Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers

A. S. Panayides; H. Chen; N. D. Filipovic; T. Geroski; J. Hou; K. Lekadir; K. Marias; G. K. Matsopoulos; G. Papanastasiou; P. Sarder; G. Tourassi; S. A. Tsaftaris; H. Fu; E. Kyriacou; C. P. Loizou; M. Zervakis; J. H. Saltz; F. E. Shamout; K. C.L. Wong; J. Yao; A. Amini; D. I. Fotiadis; C. S. Pattichis; M. S. Pattichis

doi:10.1109/JBHI.2025.3649496

Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers

A. S. Panayides
, H. Chen
, N. D. Filipovic
, T. Geroski
, J. Hou
, K. Lekadir
, K. Marias
, G. K. Matsopoulos
, G. Papanastasiou
, P. Sarder
, G. Tourassi
, S. A. Tsaftaris
, H. Fu
, E. Kyriacou
, C. P. Loizou
, M. Zervakis
, J. H. Saltz
, F. E. Shamout
, K. C.L. Wong
, J. Yao

A. Amini, D. I. Fotiadis, C. S. Pattichis, M. S. Pattichis

Computing & Computational Sciences Dir

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

Original language	English
Pages (from-to)	1187-1202
Number of pages	16
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	30
Issue number	2
DOIs	https://doi.org/10.1109/JBHI.2025.3649496
State	Published - Feb 2026

Funding

Received 1 December 2025; revised 9 December 2025; accepted 10 December 2025. Date of publication 31 December 2025; date of current version 4 February 2026. The work of G. Tourassi was supported by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The work of C.S. Pattichis was supported N. Prentza, who contributed to Explainable AI. The work of M. Zervakis was supported by M. Antonakakis, who contributed to Multimodal Fusion. (Corresponding author: M.S. Pattichis.) Please see the Acknowledgment section of this article for the author affiliations. Digital Object Identifier 10.1109/JBHI.2025.3649496

Keywords

Artificial intelligence (AI)
clinical workflow integration
computational pathology
convolutional neural networks (CNNs)
ethics
explainable AI
federated learning
foundation models
generative AI
medical imaging
medical video analysis
medical video analysis
multimodal fusion
regulatory compliance
transformers
trustworthy AI

Access to Document

10.1109/JBHI.2025.3649496

Cite this

Panayides, A. S., Chen, H., Filipovic, N. D., Geroski, T., Hou, J., Lekadir, K., Marias, K., Matsopoulos, G. K., Papanastasiou, G., Sarder, P., Tourassi, G., Tsaftaris, S. A., Fu, H., Kyriacou, E., Loizou, C. P., Zervakis, M., Saltz, J. H., Shamout, F. E., Wong, K. C. L., ... Pattichis, M. S. (2026). Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers. IEEE Journal of Biomedical and Health Informatics, 30(2), 1187-1202. https://doi.org/10.1109/JBHI.2025.3649496

@article{5085c7a58e8e437d9eeb78b0f0274a7b,

title = "Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers",

abstract = "Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.",

keywords = "Artificial intelligence (AI), clinical workflow integration, computational pathology, convolutional neural networks (CNNs), ethics, explainable AI, federated learning, foundation models, generative AI, medical imaging, medical video analysis, medical video analysis, multimodal fusion, regulatory compliance, transformers, trustworthy AI",

author = "Panayides, \{A. S.\} and H. Chen and Filipovic, \{N. D.\} and T. Geroski and J. Hou and K. Lekadir and K. Marias and Matsopoulos, \{G. K.\} and G. Papanastasiou and P. Sarder and G. Tourassi and Tsaftaris, \{S. A.\} and H. Fu and E. Kyriacou and Loizou, \{C. P.\} and M. Zervakis and Saltz, \{J. H.\} and Shamout, \{F. E.\} and Wong, \{K. C.L.\} and J. Yao and A. Amini and Fotiadis, \{D. I.\} and Pattichis, \{C. S.\} and Pattichis, \{M. S.\}",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2026",

month = feb,

doi = "10.1109/JBHI.2025.3649496",

language = "English",

volume = "30",

pages = "1187--1202",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "Institute of Electrical and Electronics Engineers",

number = "2",

}

Panayides, AS, Chen, H, Filipovic, ND, Geroski, T, Hou, J, Lekadir, K, Marias, K, Matsopoulos, GK, Papanastasiou, G, Sarder, P, Tourassi, G, Tsaftaris, SA, Fu, H, Kyriacou, E, Loizou, CP, Zervakis, M, Saltz, JH, Shamout, FE, Wong, KCL, Yao, J, Amini, A, Fotiadis, DI, Pattichis, CS & Pattichis, MS 2026, 'Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers', IEEE Journal of Biomedical and Health Informatics, vol. 30, no. 2, pp. 1187-1202. https://doi.org/10.1109/JBHI.2025.3649496

TY - JOUR

T1 - Position Paper

T2 - Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers

AU - Panayides, A. S.

AU - Chen, H.

AU - Filipovic, N. D.

AU - Geroski, T.

AU - Hou, J.

AU - Lekadir, K.

AU - Marias, K.

AU - Matsopoulos, G. K.

AU - Papanastasiou, G.

AU - Sarder, P.

AU - Tourassi, G.

AU - Tsaftaris, S. A.

AU - Fu, H.

AU - Kyriacou, E.

AU - Loizou, C. P.

AU - Zervakis, M.

AU - Saltz, J. H.

AU - Shamout, F. E.

AU - Wong, K. C.L.

AU - Yao, J.

AU - Amini, A.

AU - Fotiadis, D. I.

AU - Pattichis, C. S.

AU - Pattichis, M. S.

PY - 2026/2

Y1 - 2026/2

N2 - Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

AB - Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

KW - Artificial intelligence (AI)

KW - clinical workflow integration

KW - computational pathology

KW - convolutional neural networks (CNNs)

KW - ethics

KW - explainable AI

KW - federated learning

KW - foundation models

KW - generative AI

KW - medical imaging

KW - medical video analysis

KW - multimodal fusion

KW - regulatory compliance

KW - transformers

KW - trustworthy AI

UR - https://www.scopus.com/pages/publications/105028303138

U2 - 10.1109/JBHI.2025.3649496

DO - 10.1109/JBHI.2025.3649496

M3 - Article

C2 - 41474993

AN - SCOPUS:105028303138

SN - 2168-2194

VL - 30

SP - 1187

EP - 1202

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

IS - 2

ER -

Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this