不配对数据的两个修改的 CycleGAN，以及合成 DWI 分数各向异性的卷积自动编码器整个 FLAIR 体积的 (FA) 和平均扩散率 (MD)。总共，来自多中心痴呆和血管疾病队列的 420 个 FLAIR 和 DWI 卷（11,957 张图像）用于训练/测试。使用两组指标评估生成的图像：（1）人类感知指标，包括峰值信噪比（PSNR）和结构相似性（SSIM），（2）结构指标，包括新提出的直方图相似性（Hist-KL）结果Pix2pix 在定量和定性方面均表现出最佳性能，MD 生成的平均 PSNR、SSIM 和 MSE 指标分别为 23.41 dB、0.8、0.004，MD 生成的平均 PSNR、SSIM 和 MSE 指标分别为 24.05 dB、0.78、0.004 FA一代。新的直方图相似性度量显示了对生成图像和真实图像之间精细细节差异的敏感性，平均 pix2pix MD 和 FA Hist-KL 度量分别为 11.73 和 3.74。对 pix2pix 图像中白质 (WM) 和灰质 (GM) 临床相关区域的详细分析也显示出很强的显着性（p< 0.001) 两种组织类型中真实 FA 值和合成 FA 值之间的相关性 (右= 0.714 通用汽车，右= 0.877 for WM）。讨论/结论我们的结果表明，在真实图像和生成图像之间，pix2pix 的 FA 和 MD 模型比其他模型（包括 WM 束和 CSF 空间）在组织结构和精细细节方面具有显着更好的结构相似性。合成体积的区域分析表明，合成 DWI 图像不仅可以用于补充临床数据集，而且展示了在绕过或纠正数据预处理中的配准方面的潜在实用性。