Merchant SA, Merchant N, Varghese SL, Shaikh MJS. Large language models and large concept models in radiology: Present challenges, future directions, and critical perspectives. World J Radiol 2025; 17(11): 114754 [DOI: 10.4329/wjr.v17.i11.114754]
Corresponding Author of This Article
Suleman A Merchant, MD, Former Dean, Professor and Head, Department of Radiology, LTM Medical College and LTM General Hospital, Sion, Mumbai 400022, Maharashtra, India. suleman.a.merchant@gmail.com
Research Domain of This Article
Radiology, Nuclear Medicine & Medical Imaging
Article-Type of This Article
Review
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Nov 28, 2025 (publication date) through Nov 27, 2025
Times Cited of This Article
Times Cited (0)
Journal Information of This Article
Publication Name
World Journal of Radiology
ISSN
1949-8470
Publisher of This Article
Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA
Share the Article
Merchant SA, Merchant N, Varghese SL, Shaikh MJS. Large language models and large concept models in radiology: Present challenges, future directions, and critical perspectives. World J Radiol 2025; 17(11): 114754 [DOI: 10.4329/wjr.v17.i11.114754]
World J Radiol. Nov 28, 2025; 17(11): 114754 Published online Nov 28, 2025. doi: 10.4329/wjr.v17.i11.114754
Large language models and large concept models in radiology: Present challenges, future directions, and critical perspectives
Suleman A Merchant, Neesha Merchant, Shaju L Varghese, Mohd Javed S Shaikh
Suleman A Merchant, Department of Radiology, LTM Medical College and LTM General Hospital, Mumbai 400022, Maharashtra, India
Neesha Merchant, Department of Diagnostic Radiology, Medical Imaging, University of Toronto, Toronto M5G2C4, Ontario, Canada
Shaju L Varghese, Department of Imaging, Accura Diagnostic Centre, Mumbai 400014, Maharashtra, India
Mohd Javed S Shaikh, Department of Radiology, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA 02115, United States
Author contributions: Merchant SA was responsible for the conceptualization of the critical perspective, defining the scope and structure, conducting the primary literature searches and synthesis, and drafting the initial and final versions of the manuscript; Merchant N, Varghese SL, and Shaikh MJS performed supplementary literature searches, provided critical intellectual content throughout the analysis, and critically reviewed and revised the manuscript for scientific accuracy; and all authors have read and approved the final manuscript.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Suleman A Merchant, MD, Former Dean, Professor and Head, Department of Radiology, LTM Medical College and LTM General Hospital, Sion, Mumbai 400022, Maharashtra, India. suleman.a.merchant@gmail.com
Received: September 27, 2025 Revised: October 7, 2025 Accepted: November 3, 2025 Published online: November 28, 2025 Processing time: 61 Days and 8.4 Hours
Core Tip
Core Tip: Current capabilities, applications, limitations of large language models (LLMs) in radiology artificial intelligence (AI). LLMs transformed radiology AI, improved textual-analysis, workflow automation, clinical decision support. Challenges: Limited reasoning depth, inaccuracies. Transformative role of LLMs in radiology, their architectural foundations, clinical utility are discussed. LLM limitations, like token-level processing, hallucinations, and challenges in clinical adoption. Exploring new paradigm large concept models, having conceptual reasoning and multimodal integration to enhance clinical accuracy and reliability. Ethical, regulatory, and explainability considerations for AI tools in healthcare also discussed and a balanced and forward-looking view on AI’s role in radiology, covering both current innovations and anticipated advances through large concept models.
