Transformer and GAN-Based Super-Resolution Reconstruction Network for Medical Images

Super-resolution reconstruction in medical imaging has become more demanding due to the necessity of obtaining high-quality images with minimal radiation dose, such as low-field magnetic resonance (MRI). However, image super-resolution remains a difficult task because complexity and high textual requirements for diagnosis purpose. In this paper, we offer deep learning based strategy reconstructing from low resolutions utilizing Transformer generative adversarial networks (T-GANs). The integrated system can extract precise texture information focus on important locations through global matching after successfully inserting into network picture reconstruction. Furthermore, weighted combination content loss, feature loss final multi-task function during training our proposed model T-GAN. comparison established measures like peak signal-to-noise ratio (PSNR) structural similarity index measure (SSIM), suggested T-GAN achieves optimal performance recovers features MRI scanned knees belly.