UNASSIGNED:本文提出了一种基于深度学习(DL)的方法,称为TextureWGAN。它旨在保留图像纹理,同时保持计算机断层扫描(CT)反问题的高像素保真度。后处理算法的过度平滑图像已经是医学成像行业中众所周知的问题。因此,我们的方法试图在不影响像素保真度的情况下解决过度平滑问题。
未授权:TextureWGAN从WassersteinGAN(WGAN)延伸而来。WGAN可以创建看起来像真实图像的图像。WGAN的这一方面有助于保持图像纹理。然而,来自WGAN的输出图像与对应的地面实况图像不相关。为了解决这个问题,我们将多任务正则化(MTR)引入WGAN框架,使生成的图像与相应的地面实况图像高度相关,以便TextureWGAN可以实现高水平的像素保真度。MTR能够使用多个目标函数。在这项研究中,我们采用均方误差(MSE)损失来保持像素保真度。我们还使用感知损失来改善结果图像的外观和感觉。此外,MTR中的正则化参数与生成器网络权重一起进行训练,以最大化TextureWGAN生成器的性能。
UNASSIGNED:除了超分辨率和图像去噪应用外,还在CT图像重建应用中评估了所提出的方法。我们进行了广泛的定性和定量评估。我们使用PSNR和SSIM进行像素保真度分析,并对图像纹理进行一阶和二阶统计纹理分析。结果表明,与传统CNN和非局部均值滤波器(NLM)等其他众所周知的方法相比,TextureWGAN在保持图像纹理方面更有效。此外,我们证明,与CNN和NLM相比,TextureWGAN可以实现具有竞争力的像素保真度性能。具有MSE损失的CNN可以达到高水平的像素保真度,但它经常损害图像纹理。
UNASSIGNED:TextureWGAN可以在保持像素保真度的同时保留图像纹理。MTR不仅有助于稳定TextureWGAN的发电机训练,而且还可以最大程度地提高发电机的性能。
UNASSIGNED: This paper presents a deep learning (DL) based method called TextureWGAN. It is designed to preserve image texture while maintaining high pixel fidelity for computed tomography (CT) inverse problems. Over-smoothed images by postprocessing algorithms have been a well-known problem in the medical imaging industry. Therefore, our method tries to solve the over-smoothing problem without compromising pixel fidelity.
UNASSIGNED: The TextureWGAN extends from Wasserstein GAN (WGAN). The WGAN can create an image that looks like a genuine image. This aspect of the WGAN helps preserve image texture. However, an output image from the WGAN is not correlated to the corresponding ground truth image. To solve this problem, we introduce the multitask regularizer (MTR) to the WGAN framework to make a generated image highly correlated to the corresponding ground truth image so that the TextureWGAN can achieve high-level pixel fidelity. The MTR is capable of using multiple objective functions. In this research, we adopt a mean squared error (MSE) loss to maintain pixel fidelity. We also use a perception loss to improve the look and feel of result images. Furthermore, the regularization parameters in the MTR are trained along with generator network weights to maximize the performance of the TextureWGAN generator.
UNASSIGNED: The proposed method was evaluated in CT image reconstruction applications in addition to super-resolution and image-denoising applications. We conducted extensive qualitative and quantitative evaluations. We used PSNR and SSIM for pixel fidelity analysis and the first-order and the second-order statistical texture analysis for image texture. The results show that the TextureWGAN is more effective in preserving image texture compared with other well-known methods such as the conventional CNN and nonlocal mean filter (NLM). In addition, we demonstrate that TextureWGAN can achieve competitive pixel fidelity performance compared with CNN and NLM. The CNN with MSE loss can attain high-level pixel fidelity, but it often damages image texture.
UNASSIGNED: TextureWGAN can preserve image texture while maintaining pixel fidelity. The MTR is not only helpful to stabilize the TextureWGAN\'s generator training but also maximizes the generator performance.