Abstract
Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI’s principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called “Multi-coil Feature Fusion Variation Network” (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622 dB and 0.0021 dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network’s architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.
Similar content being viewed by others
References
Griswold M A, Jakob P M, Nittka M, et al. Partially parallel imaging with localized sensitivities (PILS). Magnetic Resonance in Medicine, 2000; 44(4): 602–9. https://doi.org/10.1002/1522-2594(200010)44:4<602::aid-mrm14>3.0.co;2-5.
Donoho D L. Compressed sensing. IEEE Transactions on information theory, 2006; 52(4): 1289–306. https://doi.org/10.1109/TIT.2006.871582.
Lustig M, Donoho D L, Santos J M, et al. Compressed sensing MRI. IEEE signal Processing Magazine, 2008; 25(2): 72–82. https://doi.org/10.1109/MSP.2007.914728.
Sodickson DK, Manning WJ. Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays. Magnetic Resonance in Medicine, 1997; 38(4): 591–603. https://doi.org/10.1002/mrm.1910380414.
Pruessmann KP, Weiger M, Scheidegger MB, et al. SENSE: sensitivity encoding for fast MRI. Magnetic Resonance in Medicine, 1999; 42(5): 952–62.
Griswold M, Jakob P, Heidemann R, et al. Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magnetic Resonance in Medicine, 2014; 71(3): 990–1001. https://doi.org/10.1002/mrm.10171.
Uecker M, Lai P, Murphy MJ, et al. ESPIRiT-an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA. Magnetic Resonance in Medicine, 2014; 71. https://doi.org/10.1002/mrm.24751.
Wang S, Su Z, Ying L, et al. Accelerating magnetic resonance imaging via deep learning. 2016 IEEE 13th international symposium on biomedical imaging (ISBI). IEEE, 2016: 514–517. https://doi.org/10.1109/ISBI.2016.7493320.
Schlemper J, Caballero J, Hajnal Jv, et al. A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction [J]. IEEE Trans Med Imaging. 2018, 37(2):491–503. https://doi.org/10.1109/TMI.2017.2760978
Gan W, Sun Y, Eldeniz C, et al. Deep image reconstruction using unregistered measurements without groundtruth. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). IEEE, 2021: 1531–1534. https://doi.org/10.1109/ISBI48211.2021.9434079
Duan C, Deng H, Xiao S, et al. Accelerate gas diffusion-weighted MRI for lung morphometry with deep learning. European Radiology. 2022, 32(1):702–713. https://doi.org/10.1007/s00330-021-08126-y.
Guo P, Valanarasu J M J, Wang P, et al. Over-and-under complete convolutional RNN for MRI reconstruction. Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VI 24. Springer International Publishing, 2021: 13–23. https://arxiv.org/abs/2106.08886
Chen E Z, Wang P, Chen X, et al. Pyramid convolutional RNN for MRI image reconstruction. IEEE Transactions on Medical Imaging, 2022, 41(8): 2033–2047. https://doi.org/10.1109/TMI.2022.3153849.
Yang G, Yu S, Dong H, et al. DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction. IEEE Trans Med Imaging. 2018, 37(6):1310–1321. https://doi.org/10.1109/TMI.2017.2785879.
Belov A, Stadelmann J, Kastryulin S, et al. Towards ultrafast MRI via extreme k-space undersampling and superresolution. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2021: 254–264. https://arxiv.org/abs/2103.02940
Li G, Lv J, Wang C. A modified generative adversarial network using spatial and channel-wise attention for CS-MRI reconstruction. IEEE Access, 2021, 9: 83185–83198. https://doi.org/10.1109/access.2021.3086839
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234–241. https://doi.org/10.1016/j.compbiomed.2021.104699
Hyun CM, Kim HP, Lee SM, et al. Deep learning for undersampled MRI reconstruction. Physics in Medicine & Biology. 2018, 63(13):135007. https://doi.org/10.1088/1361-6560/aac71a
Yang J, Küstner T, Hu P, et al. End-to-End Deep Learning of Non-rigid Groupwise Registration and Reconstruction of Dynamic MRI. Frontiers in Cardiovascular Medicine, 2022, 9. https://doi.org/10.3389/fcvm.2022.880186.
Hammernik K, Klatzer T, Kobler E, et al. Learning a variational network for reconstruction of accelerated MRI data. Magnetic Resonance in Medicine, 2018; 79(6): 3055–71. https://doi.org/10.1002/mrm.26977.
Yiasemis G, Sonke J J, Sánchez C, et al. Recurrent variational network: a deep learning inverse problem Solver applied to the task of accelerated MRI reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 732–41. https://arxiv.org/abs/2111.09639.
Zhang Z X, Du H W, Qiu B S. FFVN: An explicit feature fusion-based variational network for accelerated multi-coil MRI reconstruction. Magnetic Resonance Imaging, 2023, 97: 31–45. https://doi.org/10.1016/j.mri.2022.12.018.
Duan J, Schlemper J, Qin C, et al. VS-Net: Variable splitting network for accelerated parallel MRI reconstruction. Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part IV 22. Springer International Publishing, 2019: 713–722. https://arxiv.org/abs/1907.10033.
Murugesan B, Ramanarayanan S, Vijayarangan S, et al. A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction. Computerized Medical Imaging and Graphics, 2021, 91: 101942. https://doi.org/10.1016/j.compmedimag.2021.101942.
Küstner T, Fuin N, Hammernik K, et al. CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions. Scientific reports, 2020, 10(1): 13710. https://doi.org/10.1038/s41598-020-70551-8.
WANG Y D, SONG Y, XIE H B, et al. Reconstruction of under-sampled magnetic resonance image based on convolution neural network. Chin J Magn Reson Imaging, 2018, 9 (06): 453–459. https://doi.org/10.12015/issn.1674-8034.2018.06.010
Liu Y, Niu H, Ren P, et al. Generation of quantification maps and weighted images from synthetic magnetic resonance imaging using deep learning network. Physics in Medicine & Biology, 2022, 67(2): 025002. https://doi.org/10.1088/1361-6560/ac46dd
Sriram A, Zbontar J, Murrell T, et al. End-to-end variational networks for accelerated MRI reconstruction. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2020: 64–73. https://doi.org/10.1016/j.media.2017.06.012
Ramzi Z., Ciuciu P., and Starck J.-L., “XPDNet for MRI reconstruction: An application to the 2020 fastMRI challenge,” in Proc. ISMRM, 2020, pp. 1–4. Available: https://arxiv.org/abs/2010.07290
Ramzi Z, Chaithya G R, Starck J L, et al. NC-PDNet: A density-compensated unrolled network [[41(7): 1625–1638. https://doi.org/10.1109/tmi.2022.3144619
Sun L, Fan Z, Fu X, et al. A deep information sharing network for multi-contrast compressed sensing MRI reconstruction. IEEE Transactions on Image Processing, 2019, 28(12): 6141–6153. https://doi.org/10.1109/tip.2019.2925288
Xiang L, Chen Y, Chang W, et al. Deep-learning-based multi-modal fusion for fast MR reconstruction. IEEE Transactions on Biomedical Engineering, 2018, 66(7): 2105–2114. https://doi.org/10.1109/tbme.2018.2883958
Zbontar J, Knoll F, Sriram A, et al. fastMRI: An open dataset and benchmarks for accelerated MRI. https://arxiv.org/abs/1811.08839
Wang S, Ke Z, Cheng H, et al. DIMENSION: dynamic MR imaging with both k‐space and spatial prior knowledge obtained via multi‐supervised network training[J]. NMR in Biomedicine, 2022, 35(4): e4131. https://doi.org/10.1002/nbm.4131
Trabelsi C, Bilaniuk O, Serdyuk D, et al. Deep complex networks. 2018, https://arxiv.org/abs/1705.09792
Funding
The study was supported by research grants from The National Natural Science Foundation of China [Grant No. 81830052] and Shanghai Key Laboratory of Molecular Imaging [18DZ2260400].
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cheng, H., Hou, X., Huang, G. et al. Feature Fusion for Multi-Coil Compressed MR Image Reconstruction. J Digit Imaging. Inform. med. (2024). https://doi.org/10.1007/s10278-024-01057-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10278-024-01057-2