针对胸部X光多病种诊断，提出专用注意力模块提升准确率。
Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillation
- 设计专用于X光的MXA注意力块，融合局部细节与全局上下文。
- 在CheXpert数据集上实现0.85的AUC，比基线提升233%。
- 适合医学影像分析、尤其是多标签疾病检测的研究者使用。
医学影像特别是X光分析常需在同一张扫描中同时检测多种异常，多标签分类对临床应用至关重要。本文提出医学X光注意力（MXA）块，一种专为解决X光异常检测独特挑战而设计的新颖注意力机制。该模块通过整合特殊模块，有效捕捉细粒度局部信息与更广泛全局上下文，增强传统多头自注意力（MHSA）。据我们所知，这是首个为胸部X光诊断提出任务特定注意力机制的工作，也是首次在高效视觉变换器（EfficientViT）中尝试多标签分类。将MXA块嵌入EfficientViT架构并结合知识蒸馏，模型在广泛使用的CheXpert数据集上显著提升性能：达到0.85的受试者工作特征曲线下面积（AUC），相比基线模型的0.66提升了0.19，相对随机猜测（AUC=0.5）提高约233%。
原文摘要 · Abstract (English)
Medical imaging, particularly X-ray analysis, often involves detecting multiple conditions simultaneously within a single scan, making multi-label classification crucial for real-world clinical applications. We present the Medical X-ray Attention (MXA) block, a novel attention mechanism tailored specifically to address the unique challenges of X-ray abnormality detection. The MXA block enhances traditional Multi-Head Self Attention (MHSA) by integrating a specialized module that efficiently captures both detailed local information and broader global context. To the best of our knowledge, this is the first work to propose a task-specific attention mechanism for diagnosing chest X-rays, as well as to attempt multi-label classification using an Efficient Vision Transformer (EfficientViT). By embedding the MXA block within the EfficientViT architecture and employing knowledge distillation, our proposed model significantly improves performance on the CheXpert dataset, a widely used benchmark for multi-label chest X-ray abnormality detection. Our approach achieves an area under the curve (AUC) of 0.85, an absolute improvement of 0.19 compared to our baseline model's AUC of 0.66, corresponding to a substantial approximate 233% relative improvement over random guessing (AUC = 0.5).
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。