MR image reconstruction using iterative up and downsampling network

Amir Aghabiglou, Dursun Ali Ekinci, Ender M. Eksioglu*, Behcet Ugur Toreyin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Article number121590
JournalExpert Systems with Applications
Publication statusPublished - 1 Mar 2024

Bibliographical note

Publisher Copyright:
© 2023 Elsevier Ltd


This work was supported by TUBITAK (The Scientific and Technological Research Council of Turkey) under project no. 119E248 .

FundersFunder number
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu119E248


    • Deep learning
    • Image reconstruction
    • Iterative up and downsampling
    • Magnetic resonance imaging
    • Super-resolution


    Dive into the research topics of 'MR image reconstruction using iterative up and downsampling network'. Together they form a unique fingerprint.

    Cite this