Learned Half-Quadratic Splitting Network for MR Image Reconstruction

Bingyu Xin, Timothy Phan, Leon Axel, Dimitris Metaxas
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1403-1412, 2022.

Abstract

Magnetic Resonance (MR) image reconstruction from highly undersampled k-space data is critical in accelerated MR imaging (MRI) techniques. In recent years, deep learning-based methods have shown great potential in this task. This paper proposes a learned half-quadratic splitting algorithm for MR image reconstruction and implements the algorithm in an unrolled deep learning network architecture. We compare the performance of our proposed method on a public cardiac MR dataset against DC-CNN, ISTANet+ and LPDNet, and our method outperforms other methods in both quantitative results and qualitative results. Finally, we enlarge our model to achieve superior reconstruction quality, and the improvement is 1.00 dB and 1.76 dB over LPDNet in peak signal-to-noise ratio on 5× and 10× acceleration, respectively. Code for our method is publicly available at \url{https://github.com/hellopipu/HQS-Net.}

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-xin22a, title = {Learned Half-Quadratic Splitting Network for MR Image Reconstruction}, author = {Xin, Bingyu and Phan, Timothy and Axel, Leon and Metaxas, Dimitris}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1403--1412}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/xin22a/xin22a.pdf}, url = {https://proceedings.mlr.press/v172/xin22a.html}, abstract = {Magnetic Resonance (MR) image reconstruction from highly undersampled $k$-space data is critical in accelerated MR imaging (MRI) techniques. In recent years, deep learning-based methods have shown great potential in this task. This paper proposes a learned half-quadratic splitting algorithm for MR image reconstruction and implements the algorithm in an unrolled deep learning network architecture. We compare the performance of our proposed method on a public cardiac MR dataset against DC-CNN, ISTANet$^+$ and LPDNet, and our method outperforms other methods in both quantitative results and qualitative results. Finally, we enlarge our model to achieve superior reconstruction quality, and the improvement is $1.00$ dB and $1.76$ dB over LPDNet in peak signal-to-noise ratio on $5\times$ and $10\times$ acceleration, respectively. Code for our method is publicly available at \url{https://github.com/hellopipu/HQS-Net.}} }
Endnote
%0 Conference Paper %T Learned Half-Quadratic Splitting Network for MR Image Reconstruction %A Bingyu Xin %A Timothy Phan %A Leon Axel %A Dimitris Metaxas %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-xin22a %I PMLR %P 1403--1412 %U https://proceedings.mlr.press/v172/xin22a.html %V 172 %X Magnetic Resonance (MR) image reconstruction from highly undersampled $k$-space data is critical in accelerated MR imaging (MRI) techniques. In recent years, deep learning-based methods have shown great potential in this task. This paper proposes a learned half-quadratic splitting algorithm for MR image reconstruction and implements the algorithm in an unrolled deep learning network architecture. We compare the performance of our proposed method on a public cardiac MR dataset against DC-CNN, ISTANet$^+$ and LPDNet, and our method outperforms other methods in both quantitative results and qualitative results. Finally, we enlarge our model to achieve superior reconstruction quality, and the improvement is $1.00$ dB and $1.76$ dB over LPDNet in peak signal-to-noise ratio on $5\times$ and $10\times$ acceleration, respectively. Code for our method is publicly available at \url{https://github.com/hellopipu/HQS-Net.}
APA
Xin, B., Phan, T., Axel, L. & Metaxas, D.. (2022). Learned Half-Quadratic Splitting Network for MR Image Reconstruction. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1403-1412 Available from https://proceedings.mlr.press/v172/xin22a.html.

Related Material