{"title":"基于轻量级神经网络的结构照明显微镜微光成像重建。","authors":"Hesong Jiang, Peihong Wu, Juan Zhang, Xueyuan Wang, Jinkun Zhan, Hexuan Tang","doi":"10.1111/jmi.70009","DOIUrl":null,"url":null,"abstract":"<p><p>Structured illumination microscopy (SIM) as a type of super-resolution optical microscopy technique has been widely used in the fields of biophysics, neuroscience, and cell biology research. However, this technique often requires high-intensity illumination and multiple image acquisitions to generate a single high-resolution image. This process not only significantly reduces the imaging speed, but also increases the exposure time of samples to intense light, leading to increased phototoxicity and photobleaching issues, especially prominent in live cell imaging. Here, we propose a lightweight Multi-Convolutional UNet (MCU-Net) aiming to maintain efficient super-resolution reconstruction performance by reducing the model parameter quantity. The algorithm integrates multiple convolutional techniques with multi-scale attention mechanisms, enhancing the model's sensitivity to information at different scales and improving its precise recognition ability for image textures and structures, thus enabling high-quality super-resolution reconstruction even under low-light conditions. The overall performance of the model is evaluated in terms of efficiency and accuracy, comparing MCU-Net with deep neural network models (UNet, ScUNet, EDSR, DFCAN) and traditional reconstruction algorithms (Wiener, HiFi, TV) across different cell types, lighting intensities, and various test sets. Experimental results show that compared to other deep learning models, MCU-Net achieves a 12.66% improvement in MS-SSIM and a 50.79% increase in NRMSE index. Its prediction accuracy remains stable even in the presence of low signal-to-noise ratio inputs. Furthermore, it strikes an optimal balance between reconstruction speed and model accuracy, with a 76.10% improvement in inference speed compared to the DFCAN model.</p>","PeriodicalId":16484,"journal":{"name":"Journal of microscopy","volume":" ","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Reconstruction of structured illumination microscopy for live imaging in low light with lightweight neural networks.\",\"authors\":\"Hesong Jiang, Peihong Wu, Juan Zhang, Xueyuan Wang, Jinkun Zhan, Hexuan Tang\",\"doi\":\"10.1111/jmi.70009\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Structured illumination microscopy (SIM) as a type of super-resolution optical microscopy technique has been widely used in the fields of biophysics, neuroscience, and cell biology research. However, this technique often requires high-intensity illumination and multiple image acquisitions to generate a single high-resolution image. This process not only significantly reduces the imaging speed, but also increases the exposure time of samples to intense light, leading to increased phototoxicity and photobleaching issues, especially prominent in live cell imaging. Here, we propose a lightweight Multi-Convolutional UNet (MCU-Net) aiming to maintain efficient super-resolution reconstruction performance by reducing the model parameter quantity. The algorithm integrates multiple convolutional techniques with multi-scale attention mechanisms, enhancing the model's sensitivity to information at different scales and improving its precise recognition ability for image textures and structures, thus enabling high-quality super-resolution reconstruction even under low-light conditions. The overall performance of the model is evaluated in terms of efficiency and accuracy, comparing MCU-Net with deep neural network models (UNet, ScUNet, EDSR, DFCAN) and traditional reconstruction algorithms (Wiener, HiFi, TV) across different cell types, lighting intensities, and various test sets. Experimental results show that compared to other deep learning models, MCU-Net achieves a 12.66% improvement in MS-SSIM and a 50.79% increase in NRMSE index. Its prediction accuracy remains stable even in the presence of low signal-to-noise ratio inputs. Furthermore, it strikes an optimal balance between reconstruction speed and model accuracy, with a 76.10% improvement in inference speed compared to the DFCAN model.</p>\",\"PeriodicalId\":16484,\"journal\":{\"name\":\"Journal of microscopy\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-08-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of microscopy\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1111/jmi.70009\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MICROSCOPY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of microscopy","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1111/jmi.70009","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MICROSCOPY","Score":null,"Total":0}
Reconstruction of structured illumination microscopy for live imaging in low light with lightweight neural networks.
Structured illumination microscopy (SIM) as a type of super-resolution optical microscopy technique has been widely used in the fields of biophysics, neuroscience, and cell biology research. However, this technique often requires high-intensity illumination and multiple image acquisitions to generate a single high-resolution image. This process not only significantly reduces the imaging speed, but also increases the exposure time of samples to intense light, leading to increased phototoxicity and photobleaching issues, especially prominent in live cell imaging. Here, we propose a lightweight Multi-Convolutional UNet (MCU-Net) aiming to maintain efficient super-resolution reconstruction performance by reducing the model parameter quantity. The algorithm integrates multiple convolutional techniques with multi-scale attention mechanisms, enhancing the model's sensitivity to information at different scales and improving its precise recognition ability for image textures and structures, thus enabling high-quality super-resolution reconstruction even under low-light conditions. The overall performance of the model is evaluated in terms of efficiency and accuracy, comparing MCU-Net with deep neural network models (UNet, ScUNet, EDSR, DFCAN) and traditional reconstruction algorithms (Wiener, HiFi, TV) across different cell types, lighting intensities, and various test sets. Experimental results show that compared to other deep learning models, MCU-Net achieves a 12.66% improvement in MS-SSIM and a 50.79% increase in NRMSE index. Its prediction accuracy remains stable even in the presence of low signal-to-noise ratio inputs. Furthermore, it strikes an optimal balance between reconstruction speed and model accuracy, with a 76.10% improvement in inference speed compared to the DFCAN model.
期刊介绍:
The Journal of Microscopy is the oldest journal dedicated to the science of microscopy and the only peer-reviewed publication of the Royal Microscopical Society. It publishes papers that report on the very latest developments in microscopy such as advances in microscopy techniques or novel areas of application. The Journal does not seek to publish routine applications of microscopy or specimen preparation even though the submission may otherwise have a high scientific merit.
The scope covers research in the physical and biological sciences and covers imaging methods using light, electrons, X-rays and other radiations as well as atomic force and near field techniques. Interdisciplinary research is welcome. Papers pertaining to microscopy are also welcomed on optical theory, spectroscopy, novel specimen preparation and manipulation methods and image recording, processing and analysis including dynamic analysis of living specimens.
Publication types include full papers, hot topic fast tracked communications and review articles. Authors considering submitting a review article should contact the editorial office first.