Widely available, general-purpose generative AI applications for radiology education: determining the teaching quality of synthetic pediatric neuroradiology images

Thomas P Reith; Donna M D'Alessandro; Krishnakumari A Modi; Mohammed Sabawi; Catherina S Zadeh; Mikhael G Sebaaly; Lillian M Lai; Takashi Shawn P Sato; Simon C Kao; Yutaka Sato; Michael P D'Alessandro

doi:10.1007/s00247-026-06708-w

Back

Widely available, general-purpose generative AI applications for radiology education: determining the teaching quality of synthetic pediatric neuroradiology images

Journal article

Open access

Peer reviewed

Widely available, general-purpose generative AI applications for radiology education: determining the teaching quality of synthetic pediatric neuroradiology images

Thomas P Reith, Donna M D'Alessandro, Krishnakumari A Modi, Mohammed Sabawi, Catherina S Zadeh, Mikhael G Sebaaly, Lillian M Lai, Takashi Shawn P Sato, Simon C Kao, Yutaka Sato, …

Pediatric radiology

07/06/2026

DOI: 10.1007/s00247-026-06708-w

PMID: 42405980

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1007/s00247-026-06708-wView

Published (Version of record) Open Access

Abstract

Artificial intelligence (AI) is increasingly incorporated into medical education. Widely available, general-purpose generative AI applications are increasingly capable of producing high-fidelity synthetic medical images, which may have potential educational uses. To assess the ability of widely available, general-purpose generative AI applications to produce synthetic pediatric neuroradiology images of teaching quality. Ten significant diagnostic errors in pediatric neuroradiologic emergencies were identified and divided into 22 individual clinical scenarios. Two widely available, general-purpose generative AI applications, GPT-5 (OpenAI, San Francisco, CA) and Gemini 3 Pro with the Nano Banana Pro image-generation engine (Google, Mountain View, CA), were prompted to generate five separate images for each scenario, yielding a total of 220 images. Eight fellowship-trained pediatric radiologists independently assessed each image for teaching quality. Ratings were recorded and analyzed. Differences between applications were evaluated using Fisher's exact test. Overall, 8.6% of generated images (19/220) were deemed suitable for teaching by more than half of the pediatric radiologists. GPT-5 produced a higher proportion of acceptable images meeting this >50% criterion compared to Gemini 3 Pro (12.7% [14/110] vs. 4.5% [5/110]; P=0.031). At present, widely available, general-purpose generative AI applications should not be used to produce synthetic radiological images for educational purposes. Inaccuracies and inconsistencies limit reliability and may actively impair learning.

Generative adversarial networks

Neuroradiology

Generative AI

UIOWA OA Agreement

Details

Title: Subtitle: Widely available, general-purpose generative AI applications for radiology education: determining the teaching quality of synthetic pediatric neuroradiology images
Creators: Thomas P Reith - Northwestern University
Donna M D'Alessandro - University of Iowa
Krishnakumari A Modi - University of Iowa
Mohammed Sabawi - University of Iowa
Catherina S Zadeh - Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
Mikhael G Sebaaly - University of Iowa
Lillian M Lai - University of Iowa
Takashi Shawn P Sato - University of Iowa, Radiology
Simon C Kao - University of Iowa
Yutaka Sato - University of Iowa
Michael P D'Alessandro - University of Iowa
Resource Type: Journal article
Publication Details: Pediatric radiology
DOI: 10.1007/s00247-026-06708-w
PMID: 42405980
NLM abbreviation: Pediatr Radiol
ISSN: 1432-1998
eISSN: 1432-1998
Publisher: Springer Nature
Language: English
Electronic publication date: 07/06/2026
Academic Unit: Radiology; Stead Family Department of Pediatrics; General Pediatrics and Adolescent Medicine
Record Identifier: 9985179957002771

Metrics

5 Record Views