Development of Multi-Stage Data Consistency Integrated U-Net Model for Undersampled MRI K-Space Reconstruction
Main Article Content
Abstract
Reducing magnetic resonance imaging (MRI) acquisition time is critical to minimize patient discomfort, motion artifacts, and overall scanning costs. Compressed sensing (CS) has been widely investigated as a promising solution for MRI acceleration by reconstructing images from undersampled k-space data. However, traditional CS-based methods often suffer from instability, long reconstruction times, and limited performance due to their reliance on handcrafted regularization and iterative optimization schemes. Recent advances in deep learning have opened new possibilities for improving MRI reconstruction by learning data-driven priors directly from large datasets. Nevertheless, purely data-driven models may generate visually plausible images that lack strict consistency with the acquired measurements, potentially compromising diagnostic reliability. To address this limitation, we propose a deep learning-based MRI reconstruction framework that explicitly incorporates a data consistency (DC) layer. This physics-guided constraint enforces agreement between the network-updated k-space and the originally sampled measurements, thereby enhancing reconstruction fidelity. Experimental results demonstrate that the proposed model achieves a noticeable improvement in structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) compared with conventional reconstruction methods. These findings highlight the effectiveness of integrating learned priors with physics-based constraints, paving the way for faster MRI acquisition while preserving high diagnostic image quality in clinical practice.
Keywords
Compressed Sensing MRI, MRI reconstruction, U-net, Data consistency, undersampling k-space.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[2] Hollingsworth, K., Reducing acquisition time in clinical MRI by data undersampling and compressed sensing reconstruction. Physics in medicine and biology, 2015. 60: p. R297-R322.
[3] Sharma, P., A.K. Dubey, and A. Goyal. Hardware Acceleration Using SIMD Based Vector Processor Array to Enhance Performance of Deblurring Methods for CT and MRI Images Having Motion Blur Artifacts. in 2023 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES). 2023.
[4] Hamilton, J., D. Franson, and N. Seiberlich, Recent advances in parallel imaging for MRI. Progress in Nuclear Magnetic Resonance Spectroscopy, 2017. 101: p. 71-95.
[5] Corbin, N., et al., Fast Imaging and Acceleration Techniques. 2024. p. 51-74.
[6] Kojima, S., et al., Undersampling patterns in k-space for compressed sensing MRI using two-dimensional Cartesian sampling. Radiological Physics and Technology, 2018. 11(3): p. 303-319.
[7] Sandilya, M. and S.R. Nirmala, Compressed sensing trends in magnetic resonance imaging. Engineering Science and Technology, an International Journal, 2017. 20(4): p. 1342-1352.
[8] Candes, E.J., J. Romberg, and T. Tao, Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on Information Theory, 2006. 52(2): p. 489-509.
[9] Lustig, M., et al., Compressed Sensing MRI. IEEE Signal Processing Magazine, 2008. 25(2): p. 72-82.
[10] Lustig, M., D. Donoho, and J.M. Pauly, Sparse MRI: The application of compressed sensing for rapid MR imaging. Magnetic Resonance in Medicine, 2007. 58(6): p. 1182-1195.
[11] Tropp, J.A. and A.C. Gilbert, Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit. IEEE Transactions on Information Theory, 2007. 53(12): p. 4655-4666.
[12] Safari, M., et al., Advancing MRI reconstruction: A systematic review of deep learning and compressed sensing integration. Biomedical Signal Processing and Control, 2026. 111: p. 108291.
[13] Heckel, R., et al., Deep learning for accelerated and robust MRI reconstruction. 2024. 37(3): p. 335-368.
[14] Yang, A. and M. Finkelstein, Impact of Deep Learning Image Reconstruction Methods on MRI Throughput. 2024. 6(3): p. e230181.
[15] Jiangtao, W., N.I.R. Ruhaiyem, and F. Panpan, A Comprehensive Review of U‐Net and Its Variants: Advances and Applications in Medical Image Segmentation. IET Image Processing, 2025. 19.
[16] Elbehairy, A., I. Yassine, and M. Elattar, Stage U-Net Framework: Streamlining MRI Reconstruction from Under- sampled K-Space. 2024.
[17] Aghabiglou, A. and E.M. Eksioglu, Projection-Based cascaded U-Net model for MR image reconstruction. Computer Methods and Programs in Biomedicine, 2021. 207: p. 106151.
[18] Huang, J., et al., Data- and Physics-Driven Deep Learning Based Reconstruction for Fast MRI: Fundamentals and Methodologies. IEEE Reviews in Biomedical Engineering, 2025. 18: p. 152-171.
[19] Hammernik, K., et al., Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging: Combining physics and machine learning for improved medical imaging. IEEE Signal Process Mag, 2023. 40(1): p. 98-114.
[20] Safari, M., et al., A Physics-Informed Deep Learning Model for MRI Brain Motion Correction. ArXiv, 2025.
[21] Karkalousos, D., et al., Assessment of data consistency through cascades of independently recurrent inference machines for fast and robust accelerated MRI reconstruction. Physics in Medicine & Biology, 2022. 67(12): p. 124001.
[22] brain-development.org, IXI dataset (RRID:SCR_005839). 2025.
[23] Anh Quang Tran, T.-A.N., Phuc Thinh Doan , Duc-Nghia Tran , Duc-Tan Tran Parallel magnetic resonance imaging acceleration with a hybrid sensing approach. Mathematical Biosciences and Engineering, 2021. 18(3): p. 2288-2302.
[24] Tran, A.Q., et al., MRI Simulation-based evaluation of an efficient under-sampling approach. Mathematical Biosciences and Engineering, 2020. 17(4): p. 4048-4063.
[25] Khanh Pham, D., D.-T. Tran, and A. Quang Tran, Evaluating random–Nyquist sampling ratios in combined compressed sensing magnetic resonance imaging. Bulletin of Electrical Engineering and Informatics, 2025.
[26] Zhu, X., B. Tomanek, and J. Sharp, A pixel is an artifact: On the necessity of zero-filling in fourier imaging. Concepts in Magnetic Resonance Part A, 2013. 42A.
[27] Jyoti, P. and K. Raj, Peak Signal to Noise Ratio analysis in single image restoration technique. 2019. 5: p. 160-162.
[28] Punga, M., S. Moldovanu, and L. Moraru, Structural similarity analysis for brain MR image quality assessment. AIP Conference Proceedings, 2014. 1634(1): p. 137-143.
[29] Ghodrati, V., et al., MR image reconstruction using deep learning: evaluation of network structure and loss functions. Quant Imaging Med Surg, 2019. 9(9): p. 1516-1527.
[30] Kocanaogullari, D. and E.M. Eksioglu. Deep Learning For Mri Reconstruction Using A Novel Projection Based Cascaded Network. in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP). 2019.
[31] Dong, B. and G. Wu, A Swin Transformer-Based Cold Diffusion Model for Accelerated MRI Reconstruction, in Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security. 2025, Association for Computing Machinery. p. 226–230.