基于循环生成对抗网络的大视场显微成像方法  

Large-Field Microscopic Imaging Method Based on Cycle Generative Adversarial Networks

作　　者：付娆 方宇[1,2] 杨勇 向东 吴晓静[3] Fu Rao;Fang Yu;Yang Yong;Xiang Dong;Wu Xiaojing(Institute of Modern Optics,Nankai University,Tianjin 300350,China;Tianjin Key Laboratory of Micro-Scale Optical Information Science and Technology,Tianjin 300350,China;Tianjin Union Medical Center,Tianjin 300121,China;Institute of Intelligent Sensing,Zhejiang Lab,Hangzhou 310013,Zhejiang,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]天津市人民医院,天津300121 [4]之江实验室智能感知研究院,浙江杭州310013

出　　处：《光学学报》2023年第5期190-201,共12页Acta Optica Sinica

基　　金：国家自然科学基金(12074203,12174204,12174203);广东省基础与应用基础研究基金(2020B301030009)。

摘　　要：提出了一种利用循环生成对抗网络实现由大视场、低分辨率染色图像生成与之相匹配的高分辨率虚拟染色图像的方法,在完成了对细胞虚拟染色的同时,解决了传统光学显微镜的大视场与高分辨率两个目标无法同时满足的问题。首先,进行了理论验证,通过对选定图像的分辨率分级缩放模拟实际分辨率变化,训练对应的算法模型并与真实图像相比较,结果在主观与客观上均符合设想预期。在完成理论验证的基础上,分别进行了由10倍、4倍低分辨率真实染色图像生成25倍高分辨率虚拟染色图像的实验。通过主观视觉与客观评价指标进行评价,得到结构相似性、峰值信噪比和归一化均方根误差三个指标的具体数据。结果显示,通过循环生成对抗网络生成的虚拟染色图像与真实染色图像间的相似度较高,虚拟生成效果很好。Objective In traditional optical microscopes,large field of view and high resolution cannot be achieved at the same time.Large numerical aperture objective lens is necessary to obtain high-resolution images,which will inevitably lead to the reduced imaging field of view.Similarly,a small numerical aperture objective lens should be employed to obtain a large imaging field of view,and the corresponding imaging resolution will inevitably decrease.Therefore,when the traditional optical microscope is adopted,a trade-off is needed between imaging resolution and imaging field of view,and it is impossible to obtain large field of view and high-resolution microscopic images simultaneously.With the rapid development of deep learning technology,different algorithm models are designed based on deep learning,and the corresponding pathological cell models are diagnosed in combination with the evaluation and guidance of professional doctors to yield computer-aided calculation and detection effects.Therefore,this paper proposes a method to generate matching high-resolution virtual stained images from low-resolution stained images with large field of view using cycle generative adversarial networks(Cycle-GANs),without changing the optical systems and detector devices.Only ordinary microscopes are employed to obtain staining images with large field of view,and it is unnecessary to convert the multiple objectives to obtain high-resolution images.Virtual high-resolution staining images at any position of the large field of view can be predicted through network model calculation,and the high resolution and large field of view can be realized at the same time.Methods In this paper,Cycle-GANs are employed to complete the experiment.Firstly,the data set preparation is carried out,and the unpaired and paired data sets of images under multiple objectives are collected respectively to constitute the training and testing parts of the network model.Secondly,a theoretical pre-experiment is conducted.The resolution of the same stained onion ep

关 键 词：显微 光学显微镜 大视场 高分辨率 循环生成对抗网络 虚拟染色 细胞 

分 类 号：O436[机械工程—光学工程]