Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction.
Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction.
复制标题
DOI：
10.1109/tci.2021.3049648
复制
发表时间：
2021
影响因子：
5.4
通讯作者：
Anastasio, Mark A.
中科院分区：
文献类型：
--
作者：
Kelkar, Varun A.;Bhadra, Sayantan;Anastasio, Mark A.
关键词：
仍然存在对于能够从欠采样测量产生诊断上有用的图像的图像重建方法的开发的重要需求。例如，在磁共振成像（MRI）中，这样的方法可以促进数据采集时间的减少。基于深度学习的方法具有学习对象先验或约束的潜力，可以减轻数据不完整性对图像重建的影响。一个新兴的研究领域涉及在生成深度神经网络的潜在空间中制定基于优化的重建方法。然而，当采用生成对抗网络（GAN）时，如果所寻求的解决方案不在GAN的范围内，则此类方法可能导致图像重建错误。为了规避这个问题，在这项工作中，提出了一个框架，从不完整的测量重建图像，制定在潜在空间的可逆神经网络为基础的生成模型。引入了一种新的正则化策略，该策略利用了某些可逆神经网络的多尺度结构，这可以导致在传统度量方面优于经典方法的重建性能。所提出的方法进行了研究，重建图像欠采样的MRI数据。所示的方法，以实现可比的性能，一个国家的最先进的生成模型为基础的重建方法，同时受益于确定性的重建过程和更容易控制正则化参数。
There remains an important need for the development of image reconstruction methods that can produce diagnostically useful images from undersampled measurements. In magnetic resonance imaging (MRI), for example, such methods can facilitate reductions in data-acquisition times. Deep learning-based methods hold potential for learning object priors or constraints that can serve to mitigate the effects of data-incompleteness on image reconstruction. One line of emerging research involves formulating an optimization-based reconstruction method in the latent space of a generative deep neural network. However, when generative adversarial networks (GANs) are employed, such methods can result in image reconstruction errors if the sought-after solution does not reside within the range of the GAN. To circumvent this problem, in this work, a framework for reconstructing images from incomplete measurements is proposed that is formulated in the latent space of invertible neural network-based generative models. A novel regularization strategy is introduced that takes advantage of the multiscale architecture of certain invertible neural networks, which can result in improved reconstruction performance over classical methods in terms of traditional metrics. The proposed method is investigated for reconstructing images from undersampled MRI data. The method is shown to achieve comparable performance to a state-of-the-art generative model-based reconstruction method while benefiting from a deterministic reconstruction procedure and easier control over regularization parameters.
登录
查看更多内容
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
影响因子：
10.6
作者：
Jin, Kyong Hwan;McCann, Michael T.;Unser, Michael
通讯作者：
Unser, Michael
影响因子：
3
作者：
Donoho, DL
通讯作者：
Donoho, DL
影响因子：
2.5
作者：
Candès, EJ;Romberg, J;Tao, T
通讯作者：
Tao, T
影响因子：
1.3
作者：
Clarkson, James A.;Adams, C. Raymond
通讯作者：
Adams, C. Raymond