让医学影像小样本学习更可解释，医生引导模型关注关键区域
Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis
- 用医生标注的感兴趣区做空间监督，结合注意力图优化模型
- 在少样本下准确率达92%（脑瘤）、76%（胸片）和62%（新冠）
- 适合临床部署，能自动筛选对诊断有意义的图像样本
医学影像分析面临两大挑战：标注数据稀缺与模型不可解释性，二者均阻碍临床AI应用。小样本学习（FSL）缓解数据不足问题，但预测缺乏透明度；主动学习（AL）优化数据获取，却忽略样本的可解释性。本文提出双框架解决方案：专家引导的可解释小样本学习（EGxFSL）与可解释性引导的主动学习（xGAL）。EGxFSL利用放射科医生定义的感兴趣区域，通过基于Grad-CAM的Dice损失进行空间监督，与原型分类联合优化，实现可解释的小样本学习。xGAL采用迭代采样策略，优先选择预测不确定性和注意力不一致程度高的样本，形成可解释性驱动训练与样本选择的闭环。在BraTS（MRI）、VinDr-CXR（胸片）和SIIM-COVID-19（胸片）数据集上，准确率分别达到92%、76%和62%，显著优于非引导基线。在极端数据约束下，xGAL仅用680个样本即达76%准确率，远超随机采样的57%。Grad-CAM可视化显示模型聚焦于诊断相关区域，跨模态验证在乳腺超声中亦有效。
原文摘要 · Abstract (English)
Medical image analysis faces two critical challenges: scarcity of labeled data and lack of model interpretability, both hindering clinical AI deployment. Few-shot learning (FSL) addresses data limitations but lacks transparency in predictions. Active learning (AL) methods optimize data acquisition but overlook interpretability of acquired samples. We propose a dual-framework solution: Expert-Guided Explainable Few-Shot Learning (EGxFSL) and Explainability-Guided AL (xGAL). EGxFSL integrates radiologist-defined regions-of-interest as spatial supervision via Grad-CAM-based Dice loss, jointly optimized with prototypical classification for interpretable few-shot learning. xGAL introduces iterative sample acquisition prioritizing both predictive uncertainty and attention misalignment, creating a closed-loop framework where explainability guides training and sample selection synergistically. On the BraTS (MRI), VinDr-CXR (chest X-ray), and SIIM-COVID-19 (chest X-ray) datasets, we achieve accuracies of 92\%, 76\%, and 62\%, respectively, consistently outperforming non-guided baselines across all datasets. Under severe data constraints, xGAL achieves 76\% accuracy with only 680 samples versus 57\% for random sampling. Grad-CAM visualizations demonstrate guided models focus on diagnostically relevant regions, with generalization validated on breast ultrasound confirming cross-modality applicability.
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。