PulmoSight-XAI：用于多标签胸部X光分类的具有梯度提升元学习的可解释多视图注意力集成
PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification
- Department of Biomedical Engineering Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学（BUET）生物医学工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对胸部X光分类挑战，提出分层多视图集成框架。用五个卷积神经网络分别处理正侧位片，结合多尺度特征融合与注意力模块，采用混合损失函数优化模型，通过分层元学习策略提升性能，兼具准确性与可解释性。
AI中文摘要：
由于严重的类别不平衡、同时出现的病理情况以及传统架构中局部特征的丢失，自动胸部X光分类仍然具有挑战性。为了解决这些问题，我们提出了一个用于对14种胸部病理进行稳健分类的可解释分层多视图集成框架。该框架通过使用五个互补卷积神经网络的集合独立地对正位和侧位X光片进行建模，采用特定视图的训练。取代全局平均池化，一种用卷积块注意力模块（CBAM）增强的多尺度特征融合策略在强调高级病理特定语义特征的同时保留了细粒度的中间表示。为了减轻正负不平衡和不同类间难度，使用一种将不对称损失与自适应焦点损失相结合的新型混合目标对模型进行优化。除了简单的概率平均之外，该框架还纳入了一种分层元学习策略，其中测试时增强（TTA）预测和跨模型不确定性度量被集成到一级梯度提升元学习器（XGBoost、LightGBM和CatBoost）中，随后通过优化的α混合进行二级堆叠。在一个大规模的CheXpert风格数据集上进行评估，该框架在正位X光片上实现了0.9319的最先进宏观平均AUROC分数，在侧位X光片上实现了0.9154的分数。此外，使用七种事后归因技术进行的综合可解释性分析证明了强大的解剖学一致性和临床上有意义的决策定位。通过整合架构多样性、多尺度注意力、分层元学习和严格的可解释性，所提出的框架为胸部疾病分类提供了一个透明、高度准确且临床上实用的计算机辅助诊断系统。
英文摘要：
Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures. To address these, we propose an explainable hierarchical multi-view ensemble framework for the robust classification of 14 thoracic pathologies. The framework employs view-specific training by independently modeling frontal and lateral radiographs using an ensemble of five complementary convolutional neural networks. Replacing global average pooling, a multi-scale feature fusion strategy augmented with Convolutional Block Attention Modules (CBAM) preserves fine-grained intermediate representations while emphasizing high-level pathology-specific semantic features. To mitigate positive-negative imbalance and varying inter-class difficulty, models are optimized using a novel hybrid objective combining Asymmetric Loss with Adaptive Focal Loss. Beyond simple probability averaging, the framework incorporates a hierarchical meta-learning strategy where test-time augmentation (TTA) predictions and cross-model uncertainty measures are integrated into Level-1 gradient-boosting meta-learners (XGBoost, LightGBM, and CatBoost), followed by Level-2 stacking with optimized alpha blending. Evaluated on a large-scale CheXpert-style dataset, the framework achieves state-of-the-art macro-average AUROC scores of 0.9319 for frontal and 0.9154 for lateral radiographs. Furthermore, comprehensive explainability analysis using seven post-hoc attribution techniques demonstrates strong anatomical consistency and clinically meaningful decision localization. By integrating architectural diversity, multi-scale attention, hierarchical meta-learning, and rigorous explainability, the proposed framework provides a transparent, highly accurate, and clinically practical computer-aided diagnosis system for thoracic disease classification.
