Abstract
Reducing acquisition time in Cardiac Magnetic Resonance Imaging (MRI) brings several benefits, such as improved patient comfort, reduced motion artifacts and increased doctors’ work efficiency, but it may lead to image blurring during the reconstruction process. In this paper, we propose a new method for restoring blurry cardiac MRI images caused by under-sampling, treating it as an image deblurring problem to achieve clear reconstruction, and ensuring consistency with training by using a simple modified input during inference. A U-Net network architecture which initially designed for natural image deblurring, has been adapted to effectively discern the differences between blurred and clear MRI images, eliminating the need for sensitivity estimation. Moreover, to address the inconsistency between training on local patches and testing on the entire image, we propose a partial overlap cropping approach during inference time, effectively resolving this discrepancy. We evaluated our method using the cardiac MRI dataset from the CMRxRecon challenge, revealing its potential to reduce acquisition time while preserving high image quality in cardiac MRI, even under highly under-sampled conditions. Importantly, this achievement was attained in a coil-agnostic manner, enabling us to achieve favorable results on both multi-coil and single-coil data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pruessmann, K.P., Weiger, M., Scheidegger, M.B., Boesiger, P.: SENSE: Sensitivity encoding for fast MRI. Magn. Reson. Med. 42(5), 952–962 (1999)
Griswold, M.A., et al.: Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn. Reson. Med. 47(6), 1202–1210 (2002)
Lustig, M., Pauly, J.M.: SPIRiT: iterative self-consistent parallel imaging reconstruction from arbitrary k-space. Magn. Reson. Med. 64(2), 457–471 (2010)
Uecker, M., et al.: ESPIRiT-an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA. Magn. Reson. Med. 71(3), 990–1001 (2014)
Lee, J., Jin, K.H., Ye, J.C.: Reference-free single-pass EPI Nyquist ghost correction using annihilating filter-based low rank Hankel matrix (ALOHA). Magn. Reson. Med. 76(6), 1775–1789 (2016)
Lyu, J., et al.: Region-focused multi-view transformer-based generative adversarial network for cardiac cine MRI reconstruction. Med. Image. Anal. 85, 102760 (2023)
Lv, J., Wang, P., Tong, X., Wang, C.: Parallel imaging with a combination of sensitivity encoding and generative adversarial networks. Quant. Imaging Med. Surg. 10(12), 2260–2273 (2020)
Qin, C., Schlemper, J., Caballero, J., Price, A.N., Hajnal, J.V., Rueckert, D.: Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Trans. Med. Imaging 38(1), 280–290 (2019)
Qin, C., et al.: Complementary time-frequency domain networks for dynamic parallel MR image reconstruction. Magn. Reson. Med. 386(6), 3274–3291 (2021)
Cho, S.-J., Ji, S.-W. , Hong, J.-P., Jung, S.-W., Ko, S.-J.: Rethinking coarse-to-fine approach in single image deblurring. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4621–4630 (2021)
Mao, X., Liu, Y., Liu, F., Li, Q., Shen, W., Wang, Y.: Intriguing findings of frequency selection for image deblurring. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 1905–1913 (2023)
Cao, J., et al.: DO-conv: depthwise over-parameterized convolutional layer. IEEE Trans. Image Process. 31, 3726–3736 (2022)
Mehri, A., Ardakani, P.B., Sappa, A.D.: MPRNet: multi-path residual network for lightweight image super resolution. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2703–2712 (2021)
Zhang, K., et al.: Deep image deblurring: a survey. Int. J. Comput. Vision 130(9), 2103–2130 (2022)
Wang, C., Lyu, J., Wang, S., et al.: CMRxRecon: an open cardiac MRI dataset for the competition of accelerated image reconstruction. arXiv preprint arXiv:2309.10836 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
He, J., Liu, W., Tian, Y., Zhao, S. (2024). Accelerating Cardiac MRI via Deblurring Without Sensitivity Estimation. 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_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-52448-6_27
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)