{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T14:28:44Z","timestamp":1763735324105,"version":"3.45.0"},"reference-count":48,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Microscopy"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Structured illumination microscopy (SIM) as a type of super\u2010resolution optical microscopy technique has been widely used in the fields of biophysics, neuroscience, and cell biology research. However, this technique often requires high\u2010intensity illumination and multiple image acquisitions to generate a single high\u2010resolution 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\u2010Convolutional UNet (MCU\u2010Net) aiming to maintain efficient super\u2010resolution reconstruction performance by reducing the model parameter quantity. The algorithm integrates multiple convolutional techniques with multi\u2010scale 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\u2010quality super\u2010resolution reconstruction even under low\u2010light conditions. The overall performance of the model is evaluated in terms of efficiency and accuracy, comparing MCU\u2010Net 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\u2010Net achieves a 12.66% improvement in MS\u2010SSIM and a 50.79% increase in NRMSE index. Its prediction accuracy remains stable even in the presence of low signal\u2010to\u2010noise 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.<\/jats:p>","DOI":"10.1111\/jmi.70009","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:22:21Z","timestamp":1755868941000},"page":"325-340","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reconstruction of structured illumination microscopy for live imaging in low light with lightweight neural networks"],"prefix":"10.1111","volume":"300","author":[{"given":"Hesong","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3427-8339","authenticated-orcid":false,"given":"Peihong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinkun","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexuan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering Southwest University of Science and Technology  Sichuan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41556\u2010018\u20100251\u20108"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth929"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.1176"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1364\/OL.19.000780"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0406877102"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1107547108"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365\u20102818.2000.00710.x"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3500"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.3.000667"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cbpa.2014.04.008"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201048575\u20109"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"Lal A. Shan C. &Xi P.(2016).Structured illumination microscopy image reconstruction algorithm.IEEE Journal of Selected Topics in Quantum Electronics 22(4) 50\u201063.https:\/\/doi.org\/10.1109\/JSTQE.2016.2521542","DOI":"10.1109\/JSTQE.2016.2521542"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"Wen G. Li S. &Wang U. et\u00a0al. (2021).High\u2010fidelity structured illumination microscopy by point\u2010spread\u2010function engineering.Light: Science and Applications (English Edition) 10(5) 12.","DOI":"10.1038\/s41377-021-00513-w"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep37149"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2016.12.015"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010021\u201001092\u20102"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010020\u20100560\u2010x"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms12471"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-02057-w"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2018.12.005"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01471-3"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010018\u20100216\u20107"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010018\u20100239\u20100"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010020\u201015784\u2010x"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.414680"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001048\u20105"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"Burns Z. &Liu Z.(2022).Untrained physics\u2010informed neural networks for structured illumination microscopy. arXiv:2207.07705.https:\/\/doi.org\/10.48550\/arXiv.2207.07705","DOI":"10.1364\/OE.476781"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001035\u2010w"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.20944\/preprints201812.0137.v2"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1086\/111605"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"Taigman Y. Yang M. Ranzato M. &Wolf L.(2014).DeepFace: Closing the gap to human\u2010level performance in face verification. InIEEE Conference on Computer Vision & Pattern Recognition.IEEE Computer Societyhttps:\/\/doi.org\/10.1109\/CVPR.2014.220","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_2_8_34_1","doi-asserted-by":"crossref","unstructured":"Lu Y. Kumar A. &Zhai S. et\u00a0al. (2016).Fully\u2010adaptive feature sharing in multi\u2010task networks with applications in person attribute classification. In2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE.https:\/\/doi.org\/10.1109\/CVPR.2017.126","DOI":"10.1109\/CVPR.2017.126"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010021\u201001284\u20103"},{"key":"e_1_2_8_36_1","unstructured":"Gong Y. Liu L. Yang M. &Bourdev L.(2014).Compressing deep convolutional networks using vector quantization. arXiv:1412.6115.https:\/\/doi.org\/10.48550\/arXiv.1412.6115"},{"key":"e_1_2_8_37_1","unstructured":"Ba L. J. &Caruana R.(2013).Do deep nets really need to be deep?. arXiv:1312.6184.https:\/\/doi.org\/10.48550\/arXiv.1312.6184"},{"key":"e_1_2_8_38_1","unstructured":"Almahairi A. Ballas N. Cooijmans T. Zheng Y. Larochelle H. &Courville A.(2015).Dynamic capacity networks. arXiv:1511.07838.https:\/\/doi.org\/10.48550\/arXiv.1511.07838"},{"key":"e_1_2_8_39_1","doi-asserted-by":"crossref","unstructured":"Niessen W. J.(2001).Medical image computing and computer\u2010assisted intervention \u2013 MICCAI 2001.Springer.","DOI":"10.1007\/3-540-45468-3"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010019\u20100356\u20104"},{"key":"e_1_2_8_41_1","doi-asserted-by":"crossref","unstructured":"Ding X. Guo Y. Ding G. &Han J.(2019).ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. arXiv:1908.03930.https:\/\/doi.org\/10.1109\/ICCV.2019.00200","DOI":"10.1109\/ICCV.2019.00200"},{"key":"e_1_2_8_42_1","unstructured":"Yu F. &Koltun V.(2016).Multi\u2010scale context aggregation by dilated convolutions.ICLR.https:\/\/doi.org\/10.48550\/arXiv.1511.07122"},{"key":"e_1_2_8_43_1","doi-asserted-by":"crossref","unstructured":"Kong F. Li M. Liu S. Liu D. He J. Bai Y. Chen F. &Fu L.(2022).Residual local feature network for efficient super\u2010resolution. arXiv:2205.07514.https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00092","DOI":"10.1109\/CVPRW56347.2022.00092"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_2_8_45_1","unstructured":"Ronneberger O. Fischer P. &Brox T.(2015).UNet: Convolutional networks for biomedical image segmentation. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer International Publishing.https:\/\/doi.org\/10.1007\/978\u20103\u2010319\u201024574\u20104_28"},{"key":"e_1_2_8_46_1","doi-asserted-by":"crossref","unstructured":"Lim B. Son S. Kim H. Nah S. &Lee K. M.(2017).Enhanced deep residual networks for single image super\u2010resolution.IEEEhttps:\/\/doi.org\/10.1109\/CVPRW.2017.151","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2818.2000.00710.x"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.22.008687"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1038\/nphoton.2016.200"}],"container-title":["Journal of Microscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jmi.70009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T13:39:47Z","timestamp":1763732387000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jmi.70009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1111\/jmi.70009"],"URL":"https:\/\/doi.org\/10.1111\/jmi.70009","archive":["Portico"],"relation":{},"ISSN":["0022-2720","1365-2818"],"issn-type":[{"type":"print","value":"0022-2720"},{"type":"electronic","value":"1365-2818"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"2025-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}