研究人员开发了一种新颖的以令牌为中心的框架，用于整合来自不同乳腺钼靶视图（CC和MLO）的信息，以改进乳腺癌分类。该方法使用专用的融合令牌，在冻结的视觉 Transformer 中促进视图之间的结构化、多深度通信，从而增强了跨视图依赖关系的表示。在 VinDr-Mammo 数据集上的实验表明，与现有的基线相比，F1 分数和 AUC 有显著提高，特别是在 BI-RADS 分类方面。 AI
影响 这项研究可能带来更准确的 AI 驱动的乳腺癌诊断工具，从而改善早期检测和患者预后。
排序理由 该集群包含一篇学术论文，详细介绍了用于特定分类任务的 AI 模型自适应和融合的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.06309v1 Announce Type: cross Abstract: Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of brea…
Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities. However, existing multi-view lea…
Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities. However, existing multi-view lea…