计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (12): 221-228.doi: 10.11896/jsjkx.230300014

• 计算机图形学&多媒体 • 上一篇    下一篇

基于迭代非对称盲点网络的低剂量CT重建算法

郭广行1,2, 阴桂梅3, 刘晨旭3, 段永红2, 强彦4, 王艳飞4, 王涛4   

  1. 1 太原师范学院地理科学学院 山西 晋中 030619
    2 山西农业大学资源环境学院 山西 太谷 030801
    3 太原师范学院计算机学院 山西 晋中 030619
    4 太原理工大学信息与计算机学院 山西 晋中 030600
  • 收稿日期:2023-03-01 修回日期:2023-04-09 出版日期:2023-12-15 发布日期:2023-12-07
  • 通讯作者: 强彦(614364849@qq.com)
  • 作者简介:(614364849@qq.com)
  • 基金资助:
    国家自然科学基金面上项目(61872261)

Low-dose CT Reconstruction Algorithm Based on Iterative Asymmetric Blind Spot Network

GUO Guangxing1,2, YIN Guimei3, LIU Chenxu3, DUAN Yonghong2, QIANG Yan4, WANG Yanfei4, WANG Tao4   

  1. 1 School of Geography Science,Taiyuan Normal University,Jinzhong,Shanxi 030619,China
    2 School of Resources and Environment,Shanxi Agricultural University,Taigu,Shanxi 030801,China
    3 School of Computer,Taiyuan Normal University,Jinzhong,Shanxi 030619,China
    4 College of Information and Computer,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
  • Received:2023-03-01 Revised:2023-04-09 Online:2023-12-15 Published:2023-12-07
  • About author:GUO Guangxing,born in 1978,Ph.D,associate professor.His main research interests include big data image proces-sing and so on.
    QIANG Yan,born in 1969,Ph.D,is a member of China Computer Federation.His main research interests include intelligent information processing,image recognition and machine learning.
  • Supported by:
    National Natural Science Foundation of China(61872261).

PDF (PC)

2099

摘要： 针对通过机器学习方法进行低剂量CT重建的算法过度依赖成对图例的问题,提出了一种基于迭代非对称盲点网络的低剂量CT重建算法。首先,通过像素混洗下采样盲点网络对低剂量CT进行自监督训练,得到初步重建的CT图像;其次,建立迭代模型,迭代使用前一网络得到的结果图像作为本网络的低剂量输入进行训练,以得到最终网络模型;最后,采用非对称的方式,对像素混洗下采样的步幅进行调整,以尽可能地减少混叠伪影,得到最终的可用模型。理论分析和实验结果表明,与传统低剂量CT重建算法相比,基于迭代非对称盲点网络算法可以极大地减少低剂量CT重建算法对成对图例的依赖,且其生成结果在在图像质量、纹理特征和结构方面优于传统方法。

关键词: 低剂量, 深度学习, 重建, 自监督

Abstract: Aiming at the problem that the method of low-dose CT reconstruction by machine learning method relies too much on pairwise legends,a low-dose CT reconstruction algorithm based on iterative asymmetric blind spot network is proposed.Firstly,low-dose CT is self-supervised by pixel-mixed washing sampling blind spot network,and the preliminarily reconstructed CT images are obtained.Secondly,an iterative model is established,and the result image obtained by the previous network is used as the low-dose input of the network for training to obtain the final network model.Finally,the asymmetric method is used to adjust the stride of the sampling under pixel mixing to minimize aliasing artifacts and obtain the final usable model.Theoretical analysis and experimental results show that compared with the traditional low-dose CT reconstruction algorithm,the iterative asymmetric blind spot network algorithm can greatly reduce the dependence of the low-dose CT reconstruction algorithm on pairwise legends,and can generate images similar to or even better than the traditional method in terms of image quality,texture features and structure.

Key words: Low dose, Deep learning, Reconstruction, Self-supervision

中图分类号: 

  • TP399
[1]YIN X,ZHAO Q,LIU J,et al.Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging[J].IEEE Transactions on Medical Imaging,2019, 38(12):2903-2913.
[2]HOYEON L,JONGHA L,HYEONGSEOK K,et al.Deep-neu-ral-network based sinogram synthesis for sparse-view CT image reconstruction[J].arXiv:1803.00694,2018.
[3]HSIEH J.Adaptive streak artifact reduction in computed tomograph resulting from excessive X-ray photon noise[J].Medical Physics,1998,25(11):2139-2147.
[4]THIBAULT J B,SAUER K D,BOUMAN C A,et al.A three-dimensional statistical approach to improved image quality for multislice helical CT[J].Medical Physics,2007,34(11):4526-4544.
[5]SIDKY E Y,PAN X.Image reconstruction in circular cone-beam computed tomography by constrained,total-variation minimization[J].Physics in Medicine & Biology,2008,53(17):4777.
[6]LI Z,YU L,TRZASKO J D,et al.Adaptive non-local means filtering based on local noise level for CT denoising[C]//Procee-dings Volume 8313,Medical Imaging 2012:Physics of Medical Imaging.2012:83131H.
[7]AHARON M,ELAD M,BRUCKSTEIN A.$rm K$-SVD:An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J].IEEE Transactions on Signal Processing,2006,54:4311-4322.
[8]HU C,YI Z,ZHANG W,et al.Low-dose CT denoising with convolutional neural network[J].arXiv:1610.00321v1,2016.
[9]WU D,KIM K,FAKHRI G,et al.A cascaded convolutional neural network for X-ray low-dose CT image denoising[J].ar-Xiv:1705.04267,2017.
[10]CHEN H,YI Z,KALRA M K,et al.Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network(RED-CNN)[J].IEEE Transactions on Medical Imaging,2017,36(99):2524-2535.
[11]YANG Q,YAN P,ZHANG Y,et al.Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss[J].IEEE transactions on medical imaging,2018,37(6):1348-1357.
[12]WOLTERINK J M,LEINER T,VIERGEVER M A,et al.Ge-nerative Adversarial Networks for Noise Reduction in Low-Dose CT[J].IEEE Transactions on Medical Imaging,2017,36(12):2536-2545.
[13]GUPTA H,JIN K H,NGUYEN H Q,et al.CNN-based projected gradient descent for consistent CT image reconstruction[J].IEEE Transactions on Medical Imaging,2018,37(6):1440-1453.
[14]WU D,KIM K,EL FAKHRI G,et al.Iterative low-dose CT reconstruction with priors trained by artificial neural network[J].IEEE Transactions on Medical Imaging,2017,36(12):2479-2486.
[15]ADLER J,ÖKTEM O.Learned primal-dual reconstruction[J].IEEE Transactions on Medical Imaging,2018,37(6):1322-1332.
[16]JIN K H,MCCANN M T,FROUSTEY E,et al.Deep Convolutional Neural Network for Inverse Problems in Imaging[J].IEEE Transactions on Image Processing,2016(99):4509-4522.
[17]CHEN H,ZHANG Y,KALRA M K,et al.Low-dose CT with a residual encoder-decoder convolutional neural network[J].IEEE Transactions on Medical Imaging,2017,36(12):2524-2535.
[18]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation[J].arXiv:1505.04597,2015.
[19]YANG Q,YAN P,ZHANG Y,et al.Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss[J].IEEE Transactions on Medical Imaging,2018,37(6):1348-1357.
[20]WANG Y,CHAO L,SHAN W,et al.Improving the Quality of Sparse-view Cone-Beam Computed Tomography via Reconstruction-Friendly Interpolation Network[C]//Computer Vision－ACCV.2022:86-100.
[21]YE D H,BUZZARD G T,RUBY M, et al.Deep Back Projection For Sparse-View Ct Reconstruction[C]//2018 IEEE Global Conference on Signal and Information Processing(GlobalSIP).Anaheim,CA,USA,2018.
[22]KRULL A,BUCHHOLZ T O,JUG F.Noise2Void-Learning Denoising From Single Noisy Images[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2019.
[23]BATSON J,ROYER L.Noise2Self:Blind Denoising by Self-Supervision[J].arXiv:1901.11365,2019.
[24]KRULL A,VIČAR T,PRAKASH M,et al.Probabilisticnoise2void:Unsupervised content-aware denoising[J].Frontiers in Computer Science,2020,2:5.
[25]XIE Y,WANG Z,JI S.Noise2Same:Optimizing A Self-Supervised Bound for Image Denoising[J].arXiv:2010.11971,2020.
[26]ZHOU Y,JIAO J,HUANG H,et al.When AWGN-Based Denoiser Meets Real Noises[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.2020:13074-13081.
[27]SHI W,CABALLERO J,HUSZÁR F,et al.Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2016.
[28]LEE W,SON S,LEE K M.Ap-bsn:Self-supervised denoising for real-world images via asymmetric pd and blind-spot network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:17725-17734.
[29]WU W,HU D,NIU C,et al.DRONE:Dual-domain residual-based optimization network for sparse-view CT reconstruction[J].IEEE Transactions on Medical Imaging,2021,40(11):3002-3014.
[30]HORÉ A,ZIOU D.Image quality metrics:PSNR vs.SSIM[C]//20th International Conference on Pattern Recognition(ICPR 2010).IEEE Computer Society,2010.
[31]BOVIK H.Image information and visual quality[J].IEEETransactions on Image Processing a Publication of the IEEE Signal Processing Society,2006,15(2):430.
[32]WANG Z,BOVIK A C,SHEIKH H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[33]YOU C,YANG L,ZHANG Y,et al.Low-Dose CT via Deep CNN with Skip Connection and Network in Network[J].arXiv:1811.10564,2018.
[34]DABOV K,FOI A,KATKOVNIK V,et al.Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering[C]//IEEE Transactions on Image Processing.IEEE,2007:2080-2095.
[35]LUTHRA A,SULAKHE H,MITTAL T,et al.Eformer:Edge enhancement based transformer for medical image denoising[J].arXiv:2109.08044,2021.
[36]ZHANG Z,HAN H,SHANGGUAN X,et al.Artifact and Detail Attention Generative Adversarial Networks for Low-Dose CT Denoising[J].IEEE Transactions on Medical Imaging,2021,40(12):3901-3918.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发