The Rise of Deepfake Medical Imaging: Radiologists’ Diagnostic Accuracy in Detecting ChatGPT-generated Radiographs
Radiology · 01.03.2026 · 318 (3)
DOI: 10.1148/radiol.252094 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology, erschienen am 01.03.2026. Verfasst von Mickael Tordjman und 26 weiteren Autor:innen. Beteiligte Einrichtung: BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY 10029. Hauptthemen laut MEDLINE: Large Language Models, Radiologists. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 22 Literaturangaben.
Abstract (Originalsprache)
Synthetic radiographs, including OpenAI’s ChatGPT-generated ones, are not easily distinguishable from authentic radiographs by either radiologists or large language models; physician training and dedicated tools are crucial to mitigate risks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY 10029.
- Department of Diagnostic, Molecular, and Interventional Radiology, Mount Sinai Hospital, New York, NY.
- Department of Radiology, Hôpital Raymond-Poincaré, AP-HP, Garches, France.
- Department of Radiology, Hôpital Cochin, AP-HP, Paris, France.
- Leonard de Vinci Medical Center, Paris, France.
- Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY.
ORCID-Profile: Mickael Tordjman, Murat Yuce, Fadila Mihoubi Bouvier, Anis Meribout, Ian Bolger, Efe Ozkaya, Himanshu Joshi, Rayane El Rahi, Ashwin Singh Parihar, Carolyn Horst, Samet Ozturk, Muhammed Edip Isleyen, Ahmet Tan Cimilli, Timothy Deyer, Rola Husain, Zahi A Fayad, Xueyan Mei, Bachir Taouli
Zitieren
APA
Tordjman, M., Yuce, M., Ammar, A., Huang, M., Mihoubi Bouvier, F., Lacroix, M., Meribout, A., Bolger, I., Ozkaya, E., Joshi, H., Geahchan, A., El Rahi, R., Almansour, H., Parihar, A. S., Horst, C., Ozturk, S., Isleyen, M. E., Pamuk, G. G., Cimilli, A. T., …, & Taouli, B. (2026). The Rise of Deepfake Medical Imaging: Radiologists’ Diagnostic Accuracy in Detecting ChatGPT-generated Radiographs. Radiology, 318(3). https://doi.org/10.1148/radiol.252094
Vancouver
Tordjman M, Yuce M, Ammar A, Huang M, Mihoubi Bouvier F, Lacroix M, et al. The Rise of Deepfake Medical Imaging: Radiologists’ Diagnostic Accuracy in Detecting ChatGPT-generated Radiographs. Radiology. 2026;318(3). doi:10.1148/radiol.252094
BibTeX
@article{Tordjman2026,
author = {Tordjman, Mickael and Yuce, Murat and Ammar, Amine and Huang, Mingqian and Mihoubi Bouvier, Fadila and Lacroix, Maxime and Meribout, Anis and Bolger, Ian and Ozkaya, Efe and Joshi, Himanshu and Geahchan, Amine and El Rahi, Rayane and Almansour, Haidara and Parihar, Ashwin Singh and Horst, Carolyn and Ozturk, Samet and Isleyen, Muhammed Edip and Pamuk, Gul Gizem and Cimilli, Ahmet Tan and Deyer, Timothy and Calinghen, Arvin and Guillo, Enora and Husain, Rola and Laredo, Jean-Denis and Fayad, Zahi A and Mei, Xueyan and Taouli, Bachir},
title = {The Rise of Deepfake Medical Imaging: Radiologists’ Diagnostic Accuracy in Detecting ChatGPT-generated Radiographs},
journal = {Radiology},
year = {2026},
volume = {318},
number = {3},
doi = {10.1148/radiol.252094}
}
EUVIMED