International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 18, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 2081KB)
SWT-PnP-DnCNN: Medical Image Fusion Using Stationary Wavelet Transform and Plug-and-Play Deep Denoising Model
PDF (2081KB), PP.209-229
Views: 0 Downloads: 0
Author(s)
Amit Pandey
1
Prabhishek Singh
1
Akansha Singh
1
Achyut Shankar
1
Manoj Diwakar
2,*
Index Terms
SWT, Dncnn, Local Energy, Weighted Averaging, Image Fusion, Medical Images
Abstract
This paper presents a hybrid medical image fusion (MIF) technique (SWT-PnP-DnCNN) that combines multiscale decomposition, spatial-frequency-driven fusion, and deep denoising priors to efficiently integrate MIF images. The SWT-PnP-DnCNN begins with the Stationary Wavelet Transform (SWT) to decompose input medical images into low-frequency (LFSBs) and high-frequency (HFSBs) subbands. The LFSBs are fused using spatial frequency-based weighted averaging, effectively integrating overall intensity and contrast information. For the HFSBs, a local energy and max-selection strategy is adopted to retain salient edge features from the source images. Following the initial fusion, a Plug-and-Play (PnP) optimization strategy is applied to improve this fused image. This step uses a pretrained DnCNN model as a deep denoiser, serving as an implicit image prior in a model-driven iterative framework. Each iteration alternates between a data consistency step and a denoising step, significantly reducing artifacts and enhancing structural fidelity in the result. The effectiveness of SWT-PnP-DnCNN is demonstrated on benchmark CT-MRI, MRI-PET, and MRI-PET datasets. Extensive evaluation against classical hybrid strategies and recent CNN-based fusion methods shows that SWT-PnP-DnCNN achieves the best performance across standard metrics. We further include mean±std reporting and paired t-tests, confirming statistically significant improvements (p < 0.05). Ablation studies validate each design choice by comparing SWT-only vs. SWT+PnP and evaluating denoiser alternatives, with sensitivity to PnP iterations, regularization strength, and SWT levels. The runtime analysis clarifies feasible deployment, particularly in offline or cloud-based environments. Overall, SWT-PnP-DnCNN emerges as a robust, interpretable, and clinically valuable solution for enhancing MIF in medical imaging applications.
Cite This Paper
Amit Pandey, Prabhishek Singh, Akansha Singh, Achyut Shankar, Manoj Diwakar, "SWT-PnP-DnCNN: Medical Image Fusion Using Stationary Wavelet Transform and Plug-and-Play Deep Denoising Model", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.3, pp. 209-229, 2026. DOI:10.5815/ijigsp.2026.03.11
Reference
[1]Guo, Z., Li, X., Huang, H., Guo, N., & Li, Q. (2018, April). Medical image segmentation based on multi-modal convolutional neural network: Study on image fusion schemes. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) (pp. 903-907). IEEE.
[2]Du, J., Li, W., Lu, K., & Xiao, B. (2016). An overview of multi-modal medical image fusion. Neurocomputing, 215, 3-20.
[3]Zhou, T., Ruan, S., & Canu, S. (2019). A review: Deep learning for medical image segmentation using multi-modality fusion. Array, 3, 100004.
[4]Li, Y., Zhao, J., Lv, Z., & Li, J. (2021). Medical image fusion method by deep learning. International Journal of Cognitive Computing in Engineering, 2, 21-29.
[5]Kumar, A. (2022). Deep learning for multi-modal medical imaging fusion: Enhancing diagnostic accuracy in complex disease detection. Int J Eng Technol Res Manag, 6(11), 183.
[6]Nair, R. R., Singh, T., Basavapattana, A., & Pawar, M. M. (2022). Multi-layer, multi-modal medical image intelligent fusion. Multimedia Tools and Applications, 81(29), 42821-42847.
[7]Zhou, T., Cheng, Q., Lu, H., Li, Q., Zhang, X., & Qiu, S. (2023). Deep learning methods for medical image fusion: A review. Computers in Biology and Medicine, 160, 106959.
[8]Xiang, L., Chen, Y., Chang, W., Zhan, Y., Lin, W., Wang, Q., & Shen, D. (2018). Deep-learning-based multi-modal fusion for fast MR reconstruction. IEEE Transactions on Biomedical Engineering, 66(7), 2105-2114.
[9]Nair, R. R., Singh, T., Sankar, R., & Gunndu, K. (2021). Multi-modal medical image fusion using lmf-gan-a maximum parameter infusion technique. Journal of Intelligent & Fuzzy Systems, 41(5), 5375-5386.
[10]Maqsood, S., & Javed, U. (2020). Multi-modal medical image fusion based on two-scale image decomposition and sparse representation. Biomedical Signal Processing and Control, 57, 101810.
[11]Maneesha, P., Singh, T., Nayar, R., & Kumar, S. (2019, January). Multi modal medical image fusion using convolution neural network. In 2019 Third International Conference on Inventive Systems and Control (ICISC) (pp. 351-357). IEEE.
[12]Azam, M. A., Khan, K. B., Salahuddin, S., Rehman, E., Khan, S. A., Khan, M. A., ... & Gandomi, A. H. (2022). A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics. Computers in biology and medicine, 144, 105253.
[13]Stimpel, B., Syben, C., Schirrmacher, F., Hoelter, P., Dörfler, A., & Maier, A. (2019). Multi-modal deep guided filtering for comprehensible medical image processing. IEEE transactions on medical imaging, 39(5), 1703-1711.
[14]Islam, K. T., Wijewickrema, S., & O’Leary, S. (2021). A deep learning based framework for the registration of three dimensional multi-modal medical images of the head. Scientific Reports, 11(1), 1860.
[15]Ouerghi, H., Mourali, O., & Zagrouba, E. (2017). Multimodal medical image fusion using modified PCNN based on linking strength estimation by MSVD transform. Int. J. Comput. Commun. Eng, 6(3), 201-211.
[16]Yang, L., Liu, X., & Yao, Y. (2008, May). Medical image fusion based on wavelet packet transform and self-adaptive operator. In 2008 2nd International Conference on Bioinformatics and Biomedical Engineering (pp. 2647-2650). IEEE.
[17]Polinati, S., Bavirisetti, D. P., Rajesh, K. N., & Dhuli, R. (2022). Multimodal medical image fusion based on content-based and PCA-sigmoid. Current Medical Imaging Reviews, 18(5), 546-562.
[18]Nair, R. R., & Singh, T. (2019). Multi‐sensor medical image fusion using pyramid‐based DWT: a multi‐resolution approach. IET Image Processing, 13(9), 1447-1459.
[19]Nandeesh, M. D., & Meenakshi, M. (2015, December). A novel technique of medical image fusion using stationary wavelet transform and principal component analysis. In 2015 international conference on smart sensors and systems (IC-SSS) (pp. 1-5). IEEE.
[20]Alseelawi, N., Hazim, H. T., & Salim ALRikabi, H. T. (2022). A Novel Method of Multimodal Medical Image Fusion Based on Hybrid Approach of NSCT and DTCWT. International Journal of Online & Biomedical Engineering, 18(3).
[21]Diwakar, M., Singh, P., & Shankar, A. (2021). Multi-modal medical image fusion framework using co-occurrence filter and local extrema in NSST domain. Biomedical Signal Processing and Control, 68, 102788.
[22]Ying, Z., Nie, R., Cao, J., Ma, C., & Tan, M. (2025). A nested self-supervised learning framework for 3-D semantic segmentation-driven multi-modal medical image fusion. Biomedical Signal Processing and Control, 105, 107653.
[23]Ma, G., Qiu, X., & Tan, X. (2025). DMFusion: A dual-branch multi-scale feature fusion network for medical multi-modal image fusion. Biomedical Signal Processing and Control, 105, 107572.
[24]Zhang, Y., Ma, C., Ding, H., & Zhu, Y. (2025). MMCL: Meta-mutual contrastive learning for multi-modal medical image fusion. Digital Signal Processing, 156, 104806.
[25]Geetha Devi, A., Borra, S. P. R., & Rajesh Kumar, P. (2025). A new multimodal medical image fusion framework using Convolution Neural Networks. Journal of Medical Engineering & Technology, 1-8.
[26]Shibu, T. M., Madan, N., Paramanandham, N., Kumar, A., & Santosh, A. (2025). Multi-modal brain image fusion using multi feature guided fusion network. Biomedical Signal Processing and Control, 100, 107060.
[27]Srinivas, Y., & Kumar, M. A. (2025). Robust multi-modal COVID-19 medical image registration using dense deep learning descriptor model. Biomedical Signal Processing and Control, 100, 107007.
[28]Wang, J., Yu, L., & Tian, S. (2025). Cross-attention interaction learning network for multi-model image fusion via transformer. Engineering Applications of Artificial Intelligence, 139, 109583.
[29]Hu, T., Nan, X., Zhou, X., Shen, Y., & Zhou, Q. (2025). A dual-stream feature decomposition network with weight transformation for multi-modality image fusion. Scientific Reports, 15(1), 7467.
[30]Shao, D., Yang, H., Ma, L., & Yi, S. (2025). AFPNet: An adaptive frequency-domain optimized progressive medical image fusion network. Biomedical Signal Processing and Control, 103, 107357.
[31]Feng, X., Yang, J., Qiu, G., Mu, J., Wu, X., Zhang, H., & Hu, K. (2025). MMIF-VAEFusion: An end-to-end multi-modal medical image fusion network using vector quantized variational auto-encoder. Biomedical Signal Processing and Control, 102, 107407.
[32]Wang, Y., Li, Z., Wang, J., Yang, L., Dong, B., Zhang, H., & Liu, J. (2025). MFF: A Deep Learning Model for Multi-Modal Image Fusion Based on Multiple Filters. IEEE Access.
[33]Bhosekar, S., Singh, P., & Garg, D. (2024, December). A Method Noise Based-Multi-Modal Medical Image Fusion Technique Using Non-Subsampled Shearlet Transform and Convolutional Neural Network. In 2024 4th International Conference on Innovative Sustainable Computational Technologies (CISCT) (pp. 1-5). IEEE.
[34]Srivastava, S., Bhatia, S., Agrawal, A. P., Jayswal, A. K., Godara, J., & Dubey, G. (2025). Deep adaptive fusion with cross-modality feature transition and modality quaternion learning for medical image fusion. Evolving Systems, 16(1), 17.
[35]Multimodal medical image datasets. Available at: https://www.researchgate.net/figure/Multimodal-medical-image-datasets_fig4_351121182 (Access date: 23-06-2025)
[36]Multimodal medical image dataset. Available at: https://github.com/bsun0802/Zero-Learning-Fast-Medical-Image-Fusion/tree/master/images/MRI-PET (Access date: 26-06-2025)
[37]Multimodal medical image dataset. Available at: https://github.com/ashna111/multimodal-image-fusion-to-detect-brain-tumors/tree/master/dataset. (Access date: 26-06-2025)