Article Sidebar

pdf
Issue: Số 90-09.2026
Section: Các bài báo
DOI: 10.70117/hdujs.3030-4628.90.09.2026.1383
Views 1
Downloads 0
How to Cite
Le, T. H. H., Tran, D. M., Nguyen, H. L., Nguyen, V. C., & Nguyen, T. C. (2026). MDMFUSION: AN MRI–CT IMAGE FUSION MODEL BASED ON MULTI-LEVEL DECOMPOSITION AND DATFUSE. Hong Duc University Journal of Science – Natural Sciences, Engineering and Technology, 90(09), 16-27. https://doi.org/10.70117/hdujs.3030-4628.90.09.2026.1383

MDMFUSION: AN MRI–CT IMAGE FUSION MODEL BASED ON MULTI-LEVEL DECOMPOSITION AND DATFUSE

Lê Thị Hồng Hà1, , Trần Doãn Minh1, Nguyễn Hoàng Long1, Nguyễn Văn Cường1, The Cuong Nguyen1
1 Hong Duc University

Main Article Content

Abstract

MRI–CT medical image fusion plays an important role in diagnostic support by combining structural and soft-tissue information from different imaging modalities. This paper proposes MDMFusion, a novel image fusion model that integrates the MIDTE multi-level decomposition algorithm, the DATFuse deep learning model, and an improved pulse-coupled neural network (iPCNN). In the proposed framework, MIDTE employs THF and EGIF filters to enhance noise suppression and detail preservation; DATFuse is utilized to improve the brightness and contrast of base components; while iPCNN is designed to enhance the preservation of edge and structural information in detail components. Experimental results on the MRI–CT dataset demonstrate that MDMFusion achieves competitive performance compared with several state-of-the-art fusion methods, particularly in terms of brightness preservation and mutual information. In addition, the proposed method shows strong capability in improving visual quality and preserving important anatomical structures in the fused images.

Keywords

Tổng hợp ảnh y học, DATFuse, iPCNN, THF, EGIF

Article Details

References

[1] B. Li, H. Peng, and J. Wang, “A novel fusion method based on dynamic threshold neural P systems and nonsubsampled contourlet transform for multi-modality medical images,” Signal Processing, vol.178, pp.107793, 2021, DOI: 10.1016/J.SIGPRO.2020.107793.
[2] C. Panigrahy, A. Seal, and N. K. Mahato, “Parameter adaptive unit-linking dual-channel PCNN based infrared and visible image fusion,” Neurocomputing, vol. 514, pp.21-38, 2022, DOI: 10.1016/J.NEUCOM.2022.09.157.
[3] C. Panigrahy, A. Seal, C. Gonzalo-Martín, P. Pathak, and A. S. Jalal, “Parameter adaptive unit-linking pulse coupled neural network based MRI–PET/SPECT image fusion,” Biomed. Signal Process. Control, vol. 83, pp.104659, 2023, DOI: 10.1016/J.BSPC.2023.104659.
[4] B. Rajalingam, F. Al-Turjman, R. Santhoshkumar, and M. Rajesh, “Intelligent multimodal medical image fusion with deep guided filtering,” Multimed. Syst., 28(4):14491463, 2022, DOI: 10.1007/S00530-020-00706-0/METRICS.
[5] S. Maqsood and U. Javed, “Multi-modal Medical Image Fusion based on Two-scale Image Decomposition and Sparse Representation,” Biomed. Signal Process. Control, vol. 57, pp.101810, 2020, DOI: 10.1016/J.BSPC.2019.101810.
[6] P. Vajpayee, C. Panigrahy, and A. Kumar, “Medical image fusion by adaptive Gaussian PCNN and improved Roberts operator,” Signal Image Video Process., 17(7): 3565-3573, 2023, DOI: 10.1007/S11760-023-02581-4/METRICS.
[7] W. Liu, P. Zhang, Y. Lei, X. Huang, J. Yang, and M. Ng, “A Generalized Framework for Edge-Preserving and Structure-Preserving Image Smoothing,” IEEE Trans. Pattern Anal. Mach. Intell., 44(10):6631-6648, 2022, DOI: 10.1109/TPAMI.2021.3097891.
[8] Z. Lu, B. Long, K. Li, and F. Lu, “Effective Guided Image Filtering for Contrast Enhancement,” IEEE Signal Process. Lett., 25(10):1585-1589, 2018, DOI: 10.1109/LSP.2018.2867896.
[9] W. Tang, F. He, Y. Liu, Y. Duan, and T. Si, “DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer,” IEEE Transactions on Circuits and Systems for Video Technology, 33(7):3159-3172, 2023, DOI: 10.1109/TCSVT.2023.3234340.
[10] W. Tan, W. Thitøn, P. Xiang, and H. Zhou, “Multi-modal brain image fusion based on multi-level edge-preserving filtering,” Biomed. Signal Process. Control, vol. 64, pp. 102280, 2021, DOI: 10.1016/J.BSPC.2020.102280.
[11] W. Tan, P. Tiwari, H. M. Pandey, C. Moreira, and A. K. Jaiswal, “Multimodal medical image fusion algorithm in the era of big data,” Neural Comput. Appl., pp. 1-21, 2020, DOI: 10.1007/S00521-020-05173-2/FIGURES/18.
[12] G. Qu, D. Zhang, and P. Yan, “Information measure for performance of image fusion,” Electron. Lett., 38(7):313315, 2002, DOI: 10.1049/EL:20020212.
[13] C. S. Xydeas and V. Petrović, “Objective image fusion performance measure,” Electron. Lett., 36(4):308-309, 2000, DOI: 10.1049/EL:20000267.
[14] B. Li et al., “Medical Image Fusion Method Based on Coupled Neural P Systems in Nonsubsampled Shearlet Transform Domain,”, 31(1), 2020, DOI: 10.1142/S0129065720500501.
[15] A. Sinha et al., “Multi-modal medical image fusion using improved dual-channel PCNN,” Med. Biol. Eng. Comput., 62(9):2629-2651, 2024, DOI: 10.1007/S11517-024-03089-W/METRICS.
[16] N. Goyal et al., “Dual-channel Rybak neural network based medical image fusion,” Opt. Laser Technol., vol. 181, 2025, DOI: 10.1016/j.optlastec.2024.112018.
[17] W. Tang and F. He, “FATFusion: A functional-anatomical transformer for medical image fusion,” Inf. Process. Manag., 61(4), 2024, DOI: 10.1016/j.ipm.2024.103687.
[18] Y. Jie, X. Li, H. Tan, F. Zhou, and G. Wang, “Multi-modal medical image fusion via multi-dictionary and truncated Huber filtering,” Biomed. Signal Process. Control, vol. 88, pp. 105671, 2024, DOI: 10.1016/J.BSPC.2023.105671.
[19] X. Xie et al., “MACTFusion: Lightweight Cross Transformer for Adaptive Multimodal Medical Image Fusion,” IEEE J. Biomed. Health Inform., 29(5): 3317-3328, 2025, DOI: 10.1109/JBHI.2024.3391620.