Autors: Tsvetkova, D. S., Georgieva, V. M., Gramatikov Y.
Title: A Voxelmorph-Based Neural Network Approach for Multimodal Image Registration of MRI and PSMA Images of the Prostate Gland
Keywords: Image Registration, MRI, Neural Networks, Prostate Imaging, PSMA

Abstract: Prostate cancer is still a major health problem for men worldwide. This problem emphasizes the importance of accurate diagnosis, early detection and treatment planning. Imaging techniques like multimodal image fusion, particularly the combination of MRI/CT, CT/PSMA-PET and MRI/PSMA-PET scans, has proven to be the highly beneficial in diagnosing prostate cancer, due to the combination of the anatomical accuracy and the functionality of different modalities. The first problem is the process of aligning the multimodal images in a common coordinate system to achieve accurate registration. This study describes a 3-stage algorithm for the registration of real prostate MRI and PSMA images that utilizes a Voxelmorph-based neural network. The proposed deep learning-based approach is evaluated against that of some conventional non-deep learning algorithms. Experimental results show that this novel approach outperforms current conventional methods like ANTs and BRAINs in multimodal image registration of the prostate gland, achieving higher accuracy and speed. These results show how significant prostate imaging problems can be solved with deep learning.

References

  1. J. K. Aggarwal, editor (2013) "Multisensor fusion for computer vision", Springer Science & Business Media 99
  2. S. Sarkar, S. Das. "A Review of Imaging Methods for Prostate Cancer Detection", Biomed Eng Comput Biol. 2016 Mar 2;7(Suppl 1): 1-15. doi: 10. 4137/BECB. S34255. PMID: 26966397; PMCID: PMC4777886.
  3. A. P. Sharma et al., "Accuracy of combined multi-parametric MRI and PSMA PET-CT in diagnosing localized prostate cancer: Newer horizons for a biopsy-free pathway, " Eur. J. Hybrid Imaging, vol. 7, no. 1, p. 24, Nov. 2023, doi: 10. 1186/s41824-023-00182-5.
  4. F. Darzi and T. Bocklitz, "A Review of Medical Image Registration for Different Modalities, "Bioengineering, vol. 11, no. 8, p. 786, Aug. 2024.
  5. J. Fu, X. Zhang, Z. Lei, C. Feng, and D. Shen, "Deep Learning in Medical Image Registration: A Review, " in IEEE Transactions on Image Processing, vol. 31, pp. 3322-3340, 2022, doi: 10. 1109/TIP. 2022. 3146489.
  6. Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2019). VoxelMorph: A Learning Framework for Deformable Medical Image Registration. IEEE Transactions on Medical Imaging.
  7. B. B. Avants, N. J. Tustison, G. Song, P. A. Cook, A. Klein, and J. C. Gee. A reproducible evaluation of ants similarity metric performance in brain image registration. Neuroimage, 54(3): 2033-44, 2011. ISSN 1053 8119. doi: 10. 1016/j. neuroimage. 2010. 09. 025.
  8. H. Johnson, G. Harris, and K. Williams, "BRAINSFit: Mutual Information Registrations of Whole-Brain 3D Images, Using the Insight Toolkit, " The Insight Journal, Oct. 2007.

Issue

60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, pp. 1-4, 2025, Macedonia, https://doi.org/10.1109/ICEST66328.2025.11098347

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