HydraViT：用于胸部X射线图像多标签疾病分类的自适应多分支Transformer
HydraViT: Adaptive Multi-Branch Transformer for Multi-Label Disease Classification from Chest X-ray Images
AI总结：
HydraViT结合Transformer主干与多分支输出模块，通过自注意力聚焦关键区域，提升胸部X射线多标签疾病分类性能，平均优于现有方法1.0%-1.4%。
摘要：
胸部X射线是识别胸部疾病的重要诊断工具，因其对肺部病理异常具有高敏感性。然而，由于病理的大小和位置存在异质性，以及不同病理之间的视觉相似性和共现性，基于图像的诊断仍具挑战性。由于疾病相关区域通常仅占诊断图像的一小部分，基于传统卷积神经网络（CNN）的分类模型因其局部性偏差而受到不利影响。尽管此前通过注意力图或空间掩码增强CNN以引导关注潜在关键区域，但在病理空间分布异质性下学习定位引导仍具挑战。为提高多标签分类性能，我们提出了一种新方法HydraViT，该方法将Transformer主干与具有学习权重的多分支输出模块协同结合。Transformer主干增强了对X射线图像中长期上下文信息的敏感性，同时利用自注意力机制自适应地聚焦于任务关键区域。多分支输出模块为每个疾病标签分配独立分支，以实现跨不同疾病类别的稳健学习，并设置跨标签的聚合分支以保持对病理共现关系的敏感性。实验表明，平均而言，HydraViT在多标签分类性能上优于竞争性的注意力引导方法1.2%，区域引导方法1.4%，语义引导方法1.0%。
英文摘要：
Chest X-ray is an essential diagnostic tool in the identification of chest diseases given its high sensitivity to pathological abnormalities in the lungs. However, image-driven diagnosis is still challenging due to heterogeneity in size and location of pathology, as well as visual similarities and co-occurrence of separate pathology. Since disease-related regions often occupy a relatively small portion of diagnostic images, classification models based on traditional convolutional neural networks (CNNs) are adversely affected given their locality bias. While CNNs were previously augmented with attention maps or spatial masks to guide focus on potentially critical regions, learning localization guidance under heterogeneity in the spatial distribution of pathology is challenging. To improve multi-label classification performance, here we propose a novel method, HydraViT, that synergistically combines a transformer backbone with a multi-branch output module with learned weighting. The transformer backbone enhances sensitivity to long-range context in X-ray images, while using the self-attention mechanism to adaptively focus on task-critical regions. The multi-branch output module dedicates an independent branch to each disease label to attain robust learning across separate disease classes, along with an aggregated branch across labels to maintain sensitivity to co-occurrence relationships among pathology. Experiments demonstrate that, on average, HydraViT outperforms competing attention-guided methods by 1.2%, region-guided methods by 1.4%, and semantic-guided methods by 1.0% in multi-label classification performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
