Self-Governing Assessment Network (SGAN) Based Super-Resolution for CT chest images

Chest cancer is a common and potentially life-threatening disease that affects humanity worldwide. Early detection of chest cancer is critical for successful treatment and improved survival rates. Medical technology advancements in recent years have resulted in the development of various methods for detecting chest cancer. These methods have significantly improved the accuracy and reliability of chest cancer detection. However, the challenge remains to identify chest cancer at an early stage when it is most treatable. Therefore, ongoing research is focused on developing new and innovative approaches to enhance the resolution of CT chest images for early detection of chest cancer. In this paper the Self- Governing Assessment Network (SGAN) model is proposed to produce super resolution images from the low-resolution CT chest images. The proposed SGAN model is tested on 900 chest CT images dataset for super resolution factors 2, 4 and 6 respectively. The proposed model outperformed the existing models with PSNR values 35.82, 36.732, 37.196 and SSIM values 0.914, 0.9421, 0.9653 for super resolution factors 2,4 and 6 respectively.