Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (10): 2964-2969.DOI: 10.11772/j.issn.1001-9081.2020121985

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

High-precision sparse reconstruction of CT images based on multiply residual UNet

ZHANG Yanjiao, QIAO Zhiwei   

  1. School of Computer and Information Technology, Shanxi University, Taiyuan Shanxi 030006, China
  • Received:2020-12-16 Revised:2021-03-31 Online:2021-10-10 Published:2021-07-14
  • Supported by:
    This work is partially supported by the Surface Program of National Natural Science Foundation of China (62071281), the Shanxi Provincial Key Research and Development Program (201803D421012), the Funded Scientific Research Project for Returned Overseas Students of Shanxi Province (2020-008), the Selected Science and Technology Activities Project of Overseas Students from Shanxi Province (RSC1622).

基于多残差UNet的CT图像高精度稀疏重建

张艳娇, 乔志伟   

  1. 山西大学 计算机与信息技术学院, 太原030006
  • 通讯作者: 乔志伟
  • 作者简介:张艳娇(1995-),女,山西长治人,硕士研究生,主要研究方向:医学图像重建、深度学习、图像处理;乔志伟(1977-),男,山西临汾人,教授,博士,主要研究方向:医学图像重建、信号处理、高性能计算。
  • 基金资助:
    国家自然科学基金面上项目(62071281);山西省重点研发计划项目(201803D421012);山西省回国留学人员科研资助项目(2020?008);山西省留学人员科技活动择优资助项目(RSC1622)。

Abstract: Aiming at the problem of producing streak artifacts during sparse analytic reconstruction of Computed Tomography (CT), in order to better suppress strip artifacts, a Multiply residual UNet (Mr-UNet) network architecture was proposed based on the classical UNet network architecture. Firstly, the sparse images with streak artifacts were sparsely reconstructed by the traditional Filtered Back Projection (FBP) analytic reconstruction algorithm. Then, the reconstructed images were used as the input of the network structure, and the corresponding high-precision images were trained as the labels of the network, so that the network had a good performance of suppressing streak artifacts. Finally, the original four-layer down-sampling of the classical residual UNet was deepened to five layers, and the residual learning mechanism was introduced into the proposed model, so that each convolution unit was constructed to residual structure to improve the training performance of the network. In the experiments, 2 000 pairs of images containing images with streak artifacts and the corresponding high-precision images with the size of 256×256 were used as the dataset, among which, 1 900 pairs were used as the training set, 50 pairs were used as the verification set, and the rest were used as the test set to train the network, and verify and evaluate the network performance. The experimental results show that, compared with the traditional Total Variation (TV) minimization algorithm and the classical deep learning method of UNet, the proposed model can reduce the Root Mean Square Error (RMSE) by about 0.002 5 on average and improve the Structural SIMilarity (SSIM) by about 0.003 on average, and can retain the texture and detail information of the image better.

Key words: sparse reconstruction, streak artifact, Convolutional Neural Network (CNN), UNet, Multiply residual UNet

摘要: 为了解决计算机断层成像(CT)稀疏解析重建过程中产生条状伪影的问题,在经典的UNet网络结构的基础上,提出了多残差UNet (Mr-UNet)网络结构,以更好地压制条状伪影。首先,用传统滤波反投影(FBP)解析重建算法稀疏重建出含条状伪影的稀疏图像;然后,将该类图像作为网络结构的输入,且将相对应的高精度图像作为网络的标签进行训练,使得该网络具有很好的压制条状伪影的性能;最后,将经典UNet原先的四层下采样加深到五层,并在模型中引入残差学习机制将每个卷积单元构建为残差结构,从而提升网络的训练性能。实验中采用了2 000对大小为256×256的含条状伪影图像和对应的高精度图像作为数据集,其中,1 900对作为训练集,50对作为验证集,其余的作为测试集来训练网络,并验证、评估网络性能。实验结果表明,与传统的总变差(TV)最小化算法及经典的UNet深度学习方法的比较表明,所提模型重建图像的均方根误差(RMSE)平均降低了约0.002 5,结构相似度(SSIM)平均提高了约0.003,且能更好地保留图像纹理和细节信息。

关键词: 稀疏重建, 条状伪影, 卷积神经网络, UNet, 多残差UNet

CLC Number: