基于卷积神经网络的细胞折射率显微图像和明场显微图像的融合方法  

Fusion of Cell Refractive Index and Bright-Field Micrographs Based on Convolutional Neural Networks

作　　者：刘中法 杨艺哲 方宇[1,2] 吴晓静 朱思伟[3] 杨勇[1,2] Liu Zhongfa;Yang Yizhe;Fang Yu;Wu Xiaojing;Zhu Siwei;Yang Yong(Institute of Modern Optics,Nankai University,Tianjin 300350,China;Tiamjin Key Laboratory of Micro-scale Optical Ilnformation Science and Teclnology,Tianjin 300350,China;Tianjin Union Medical Center,Institute of Translational Medicine,Nankai University,Tianjin 300121,China)

机构地区：[1]南开大学现代光学研究所,天津300350 [2]天津市微尺度光学信息技术科学重点实验室,天津300350 [3]南开大学人民医院转化医学研究院,天津300121

出　　处：《激光与光电子学进展》2021年第22期416-424,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(12074203,11774256)。

摘　　要：为了改善细胞折射率显微成像的质量,提高特征的辨识度,本文提出了一种基于卷积神经网络算法的细胞折射率显微图像和明场显微图像的融合方法,该方法克服了传统融合方法人工制定融合规则的困难,通过训练数据学习自适应强鲁棒融合函数,获得了更佳的融合效果。主观和客观评价结果表明,该方法有效地改善了细胞折射率显微图像的分辨率,提升了特征辨识度。To improve the quality of cell refractive index microscopy imaging and enhance feature recognition,this paper proposes a fusion method for cell refractive index and bright-field micrographs based on convolutional neural network algorithm,which overcomes the shortcomings of traditional fusion methods involving manual formulation of fusion rules,and learns adaptive strong robust fusion functions from training data to obtain better fusion results.The subjective and objective evaluation results show that the proposed method effectively improves the resolution of the cell refractive index micrographs,which in turn improves feature recognition.

关 键 词：图像处理 图像融合 折射率显微图像 明场显微图像 卷积神经网络 细胞 

分 类 号：O436[机械工程—光学工程]