Deep Learning-Based MRI Denoising Using Noise Statistics Derived from Physical Phantom Measurements
Abstract
High-quality MRI images are essential for accurate definition of target volumes and organs at risk, as well as for correct registration with CT scans when planning radiotherapy. The aim of this work is to develop a robust denoising method that improves visualization of brain structures and preserves anatomical details. A model based on a modified U-Net architecture with residual blocks, attention modules (CBAM) and spatial pyramidal pooling is proposed. The approach is characterized by the integration of statistical noise characteristics obtained from phantom measurements and modeling of degradations in pseudo-k-space (including Gaussian and Rayleigh noise distributions). The validation was performed on 1000 anonymized clinical DICOM images with variable noise levels. The proposed model provided an increase in PSNR by 8–10 dB and an increase in SSIM from 0.72 to 0.97. The edge preservation index (EPI), which reached values of 8.0 on noisy images due to artifacts, stabilized at 1.0 after processing, indicating effective removal of pseudo-contours without blurring true anatomical boundaries. In addition, an average SNR improvement of 7% and a CV reduction of 4–7% were observed on real images, confirming the stability of the method. The combination of physically based noise modeling in the frequency domain and modern deep learning architectures allows for effective noise removal while preserving critical anatomical boundaries. The method has high potential for clinical implementation in radiotherapy planning procedures, in particular to improve the accuracy of MRI/CT fusion.
Downloads
References
Z. Chen, K. Pawar, M. Ekanayake, C. Pain, S. Zhong, and G.F. Egan, J. Digit. Imaging, 36, 204 (2023). https://doi.org/10.1007/s10278-022-00721-9
J.I. Tamir, M. Blumenthal, J. Wang, T. Oved, E. Shimron, and M. Zaiss, Magn. Reson. Mater. Phys. Biol. Med. 38, 367 (2025). https://doi.org/10.1007/s10334-025-01236-4
T. Ssentamu, A. Kimbowa, R. Omoding, E. Atamba, P.K. Mukwaya, G.W. Jjuuko, and S. Geethanath, Front. Neuroimaging, 4, (2025). https://doi.org/10.3389/fnimg.2025.1501801
A. Salehi, M. Mach, C. Najac, B. Lena, T. O’Reilly, Y. Dong, P. Börnert, et al., J. Magn. Reson. 370, 107812 (2025). https://doi.org/10.1016/j.jmr.2024.107812
P. Song, J. Xu, X. Liu, Z. Zhang, X. Rao, R.P. Martinho, Q. Bao, and C. Liu, J. Magn. Reson. 359, 107615 (2024). https://doi.org/10.1016/j.jmr.2023.107615
D. Koprivica, R.P. Martinho, M. Novakovic, M.J. Jaroszewicz, and L. Frydman, J. Magn. Reson. 338, 107187 (2022). https://doi.org/10.1016/j.jmr.2022.107187
Y. Zhang, W. He, F. Chen, J. Wu, Y. He, and Z. Xu, J. Magn. Reson. 344, 107319 (2022). https://doi.org/10.1016/j.jmr.2022.107319
D. Singh, A. Monga, H.L. de Moura, X. Zhang, M.V.W. Zibetti, and R.R. Regatte, Bioeng. Basel Switz. 10, 1012 (2023). https://doi.org/10.3390/bioengineering10091012
M. Jiang, S. Wang, K.-H. Chan, Y. Sun, Y. Xu, Z. Zhang, Q. Gao, et al., Comput. Med. Imaging Graph. Off. J. Comput. Med. Imaging Soc. 121, 102497 (2025). https://doi.org/10.1016/j.compmedimag.2025.102497
B. Kang, W. Lee, H. Seo, H.-Y. Heo, and H. Park, Magn. Reson. Med. 92, 1980 (2024). https://doi.org/10.1002/mrm.30197
M.A. Sultan, C. Chen, Y. Liu, K. Gil, K. Zareba, and R. Ahmad, Magn. Reson. Mater. Phys. Biol. Med. 38, 859 (2025). https://doi.org/10.1007/s10334-025-01257-z
Q. Tian, Z. Li, Q. Fan, J.R. Polimeni, B. Bilgic, D.H. Salat, and S.Y. Huang, NeuroImage, 253, 119033 (2022). https://doi.org/10.1016/j.neuroimage.2022.119033
E.D. Hussner, S. Sundby, C.B. Outzen, J. Jensen, A. Tingberg, and H. Precht, J. Med. Imaging Radiat. Sci. 56, 101814 (2025). https://doi.org/10.1016/j.jmir.2024.101814
S. Kojima, T. Ito, and T. Hayashi, J. Med. Phys. 47, 387 (2022). https://doi.org/10.4103/jmp.jmp_71_22
S.M.A. Sharif, R.A. Naqvi, and W.-K. Loh, IEEE Trans. Radiat. Plasma Med. Sci. 8, 521 (2024). https://doi.org/10.1109/TRPMS.2024.3380090
K.V. Jordanova, S.E. Russek, and K.E. Keenan, Magn. Reson. Mater. Phys. Biol. Med. 38, 727 (2025). https://doi.org/10.1007/s10334-025-01270-2
K.E. Keenan, K.V. Jordanova, S.E. Ogier, D. Tamada, N. Bruhwiler, J. Starekova, J. Riek, et al., Magn. Reson. Mater. Phys. Biol. Med. 37, 535 (2024). https://doi.org/10.1007/s10334-024-01181-8
K.E. Keenan, M. Ainslie, A.J. Barker, M.A. Boss, K.M. Cecil, C. Charles, T.L. Chenevert, et al., Magn. Reson. Med. 79, 48 (2018). https://doi.org/10.1002/mrm.26982
C.P. Cheng, and Y.O. Halchenko, F1000Research, 9, 1131 (2020). https://doi.org/10.12688/f1000research.24544.1
R.W. Brown, Y.-C.N. Cheng, E.M. Haacke, M.R. Thompson, and R. Venkatesan, Magnetic Resonance Imaging: Physical Principles and Sequence Design, (John Wiley & Sons, 2014).
W.A. Edelstein, G.H. Glover, C.J. Hardy, and R.W. Redington, Magn. Reson. Med. 3, 604 (1986). https://doi.org/10.1002/mrm.1910030413
H. Gudbjartsson and S. Patz, Magn. Reson. Med. 34, 910 (1995). https://doi.org/10.1002/mrm.1910340618
N. Just, Br. J. Cancer 111, 2205 (2014). https://doi.org/10.1038/bjc.2014.512
G. Vegas-Sánchez-Ferrero, M.J. Ledesma-Carbayo, G.R. Washko, and R.S.J. Estépar, Med. Image Anal. 40, 44 (2017). https://doi.org/10.1016/j.media.2017.06.001
H. Liu, Z. Li, S. Lin, and L. Cheng, Sensors, 23, 7044 (2023). https://doi.org/10.3390/s23167044
L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, (2017). https://doi.org/10.48550/arXiv.1706.05587
E. Perez, F. Strub, H. de Vries, V. Dumoulin, and A. Courville, in: Proc. Thirty-Second AAAI Conf. Artif. Intell. Thirtieth Innov. Appl. Artif. Intell. Conf. Eighth AAAI Symp. Educ. Adv. Artif. Intell, (AAAI Press, New Orleans, Louisiana, USA, 2018), pp. 3942 3951. https://doi.org/10.48550/arXiv.1709.07871
C. Bregler, in: 2015 IEEE Conf. Comput. Vis. Pattern Recognit. CVPR, (2015). https://doi.org/10.1109/CVPR.2015.7298664
A.L. Maas, in: Rectifier Nonlinearities Improve Neural Network Acoustic Models, (2013). https://api.semanticscholar.org/CorpusID:16489696
S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, ArXiv preprint, (2018), pp. 3–19. https://doi.org/10.48550/arXiv.1807.06521
J. Hu, L. Shen, and G. Sun, ArXiv preprint, ArXiv preprint, (2018), pp. 7132–7141. https://https://doi.org/10.48550/arXiv.1709.01507
B. Yaman, S.A.H. Hosseini, S. Moeller, J. Ellermann, K. Uğurbil, and M. Akçakaya, Magn. Reson. Med. 84, 3172 (2020). https://doi.org/10.1002/mrm.28378
L. Zhang, M. Wu, L. Wang, D.C. Steffens, G.G. Potter, and M. Liu, ArXiv preprint, (2024). https://doi.org/10.48550/arXiv.2403.08162
H. Chen, Y. Zhang, W. Zhang, P. Liao, K. Li, J. Zhou, and G. Wang, ArXiv preprint, (2016). https://doi.org/10.48550/arXiv.1609.08508
S. Gou, W. Liu, C. Jiao, H. Liu, Y. Gu, X. Zhang, J. Lee, and L. Jiao, Phys. Med. Biol. 64, 165017 (2019). https://doi.org/10.1088/1361-6560/ab325e
K. He, X. Zhang, S. Ren, and J. Sun, in: 2015 IEEE International Conference on Computer Vision (ICCV), (Santiago, Chile, 2015). https://doi.org/10.1109/ICCV.2015.123
A. Horé and D. Ziou, in: 2010 20th Int. Conf. Pattern Recognit. (2010), pp. 2366–2369. https://doi.org/10.1109/ICPR.2010.579
K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, IEEE Trans. Image Process. 26, 3142 (2017). https://doi.org/10.1109/TIP.2017.2662206
G.P. Renieblas, A.T. Nogués, A.M. González, N. Gómez-Leon, and E.G. del Castillo, J. Med. Imaging, 4, 035501 (2017). https://doi.org/10.1117/1.JMI.4.3.035501
P. Jain, and V. Tyagi, Inf. Syst. Front. 18, 159–170 (2016). https://doi.org/10.1007/s10796-014-9527-0
K. P.g., J. Joseph, and S.J., Biocybern, Biomed. Eng. 37, 159 (2017). https://doi.org/10.1016/j.bbe.2016.12.008
J. Lewis, Vision Interface, 10(1), 120-123 (1995). https://www.bibsonomy.org/bibtex/232f4a4901ce85a2b37f806ba675c8a0
F.L. Goerner and G.D. Clarke, Med. Phys. 38, 5049 (2011). https://doi.org/10.1118/1.3618730
E. Alizadeh, Data Sci. (2023). https://towardsdatascience.com/dispersion-cv-qcd-32849f828434/
Z. Jalilibal, A. Amiri, P. Castagliola, and M.B.C. Khoo, Comput. Ind. Eng. 161, 107600 (2021). https://doi.org/10.1016/j.cie.2021.107600
M. Kidoh, K. Shinoda, M. Kitajima, K. Isogawa, M. Nambu, H. Uetani, K. Morita, et al., Magn. Reson. Med. Sci. 19, 195 (2019). https://doi.org/10.2463/mrms.mp.2019-0018
N. Nazir, A. Sarwar, and B.S. Saini, Micron, 180, 103615 (2024). https://doi.org/10.1016/j.micron.2024.103615
H.M.S.S. Herath, H.M.K.K.M.B. Herath, N. Madusanka, and B.-I. Lee, J. Imaging, 11, 100 (2025). https://doi.org/10.3390/jimaging11040100
J. Joseph, S. Jayaraman, R. Periyasamy, and S.V. Renuka, Curr. Med. Imaging, 13, 58 (2017). https://doi.org/10.2174/1573405612666160609131149
K. Ohashi, Y. Nagatani, M. Yoshigoe, K. Iwai, K. Tsuchiya, A. Hino, Y. Kida, et al., J. Digit. Imaging, 36, 2623 (2023). https://doi.org/10.1007/s10278-023-00875-0
D. Sliusarenko, A. Netreba, and S. Radchenko, in: 2024 IEEE 42nd Int. Conf. Electron. Nanotechnol. ELNANO, (2024), pp. 456–460. https://doi.org/10.1109/ELNANO63394.2024.10756858
K. Usui, K. Ogawa, M. Goto, Y. Sakano, S. Kyougoku, and H. Daida, Vis. Comput. Ind. Biomed. Art 4, 21 (2021). https://doi.org/10.1186/s42492-021-00087-9
A. Ferdi, S. Benierbah, and A. Nakib, Multimed. Tools Appl. 84, 21625 (2025). https://doi.org/10.1007/s11042-024-20175-1
Z. Wang, J. Chen, and S.C.H. Hoi, ArXiv preprint, (2020). https://doi.org/10.48550/arXiv.1902.06068
M.J. Muckley, B. Riemenschneider, A. Radmanesh, S. Kim, G. Jeong, J. Ko, Y. Jun, et al., IEEE Trans. Med. Imaging, 40, 2306 (2021). https://doi.org/10.1109/TMI.2021.3075856
A. Buades, B. Coll, and J.-M. Morel, in: 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. CVPR05, (2005), pp. 60–65 vol. 2. https://doi.org/10.1109/CVPR.2005.38
K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, IEEE Trans. Image Process. 16, 2080 (2007). https://doi.org/10.1109/TIP.2007.901238
K. Zhang, W. Zuo, and L. Zhang, IEEE Trans. Image Process. 27, 4608 (2018). https://doi.org/10.1109/TIP.2018.2839891
Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, in: Comput. Vis. – ECCV 2018 15th Eur. Conf. Proc. Part VII (Springer-Verlag, Berlin, Heidelberg, 2018), pp. 294–310. https://doi.org/10.1007/978-3-030-01234-2_18
J. Liang, J. Cao, G. Sun, K. Zhang, L.V. Gool, and R. Timofte, ArXiv preprint, (2021). https://doi.org/10.48550/arXiv.2108.10257
S.W. Zamir, A. Arora, S. Khan, M. Hayat, F.S. Khan, and M.-H. Yang, ArXiv preprint, (2022). https://doi.org/10.48550/arXiv.2111.09881
E. Jeong, J. Jang, J. Kim, and H. Kim, J. Magn. Reson. 368, 107762 (2024). https://doi.org/10.1016/j.jmr.2024.107762
C. Millard and M. Chiew, Bioengineering, 11, 1305 (2024). https://doi.org/10.3390/bioengineering11121305
Copyright (c) 2026 D.G. Sliusarenko, A.V. Netreba
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
