变换域多尺度信息蒸馏网络的医学影像超分辨率重建  

Medical image super-resolution reconstruction via multi-scale information distillation network under multi-scale geometric transform domain

作　　者：王华东[1] 孙挺[1,2] WANG Huadong;SUN Ting(School of Computer Science and Technology,Zhoukou Normal University,Zhoukou,Henan 466001,P.R.China;Institute of Visualization Technology,Northwest University,Xi’an 710049,P.R.China)

机构地区：[1]周口师范学院计算机科学与技术学院,河南周口466001 [2]西北大学可视化研究所,西安710049

出　　处：《生物医学工程学杂志》2022年第5期887-896,共10页Journal of Biomedical Engineering

基　　金：国家自然科学基金(62172457);河南省高等学校重点科研项目(17A520068)。

摘　　要：高分辨率磁共振成像(MRI)和计算机断层扫描(CT)影像能够提供更清晰的人体解剖细节,有助于疾病的早期诊断。但是,由于成像系统、成像环境和人为等因素限制,清晰的高分辨率图像难于获得。本文提出一种非下采样剪切波变换域(NSST)多尺度信息蒸馏(MSID)网络的医学影像超分辨率重建方法(即NSSTMSID网络)。首先,提出一种MSID网络,主要由多个级联的MSID块构成,充分探取图像的多尺度特征,有效恢复低分辨率图像至高分辨率图像。此外,由于现有方法往往在空间域预测高分辨率图像,使得输出过于平滑且丢失了纹理细节,因此将医学图像的超分辨率问题描述为NSST系数的预测问题,使得MSID网络比空间域保持更丰富的结构细节。最后,在建立的医学影像数据集上对提出的方法进行性能评价。实验结果表明,与其他现有杰出的方法相比,NSST-MSID网络可以得到较优的峰值信噪比(PSNR)、结构相似性(SSIM)及均方根误差(RMSE)值,更好地保留了局部纹理细节与全局拓扑结构,实现了不错的医学影像重建效果。High resolution(HR) magnetic resonance images(MRI) or computed tomography(CT) images can provide clearer anatomical details of human body, which facilitates early diagnosis of the diseases. However, due to the imaging system, imaging environment and human factors, it is difficult to obtain clear high-resolution images. In this paper, we proposed a novel medical image super resolution(SR) reconstruction method via multi-scale information distillation(MSID) network in the non-subsampled shearlet transform(NSST) domain, namely NSST-MSID network. We first proposed a MSID network that mainly consisted of a series of stacked MSID blocks to fully exploit features from images and effectively restore the low resolution(LR) images to HR images. In addition, most previous methods predict the HR images in the spatial domain, producing over-smoothed outputs while losing texture details. Thus, we viewed the medical image SR task as the prediction of NSST coefficients, which make further MSID network keep richer structure details than that in spatial domain. Finally, the experimental results on our constructed medical image datasets demonstrated that the proposed method was capable of obtaining better peak signal to noise ratio(PSNR), structural similarity(SSIM) and root mean square error(RMSE) values and keeping global topological structure and local texture detail better than other outstanding methods, which achieves good medical image reconstruction effect.

关 键 词：医学影像 超分辨率重建 卷积神经网络 多尺度信息蒸馏 非下采样剪切波变换 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]