Towards Efficient Medical Video Super-Resolution Based on Deep Back-Projection Networks
Sheng Ren, Haifu Guo, Kehua Guo · 2019
Medical video super-resolution reconstruction helps doctors clearly observe the patient's lesions, and increases the likelihood of the disease being diagnosed and cured. In this paper, we propose an efficient medical video super-resolution method based on deep back-projection networks. First, three medical video super-resolution models based on deep back-projection networks are trained for real-time, high-quality and high-magnification medical video super-resolution reconstruction. Second, an easy-to-use interface is designed. Third, our proposed model is used to reconstruct different kinds of medical videos, and calculate their peak signal-to-noise ratio and structural similarity. The experimental results show that the proposed medical video super-resolution method achieves superior performance over the other compared methods in this work.