DIFFUSION AND TRANSFORMER-BASED DEEP LEARNING MODELS FOR MEDICAL IMAGE PROCESSING: A COMPREHENSIVE SURVEY
DOI:
https://doi.org/10.63458/ijerst.v4i3.164Keywords:
Deep Learning, Diffusion Models, Transformers, Medical ImagingAbstract
Deep learning has played an important role in improving medical image processing tasks such as image segmentation, reconstruction, and diagnosis. In recent years, diffusion models and transformer-based methods have gained attention due to their strong performance. Diffusion models are effective in generating and restoring images by learning from noise, while transformers help in capturing global features through attention mechanisms.This survey reviews the use of diffusion and transformer models in medical imaging, focusing on their applications, advantages, and limitations. It also discusses recent developments that combine both approaches and highlights future research directions for improving efficiency and accuracy in real-world medical applications
References
Y. Shi et al., “Diffusion Models for Medical Image Computing: A Survey,” Tsinghua Science and Technology, vol. 30, no. 1, pp. 1–20, 2025.
G. Webber et al., “Diffusion Models for Medical Image Reconstruction,” British Journal of Radiology AI, vol. 1, no. 1, 2024.
J. W. Kim et al., “Systematic Review of Hybrid Vision Transformer Architectures for Radiological Image Analysis,” Journal of Imaging Informatics in Medicine, vol. 38, pp. 3248–3262, 2025. (Springer)
H. Ramadan et al., “Medical Image Registration in the Era of Transformers: A Review,” Informatics in Medicine Unlocked, vol. 49, pp. 101540, 2024. (ResearchGate)
X. Liu et al., “Recent Progress in Transformer-Based Medical Image Analysis,” Computers in Biology and Medicine, vol. 165, pp. 107268, 2023. (ScienceDirect)
S. Khan et al., “Generative AI Models for Medical Image Enhancement: A Systematic Review,” International Journal of Medical Informatics, vol. 199, pp. 105903, 2025. (ScienceDirect)
B. Fei et al., “A Diffusion Model for Universal Medical Image Enhancement,” Communications Medicine, vol. 5, pp. 294, 2025. (Nature)
W. Wang et al., “Diffusion Models for Medical Image Denoising and Reconstruction,” Information Fusion, vol. 102, pp. 102045, 2025.
J. Pinaya et al., “Brain Imaging Generation Using Diffusion Models,” Medical Image Analysis, vol. 80, pp. 102487, 2023.
H. Chen et al., “Diffusion Models for MRI Reconstruction,” IEEE Transactions on Medical Imaging, vol. 43, no. 2, pp. 567–579, 2024.
Z. Wu et al., “Diffusion-Based Medical Image Segmentation: A Review,” Electronics, vol. 15, no. 7, pp. 1400, 2025.
X. Tu et al., “Diffusion Transformer for MRI Super-Resolution,” Computers in Biology and Medicine, vol. 172,pp. 108234, 2025.
S. Raminedi et al., “Multi-Modal Transformer Architecture for Medical Image Analysis and Automated Report Generation,” Scientific Reports, vol. 14, pp. 19281, 2024. (Nature)
Z. Liu et al., “Swin Transformer-Based Medical Image Analysis,” IEEE Transactions on Medical Imaging, vol. 43, no. 5, pp. 1345–1357, 2024.
J. Chen et al., “TransUNet: Transformers for Medical Image Segmentation,” Medical Image Analysis, vol. 85, pp. 102700, 2023.
Y. Tang et al., “Self-Supervised Vision Transformers for Medical Imaging,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 8, pp. 3890–3901, 2023.
S. Valanarasu et al., “Medical Transformer for Image Segmentation,” IEEE Transactions on Medical Imaging, vol. 42, no. 6, pp. 1602–1612, 2023.
Y. Zhang et al., “Vision Transformer-Based Diagnosis in Medical Imaging,” IEEE Access, vol. 11, pp. 98765–98778, 2023.
L. Chen et al., “Hybrid Diffusion-Transformer Models for Medical Image Reconstruction,” IEEE Access, vol. 12,pp. 45678–45690, 2024.
K. Wang et al., “Multimodal Diffusion Transformer Models for Medical Imaging,” IEEE Transactions on Medical Imaging, vol. 44, no. 1, pp. 112–125, 2025.
Z. Wu et al., “Spatial-Spectral Transformer-Based Diffusion Model for Image Denoising,” International Journal of Remote Sensing, vol. 46, no. 5, pp. 2100–2115, 2025.
Y. Li et al., “Knowledge-Controlled Diffusion Transformer for Medical Imaging,” IEEE Journal of Biomedical and Health Informatics, 2024.
J. Chen et al., “Foundation Models for Volumetric Medical Imaging,” Electronics, vol. 15, no. 6, pp. 1245, 2025.
M. Azad et al., “Diffusion Models in Medical Imaging: Recent Advances,” IEEE Reviews in Biomedical Engineering, 2026.
S. Pan et al., “Transformer-Based Diffusion Model for Medical Image Synthesis,” Physics in Medicine & Biology, vol. 68, no. 12, 2023.
Z. Sordo et al., “Comparative Analysis of Generative Models in Medical Imaging,” Journal of Imaging, vol. 11, no. 8, pp. 252, 2025.
H. Zhang et al., “High-Quality Medical Image Synthesis Using Diffusion Models,” Neural Computing and Applications, 2026.
C. Du et al., “Improving 3D Medical Imaging with Diffusion Models,” Pattern Recognition, vol. 150, pp. 110234, 2024.
Y. Xie et al., “UnetTransCNN: Integrating Transformers and CNNs for Medical Image Segmentation,” Frontiers in Oncology, vol. 15, pp. 1467672, 2025. (Frontiers)
Banerjee et al., “Hybrid Attention Models for Radiological Image Analysis,” Journal of Digital Imaging, vol. 38, pp. 2001–2015, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Anbumaheshwari K, Shobana R
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Statement
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Authors retain copyright of their articles and grant International Journal of Engineering Research in Science and Technology (IJERST) the right of first publication.
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The journal encourages open access and supports the global exchange of knowledge.
