用主动学习清理众包标注噪声，提升电子显微图像病变检测精度
Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images
- 通过差异分析筛选最需专家重标注的噪声样本
- 在私有数据集上达67.18% AP50，较直接训练噪声数据提升18.83%
- 仅需26.7%标注成本即接近全专家标注性能
肾小球疾病中电子致密沉积物（EDD）的自动检测受限于高质量标注数据稀缺。尽管众包可降低标注成本，但引入标签噪声。本文提出一种主动标签清洗方法，通过主动学习选择最具价值的噪声样本供专家重标注，构建高精度清洗模型。标签选择模块利用众包标签与模型预测间的差异，实现样本筛选与实例级噪声评级。实验表明，该方法在私有数据集上达到67.18% AP₅₀，相比直接训练噪声标签提升18.83%；性能达全专家标注的95.79%，同时标注成本降低73.30%。该方法为有限专家资源下开发可靠医疗AI提供了实用、低成本解决方案。
原文摘要 · Abstract (English)
Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, building high-accuracy cleaning models. A Label Selection Module leverages discrepancies between crowdsourced labels and model predictions for both sample selection and instance-level noise grading. Experiments show our method achieves 67.18% AP\textsubscript{50} on a private dataset, an 18.83% improvement over training on noisy labels. This performance reaches 95.79% of that with full expert annotation while reducing annotation cost by 73.30%. The method provides a practical, cost-effective solution for developing reliable medical AI with limited expert resources.
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。