用少量标注数据实现肺病严重程度精准分类，解决样本不均衡问题。
Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
- 基于贝叶斯神经网络和主动学习，动态选择最有价值的未标注影像
- 仅用15.4%数据即达93.7%准确率，多分类下23.1%数据达70.3%准确率
- 适合标注成本高、数据不均衡的医学影像诊断场景
为减少肺部疾病严重程度分类对标注数据的需求，本研究在存在类别不平衡的情况下，采用基于贝叶斯神经网络近似和加权损失函数的深度主动学习方法。回顾性收集了2020年1月至11月期间埃默里医疗体系963名患者的2,319张胸部X光片（平均年龄59.2±16.6岁；女性481人），所有患者均有临床确诊的新冠感染。每张胸片由3至6名认证放射科医生独立标注为正常、中度或重度。使用蒙特卡洛丢弃的深度神经网络进行主动学习训练，通过多种采样策略从无标签数据池中迭代选取最具信息量的样本。评估指标包括准确率、受试者工作特征曲线下面积（AU ROC）和精确率-召回率曲线下面积（AU PRC）。记录训练时间和采样时间。统计分析包括描述性指标及不同采样策略的性能比较。熵采样在二分类任务（正常 vs. 病变）中仅使用15.4%训练数据即达到93.7%准确率（AU ROC 0.91）；在多分类设置下，均值标准差采样使用23.1%标注数据实现70.3%准确率（AU ROC 0.86）。这些方法优于更复杂且计算成本更高的采样函数，显著降低标注需求。结合贝叶斯近似与加权损失的深度主动学习有效减少了标注数据依赖，在保持或超越诊断性能的同时缓解了类别不平衡问题。
原文摘要 · Abstract (English)
To reduce the amount of required labeled data for lung disease severity classification from chest X-rays (CXRs) under class imbalance, this study applied deep active learning with a Bayesian Neural Network (BNN) approximation and weighted loss function. This retrospective study collected 2,319 CXRs from 963 patients (mean age, 59.2 $\pm$ 16.6 years; 481 female) at Emory Healthcare affiliated hospitals between January and November 2020. All patients had clinically confirmed COVID-19. Each CXR was independently labeled by 3 to 6 board-certified radiologists as normal, moderate, or severe. A deep neural network with Monte Carlo Dropout was trained using active learning to classify disease severity. Various acquisition functions were used to iteratively select the most informative samples from an unlabeled pool. Performance was evaluated using accuracy, area under the receiver operating characteristic curve (AU ROC), and area under the precision-recall curve (AU PRC). Training time and acquisition time were recorded. Statistical analysis included descriptive metrics and performance comparisons across acquisition strategies. Entropy Sampling achieved 93.7% accuracy (AU ROC, 0.91) in binary classification (normal vs. diseased) using 15.4% of the training data. In the multi-class setting, Mean STD sampling achieved 70.3% accuracy (AU ROC, 0.86) using 23.1% of the labeled data. These methods outperformed more complex and computationally expensive acquisition functions and significantly reduced labeling needs. Deep active learning with BNN approximation and weighted loss effectively reduces labeled data requirements while addressing class imbalance, maintaining or exceeding diagnostic performance.
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。