International Journal of Electronics and Computer Applications

Volume: 2 Issue: 1

  • Open Access
  • Original Article

Emerging Advances in Multimodal Imaging and Fusion Techniques

Arati J Vyavahare1∗, Diksha Anand Sawant2

1Professor, ENTC, Modern College of Engineering, Pune-05, Maharashtra, India
2Student, Modern College of Engineering, Pune-05, Maharashtra, India

Corresponding author.Email: [email protected]

Year: 2025, Page: 29-31, Doi: https://doi.org/10.70968/ijeaca.v2i1.D1019

Received: March 20, 2025 Accepted: May 10, 2025 Published: June 18, 2025

Abstract

Multimodal image fusion is a rapidly evolving domain that combines complementary information from different imaging modalities into a unified representation, enhancing visual perception and decision-making in areas such as medical diagnostics, surveillance, and remote sensing. This paper surveys the taxonomy of multimodal fusion tasks, discusses classical and emerging deep learning-based methods including convolutional neural networks, autoencoders, generative adversarial networks, and transformer-based architectures and outlines key evaluation metrics. Through this comprehensive review, we highlight recent trends, performance benchmarks, and future directions for effective multimodal image fusion.

Keywords: Emerging Advances in Multimodal Imaging and Fusion Techniques

References

  1. Lv W, Ashrafinia S, Ma J, Lu L, Rahmim A. Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck CancerIEEE Journal of Biomedical and Health Informatics. 2020;24(8):2268–2277. Available from: https://doi.org/10.1109/jbhi.2019.2956354

  2. Zhang Y, et al. Joint Modeling of Spatial Dependencies Across Multiple Subjects in Multiplexed Tissue ImagingIEEE Transactions on Medical Imaging. 2025. Available from: https://arxiv.org/abs/2504.02693

  3. Bhardwaj S, et al. Revolutionizing Tumor Detection and Classification in Multimodality Imaging: Deep Learning Methods and ApplicationsProc. IEEE Int. Conf. Biomed. Imaging (ISBI). 2024;p. 103–107.

  4. Zhang Y, et al. Attention-Map Augmentation for Hypercomplex Breast Cancer ClassificationIEEE Trans. Med. Imaging. 2025;44(9):1456–1467.

  5. Chen M, Wang L, Khosravi A, Navab N. AI-powered Interpretable Imaging Phenotypes Noninvasively Characterize Tumor Microenvironment in Breast CancerNPJ Breast Cancer. 2023;9(55):1–11.

  6. Liu K, et al. Current Status and Future Prospects of Molecular Imaging in Targeting the Tumor Immune MicroenvironmentJ. Nanobiotechnol. 2024;21(3):1–15.

  7. Alavi M, et al. Artificial Intelligence in Four-Dimensional Imaging for Motion Management in Radiation TherapyArtif. Intell. Rev. 2024;68(4):1245–1267.

  8. Alavi M, et al. AI Applications in 4D Imaging for Radiation Therapy: State of the ArtProc. IEEE Eng. Med. Biol. Soc. (EMBC). 2024;p. 567–571.

  9. Alavi M, et al. Artificial Intelligence-Assisted Multimodal Imaging for the Clinical Applications of Breast Cancer: A Bibliometric AnalysisIEEE Trans. Med. Imaging. 2025;44(8):1345–1356.

  10. Chen S, et al. Diff4MMLiTS: Advanced Multimodal Liver Tumor Segmentation via Diffusion-Based Image Synthesis and AlignmentIEEE Trans. Biomed. Eng. 2024;72(6):789–800. Available from: https://arxiv.org/abs/2412.20418

  11. Gu Y, Huang H, Tong Q, Cao M, Ming W, Zhang R, et al. Multi-View Radiomics Feature Fusion Reveals Distinct Immuno-Oncological Characteristics and Clinical Prognoses in Hepatocellular CarcinomaCancers. 2023;15(8):2338. Available from: https://dx.doi.org/10.3390/cancers15082338

  12. Li H, Zhou X, Zhang W, Fang J. 4D-ACFNet: A 4D Attention Mechanism-Based Prognostic Framework for CRLM. In: Proc. ACM Int. Conf. Multimedia (MM’25). (pp. 456-465) 2025.

  13. Bhardwaj S, et al. Revolutionizing Tumor Detection and Classification in Multimodality Imaging Based on Deep Learning Approaches: Methods, Applications, and LimitationsJ. X-ray Sci. Technol. 2024;31(2):233–245.

Cite this article

Vyavahare AJ, Sawant DA. (2025). Emerging Advances in Multimodal Imaging and Fusion Techniques. International Journal of Electronics and Computer Applications. 2(1): 29-31. https://doi.org/10.70968/ijeaca.v2i1.D1019

Views
7
Downloads
4
Citations