Modified GAN-CAED to Minimize Risk of Unintentional Liver Major Vessels Cutting by Controlled Segmentation Using CTA/SPET-CT

This article substantially advances upon state-of-the-art to enhance liver vessels segmentation accuracy by leveraging advantages of synthetic PET-CT (SPET-CT) images in addition computed tomography angiography (CTA) volumes. Our setup makes a hybrid solution modified generative adversarial network-convolutional autoencoder (GAN-cAED) combining ability GAN deliver SPET-CT with cAED network terms latent learning more refined major vessels. We improve time complexity through novel concept controlled introducing threshold metric stop up desired level. The innovative vessel stopping criterion via variant levels will help surgeons avoid unintentional blood cutting, reducing the risk excessive loss. Clinically, such solutions offer computer-aided surgeries and drug treatment evaluation CTA-only environment, shorten requirement radioactive expensive fused images.