文献速递技术与安全CTMRUSDR

放射科医师能否区分AI生成影像与真实影像?

Real or not real? Can radiologists distinguish artificial intelligence generated radiological images from real ones?
PubMed 文献 · Clin Radiol · 2026-07-16

本研究通过在线问卷纳入182名放射科医师,要求对10张真实影像和20张AI生成影像进行分类。结果显示每位医师正确识别率中位数为77.8%,AI生成与真实影像的正确率无显著差异。正确率受亚专科专长影响,但与工作年限及AI熟悉度无关。

要点

  • 放射科医师仅能正确识别约四分之三的AI生成影像,存在误判风险。
  • 超声和X线影像比CT、MRI更易被正确识别。
  • 具有相关亚专科兴趣的医师分类正确率更高,阅片时可关注专科经验价值。

核心结论

  • 放射科医师仅能正确识别约四分之三的AI生成影像,正确率受亚专科专长影响,但与工作年限及AI熟悉度无关。

研究设计与样本

  • 采用在线问卷调查的研究设计,AI生成影像基于Stable Diffusion v2.1的Dreambooth微调方法生成。
  • 共182名放射科医师完成问卷,要求对10张真实影像和20张AI生成影像进行分类并给出置信度评分(1最低、5最高)。

关键影像表现/征象

  • 超声和X线影像的正确识别率高于CT和MRI等断层影像(分别为88%、91%、70%和77%)。

诊断标准与关键数值

  • 每位医师正确识别影像的比例中位数为77.8%(四分位距IQR 70.0, 86.7%)。
  • AI生成影像的正确识别率为75.0%(IQR 70.5, 87.1%),真实影像为83.4%(IQR 74.2, 92.6%),两者差异p=0.19。
  • 超声、X线、CT和MRI的正确识别率分别为88%、91%、70%和77%,差异p=0.015。
  • AI生成与真实影像的平均置信度分别为3.50±0.23和3.56±0.23,差异p=0.49。
  • 有相关亚专科兴趣的医师正确分类率为80.7±1.3%,无相关兴趣者为76.9±0.8%,差异p=0.012。

临床应用与阅片要点

  • 阅片时对AI生成影像需保持警惕,不能仅凭主观经验完全排除造假可能。
  • 超声和X线影像的识别相对容易,CT和MRI影像误判风险更高,应加强关注。
  • 工作年限和AI熟悉度并不能提高识别能力,相关亚专科专长才是更有用的判断基础。

局限性

  • 本研究仅使用一种AI生成方法,可能不足以代表所有类型的AI生成放射影像。
  • 问卷形式与真实临床阅片场景存在差异,结果的外推性受限。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

AIM: Artificial intelligence (AI) models can create radiological images. We aimed to determine whether radiologists could distinguish AI-generated from real images, and factors associated with correct classification.

MATERIALS AND METHODS: AI-generated images were made using an implementation of the Dreambooth fine-tuning approach applied to Stable Diffusion v2.1. Radiologists were asked to classify images as real (n = 10) or AI-generated (n = 20) and their confidence in this decision (1 least, 5 most) in an online form.

RESULTS: 182 radiologists completed the survey. The median proportion of correctly identified images per respondent was 77.8% (interquartile range, IQR 70.0, 86.7%), with no difference between AI-generated (75.0%, IQR 70.5, 87.1%) and real images (83.4%, IQR 74.2, 92.6%, p = 0.19). Ultrasound and X-ray were more likely to be correctly identified than cross-sectional images like CT or MRI (88%, 91%, 70% and 77% respectively, p = 0.015). Mean confidence was similar for AI-generated and real images (3.50 ± 0.23 versus 3.56 ± 0.23, p = 0.49). There was no difference in classification based on number of years of experience (p = 0.57) or familiarity with AI (p = 0.37). However, radiologists with relevant specialist interests were more likely to correctly classify images (80.7 ± 1.3% versus 76.9 ± 0.8%, p = 0.012).

CONCLUSIONS: Radiologists were only able to correctly identify three-quarters of AI-generated images. This was impacted by sub-specialist expertise but not the number of years of experience or familiarity with AI.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Cronshaw, Williams. Real or not real? Can radiologists distinguish artificial intelligence generated radiological images from real ones? Clin Radiol. 2026. PMID: 42570571. doi:10.1016/j.crad.2026.107438

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。