基于卷积辅助自注意力的胸部疾病分类网络

张自然,李锵,关欣

Classification network for chest disease based on convolution-assisted self-attention

Ziran ZHANG,Qiang LI,Xin GUAN

表 6 不同模块对网络分类效果的影响

Tab.6 Effect of different module on network classification performance

CAWS CSRA IRPE 平均AUC ChestX-ray14 CheXpert MIMIC-CXR ✔ ✔ ✔ 0.853 0.898 0.819 ✘ ✔ ✔ 0.844 0.886 0.811 ✔ ✘ ✔ 0.849 0.894 0.814 ✔ ✔ ✘ 0.850 0.891 0.816