用合成影像训练肺炎检测模型，真实数据上表现优异。
Recognizing Pneumonia in Real-World Chest X-rays with a Classifier Trained with Images Synthetically Generated by Nano Banana
- 用谷歌新模型Nano Banana生成肺部X光片合成数据训练分类器
- 在真实数据集上达AUROC 0.923，AUPR 0.900，效果接近真实数据训练
- 适合医疗AI研发者关注合成数据应用前景
我们使用谷歌最新发布的图像生成与编辑模型Nano Banana生成的合成胸部X光片（CXR）训练分类器。在仅用合成数据训练的情况下，该分类器在2018年RSNA肺炎检测数据集（14,863张CXRs）上达到AUROC 0.923（95%置信区间：0.919–0.927）和AUPR 0.900（95%置信区间：0.894–0.907）；在Chest X-Ray数据集（5,856张CXRs）上实现AUROC 0.824（95%置信区间：0.810–0.836）和AUPR 0.913（95%置信区间：0.904–0.922）。外部验证结果表明该方法可行，提示合成数据在医疗AI开发中的潜力。然而，当前仍存在提示设计困难、难以控制合成数据多样性，以及需后处理以匹配真实数据等挑战。未来医疗智能的发展需经过充分验证、监管审批与伦理审查方可临床转化。
原文摘要 · Abstract (English)
We trained a classifier with synthetic chest X-ray (CXR) images generated by Nano Banana, the latest AI model for image generation and editing, released by Google. When directly applied to real-world CXRs having only been trained with synthetic data, the classifier achieved an AUROC of 0.923 (95% CI: 0.919 - 0.927), and an AUPR of 0.900 (95% CI: 0.894 - 0.907) in recognizing pneumonia in the 2018 RSNA Pneumonia Detection dataset (14,863 CXRs), and an AUROC of 0.824 (95% CI: 0.810 - 0.836), and an AUPR of 0.913 (95% CI: 0.904 - 0.922) in the Chest X-Ray dataset (5,856 CXRs). These external validation results on real-world data demonstrate the feasibility of this approach and suggest potential for synthetic data in medical AI development. Nonetheless, several limitations remain at present, including challenges in prompt design for controlling the diversity of synthetic CXR data and the requirement for post-processing to ensure alignment with real-world data. However, the growing sophistication and accessibility of medical intelligence will necessitate substantial validation, regulatory approval, and ethical oversight prior to clinical translation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。