{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:14:54Z","timestamp":1783419294790,"version":"3.54.6"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T00:00:00Z","timestamp":1681689600000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1U01CA242936"],"award-info":[{"award-number":["1U01CA242936"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T32EY07092"],"award-info":[{"award-number":["T32EY07092"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30EY006360"],"award-info":[{"award-number":["P30EY006360"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EY028450"],"award-info":[{"award-number":["R01EY028450"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"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":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Morphological analyses with flatmount fluorescent images are essential to retinal pigment epithelial (RPE) aging studies and thus require accurate RPE cell segmentation. Although rapid technology advances in deep learning semantic segmentation have achieved great success in many biomedical research, the performance of these supervised learning methods for RPE cell segmentation is still limited by inadequate training data with high-quality annotations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To address this problem, we develop a Self-Supervised Semantic Segmentation (S4) method that utilizes a self-supervised learning strategy to train a semantic segmentation network with an encoder\u2013decoder architecture. We employ a reconstruction and a pairwise representation loss to make the encoder extract structural information, while we create a morphology loss to produce the segmentation map. In addition, we develop a novel image augmentation algorithm (AugCut) to produce multiple views for self-supervised learning and enhance the network training performance. To validate the efficacy of our method, we applied our developed S4 method for RPE cell segmentation to a large set of flatmount fluorescent microscopy images, we compare our developed method for RPE cell segmentation with other state-of-the-art deep learning approaches. Compared with other state-of-the-art deep learning approaches, our method demonstrates better performance in both qualitative and quantitative evaluations, suggesting its promising potential to support large-scale cell morphological analyses in RPE aging investigations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The codes and the documentation are available at: https:\/\/github.com\/jkonglab\/S4_RPE.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad191","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T14:25:33Z","timestamp":1681741533000},"source":"Crossref","is-referenced-by-count":4,"title":["Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images"],"prefix":"10.1093","volume":"39","author":[{"given":"Hanyi","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Emory University , Atlanta, GA 30322, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9369-9361","authenticated-orcid":false,"given":"Fusheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University , Stony Brook, NY 11794, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6289-3914","authenticated-orcid":false,"given":"George","family":"Teodoro","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Federal University of Minas Gerais , Belo Horizonte 31270, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Chen","sequence":"additional","affiliation":[{"name":"Huangpu Branch, Guangzhou Urban Planning & Design Survey Research Institute , Guangzhou 510060, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University , Atlanta, GA 30322, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John M","family":"Nickerson","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Emory University , Atlanta, GA 30322, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8757-8339","authenticated-orcid":false,"given":"Jun","family":"Kong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University , Atlanta, GA 30322, USA"},{"name":"Department of Mathematics and Statistics, Georgia State University , Atlanta, GA 30303, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,4,17]]},"reference":[{"key":"2023042723054181000_btad191-B1","doi-asserted-by":"crossref","first-page":"4832","DOI":"10.1167\/iovs.14-14802","article-title":"Quantitative autofluorescence and cell density maps of the human retinal pigment epithelium","volume":"55","author":"Ach","year":"2014","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2023042723054181000_btad191-B2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/S0039-6257(03)00030-4","article-title":"Age-related macular degeneration: etiology, pathogenesis, and therapeutic strategies","volume":"48","author":"Ambati","year":"2003","journal-title":"Surv Ophthalmol"},{"key":"2023042723054181000_btad191-B3","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10462-020-09854-1","article-title":"Deep semantic segmentation of natural and medical images: a review","volume":"54","author":"Asgari Taghanaki","year":"2021","journal-title":"Artif Intell Rev"},{"key":"2023042723054181000_btad191-B4","author":"Bao","year":"2022"},{"key":"2023042723054181000_btad191-B5","first-page":"898","article-title":"Analysis of RPE morphometry in human eyes","volume":"22","author":"Bhatia","year":"2016","journal-title":"Mol Vis"},{"key":"2023042723054181000_btad191-B6","first-page":"40","article-title":"Methodologies for analysis of patterning in the mouse RPE sheet","volume":"21","author":"Boatright","year":"2015","journal-title":"Mol Vis"},{"key":"2023042723054181000_btad191-B7","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023042723054181000_btad191-B8","first-page":"9650","author":"Caron","year":"2021"},{"key":"2023042723054181000_btad191-B9","volume-title":"Digital Image Processing","author":"Castleman","year":"1996"},{"key":"2023042723054181000_btad191-B10","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023042723054181000_btad191-B11","first-page":"15750","author":"Chen","year":"2021"},{"key":"2023042723054181000_btad191-B12","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1007\/978-1-4614-0631-0_81","volume-title":"Retinal Degenerative Diseases","author":"Chrenek","year":"2012"},{"key":"2023042723054181000_btad191-B13","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2023042723054181000_btad191-B14","author":"Gidaris","year":"2018"},{"key":"2023042723054181000_btad191-B15","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023042723054181000_btad191-B16","doi-asserted-by":"crossref","first-page":"100297","DOI":"10.1016\/j.imu.2020.100297","article-title":"Deep learning approaches to biomedical image segmentation","volume":"18","author":"Haque","year":"2020","journal-title":"Inform Med Unlocked"},{"key":"2023042723054181000_btad191-B17","first-page":"9729","author":"He","year":"2020"},{"key":"2023042723054181000_btad191-B18","first-page":"16000","author":"He","year":"2022"},{"key":"2023042723054181000_btad191-B19","author":"Hendrycks","year":"2020"},{"key":"2023042723054181000_btad191-B20","author":"Higgins","year":"2017"},{"key":"2023042723054181000_btad191-B21","first-page":"432","author":"Hu","year":"2019"},{"key":"2023042723054181000_btad191-B22","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","article-title":"MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw"},{"key":"2023042723054181000_btad191-B23","first-page":"2733","author":"Jenni","year":"2018"},{"key":"2023042723054181000_btad191-B24","doi-asserted-by":"crossref","first-page":"7274","DOI":"10.1167\/iovs.13-12450","article-title":"Functional principal component analysis reveals discriminating categories of retinal pigment epithelial morphology in mice","volume":"54","author":"Jiang","year":"2013","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2023042723054181000_btad191-B25","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1167\/iovs.62.2.32","article-title":"Morphometric analysis of retinal pigment epithelial cells from c57bl\/6j mice during aging","volume":"62","author":"Kim","year":"2021","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2023042723054181000_btad191-B26","author":"Kingma","year":"2014"},{"key":"2023042723054181000_btad191-B27","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","article-title":"H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes","volume":"37","author":"Li","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"2023042723054181000_btad191-B28","first-page":"30865","author":"Li"},{"key":"2023042723054181000_btad191-B29","first-page":"3431","author":"Long","year":"2015"},{"key":"2023042723054181000_btad191-B30","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"2023042723054181000_btad191-B32","first-page":"319","author":"Park","year":"2020"},{"key":"2023042723054181000_btad191-B33","first-page":"8024","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023042723054181000_btad191-B34","first-page":"234","author":"Ronneberger","year":"2015"},{"key":"2023042723054181000_btad191-B35","author":"Shamshad"},{"key":"2023042723054181000_btad191-B36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J Big Data"},{"key":"2023042723054181000_btad191-B37","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1152\/physrev.00021.2004","article-title":"The retinal pigment epithelium in visual function","volume":"85","author":"Strauss","year":"2005","journal-title":"Physiol Rev"},{"key":"2023042723054181000_btad191-B38","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1038\/s41592-020-01018-x","article-title":"Cellpose: a generalist algorithm for cellular segmentation","volume":"18","author":"Stringer","year":"2021","journal-title":"Nat Methods"},{"key":"2023042723054181000_btad191-B39","first-page":"776","author":"Tian","year":"2020"},{"key":"2023042723054181000_btad191-B31","author":"van den Oord","year":"2018"},{"key":"2023042723054181000_btad191-B40","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023042723054181000_btad191-B41","author":"Wang","year":"2018"},{"key":"2023042723054181000_btad191-B42","first-page":"3","author":"Woo","year":"2018"},{"key":"2023042723054181000_btad191-B43","author":"Xu","year":"2021"},{"key":"2023042723054181000_btad191-B44","doi-asserted-by":"crossref","first-page":"105596","DOI":"10.1016\/j.compbiomed.2022.105596","article-title":"MultiHeadGAN: a deep learning method for low contrast retinal pigment epithelium cell segmentation with fluorescent flatmount microscopy images","volume":"146","author":"Yu","year":"2022","journal-title":"Comput Biol Med"},{"key":"2023042723054181000_btad191-B45","first-page":"6023","author":"Yun","year":"2019"},{"key":"2023042723054181000_btad191-B46","author":"Zhang","year":"2018"},{"key":"2023042723054181000_btad191-B47","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc IEEE"},{"key":"2023042723054181000_btad191-B48","first-page":"6002","author":"Zhuang","year":"2019"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad191\/49989239\/btad191.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad191\/50117098\/btad191.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad191\/50117098\/btad191.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T23:06:30Z","timestamp":1682636790000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad191\/7126414"}},"subtitle":[],"editor":[{"given":"Hanchuan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad191","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,4,1]]},"published":{"date-parts":[[2023,4,1]]},"article-number":"btad191"}}