Compound W-Net with Fully Accumulative Residual Connections for Liver Segmentation Using CT Images

<div>The accuracies in percentage for trading, validation, and testing using normal data and testing using augmented data for all models’ structure (U-Net, original bridge, modified bridge, and compound bridge) with both filter structures (32 ➔ 512) and (64➔ 1024).</div>

Computational and Mathematical Methods in Medicine

fig5

Figure 5

Figure 5: Compound W-Net with Fully Accumulative Residual Connections for Liver Segmentation Using CT Images 