计算机与现代化Issue(3)：67-71,5.DOI:10.3969/j.issn.1006-2475.2024.03.011
基于形变场灰度场插值网络的切片间超分辨率
Inter-slice Super-resolution Based on Deformation Field and Grey Field Interpolation Networks
摘要
Abstract
Magnetic resonance imaging is a widely used medical imaging method.Constrained by hardware conditions and other factors,the inter-slice resolution of MR images is much lower than the intra-slice resolution,resulting in low image quality and affecting the doctor's diagnosis of the patient's condition.Therefore,it is necessary to improve the inter-slice resolution to dis-play more details of the image.In order to achieve super resolution between slices,an algorithm based on non-parametric defor-mation field and gray field interpolation network is proposed.Firstly,according to the principle of image registration,an approxi-mate U-Net network is used for unsupervised training of two adjacent slices in low-resolution images to generate bidirectional de-formation fields between slices.Then,the registered image is generated by using the first slice and the deformation field,and the registered image and the second slice are trained to obtain the bidirectional gray field between them,from which the deformation field and gray field at any position in the middle of the adjacent two slices can be obtained.Finally,any position slice in the middle can be obtained by interpolation method.Compared to other existing algorithms,this algorithm has significant improve-ment in visual effect and objective evaluation index,with PSNR and SSIM above 30 dB and 0.99,respectively.关键词
磁共振成像/超分辨率/形变场/灰度场Key words
magnetic resonance imaging/super-resolution/deformation field/grayscale field分类
信息技术与安全科学引用本文复制引用
刘迅,张东,袁达龙..基于形变场灰度场插值网络的切片间超分辨率[J].计算机与现代化,2024,(3):67-71,5.基金项目
国家重点研发计划项目(2011CB707900) （2011CB707900）
