白细胞图像超分辨率重建研究  

Study on Super-resolution Image Reconstruction of Leukocytes

作　　者：王伟[1,2] 胡涛[1,2] 李欣蔚 沈思婉 姜小明 刘峻源 WANG Wei;HU Tao;LI Xin-wei;SHEN Si-wan;JIANG Xiao-ming;LIU Jun-yuan(Research Center of Biomedical Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Chongqing Engineering Research Center of Medical Electronics and Information Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学生物医学工程研究中心,重庆400065 [2]重庆邮电大学重庆市医用电子与信息技术工程研究中心,重庆400065

出　　处：《计算机科学》2021年第4期164-168,共5页Computer Science

基　　金：国家自然科学基金(61801069);重庆市教育委员会科学技术研究项目(KJQN201800622)。

摘　　要：近年来,计算机视觉已成为各类学科领域研究的重点,逐渐被应用于各类科研场景。医务工作者在临床上做血常规检验时,经常会采用血细胞图像分析系统对镜下白细胞图像进行自动计数与分类。其中,白细胞图像质量影响着血细胞分析系统计数分类的效果。针对镜下白细胞图像细节模糊的问题,文中尝试引入超分辨率方法对图片进行优化,以达到使白细胞图像更清晰的目的。所提出的方法在现有生成对抗网络的超分辨率方法(Super-Resolution Generative Adversarial Network,SRGAN)的基础上,设计引入嵌套型残差密集块(Residual-in-Residual Dense Block,RRDB)来改进网络结构,并对原有标准残差块中的批量规范化层进行删减,以提升网络性能,另外还对判别器的损失函数进行了改进。实验结果表明,该方法(SRGAN+)与3种插值法以及4种基于学习的超分辨率方法相比,在提高分辨率的同时,获得了图片细节更丰富、人眼视觉更优的图像。与SRGAN方法相比,改进算法在峰值信噪比(Peak Signal-to-noise Ratio,PSNR)和结构相似度(Structural SIMilarity,SSIM)上分别有1.008 dB和1.07%的提高。In recent years,computer vision has become the focus of research in various disciplines and has been gradually applied to numerous scientific research scenarios.Medical workers often use blood cell image analysis systems to automatically count and classify white blood cell images when performing blood routine tests in the clinic.Among them,the white blood cell image quality affects the counting classification effect of the blood cell analysis system.This paper focuses on the problem of blurred details of white blood cell images under the microscope and attempts to introduce a super-resolution method to solve the problem.This method introduces a Residual-in-Residual Dense Block(RRDB)based on the Super-Resolution Generative Adversarial Network(SRGAN)to improve the network structure and remove the batch normalization layer in the standard residual block.The network performance is improved and the loss function of the discriminator is improved.Experimental results show that,compared with 3 interpolation methods and 4 learning-based super-resolution methods,the proposed method(SRGAN+)improves the reso-lution while obtaining images with richer textures and more realistic visuals.Compared with the SRGAN method,the proposed algorithm has a 1.008 dB improvement in peak signal-to-noise ratio(PSNR)and 1.07%improvement in Structural SIMilarity(SSIM).

关 键 词：白细胞图像 超分辨率 生成对抗网络 嵌套型残差密集块 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]