动态上下文注意力网络：将空间表示转化为用于内窥镜息肉诊断的自适应洞察
Dynamic Contextual Attention Network: Transforming Spatial Representations into Adaptive Insights for Endoscopic Polyp Diagnosis
- Department of Computer Science, Georgia State University（计算机科学系，佐治亚州立大学）
- Gachon University, Gil Medical Center（加恩大学，Gil医疗中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对内窥镜息肉诊断中定位不准与缺乏上下文感知的问题，提出动态上下文注意力网络（DCAN），利用注意力机制将空间表示转化为自适应上下文洞察，无需显式定位模块即可提升诊断的可解释性与性能。
AI中文摘要：
结直肠息肉是早期发现结直肠癌的关键指标。然而，传统内窥镜成像常难以准确定位息肉，且缺乏全面的上下文感知能力，这可能限制诊断的可解释性。为解决这些问题，我们提出了动态上下文注意力网络（DCAN）。这一新方法利用注意力机制将空间表示转化为自适应的上下文洞察，增强对关键息肉区域的关注，且无需显式的定位模块。通过将上下文感知整合到分类过程中，DCAN提升了决策的可解释性与整体诊断性能。这一成像技术的进步有望实现更可靠的结直肠癌检测，从而改善患者的预后。
英文摘要：
Colorectal polyps are key indicators for early detection of colorectal cancer. However, traditional endoscopic imaging often struggles with accurate polyp localization and lacks comprehensive contextual awareness, which can limit the explainability of diagnoses. To address these issues, we propose the Dynamic Contextual Attention Network (DCAN). This novel approach transforms spatial representations into adaptive contextual insights, using an attention mechanism that enhances focus on critical polyp regions without explicit localization modules. By integrating contextual awareness into the classification process, DCAN improves decision interpretability and overall diagnostic performance. This advancement in imaging could lead to more reliable colorectal cancer detection, enabling better patient outcomes.
