IRMIRS:Inception-ResNet-Based Network for MRI Image Super-Resolution
作者机构:Department of Electrical EngineeringBalochistan University of Engineering and TechnologyKhuzdar89100Pakistan Department of Computer Systems EngineeringBalochistan University of Engineering and TechnologyKhuzdar89100Pakistan Department of Mechanical EngineeringBalochistan University of Engineering and TechnologyKhuzdar89100Pakistan Department of Mechanical EngineeringNational Taiwan University of Science and Technology10607Taiwan Department of Information SystemsKyungsung UniversityBusan613010South Korea
出 版 物:《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模(英文))
年 卷 期:2023年第136卷第8期
页 面:1121-1142页
核心收录:
学科分类:0831[工学-生物医学工程(可授工学、理学、医学学位)] 1002[医学-临床医学] 08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程(可授工学、理学学位)] 0802[工学-机械工程] 0702[理学-物理学]
基 金:supported by Balochistan University of Engineering and Technology Khuzdar Balochistan Pakistan
主 题:Super-resolution magnetic resonance imaging ResNet block inception block convolutional neural network deconvolution layer
摘 要:Medical image super-resolution is a fundamental challenge due to absorption and scattering in *** challenges are increasing the interest in the quality of medical *** research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image ***,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory ***,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead *** this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as *** our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling ***,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input *** and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.