Skip to main content
. Author manuscript; available in PMC: 2019 Nov 22.
Published in final edited form as: Proc SPIE Int Soc Opt Eng. 2019 Mar 15;10949:1094917. doi: 10.1117/12.2512541

Figure 2.

Figure 2.

The network structure of proposed AID-Net. The inputs of the network are the longitudinal scan and rescan data, where each data consists of two channels: preprocessed CT and HU>130 mask. The outputs of the network are the classification results and training and testing attention maps. The definition on symbols of SAG subnetwork is the same as [1].

HHS Vulnerability Disclosure