研究人员开发了一种新颖的以Token为中心的框架，通过有效融合头尾（CC）和内侧斜位（MLO）视图的信息来改进乳腺X线摄影图像的乳腺癌分类。该方法利用冻结的视觉Transformer骨干网络，并将视图间交互重新构建为结构化的Token级通信，专用的融合Token促进了跨多个Transformer深度的双向信息交换。在VinDr-Mammo数据集上的实验显示，与现有的融合基线相比，BI-RADS评估的二元分类AUC提高了0.10，取得了显著的改进。 AI
影响 这项研究可能带来更准确、更全面的AI辅助医学影像诊断，尤其是在乳腺癌检测方面。
排序理由 该集群包含一篇学术论文，详细介绍了一种新的AI驱动的医学图像分析方法。
AI 生成摘要 · Google Gemini · 来自 4 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…
A token-centric dual-view learning framework unifies prompt-based adaptation and cross-view fusion in a frozen vision transformer to improve breast cancer classification from mammography images.