MR image reconstruction using iterative up and downsampling network

被引:0
|
作者
Aghabiglou, Amir [1 ]
Ekinci, Dursun Ali [2 ]
Eksioglu, Ender M. [3 ]
Toreyin, Behcet Ugur [2 ]
机构
[1] Istanbul Tech Univ, Grad Sch, TR-34469 Istanbul, Turkiye
[2] Istanbul Tech Univ, Informat Inst, TR-34469 Istanbul, Turkiye
[3] Istanbul Tech Univ, Elect & Commun Engn Dept, TR-34469 Istanbul, Turkiye
关键词
Magnetic resonance imaging; Image reconstruction; Deep learning; Super-resolution; Iterative up and downsampling; SUPERRESOLUTION; ALGORITHM;
D O I
10.1016/j.eswa.2023.121590
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Magnetic resonance imaging (MRI) is one of the most significant modalities in medical imaging. It suffers from rather lengthy acquisition times, which lead to prolonged patient restriction, patient discomfort, and imaging artifacts. Hence, satisfactory MRI reconstruction from undersampled data sequences constitutes an important research problem. With the advances in deep learning (DL), a plethora of new models have been proposed to solve the MRI reconstruction problem using deep networks. On the other hand, single image super-resolution (SR) is another well-studied field that benefited from the success of DL, and it has applications in various imaging modalities. SR is the process of recovering a high-resolution image from a low-resolution image. SR models work on low-resolution images to recover missing details. MR image reconstruction on the other hand is a battle to eliminate the aliasing artifacts which originate from data downsampling. The motivation for the proposed work is based on the premise that SR approaches can possibly get adapted to MR image reconstruction. Hence in this study, inspired by the great success of deep SR networks, we customize an architecture introduced in SR setting to MRI reconstruction. This novel approach uses the iterative up and downsampling framework labeled as Iterative Up and Down Network (IUDN) for MRI reconstruction. We design two variants of the proposed network with different number of scale factors. We present extensive simulations for the proposed architecture using multiple k-space undersampling ratios. The simulation results indicate cutting edge MRI reconstruction performance for the proposed models. The networks were trained on fastMRI dataset and tested on both fastMRI and IXI datasets to show the robustness of the method. The proposed models achieved improved results in terms of PSNR and visual quality of the reconstructed image when compared to some recent state-of-the-art solutions for MRI reconstruction.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Statistical Iterative CBCT Reconstruction Using Convolutional Neural Network
    Gong, Z.
    Shi, Q.
    Liu, L.
    Wang, J.
    Tan, S.
    MEDICAL PHYSICS, 2017, 44 (06)
  • [32] Magnetic Resonance(MR) Image Reconstruction using Compressive Sensing
    Waseem, Mona
    Anwar, Syed
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2015, 15 (01): : 66 - 70
  • [33] Enhancing MR Image Reconstruction Using Block Dictionary Learning
    Ikram, Shahid
    Zubair, Syed
    Shah, Jawad Ali
    Qureshi, Ijaz Mansoor
    Wahid, Abdul
    Khan, Adnan Umar
    IEEE ACCESS, 2019, 7 : 158434 - 158444
  • [34] Parallel MR Image Reconstruction Using Augmented Lagrangian Methods
    Ramani, Sathish
    Fessler, Jeffrey A.
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2011, 30 (03) : 694 - 706
  • [35] PARTIALLY PARALLEL MR IMAGE RECONSTRUCTION USING SENSITIVITY ENCODING
    Yashtini, Maryam
    Hager, William W.
    Chen, Yunmei
    Ye, Xiaojing
    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, : 2077 - 2080
  • [36] Iterative Image Reconstruction for Limited-Angle CT Using Optimized Initial Image
    Guo, Jingyu
    Qi, Hongliang
    Xu, Yuan
    Chen, Zijia
    Li, Shulong
    Zhou, Linghong
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2016, 2016
  • [37] MR spectroscopic image reconstruction using structural information from anatomical MR images
    Denney, TS
    Reeves, SJ
    COMPUTATIONAL IMAGING, 2003, 5016 : 131 - 140
  • [38] Convergence of iterative algorithms for image reconstruction
    Jiang, M
    Wang, G
    2002 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, PROCEEDINGS, 2002, : 685 - 688
  • [39] An iterative image reconstruction algorithm for SPECT
    赵经武
    苏为宁
    Nuclear Science and Techniques, 2014, 25 (03) : 29 - 33
  • [40] A Myth of Iterative Image Reconstruction Algorithms
    Zeng, Gengsheng L.
    2017 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE (NSS/MIC), 2017,