基于特征损失的医学图像超分辨率重建-计算机工程与应用.PDF

202 2018 ，54（20 ） Computer Engineering and Applications 计算机工程与应用 基于特征损失的医学图像超分辨率重建 用 1，2 1，2 1，2 邢晓羊 ，魏 敏 ，符 颖 应 XING Xiaoyang1，2 , WEI Min1，2 , FU Ying1，2 与 1. 成都信息工程大学 计算机学院，成都 610225 程 2. 成都信息工程大学 图形图像与空间信息协同创新中心，成都 610225 g r 1.School of Computer Science, Chengdu University of Information and Technology, Chengdu 610225, China 工 o 2.Collaborative Innovation Center for Image and Geospatial Information, Chengdu University of Information and Technology, . Chengdu 610225, China j 机 a 算 e XING Xiaoyang, WEI Min, FU Ying. Super-resolution reconstruction of medical images using feature-based loss. c . Computer Engineering and Applications, 2018, 54 （20 ）：202-207. 计 w Abstract ：High-resolution Magnetic Resonance （MR ）images can provide a clearer anatomical image to facilitate early w diagnosis of the disease. However, the inherent defects of medical imaging system make the acquisition of high-resolution w medical images face many problems, and one of the methods to solve these problems is to use the super-resolution recon- struction technique. In view of the problem of medical image super-resolution reconstruction, a feedforward full connec- tion convolution neural network is designed, which includes five-layer convolution layer and five residual blocks, and the loss function based on feature is also used to solve the problem caused by mean square error loss function which cannot meet the human visual sense. This method realizes the image 4 times magnification reconstruction in the network and avoids the checkerbo