Scholarlink

<p>Multi-label chest X-ray (CXR) classification is challenging because thoracic abnormalities vary substantially in scale, visual saliency, and anatomical distribution, while disease labels often exhibit clinically meaningful dependencies. We propose a visual–semantic framework that integrates heterogeneous visual representations with graph-guided label reasoning for image-level multi-label CXR classification. The visual encoder consists of a Vision Transformer (ViT) branch and a DenseNet-121 branch with complementary inductive biases: the ViT branch provides self-attention-based content-adaptive token representations, whereas the DenseNet branch provides hierarchical convolutional feature maps with explicit spatial layouts. A multi-scale bidirectional dual cross-attention fusion (DCAF) module aligns these two representations and enables bidirectional cross-representation interaction at the <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(C_3\)</EquationSource></InlineEquation> and <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(C_4\)</EquationSource></InlineEquation> stages to construct a fused visual memory. To model label dependencies, we construct an ML-GCN-style label graph whose edges are derived from training-set conditional co-occurrence statistics and whose node features are initialized using GloVe label-name embeddings. The resulting GCN-refined label embeddings initialize the label queries of a Transformer decoder, which retrieves label-specific evidence from the fused visual memory and predicts a single logits matrix for multi-label classification. The proposed method achieves a Mean AUC of 0.849 on ChestX-ray14 following its official evaluation protocol and 0.815 on CheXpert using an internal 70%/10%/20% training/validation/testing partition. Qualitative Grad-CAM visualizations on selected cases further suggest that the proposed framework tends to produce activation patterns consistent with manually indicated visually suspicious regions; these visualizations are not intended as a formal localization evaluation. Overall, the results indicate that cross-representation visual fusion and graph-guided label-query decoding provide complementary benefits for multi-label CXR classification.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Graph guided multiscale cross attention for multilabel chest X ray classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月19日

查看全文
  • Guokun Shi,
  • Zijian Wang,
  • Yucheng Shi,
  • Jingwen Pan,
  • Liping Sun,
  • Fang Fang,
  • Li Jin

摘要

Multi-label chest X-ray (CXR) classification is challenging because thoracic abnormalities vary substantially in scale, visual saliency, and anatomical distribution, while disease labels often exhibit clinically meaningful dependencies. We propose a visual–semantic framework that integrates heterogeneous visual representations with graph-guided label reasoning for image-level multi-label CXR classification. The visual encoder consists of a Vision Transformer (ViT) branch and a DenseNet-121 branch with complementary inductive biases: the ViT branch provides self-attention-based content-adaptive token representations, whereas the DenseNet branch provides hierarchical convolutional feature maps with explicit spatial layouts. A multi-scale bidirectional dual cross-attention fusion (DCAF) module aligns these two representations and enables bidirectional cross-representation interaction at the \(C_3\) and \(C_4\) stages to construct a fused visual memory. To model label dependencies, we construct an ML-GCN-style label graph whose edges are derived from training-set conditional co-occurrence statistics and whose node features are initialized using GloVe label-name embeddings. The resulting GCN-refined label embeddings initialize the label queries of a Transformer decoder, which retrieves label-specific evidence from the fused visual memory and predicts a single logits matrix for multi-label classification. The proposed method achieves a Mean AUC of 0.849 on ChestX-ray14 following its official evaluation protocol and 0.815 on CheXpert using an internal 70%/10%/20% training/validation/testing partition. Qualitative Grad-CAM visualizations on selected cases further suggest that the proposed framework tends to produce activation patterns consistent with manually indicated visually suspicious regions; these visualizations are not intended as a formal localization evaluation. Overall, the results indicate that cross-representation visual fusion and graph-guided label-query decoding provide complementary benefits for multi-label CXR classification.