arXiv · Computer Vision· Simon Hadush Nrea (Mekelle University, Mekelle, Ethiopia), Filimon Gidey Gebremichael (Mekelle University, Mekelle, Ethiopia), Gebrekirstos Hagos Gebrekirstos (Clinical Oncologist London School of Hygiene and Tropical Medicine London, UK), Yaecob Girmay Gezahegn (Mekelle University, Mekelle, Ethiopia)·· 4 hr agoAI score31
HCMAN：面向低收入临床环境的乳腺癌早期检测混合跨模态注意力网络
Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings
AI brief
论文提出混合跨模态注意力网络 HCMAN，用 transformer 跨模态注意力机制融合乳腺 X 光图像与结构化临床数据。模型基于埃塞俄比亚四家转诊医院 1,024 名患者的 2,560 张乳腺 X 光图像验证，准确率 97.8%、灵敏度 97.2%、特异性 98.3%、AUC 0.987，显著优于仅用图像的基线。
Source: arXiv · Computer Vision · arxiv.org