Comparative Analysis of DCT, DWT& CNN Based Medical Image Fusion For PET-MRI

Authors

  • G. Ramesh Babu
  • K. Nilesh Sai
  • G .Himaja
  • K .Harish
  • G .Chaitanya
  • K .Rohit

Keywords:

Medical Image Fusion, Discrete Wavelet Transform (DWT), PET-MRI Integration, Multimodal Imaging, Wavelet-Based Fusion, MATLAB Implementation, Diagnostic Enhancement.

Abstract

Medical image fusion is the process of integrating complimentary information from many imaging modalities, and it significantly increases the accuracy of diagnosis. In this research, we develop a fusion approach based on the discrete wavelet transform (DWT) for PET-MRI image integration using MATLAB. Both PET and MRI images must be frequency subband decomposed before an energy-based fusion rule is applied and the fused image is reconstructed using the inverse discrete wavelet transform. The proposed technique preserves the spatial information gained from MRI while maintaining the functional insights gained from PET. Performance is evaluated using metrics like Mutual Information (MI), the Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index (SSIM). The tests' comparative results demonstrate that DWT-based fusion outperforms conventional fusion techniques in terms of effectively enhancing contrast and structural integrity. Clinical decision-making is aided by the enhanced visibility of lesions due to the combined images. The findings of this research show that wavelet-based fusion may prove to be a computationally efficient approach for applications involving multimodal medical imaging. Future work will use deep learning enhancements to further automate procedures.

Downloads

Download data is not yet available.

References

H. Li, L. Wu, and J. K. Aggarwal, “Medical image fusion using discrete wavelet transform, ” IEEE Transactions on Medical Imaging, vol. 30, no. 5, pp. 1192-1203, May 2011, doi: 10.1109/TMI.2011.2113374.

Z. Zhang, H. Peng, and B. Lei, “A novel PET-MRI image fusion algorithm based on wavelet transform and energy weighting, ” IEEE Access, vol. 7, pp. 109576-109587, Aug. 2019, doi: 10.1109/ACCESS.2019.2933245.

C. Wang and X. Liu, “Multimodal medical image fusion based on DWT and CNN feature learning, ” IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 8, pp. 2316-2327, Aug. 2020, doi: 10.1109/JBHI.2020.2994562.

S. Patel and P. Bhatt, “A comparative research of DWT, DCT, and PCA-based image fusion techniques, ” International Conference on Signal Processing and Communication (ICSPC), Coimbatore, India, pp. 1-6, Dec. 2018, doi: 10.1109/ICSPC.2018.8549691.

A. Singh, R. Kumar, and J. Jha, “An efficient medical image fusion framework using wavelet and morphological processing, ” IEEE Sensors Journal, vol. 20, no. 12, pp. 6564-6572, Jun. 2020, doi: 10.1109/JSEN.2020.2986423.

P. Mohanty and R. Panigrahi, “PET and MRI image fusion using discrete wavelet transform and region-based feature extraction, ” IEEE International Conference on Computational Intelligence in Data Science (ICCIDS), Chennai, India, pp. 1-6, Mar. 2021, doi: 10.1109/ICCIDS.2021.9450993.

M. J. James, S. H. A. Mohammed, and A. M. Khan, “DWT-based multimodal image fusion: A comprehensive review, ” IEEE Reviews in Biomedical Engineering, vol. 14, pp. 162-176, 2021, doi: 10.1109/RBME.2021.3053948.

L. Yin, T. Chen, and J. Xu, “Medical image fusion for disease diagnosis using dual-tree complex wavelet transform and deep learning, ” IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 5, pp. 2648-2658, May 2020, doi: 10.1109/TIM.2019.2946588.

X. Zhang and H. Sun, “A novel PET-MRI image fusion approach using modified wavelet transform and sparse representation, ” IEEE International Conference on Image Processing (ICIP), Abu Dhabi, UAE, pp. 4567-4571, Sep. 2020, doi: 10.1109/ICIP40778.2020.9191172.

J. Wang, R. Chen, and L. Qiao, “Performance analysis of wavelet-based image fusion techniques for medical imaging applications, ” IEEE Transactions on Biomedical Engineering, vol. 68, no. 3, pp. 873-882, Mar. 2021, doi: 10.1109/TBME.2020.3029789.

Downloads

Published

2025-05-19

How to Cite

1.
Babu GR, Sai KN, G .Himaja G .Himaja, K .Harish K .Harish, G .Chaitanya G .Chaitanya, K .Rohit K .Rohit. Comparative Analysis of DCT, DWT& CNN Based Medical Image Fusion For PET-MRI. J Neonatal Surg [Internet]. 2025May19 [cited 2025Sep.21];14(24S):968-974. Available from: https://jneonatalsurg.com/index.php/jns/article/view/6091

Issue

Vol. 14 No. 24S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.