Searcharxiv⌕ Search

arXiv subjects

Guoen Hu

Publications and source records attributed to Guoen Hu.

22 records · Page 2Linked to original sources

Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network

Limited angle problem is a challenging issue in x-ray computed tomography (CT) field. Iterative reconstruction methods that utilize the additional prior can suppress artifacts and improve image quality, but unfortunately require increased computation time. An interesting way is to restrain the artifacts in the images reconstructed from the practical filtered back projection (FBP) method. Frikel and Quinto have proved that the streak artifacts in FBP results could be characterized. It indicates that the artifacts created by FBP method have specific and similar characteristics in a stationary limited-angle scanning configuration. Based on this understanding, this work aims at developing a method to extract and suppress specific artifacts of FBP reconstructions for limited-angle tomography. A data-driven learning-based method is proposed based on a deep convolutional neural network. An end-to-end mapping between the FBP and artifact-free images is learned and the implicit features involving artifacts will be extracted and suppressed via nonlinear mapping. The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography. The presented strategy provides a simple and efficient approach for improving image quality of the reconstruction results from limited projection data.

physics.med-ph↗

Weighted vector-valued bounds for a class of multilinear singular integral operators

In this paper, we investigate the weighted vector-valued bounds for a class of multilinear singular integral operators, and its commutators, from $L^{p_1}(l^{q_1};\,\mathbb{R}^n,w_1)\times\dots\times L^{p_m}(l^{q_m};\,\mathbb{R}^n,w_m)$ to $L^{p}(l^q;\,\mathbb{R}^n,ν_{\vec{w}})$, with $p_1,\dots,p_m\in (1,\,\infty)$ and $1/p=1/p_1+\dots+1/p_m$ and $\vec{w}$ is a multiple $A_{\vec{P}}$ weights. Our argument also leads to the weighted weak type endpoint estimates for the commutators.

math.CA↗

Weighted $L^p$ bounds for the Marcinkiewicz integral

Let $Ω$ be homogeneous of degree zero, have mean value zero and integrable on the unit sphere, and $\mathcal{M}_Ω$ be the higher-dimensional Marcinkiewicz integral associated with $Ω$. In this paper, the authors proved that if $Ω\in L^q(S^{n-1})$ for some $q\in (1,\,\infty]$, then for $p\in (q',\,\infty)$ and $w\in A_{p}(\mathbb{R}^n)$, the bound of $\mathcal{M}_Ω$ on $L^p(\mathbb{R}^n,\,w)$ is less than $C[w]_{A_{p/q'}}^{2\max\{1,\,\frac{1}{p-q'}\}}$.

math.CA↗

Weighted norm inequalities for multilinear singular integral operators and applications

In this paper, weighted norm inequalities with $A_p$ weights are established for the multilinear singular integral operators whose kernels satisfy $L^{r'}$-Hörmander regularity condition. As applications, we recover a weighted estimate for the multilinear Fourier multiplier obtained by Fujita and Tomita, and obtain several new weighted estimates for the multilinear Fourier multiplier as well.

math.FA↗