基于深度学习的脑磁共振成像降噪：在体模和健康志愿者上的测试。
Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers.
机构信息
Department of Diagnostic Radiology, Faculty of Life Sciences, Kumamoto University.
MRI Systems Division, Canon Medical Systems Corporation.
出版信息
Magn Reson Med Sci. 2020 Aug 3;19(3):195-206. doi: 10.2463/mrms.mp.2019-0018. Epub 2019 Sep 4.
PURPOSE
To test whether our proposed denoising approach with deep learning-based reconstruction (dDLR) can effectively denoise brain MR images.
METHODS
In an initial experimental study, we obtained brain images from five volunteers and added different artificial noise levels. Denoising was applied to the modified images using a denoising convolutional neural network (DnCNN), a shrinkage convolutional neural network (SCNN), and dDLR. Using these brain MR images, we compared the structural similarity (SSIM) index and peak signal-to-noise ratio (PSNR) between the three denoising methods. Two neuroradiologists assessed the image quality of the three types of images. In the clinical study, we evaluated the denoising effect of dDLR in brain images with different levels of actual noise such as thermal noise. Specifically, we obtained 2D-T-weighted image, 2D-fluid-attenuated inversion recovery (FLAIR) and 3D-magnetization-prepared rapid acquisition with gradient echo (MPRAGE) from 15 healthy volunteers at two different settings for the number of image acquisitions (NAQ): NAQ2 and NAQ5. We reconstructed dDLR-processed NAQ2 from NAQ2, then compared with SSIM and PSNR. Two neuroradiologists separately assessed the image quality of NAQ5, NAQ2 and dDLR-NAQ2. Statistical analysis was performed in the experimental and clinical study. In the clinical study, the inter-observer agreement was also assessed.
RESULTS
In the experimental study, PSNR and SSIM for dDLR were statistically higher than those of DnCNN and SCNN (P < 0.001). The image quality of dDLR was also superior to DnCNN and SCNN. In the clinical study, dDLR-NAQ2 was significantly better than NAQ2 images for SSIM and PSNR in all three sequences (P < 0.05), except for PSNR in FLAIR. For all qualitative items, dDLR-NAQ2 had equivalent or better image quality than NAQ5, and superior quality to that of NAQ2 (P < 0.05), for all criteria except artifact. The inter-observer agreement ranged from substantial to near perfect.
CONCLUSION
dDLR reduces image noise while preserving image quality on brain MR images.
目的
测试我们提出的基于深度学习重建的去噪方法（dDLR）是否能有效去除脑磁共振图像中的噪声。
方法
在初步的实验研究中，我们从五名志愿者中获得脑图像，并添加不同的人为噪声水平。使用去噪卷积神经网络（DnCNN）、收缩卷积神经网络（SCNN）和 dDLR 对修改后的图像进行去噪。使用这些脑磁共振图像，我们比较了三种去噪方法的结构相似性（SSIM）指数和峰值信噪比（PSNR）。两位神经放射科医生评估了三种类型图像的图像质量。在临床研究中，我们评估了 dDLR 在具有不同实际噪声水平（如热噪声）的脑图像中的去噪效果。具体来说，我们从 15 名健康志愿者中获得了二维 T 加权图像、二维液体衰减反转恢复（FLAIR）和三维磁化准备快速获取梯度回波（MPRAGE），并在两种不同的采集次数（NAQ）设置下获得：NAQ2 和 NAQ5。我们从 NAQ2 重建了经过 dDLR 处理的 NAQ2，并比较了 SSIM 和 PSNR。两位神经放射科医生分别评估了 NAQ5、NAQ2 和 dDLR-NAQ2 的图像质量。在实验和临床研究中都进行了统计学分析。在临床研究中，还评估了观察者间的一致性。
结果
在实验研究中，dDLR 的 PSNR 和 SSIM 均明显高于 DnCNN 和 SCNN（P<0.001）。dDLR 的图像质量也优于 DnCNN 和 SCNN。在临床研究中，对于所有三个序列（P<0.05），除了 FLAIR 的 PSNR 外，dDLR-NAQ2 的 SSIM 和 PSNR 均明显优于 NAQ2 图像。对于所有定性项目，dDLR-NAQ2 的图像质量与 NAQ5 相当或更好，与 NAQ2 相比质量更好（P<0.05），除了伪影外，所有标准都是如此。观察者间的一致性从高度一致到几乎完全一致。
结论
dDLR 可降低脑磁共振图像的图像噪声，同时保持图像质量。
Zotero 插件