{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T04:09:25Z","timestamp":1786162165863,"version":"3.56.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioinform."],"abstract":"<jats:p><jats:bold>Introduction:<\/jats:bold> Although a powerful biological imaging technique, fluorescence lifetime imaging microscopy (FLIM) faces challenges such as a slow acquisition rate, a low signal-to-noise ratio (SNR), and high cost and complexity. To address the fundamental problem of low SNR in FLIM images, we demonstrate how to use pre-trained convolutional neural networks (CNNs) to reduce noise in FLIM measurements.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> Our approach uses pre-learned models that have been previously validated on large datasets with different distributions than the training datasets, such as sample structures, noise distributions, and microscopy modalities in fluorescence microscopy, to eliminate the need to train a neural network from scratch or to acquire a large training dataset to denoise FLIM data. In addition, we are using the pre-trained networks in the inference stage, where the computation time is in milliseconds and accuracy is better than traditional denoising methods. To separate different fluorophores in lifetime images, the denoised images are then run through an unsupervised machine learning technique named \u201cK-means clustering\u201d.<\/jats:p><jats:p><jats:bold>Results and Discussion:<\/jats:bold> The results of the experiments carried out on in vivo mouse kidney tissue, Bovine pulmonary artery endothelial (BPAE) fixed cells that have been fluorescently labeled, and mouse kidney fixed samples that have been fluorescently labeled show that our demonstrated method can effectively remove noise from FLIM images and improve segmentation accuracy. Additionally, the performance of our method on out-of-distribution highly scattering in vivo plant samples shows that it can also improve SNR in challenging imaging conditions. Our proposed method provides a fast and accurate way to segment fluorescence lifetime images captured using any FLIM system. It is especially effective for separating fluorophores in noisy FLIM images, which is common in in vivo imaging where averaging is not applicable. Our approach significantly improves the identification of vital biologically relevant structures in biomedical imaging applications.<\/jats:p>","DOI":"10.3389\/fbinf.2023.1335413","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T04:12:46Z","timestamp":1703218366000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Improving fluorescence lifetime imaging microscopy phasor accuracy using convolutional neural networks"],"prefix":"10.3389","volume":"3","author":[{"given":"Varun","family":"Mannam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"P. Brandt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody J.","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Howard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/s0091-679x(06)81024-1","article-title":"Fluorescence lifetime imaging microscopy","volume":"81","author":"Chang","year":"2007","journal-title":"Methods Cell Biol."},{"key":"B2","unstructured":"Skellam distribution\n            contributorsW.\n          2004"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/tip.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"B4","doi-asserted-by":"publisher","first-page":"071203","DOI":"10.1117\/1.jbo.25.7.071203","article-title":"Fluorescence lifetime imaging microscopy: fundamentals and advances in instrumentation, analysis, and applications","volume":"25","author":"Datta","year":"2020","journal-title":"J. Biomed. Opt."},{"key":"B5","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1201\/b17018-14","article-title":"The phasor approach to fluorescence lifetime imaging: exploiting phasor linear properties","author":"Digman","year":"2014","journal-title":"Fluoresc. Lifetime Spectrosc. Imaging"},{"key":"B6","unstructured":"SSIM: a java plugin in ImageJ\n            GabrielP. R.\n          2008"},{"key":"B7","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"B8","unstructured":"Distribution of the ratio of two Poisson random variables\n            GriffinT. F.\n          1992"},{"key":"B9","first-page":"2366","article-title":"Image quality metrics: PSNR vs. SSIM","author":"Hore","year":"2010"},{"key":"B10","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","article-title":"Data clustering: 50 years beyond K-means","volume":"31","author":"Jain","year":"2010","journal-title":"Pattern Recognit. Lett."},{"key":"B11","first-page":"2965","article-title":"Noise2Noise: learning image restoration without clean data","volume":"80","author":"Lehtinen","year":"2018","journal-title":"Proc. Mach. Learn. Res."},{"key":"B12","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","author":"MacQueen","year":"1967"},{"key":"B13","volume-title":"Overcoming fundamental limits of three-dimensional","author":"Mannam","year":"2022"},{"key":"B14","doi-asserted-by":"publisher","first-page":"036501","DOI":"10.1117\/1.jbo.28.3.036501","article-title":"Small training dataset convolutional neural networks for application-specific super-resolution microscopy","volume":"28","author":"Mannam","year":"2023","journal-title":"J. Biomed. Opt."},{"key":"B15","volume-title":"Performance analysis of semi-supervised learning in the small-data regime using VAEs","author":"Mannam","year":"2020"},{"key":"B16","first-page":"116481C","article-title":"Convolutional neural network denoising in fluorescence lifetime imaging microscopy (FLIM)","volume":"11648","author":"Mannam","year":"2021"},{"key":"B17","doi-asserted-by":"publisher","first-page":"042005","DOI":"10.1088\/2515-7647\/abac1a","article-title":"Machine learning for faster and smarter fluorescence lifetime imaging microscopy","volume":"2","author":"Mannam","year":"","journal-title":"J. Phys. Photonics"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.1364\/MICROSCOPY.2020.MW2A.3","volume-title":"Instant image denoising plugin for ImageJ using convolutional neural networks","author":"Mannam","year":""},{"key":"B19","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1364\/optica.448287","article-title":"Real-time image denoising of mixed Poisson\u2013Gaussian noise in fluorescence microscopy images using ImageJ","volume":"9","author":"Mannam","year":"2022","journal-title":"Optica"},{"key":"B20","volume-title":"9.7.0.1190202 (R2019b) (natick, Massachusetts: the MathWorks inc.)","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1364\/optica.5.000458","article-title":"Deep-STORM: super-resolution single-molecule microscopy by deep learning","volume":"5","author":"Nehme","year":"2018","journal-title":"Optica"},{"key":"B22","unstructured":"ImageJ tensorflow library\n            RuedenC.\n            SchmidtD.\n            WilhelmB.\n          2017"},{"key":"B23","unstructured":"ImageJ\u2019s plugin to assess the quality of images\n            SageD.\n          2017"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1038\/s41467-021-22518-0","article-title":"Democratising deep learning for microscopy with ZeroCostDL4Mic","volume":"12","author":"von Chamier","year":"2021","journal-title":"Nat. Commun."},{"key":"B25","doi-asserted-by":"publisher","first-page":"3463","DOI":"10.1364\/boe.420953","article-title":"Complex wavelet filter improves FLIM phasors for photon starved imaging experiments","volume":"12","author":"Wang","year":"2021","journal-title":"Biomed. Opt. Express"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1038\/s41592-018-0216-7","article-title":"Content-Aware Image Restoration: pushing the limits of fluorescence microscopy","volume":"15","author":"Weigert","year":"2018","journal-title":"Nat. Methods"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/tip.2017.2662206","article-title":"Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"B28","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1364\/optica.426870","article-title":"Instant FLIM enables 4D in vivo lifetime imaging of intact and injured zebrafish and mouse brains","volume":"8","author":"Zhang","year":"2021","journal-title":"Optica"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3928","DOI":"10.1364\/ol.44.003928","article-title":"Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors","volume":"44","author":"Zhang","year":"2019","journal-title":"Opt. Lett."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2023.1335413\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T04:12:52Z","timestamp":1703218372000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2023.1335413\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":29,"alternative-id":["10.3389\/fbinf.2023.1335413"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2023.1335413","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,22]]},"article-number":"1335413"}}