Abstract
The key to dynamic or multi-contrast magnetic resonance imaging (MRI) reconstruction lies in exploring inter-frame or inter-contrast information. Currently, the unrolled model, an approach combining iterative MRI reconstruction steps with learnable neural network layers, stands as the best-performing method for MRI reconstruction. However, there are two main limitations to overcome: firstly, the unrolled model structure and GPU memory constraints restrict the capacity of each denoising block in the network, impeding the effective extraction of detailed features for reconstruction; secondly, the existing model lacks the flexibility to adapt to variations in the input, such as different contrasts, resolutions or views, necessitating the training of separate models for each input type, which is inefficient and may lead to insufficient reconstruction. In this paper, we propose a two-stage MRI reconstruction pipeline to address these limitations. The first stage involves filling the missing k-space data, which we approach as a physics-based reconstruction problem. We first propose a simple yet efficient baseline model, which utilizes adjacent frames/contrasts and channel attention to capture the inherent inter-frame/-contrast correlation. Then, we extend the baseline model to a prompt-based learning approach, PromptMR, for all-in-one MRI reconstruction from different views, contrasts, adjacent types, and acceleration factors. The second stage is to refine the reconstruction from the first stage, which we treat as a general video restoration problem to further fuse features from neighboring frames/contrasts in the image domain. Extensive experiments show that our proposed method significantly outperforms previous state-of-the-art accelerated MRI reconstruction methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)
Fabian, Z., Tinaz, B., Soltanolkotabi, M.: Humus-net: hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction. Adv. Neural. Inf. Process. Syst. 35, 25306–25319 (2022)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Huang, Q., Yang, D., Wu, P., Qu, H., Yi, J., Metaxas, D.: MRI reconstruction via cascaded channel-wise attention network. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 1622–1626. IEEE (2019)
Jia, M., et al.: Visual prompt tuning. In: European Conference on Computer Vision. pp. 709–727. Springer (2022). https://doi.org/10.1007/978-3-031-19827-4_41
Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113–19122 (2023)
Li, B., Liu, X., Hu, P., Wu, Z., Lv, J., Peng, X.: All-in-one image restoration for unknown corruption. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17452–17462 (2022)
Li, D., et al.: A simple baseline for video restoration with grouped spatial-temporal shift. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9822–9832 (2023)
Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R.: Swinir: image restoration using swin transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1833–1844 (2021)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11) (2008)
Potlapalli, V., Zamir, S.W., Khan, S., Khan, F.S.: Promptir: prompting for all-in-one blind image restoration. arXiv preprint arXiv:2306.13090 (2023)
Rajiah, P.S., François, C.J., Leiner, T.: Cardiac MRI: state of the art. Radiology 307(3), 223008 (2023)
Roemer, P.B., Edelstein, W.A., Hayes, C.E., Souza, S.P., Mueller, O.M.: The NMR phased array. Magn. Reson. Med. 16(2), 192–225 (1990)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Sriram, A., et al.: End-to-end variational networks for accelerated MRI reconstruction. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 64–73. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59713-9_7
Wang, C., et al.: Cmrxrecon: an open cardiac MRI dataset for the competition of accelerated image reconstruction. arXiv preprint arXiv:2309.10836 (2023)
Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Restormer: eDfficient transformer for high-resolution image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728–5739 (2022)
Zbontar, J., et al.: fastmri: An open dataset and benchmarks for accelerated MRI. arXiv preprint arXiv:1811.08839 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix
A Details of the Baseline Model
1.1 A.1 CAUnet
(See Fig. 6).
1.2 A.2 Unrolled Model Architecture
(See Fig. 7).
B Experiments on FastMRI Multi-Coil Knee Dataset
Benchmark on FastMRI Multi-Coil Knee Dataset. To assess the performance of our proposed method across different anatomies, we benchmarked it on another large-scale MRI reconstruction dataset, the fastMRI multi-coil knee dataset [19]. Since the online evaluation platform for the fastMRI test set is unavailableFootnote 1, we divided the original 199 validation cases into 99 for validation and 100 for testing. The results of other methods are reported using their officially pretrained models. As presented in Table 4, our models outperform all previous state-of-the-art methods, without significantly increasing the number of network parameters compared to E2E-Varnet.
Effectiveness of Two-Stage Pipeline. We employed ShiftNet to refine the images reconstructed by the pretrained E2E-Varnet on the fastMRI multi-coil knee test dataset with \(\times 8\) undersampling. Table 5 shows that the second-stage refinement substantially improves the reconstruction quality, which implies that the multi-slice information in the fastMRI dataset might not be comprehensively utilized by the single-stage unrolled model.
C Additional Qualitative Results on CMRxRecon Dataset
(See Fig. 8).
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xin, B., Ye, M., Axel, L., Metaxas, D.N. (2024). Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction. In: Camara, O., et al. Statistical Atlases and Computational Models of the Heart. Regular and CMRxRecon Challenge Papers. STACOM 2023. Lecture Notes in Computer Science, vol 14507. Springer, Cham. https://doi.org/10.1007/978-3-031-52448-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-52448-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52447-9
Online ISBN: 978-3-031-52448-6
eBook Packages: Computer ScienceComputer Science (R0)