The proposed CNN-GCN method combines local image information with graph connectivity information, improving pulmonary A/V separation over a baseline CNN method, approaching the performance of human observers.
Z. Zhai
1 papers
M. Staring
Xuhui Zhou
Qiuxia Xie
Xiaojuan Xiao
M. E. Bakker
L. Kroft
B. Lelieveldt
G. Boon
F. Klok
B. Stoel