{"title":"A generalized deep neural network approach for improving resolution of fluorescence microscopy images","authors":"Zichen Jin, Qing He, Yang Liu, Kaige Wang","doi":"10.1142/s1793545824500111","DOIUrl":null,"url":null,"abstract":"Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed, imaging resolution, and imaging flux. This paper proposes a deep neural network based on a generative adversarial network (GAN). The generator employs a U-Net-based network, which integrates DenseNet for the downsampling component. The proposed method has excellent properties, for example, the network model is trained with several different datasets of biological structures; the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging; and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets. In addition, experimental results showed that the method improved the resolution of caveolin-coated pits (CCPs) structures from 264[Formula: see text]nm to 138[Formula: see text]nm, a 1.91-fold increase, and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.","PeriodicalId":16248,"journal":{"name":"Journal of Innovative Optical Health Sciences","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Innovative Optical Health Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1142/s1793545824500111","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed, imaging resolution, and imaging flux. This paper proposes a deep neural network based on a generative adversarial network (GAN). The generator employs a U-Net-based network, which integrates DenseNet for the downsampling component. The proposed method has excellent properties, for example, the network model is trained with several different datasets of biological structures; the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging; and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets. In addition, experimental results showed that the method improved the resolution of caveolin-coated pits (CCPs) structures from 264[Formula: see text]nm to 138[Formula: see text]nm, a 1.91-fold increase, and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.
期刊介绍:
JIOHS serves as an international forum for the publication of the latest developments in all areas of photonics in biology and medicine. JIOHS will consider for publication original papers in all disciplines of photonics in biology and medicine, including but not limited to:
-Photonic therapeutics and diagnostics-
Optical clinical technologies and systems-
Tissue optics-
Laser-tissue interaction and tissue engineering-
Biomedical spectroscopy-
Advanced microscopy and imaging-
Nanobiophotonics and optical molecular imaging-
Multimodal and hybrid biomedical imaging-
Micro/nanofabrication-
Medical microsystems-
Optical coherence tomography-
Photodynamic therapy.
JIOHS provides a vehicle to help professionals, graduates, engineers, academics and researchers working in the field of intelligent photonics in biology and medicine to disseminate information on the state-of-the-art technique.