利用人工智能提升人类表现:使用合成图像进行高效的视网膜疾病检测训练
研究设计了一门基于网络的课程,使用600张由稳定扩散模型生成的合成超广角视网膜图像,训练161名实习视能矫正师检测五类视网膜疾病和正常眼底。学生在训练前后各接受一次超广角和标准视野图像测试,超广角图像诊断准确率从43.6%提升至74.1%(p<0.0001),标准视野图像从42.7%提升至68.7%(p<0.0001)。
要点
- 合成超广角视网膜图像可有效用于医学教育,学生平均53分钟完成课程。
- 超广角图像诊断准确率从43.6%升至74.1%(p<0.0001),接近已发表AI模型的73.3%。
- 标准视野图像准确率从42.7%升至68.7%(p<0.0001),超过AI模型的40%。
核心结论
- 合成图像可有效用于医学教育。
- 人类对新情况的稳健性高于AI模型,凸显人类判断在医学诊断中的关键作用。
研究设计与样本
- 研究设计了一门基于网络的课程,使用600张合成超广角视网膜图像。
- 合成图像由稳定扩散(stable diffusion)大规学生成基础模型生成,该模型用6285张真实超广角图像微调,涵盖五类视网膜疾病(年龄相关性黄斑变性、青光眼、糖尿病视网膜病变、视网膜脱离和视网膜静脉阻塞)及正常。
- 161名实习视能矫正师参加课程,在训练前后各接受一次测试,测试包含超广角图像和标准视野图像各120张真实患者图像(每类20张),两次测试之间有冷却期。
主要发现
- 学生平均53分钟完成课程,诊断准确率显著提高。
- 超广角图像准确率从43.6%升至74.1%(p<0.0001,配对t检验),接近已发表最先进AI模型的73.3%。
- 标准视野图像准确率从42.7%升至68.7%(p<0.0001),超过最先进AI模型的40%。
局限性
- 原文未报告局限性。
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)。
原文
BACKGROUND: Artificial intelligence (AI) in medical imaging diagnostics has huge potential, but human judgement is still indispensable. We propose an AI-aided teaching method that leverages generative AI to train students on many images while preserving patient privacy. METHODS: A web-based course was designed using 600 synthetic ultra-widefield (UWF) retinal images to teach students to detect disease in these images. The images were generated by stable diffusion, a large generative foundation model, which we fine-tuned with 6285 real UWF images from six categories: five retinal diseases (age-related macular degeneration, glaucoma, diabetic retinopathy, retinal detachment and retinal vein occlusion) and normal. 161 trainee orthoptists took the course. They were evaluated with two tests: one consisting of UWF images and another of standard field (SF) images, which the students had not encountered in the course. Both tests contained 120 real patient images, 20 per category. The students took both tests once before and after training, with a cool-off period in between. RESULTS: On average, students completed the course in 53 min, significantly improving their diagnostic accuracy. For UWF images, student accuracy increased from 43.6% to 74.1% (p<0.0001 by paired t-test), nearly matching the previously published state-of-the-art AI model's accuracy of 73.3%. For SF images, student accuracy rose from 42.7% to 68.7% (p<0.0001), surpassing the state-of-the-art AI model's 40%. CONCLUSION: Synthetic images can be used effectively in medical education. We also found that humans are more robust to novel situations than AI models, thus showcasing human judgement's essential role in medical diagnosis.
引用
- Tabuchi H, Engelmann J, Maeda F, et al. Using artificial intelligence to improve human performance: efficient retinal disease detection training with synthetic images. Br J Ophthalmol. 2024. PMID: 38485215. doi:10.1136/bjo-2023-324923
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。