让模型选图像时像医生一样思考，提升医疗影像标注效率与可解释性。
Learning to Select Like Humans: Explainable Active Learning for Medical Imaging
- 结合预测不确定性和注意力区域偏差，双重筛选最有价值的图像样本。
- 仅用570张样本即在3个数据集上超越随机采样，最高准确率达77.22%。
- 适合关注临床可解释性的医疗AI研究者和开发者使用。
医疗影像分析需要大量标注数据，但专家标注成本高、耗时长。主动学习通过有策略地选择最有效样本缓解此问题，但传统方法仅依赖预测不确定性，忽视模型是否学习到临床上有意义的特征——这对临床部署至关重要。本文提出一种可解释性引导的主动学习框架，将空间注意力对齐融入样本选择过程。该方法采用双准则策略：(i) 分类不确定性用于识别信息量大的样本；(ii) 与放射科医生定义的感兴趣区域（ROIs）的注意力错位程度，用于筛选模型关注错误区域的样本。通过Dice相似度衡量Grad-CAM注意力图与专家标注的错位程度，构建采样函数，合理选取能同时提升预测性能与空间可解释性的样本。我们在三个专家标注的医学影像数据集上评估：BraTS（MRI脑肿瘤）、VinDr-CXR（胸部X光）、SIIM-COVID-19（胸部X光）。仅使用570张精心挑选的样本，本方法在所有数据集上均优于随机采样，分别达到77.22%、52.37%和52.66%的准确率。Grad-CAM可视化显示，经该策略训练的模型聚焦于诊断相关区域，证明在样本选择中引入解释性指导可实现更高数据效率，同时保障临床可解释性。
原文摘要 · Abstract (English)
Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for the annotation purpose, but traditional methods solely rely on predictive uncertainty while ignoring whether models learn from clinically meaningful features a critical requirement for clinical deployment. We propose an explainability-guided active learning framework that integrates spatial attention alignment into a sample acquisition process. Our approach advocates for a dual-criterion selection strategy combining: (i) classification uncertainty to identify informative examples, and (ii) attention misalignment with radiologist-defined regions-of-interest (ROIs) to target samples where the model focuses on incorrect features. By measuring misalignment between Grad-CAM attention maps and expert annotations using Dice similarity, our acquisition function judiciously identifies samples that enhance both predictive performance and spatial interpretability. We evaluate the framework using three expert-annotated medical imaging datasets, namely, BraTS (MRI brain tumors), VinDr-CXR (chest X-rays), and SIIM-COVID-19 (chest X-rays). Using only 570 strategically selected samples, our explainability-guided approach consistently outperforms random sampling across all the datasets, achieving 77.22% accuracy on BraTS, 52.37% on VinDr-CXR, and 52.66% on SIIM-COVID. Grad-CAM visualizations confirm that the models trained by our dual-criterion selection focus on diagnostically relevant regions, demonstrating that incorporating explanation guidance into sample acquisition yields superior data efficiency while maintaining clinical interpretability.
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。