Scholarlink

Background <p>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.</p> Objective <p>To assess the ability of widely available, general-purpose generative AI applications to produce synthetic pediatric neuroradiology images of teaching quality.</p> Materials and methods <p>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.</p> Results <p>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 &gt;50% criterion compared to Gemini 3 Pro (12.7% [14/110] vs. 4.5% [5/110]; <i>P</i>=0.031).</p> Conclusion <p>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.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月6日

查看全文
  • 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

摘要

Background

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.

Objective

To assess the ability of widely available, general-purpose generative AI applications to produce synthetic pediatric neuroradiology images of teaching quality.

Materials and methods

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.

Results

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).

Conclusion

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.

Graphical abstract