Multicenter Computer-Aided Diagnosis for Lymph Nodes Using Unsupervised Domain-Adaptation Networks Based on Cross-Domain Confounding Representations

<div>A graphical illustration of the proposed method: the cross-domain confounding representation is generated by constraining the cross-domain mapping reconstruction. The classification cycle consistency enables the network to perceive the significant discriminative representation in a domain-invariant space for final classification.</div>

Computational and Mathematical Methods in Medicine

fig1

Figure 1

Figure 1: Multicenter Computer-Aided Diagnosis for Lymph Nodes Using Unsupervised Domain-Adaptation Networks Based on Cross-Domain Confounding Representations 

Figure 1 | Multicenter Computer-Aided Diagnosis for Lymph Nodes Using Unsupervised Domain-Adaptation Networks Based on Cross-Domain Confounding Representations 