当前位置: X-MOL 学术SIAM J. Imaging Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Neural Networks for Inverse Problems with Pseudodifferential Operators: An Application to Limited-Angle Tomography
SIAM Journal on Imaging Sciences ( IF 2.1 ) Pub Date : 2021-05-03 , DOI: 10.1137/20m1343075
Tatiana A. Bubba , Mathilde Galinier , Matti Lassas , Marco Prato , Luca Ratti , Samuli Siltanen

SIAM Journal on Imaging Sciences, Volume 14, Issue 2, Page 470-505, January 2021.
We propose a novel convolutional neural network (CNN), called $\Psi$DONet, designed for learning pseudodifferential operators ($\Psi$DOs) in the context of linear inverse problems. Our starting point is the iterative soft thresholding algorithm (ISTA), a well-known algorithm to solve sparsity-promoting minimization problems. We show that, under rather general assumptions on the forward operator, the unfolded iterations of ISTA can be interpreted as the successive layers of a CNN, which in turn provides fairly general network architectures that, for a specific choice of the parameters involved, allow us to reproduce ISTA, or a perturbation of ISTA for which we can bound the coefficients of the filters. Our case study is the limited-angle X-ray transform and its application to limited-angle computed tomography (LA-CT). In particular, we prove that, in the case of LA-CT, the operations of upscaling, downscaling, and convolution, which characterize our $\Psi$DONet and most deep learning schemes, can be exactly determined by combining the convolutional nature of the limited-angle X-ray transform and basic properties defining an orthogonal wavelet system. We test two different implementations of $\Psi$DONet on simulated data from limited-angle geometry, generated from the ellipse data set. Both implementations provide equally good and noteworthy preliminary results, showing the potential of the approach we propose and paving the way to applying the same idea to other convolutional operators which are $\Psi$DOs or Fourier integral operators.


中文翻译:

伪微分算子反问题的深层神经网络:在有限角层析成像中的应用

SIAM影像科学杂志,第14卷,第2期,第470-505页,2021年1月。
我们提出了一种新颖的卷积神经网络(CNN),称为$ \ Psi $ DONet,其设计用于在线性逆问题的背景下学习伪微分算子($ \ Psi $ DOs)。我们的出发点是迭代软阈值算法(ISTA),这是解决稀疏性最小化问题的著名算法。我们显示,在前向运算符的相当一般的假设下,ISTA的展开迭代可以解释为CNN的连续层,这反过来又提供了相当通用的网络体系结构,对于所涉及的参数的特定选择,它允许我们重现ISTA或ISTA的摄动,我们可以为其绑定滤波器的系数。我们的案例研究是有限角度X射线变换及其在有限角度计算机断层扫描(LA-CT)中的应用。特别是,我们证明,对于LA-CT,可以通过组合有限角度X射线变换的卷积性质来精确确定代表我们的\\ Psi $ DONet和大多数深度学习方案的放大,缩小和卷积运算。和定义正交小波系统的基本属性。我们对椭圆数据集生成的有限角度几何数据的模拟数据测试$ \ Psi $ DONet的两种不同实现。两种实现方式都提供了同样良好且引人注目的初步结果,显示了我们提出的方法的潜力,并为将同一思想应用于$ \ Psi $ DO或Fourier积分运算符的其他卷积运算符铺平了道路。通过结合有限角度X射线变换的卷积性质和定义正交小波系统的基本性质,可以精确确定。我们对椭圆数据集生成的有限角度几何数据的模拟数据测试$ \ Psi $ DONet的两种不同实现。两种实现方式都提供了同样良好且引人注目的初步结果,显示了我们提出的方法的潜力,并为将同一思想应用于$ \ Psi $ DO或Fourier积分运算符的其他卷积运算符铺平了道路。通过结合有限角度X射线变换的卷积性质和定义正交小波系统的基本性质,可以精确确定。我们对椭圆数据集生成的有限角度几何数据的模拟数据测试$ \ Psi $ DONet的两种不同实现。两种实现方式都提供了同样良好且引人注目的初步结果,显示了我们提出的方法的潜力,并为将同一思想应用于$ \ Psi $ DO或Fourier积分运算符的其他卷积运算符铺平了道路。
更新日期:2021-05-04
down
wechat
bug