Autors: Tsvetkova, D. S., Georgieva, V. M.
Title: Comparison of different fusion techniques on MRI and PSMA images of the prostate gland
Keywords: Medical image Fusion, MRI, Prostate imaging, PSMA

Abstract: Accurate visualization of the prostate gland is essential for effective diagnosis, treatment planning, and disease monitoring in prostate cancer. This study presents a comparative analysis of four image fusion techniques—Principal Component Analysis (PCA), Laplacian Pyramid, Curvelet Transform, and Wavelet Transform—applied to the multimodal fusion of Magnetic Resonance Imaging (MRI) and PSMA PET images of the prostate gland. Both modalities undergo spatial registration and modality-specific denoising according to their noise characteristics prior to fusion. Quantitative assessment of the fused images is performed using image quality metrics, including Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Entropy, Pearson Correlation Coefficient (PCC), and Mutual Information (MI). In addition, qualitative visual assessment is performed. The findings provide insights for selecting an optimal fusion strategy for prostate imaging and support the integration of multimodal fusion techniques into clinical prostate cancer workflows.

References

  1. W. Huang, J. Han, and L. Zhang, “A review of multimodal medical image fusion techniques,” J. Healthc. Eng., vol. 2020, Art. no. 8279342, 2020.
  2. M. Zubair et al., “A comprehensive review of techniques, algorithms, advancements, challenges, and clinical applications of multi-modal medical image fusion for improved diagnosis,” arXiv preprint arXiv:2505.14715, 2025.
  3. F. Luo, D. Wu, L. R. Pino et al., “A novel multimodal medical image fusion framework with edge enhancement and cross-scale transformer,” Sci. Rep., vol. 15, Art. no. 11657, 2025, doi: 10.1038/s41598-025-93616-y.
  4. G. Mehawed, M. J. Roberts, J. Bugeja, J. Dowling, K. Stewart, R. Gunasena, F. Malczewski, N. J. Rukin, and R. Murray, “A pilot study of PSMA PET/CT and MRI fusion for prostate cancer: Software to replace PET/MRI hardware,” J. Clin. Med., vol. 13, no. 23, Art. no. 7384, 2024, doi: 10.3390/jcm13237384.
  5. M. Eiber, G. Weirich, K. Holzapfel, M. Souvatzoglou, B. Haller, I. Rauscher et al., “Simultaneous 68Ga-PSMA HBED-CC PET/MRI improves the localization of primary prostate cancer,” Eur. Urol., vol. 70, pp. 829–836, 2016.
  6. M. Chen, Q. Zhang, C. Zhang, X. Zhao, G. Marra, J. Gao et al., “Combination of 68Ga-PSMA PET/CT and multiparametric MRI improves the detection of clinically significant prostate cancer: A lesion-by-lesion analysis,” J. Nucl. Med., vol. 60, pp. 944–949, 2019.
  7. H. Kaur, J. H. Lee, and R. S. Chora, “Image fusion techniques: A survey,” J. Healthc. Eng., vol. 2021, Art. no. 8279342, 2021.
  8. B. Meher, “A survey on region-based image fusion methods,” Inf. Fusion, vol. 48, pp. 119–144, 2019.
  9. B. Huang, X. Ma, and D. Shang, “A review of multimodal medical image fusion techniques,” BioMed Res. Int., vol. 2020, Art. no. 7195632, 2020.
  10. M. Pajares and J. M. de la Cruz, “A wavelet-based image fusion tutorial,” Pattern Recognit., vol. 37, no. 9, pp. 1855–1872, 2004.
  11. B. Li, Z. Yang, and J. Wang, “Medical image fusion based on discrete wavelet transform and local energy,” Comput. Biol. Med., vol. 64, pp. 1–12, 2015.
  12. V. M. Georgieva, P. P. Petrov, D. S. Tsvetkova and L. B. Laskov, "MRI/SPECT Image Fusion of Brain Based on Multi-Scale Wavelet Decomposition, "56th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), pp. 85-88, 2021.
  13. D.Tsvetkova, V.Georgieva, "Wavelet-Based Image Fusion of PreRegistered MRI and PSMA Scans of the Prostate Gland", New Approaches for Multidimensional Signal Processing (Proceeding of 6th International Workshop NAMSP 2025), Springer, in printing.
  14. J. Ma and G. Plonka, “The curvelet transform: A review of recent applications,” in Numerical Mathematics and Advanced Applications, G. Kreiss, P. Lötstedt, A. Målqvist, and M. Viklund, Eds. Berlin, Heidelberg: Springer, 2009, pp. 753–762.
  15. T. Zhou, J. Lu, and Y. Wang, “Deep learning methods for medical image fusion: A review,” Inf. Fusion, vol. 91, pp. 174–203, 2023.
  16. D. Tsvetkova, V. Georgieva and Y. Gramatikov, "A Voxelmorph-Based Neural Network Approach for Multimodal Image Registration of MRI and PSMA Images of the Prostate Gland," 2025 60th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), Ohrid, North Macedonia, 2025, pp. 1-4, doi: 10.1109/ICEST66328.2025.11098347.
  17. D. Tsvetkova, "Training Unsupervised Deep Learning Model for Multimodal Prostate Im age Registration," 2025 60th International Scientific Conference on Information, Commu nication and Energy ystems and Technologies (ICEST), Ohrid, North Macedonia, 2025, pp. 1-4, doi: 10.1109/ICEST66328.2025.11098192.

Issue

National Conference with International Participation, TELECOM, pp. 1-4, 2026, Albania, https://doi.org/10.1109/TELECOM66943.2025.11304093

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus