Research on CT to CTA image translation based on vessel-enhanced generative adversarial networks

Abstract

Computed Tomography Angiography (CTA) is an important imaging modality for the diagnosis of vascular diseases. However, it requires intravenous injection of iodine contrast agents, which carries risks such as renal injury and allergic reactions, and increases medical costs. To address these issues, this paper proposes a CT-to-CTA image translation method based on Vessel-Enhanced GAN (VE-GAN), which can generate high-quality CTA images from routine CT images without contrast agents.Based on conditional Generative Adversarial Networks (cGAN), the method designs a UNet generator integrating multi-scale vessel enhancement blocks, edge preservation blocks, and frequency-domain attention mechanisms. A spectral-normalized PatchGAN discriminator is adopted to ensure training stability, and a multi-objective loss function including vessel-specific loss and edge loss is constructed to optimize generation quality. Experiments are conducted using 1491 pairs of CT-CTA images as the training set, 100 pairs as the validation set, and 216 CT images as the test set. Results show that the generated images achieve a Peak Signal-to-Noise Ratio (PSNR) of 31.35 dB and a Structural Similarity Index Measure (SSIM) of 0.881, verifying the feasibility of the method. Ablation studies demonstrate that each innovative module effectively improves translation performance, with the vessel enhancement module and perceptual loss contributing the most significantly.Although the current performance does not yet meet clinical application standards, this study provides a new technical path for non-invasive vascular visualization and lays a solid foundation for further optimization.