{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:33:56Z","timestamp":1772138036590,"version":"3.50.1"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2021,1,8]],"date-time":"2021-01-08T00:00:00Z","timestamp":1610064000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"LIEF","award":["LE170100200"],"award-info":[{"award-number":["LE170100200"]}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"NHLBI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The inherent low contrast of electron microscopy (EM) datasets presents a significant challenge for rapid segmentation of cellular ultrastructures from EM data. This challenge is particularly prominent when working with high-resolution big-datasets that are now acquired using electron tomography and serial block-face imaging techniques. Deep learning (DL) methods offer an exciting opportunity to automate the segmentation process by learning from manual annotations of a small sample of EM data. While many DL methods are being rapidly adopted to segment EM data no benchmark analysis has been conducted on these methods to date.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present EM-stellar, a platform that is hosted on Google Colab that can be used to benchmark the performance of a range of state-of-the-art DL methods on user-provided datasets. Using EM-stellar we show that the performance of any DL method is dependent on the properties of the images being segmented. It also follows that no single DL method performs consistently across all performance evaluation metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>EM-stellar (code and data) is written in Python and is freely available under MIT license on GitHub (https:\/\/github.com\/cellsmb\/em-stellar).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa1094","type":"journal-article","created":{"date-parts":[[2020,12,23]],"date-time":"2020-12-23T10:24:03Z","timestamp":1608719043000},"page":"97-106","source":"Crossref","is-referenced-by-count":22,"title":["EM-stellar: benchmarking deep learning for electron microscopy image segmentation"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0496-5219","authenticated-orcid":false,"given":"Afshin","family":"Khadangi","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, University of Melbourne , Victoria, 3000, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0148-7733","authenticated-orcid":false,"given":"Thomas","family":"Boudier","sequence":"additional","affiliation":[{"name":"Institute of Molecular Biology, Academia Sinica , Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5509-402X","authenticated-orcid":false,"given":"Vijay","family":"Rajagopal","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Melbourne , Victoria, 3000, Australia"}]}],"member":"286","published-online":{"date-parts":[[2021,1,8]]},"reference":[{"key":"2023051510475226600_btaa1094-B1","first-page":"265","author":"Abadi","year":"2016"},{"key":"2023051510475226600_btaa1094-B2","doi-asserted-by":"crossref","first-page":"142","DOI":"10.3389\/fnana.2015.00142","article-title":"Crowdsourcing the creation of image segmentation algorithms for connectomics","volume":"9","author":"Arganda-Carreras","year":"2015","journal-title":"Front. Neuroanat"},{"key":"2023051510475226600_btaa1094-B3","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023051510475226600_btaa1094-B4","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1002\/cyto.a.23863","article-title":"Evaluation of deep learning strategies for nucleus segmentation in fluorescence images","volume":"95","author":"Caicedo","year":"2019","journal-title":"Cytometry Part A"},{"key":"2023051510475226600_btaa1094-B5","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-3-319-42999-1_2","volume-title":"Deep Learning and Convolutional Neural Networks for Medical Image Computing","author":"Carneiro","year":"2017"},{"key":"2023051510475226600_btaa1094-B6","first-page":"248","author":"Deng","year":"2009"},{"key":"2023051510475226600_btaa1094-B7","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1038\/nature14614","article-title":"Mitochondrial reticulum for cellular energy distribution in muscle","volume":"523","author":"Glancy","year":"2015","journal-title":"Nature"},{"key":"2023051510475226600_btaa1094-B8","author":"Goyal","year":"2017"},{"key":"2023051510475226600_btaa1094-B9","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1038\/s41592-018-0106-z","article-title":"CDeep3M\u2014plug-and-play cloud-based deep learning for image segmentation","volume":"15","author":"Haberl","year":"2018","journal-title":"Nat. Methods"},{"key":"2023051510475226600_btaa1094-B10","first-page":"1026","author":"He","year":"2015"},{"key":"2023051510475226600_btaa1094-B11","first-page":"770","author":"He","year":"2016"},{"key":"2023051510475226600_btaa1094-B12","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.jsb.2018.02.005","article-title":"An automated workflow for segmenting single adult cardiac cells from large-volume serial block-face scanning electron microscopy data","volume":"202","author":"Hussain","year":"2018","journal-title":"J. Struct. Biol"},{"key":"2023051510475226600_btaa1094-B13","author":"Iglovikov","year":"2018"},{"key":"2023051510475226600_btaa1094-B14","author":"Ioffe","year":"2015"},{"issue":"2016","key":"2023051510475226600_btaa1094-B15","article-title":"On loss functions for deep neural networks in classification","volume":"1","author":"Janocha","year":"2017","journal-title":"arXiv:170205659"},{"key":"2023051510475226600_btaa1094-B16","first-page":"877","author":"Khadangi","year":"2018"},{"key":"2023051510475226600_btaa1094-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-019-0962-1","article-title":"Automated segmentation of cardiomyocyte Z-disks from high-throughput scanning electron microscopy data","volume":"19","author":"Khadangi","year":"2019","journal-title":"BMC Med. Inform. Decis. Making"},{"key":"2023051510475226600_btaa1094-B18","article-title":"EM-net: deep learning for electron microscopy image segmentation","author":"Khadangi","year":"2020","journal-title":"bioRxiv"},{"key":"2023051510475226600_btaa1094-B19","first-page":"1970","author":"Khadangi","year":"2016"},{"key":"2023051510475226600_btaa1094-B20","article-title":"Spartan performance and flexibility: an HPC-cloud chimera","author":"Lafayette","year":"2016"},{"key":"2023051510475226600_btaa1094-B21","first-page":"2980","author":"Lin","year":"2017"},{"key":"2023051510475226600_btaa1094-B22","author":"Liu","year":"2019"},{"key":"2023051510475226600_btaa1094-B23","year":"2015"},{"key":"2023051510475226600_btaa1094-B24","first-page":"234","article-title":"U","author":"Ronneberger","year":"2015"},{"key":"2023051510475226600_btaa1094-B25","first-page":"265","author":"Schmidt","year":"2018"},{"key":"2023051510475226600_btaa1094-B26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:14091556"},{"key":"2023051510475226600_btaa1094-B27","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"Szegedy","year":"2017"},{"key":"2023051510475226600_btaa1094-B28","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","article-title":"Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool","volume":"15","author":"Taha","year":"2015","journal-title":"BMC Med. Imaging"},{"key":"2023051510475226600_btaa1094-B29","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:190511946"},{"key":"2023051510475226600_btaa1094-B30","article-title":"ZeroCostDL4Mic: an open platform to simplify access and use of deep-learning in microscopy","author":"Von Chamier","year":"2020","journal-title":"BioRxiv"},{"key":"2023051510475226600_btaa1094-B31","doi-asserted-by":"crossref","first-page":"4550","DOI":"10.1109\/TNNLS.2017.2766168","article-title":"Deep learning in microscopy image analysis: a survey","volume":"29","author":"Xing","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa1094\/35926679\/btaa1094.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/1\/97\/50321585\/btaa1094.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/1\/97\/50321585\/btaa1094.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T06:50:23Z","timestamp":1684133423000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/1\/97\/6069571"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,4,9]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa1094","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.15.203836","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,1,1]]},"published":{"date-parts":[[2021,1,1]]}}}