Published May 14, 2026 | Version 1.0
Preprint Open

The Evolution of Artificial Intelligence in Medical Imaging: Foundation Models and Clinical Integration(2024 - 2026)

Authors/Creators

  • 1. Department of Biomedical Engineering, SRM Institute of Science and Technology, Kattankulathur, India

Description

The rapid evolution of medical imaging has shifted from conventional structural assessment toward a digitally driven paradigm in which Artificial Intelligence (AI) plays a central role in diagnostic workflows. While traditional modalities including Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) have enabled non-invasive diagnosis, they remain limited by challenges such as ionizing radiation exposure, inter-observer variability, and increasing global imaging workloads.

This review synthesizes recent advancements in medical imaging AI from 2024 to 2026, with a focus on the transition from task-specific Convolutional Neural Networks (CNNs) to more generalizable architectures, including Vision Transformers (ViTs) and Medical Foundation Models. We examine the integration of Large Multi-modal Models (LMMs), which combine imaging data with clinical information such as electronic health records to enable more context-aware diagnostic reasoning.

In addition, the role of generative AI in image reconstruction is discussed, particularly in relation to radiation dose reduction and accelerated image acquisition. By addressing the persistent gap between algorithmic development and real-world clinical deployment, this review highlights how emerging AI frameworks are contributing to safer, more efficient, and increasingly personalized diagnostic practices.

Files

AI_Medical_Imaging_Review_2026 (1).pdf

Files (705.5 kB)

Name Size
md5:0f60890bb3012747ac56c75389135f84
705.5 kB Preview Download

Additional details

Audiovisual core

Subject part
Artificial Intelligence , Deep Learning , Medical Imaging

References

  • [1] B. Siewert and R. Ayyala, "Moral Distress, Moral Injury, and Burnout in Radiology Practice," Radiology, vol. 315, no. 2, p. e241174, May 2025, doi: 10.1148/radiol.241174. [2] J. S. Ryu, H. Kang, Y. Chu, and S. Yang, "Vision-language foundation models for medical imaging: a review of current practices and innovations," Biomed. Eng. Lett., vol. 15, no. 5, pp. 809–830, Sep. 2025, doi: 10.1007/s13534-025-00484-6. [3] E. U. Henry, O. Emebob, and C. A. Omonhinmin, "Vision Transformers in Medical Imaging: A Review," Nov. 18, 2022, arXiv: arXiv:2211.10043. doi: 10.48550/arXiv.2211.10043. [4] W. Khan, S. Leem, K. B. See, J. K. Wong, S. Zhang, and R. Fang, "A comprehensive survey of foundation models in medicine," IEEE Rev. Biomed. Eng., 2025, Accessed: Jan. 18, 2026. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10847310/ [5] C. Wei, S. Ren, K. Guo, H. Hu, and J. Liang, "High-resolution Swin transformer for automatic medical image segmentation," Sensors, vol. 23, no. 7, p. 3420, 2023. [6] M. R. Hosseinzadeh Taher, M. B. Gotway, and J. Liang, "Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-supervision," in Domain Adaptation and Representation Transfer, vol. 14293, L. Koch, M. J. Cardoso, E. Ferrante, K. Kamnitsas, M. Islam, M. Jiang, N. Rieke, S. A. Tsaftaris, and D. Yang, Eds., in Lecture Notes in Computer Science, vol. 14293. , Cham: Springer Nature Switzerland, 2024, pp. 94–104. doi: 10.1007/978-3-031-45857-6_10. [7] Z. Qin, H. Yi, Q. Lao, and K. Li, "Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study," Feb. 07, 2023, arXiv: arXiv:2209.15517. doi: 10.48550/arXiv.2209.15517. [8] B. Jandoubi and M. A. Akhloufi, "Multimodal artificial intelligence in medical diagnostics," Information, vol. 16, no. 7, p. 591, 2025. [9] L. Yang et al., "Advancing Multimodal Medical Capabilities of Gemini," May 06, 2024, arXiv: arXiv:2405.03162. doi: 10.48550/arXiv.2405.03162. [10] C. Wu, X. Zhang, Y. Zhang, H. Hui, Y. Wang, and W. Xie, "Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data," Nat. Commun., vol. 16, no. 1, p. 7866, 2025. [11] G. Aldosary, "Four-Dimensional Computed Tomography (4DCT) in Radiation Oncology: A Practical Overview," Curr. Radiol. Rep., vol. 12, no. 7, pp. 65–76, Apr. 2024, doi: 10.1007/s40134-024-00427-6. [12] W. Yinghui et al., "Artificial intelligence in four-dimensional imaging for motion management in radiation therapy," Artif. Intell. Rev., vol. 58, no. 4, p. 103, Jan. 2025, doi: 10.1007/s10462-025-11109-w. [13] K. Itatani et al., "New imaging tools in cardiovascular medicine: computational fluid dynamics and 4D flow MRI," Gen. Thorac. Cardiovasc. Surg., vol. 65, no. 11, pp. 611–621, Nov. 2017, doi: 10.1007/s11748-017-0834-5. [14] J. Oyeniyi and P. Oluwaseyi, "Emerging trends in AI-powered medical imaging: enhancing diagnostic accuracy and treatment decisions," Int. J. Enhanc. Res. Sci. Technol. Eng., vol. 13, no. 4, pp. 81–94, 2024. [15] R. Mladin et al., "The Role of 18F-FDG PET/CT in Monitoring Immunotherapy Response in Non-Small Cell Lung Cancer: Current Evidence and Challenges: A Narrative Review," Diagnostics, vol. 15, no. 21, p. 2754, 2025. [16] D. Albano et al., "Whole-body MRI for staging and follow-up of primary musculoskeletal tumours: a systematic review," Br. J. Radiol., p. tqag009, 2026. [17] L. Calderoni, L. Giovanella, and S. Fanti, "Endocrinology application of molecular imaging: current role of PET/CT," J. Endocrinol. Invest., vol. 47, no. 10, pp. 2383–2396, Jun. 2024, doi: 10.1007/s40618-024-02400-8. [18] A. G. Nappi et al., "Emerging role of [18F] FLT PET/CT in lymphoid malignancies: a review of clinical results," Hematol. Rep., vol. 16, no. 1, pp. 32–41, 2024. [19] J. I. Tudela Martínez et al., "Cardiac Magnetic Resonance in Adults: An Updated Review of the Diagnostic Approach to Major Heart Diseases," J. Clin. Med., vol. 14, no. 20, p. 7323, 2025. [20] E. Ferdian et al., "Cerebrovascular super-resolution 4D Flow MRI–Sequential combination of resolution enhancement by deep learning and physics-informed image processing to non-invasively quantify intracranial velocity, flow, and relative pressure," Med. Image Anal., vol. 88, p. 102831, 2023. [21] S. Sillanmäki, S. Hartikainen, and E. Ylä-Herttuala, "Review of Myocardial Ischemia, Scar, and Viability Estimation with Molecular Magnetic Resonance Imaging," Biomedicines, vol. 12, no. 8, p. 1681, 2024. [22] M. Dabiri, F. Dehghani Firouzabadi, K. Yang, P. B. Barker, R. R. Lee, and D. M. Yousem, "Neuroimaging in schizophrenia: A review article," Front. Neurosci., vol. 16, p. 1042814, 2022. [23] C. L. Mac Donald et al., "Neuroimaging Characterization of Acute Traumatic Brain Injury with Focus on Frontline Clinicians: Recommendations from the 2024 National Institute of Neurological Disorders and Stroke Traumatic Brain Injury Classification and Nomenclature Initiative Imaging Working Group," J. Neurotrauma, vol. 42, no. 13–14, pp. 1056–1064, Jul. 2025, doi: 10.1089/neu.2025.0079. [24] M. L. Raza et al., "Advancements in deep learning for early diagnosis of Alzheimer's disease using multimodal neuroimaging: challenges and future directions," Front. Neuroinformatics, vol. 19, p. 1557177, 2025. [25] G. Gatta et al., "Automated 3D ultrasound as an adjunct to screening mammography programs in dense breast: literature review and metanalysis," J. Pers. Med., vol. 13, no. 12, p. 1683, 2023. [26] J. Yang, Y. Zeng, and W. Yu, "Criteria for osteoporosis diagnosis: a systematic review and meta-analysis of osteoporosis diagnostic studies with DXA and QCT," eClinicalMedicine, vol. 83, 2025, Accessed: Jan. 31, 2026. [Online]. Available: https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(25)00176-2/fulltext [27] J. M. Albert, "Radiation Risk From CT: Implications for Cancer Screening," Am. J. Roentgenol., vol. 201, no. 1, pp. W81–W87, Jul. 2013, doi: 10.2214/AJR.12.9226. [28] M. Zhang, S. Gu, and Y. Shi, "The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review," Complex Intell. Syst., vol. 8, no. 6, pp. 5545–5561, Dec. 2022, doi: 10.1007/s40747-022-00724-7. [29] Y. Hafeez, K. Memon, M. S. Al-Quraishi, N. Yahya, S. Elferik, and S. S. A. Ali, "Explainable AI in diagnostic radiology for neurological disorders: a systematic review, and what doctors think about it," Diagnostics, vol. 15, no. 2, p. 168, 2025. [30] A. Kumar et al., "Artificial intelligence bias in medical system designs: a systematic review," Multimed. Tools Appl., vol. 83, no. 6, pp. 18005–18057, Jul. 2023, doi: 10.1007/s11042-023-16029-x. [31] M. H. U. Rehman, W. Hugo Lopez Pinaya, P. Nachev, J. T. Teo, S. Ourselin, and M. J. Cardoso, "Federated learning for medical imaging radiology," Br. J. Radiol., vol. 96, no. 1150, p. 20220890, 2023. [32] A. I. Pérez-Sanpablo, J. Quinzaños-Fresnedo, J. Gutiérrez-Martínez, I. G. Lozano- Rodríguez, and E. Roldan-Valadez, "Transforming Medical Imaging: The Role of Artificial Intelligence Integration in PACS for Enhanced Diagnostic Accuracy and Workflow Efficiency," Curr. Med. Imaging Former. Curr. Med. Imaging Rev., vol. 21, p. e15734056370620, Jun. 2025, doi: 10.2174/0115734056370620250403030638. [33] V. Muralidharan et al., "A scoping review of reporting gaps in FDA-approved AI medical devices," NPJ Digit. Med., vol. 7, no. 1, p. 273, 2024. [34] D. Queiroz, A. Carlos, A. Anjos, and L. Berton, "Fair foundation models for medical image analysis: Challenges and perspectives," ACM Trans. Comput. Healthc., vol. 7, no. 2, pp. 1–24, 2026. [35] J. C. Y. Seah, J. S. N. Tang, and A. Tran, "Drafting the Future: The Dawn of AI Report Generation in Radiology," Radiology, vol. 316, no. 1, p. e243378, Jul. 2025, doi: 10.1148/radiol.243378. [36] T. Talluri, "Interpretive Applications of Artificial Intelligence in Breast Radiology," in The Radiology AI Handbook, Elsevier, 2026, pp. 31–44. Accessed: Apr. 19, 2026. [Online]. Available: https://www.sciencedirect.com/science/chapter/edited-volume/pii/B9780323877602000049 [37] P. Rai et al., "Deep Learning–Based Acceleration in MRI: Current Landscape and Clinical Applications in Neuroradiology," Am. J. Neuroradiol., vol. 47, no. 1, pp. 9–16, 2026. [38] P. Rai et al., "Deep Learning–Based Acceleration in MRI: Current Landscape and Clinical Applications in Neuroradiology," Am. J. Neuroradiol., vol. 47, no. 1, pp. 9–16, 2026. [39] A. K. Adeniran et al., "The Role of Point-of-Care Ultrasound (POCUS) Powered by Artificial Intelligence in Trauma and Cardiac Arrest Assessment: A Narrative Review," SN Compr. Clin. Med., vol. 8, no. 1, p. 92, Mar. 2026, doi: 10.1007/s42399-026-02315-w. [40] Y. Qin et al., "A Review and Perspective of Techniques for Autonomous Robotic Ultrasound Acquisitions," Sensors, vol. 26, no. 7, p. 2081, 2026.