{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:03:40Z","timestamp":1789668220659,"version":"4.0.1"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea (NRF) grant funded by the Korean Government","award":["NRF-2021R1A2C1011351"],"award-info":[{"award-number":["NRF-2021R1A2C1011351"]}]},{"name":"the Institute of Information and Communications Technology Planning, and Evaluation (IITP) grant funded by the Korean Government","award":["2021-0-01341"],"award-info":[{"award-number":["2021-0-01341"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Purpose<\/jats:title>\n<jats:p>To propose a neural network (NN) that can effectively segment orbital tissue in computed tomography (CT) images of Graves\u2019 orbitopathy (GO) patients.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We analyzed orbital CT scans from 701 GO patients diagnosed between 2010 and 2019 and devised an effective NN specializing in semantic orbital tissue segmentation in GO patients\u2019 CT images. After four conventional (Attention U-Net, DeepLab V3+, SegNet, and HarDNet-MSEG) and the proposed NN train the various manual orbital tissue segmentations, we calculated the Dice coefficient and Intersection over Union for comparison.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>CT images of the eyeball, four rectus muscles, the optic nerve, and the lacrimal gland tissues from all 701 patients were analyzed in this study. In the axial image with the largest eyeball area, the proposed NN achieved the best performance, with Dice coefficients of 98.2% for the eyeball, 94.1% for the optic nerve, 93.0% for the medial rectus muscle, and 91.1% for the lateral rectus muscle. The proposed NN also gave the best performance for the coronal image. Our qualitative analysis demonstrated that the proposed NN outputs provided more sophisticated orbital tissue segmentations for GO patients than the conventional NNs.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>We concluded that our proposed NN exhibited an improved CT image segmentation for GO patients over conventional NNs designed for semantic segmentation tasks.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0285488","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T18:27:25Z","timestamp":1683743245000},"page":"e0285488","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Effective encoder-decoder neural network for segmentation of orbital tissue in computed tomography images of Graves\u2019 orbitopathy patients"],"prefix":"10.1371","volume":"18","author":[{"given":"Seung Hyeun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0903-4392","authenticated-orcid":true,"given":"Sanghyuck","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaesung","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9797-9945","authenticated-orcid":true,"given":"Jeong Kyu","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nam Ju","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"key":"pone.0285488.ref001","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1167\/iovs.07-1030","article-title":"A new and validated CT-based method for the calculation of orbital soft tissue volumes","volume":"49","author":"NI Regensburg","year":"2008","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0285488.ref002","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.jcms.2011.05.014","article-title":"Endocrine orbitopathy: 11 years retrospective study and review of 102 patients & 196 orbits.","volume":"40","author":"LC Clauser","year":"2012","journal-title":"J Craniomaxillofac Surg."},{"key":"pone.0285488.ref003","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s00417-016-3538-0","article-title":"Quantitative analysis of orbital soft tissues on computed tomography to assess the activity of thyroid-associated orbitopathy.","volume":"255","author":"JS Byun","year":"2017","journal-title":"Graefes Arch Clin Exp"},{"key":"pone.0285488.ref004","doi-asserted-by":"crossref","first-page":"034006","DOI":"10.1117\/1.JMI.1.3.034006","article-title":"Robust optic nerve segmentation on clinically acquired computed tomography.","volume":"1","author":"RL Harrigan","year":"2014","journal-title":"J Med Imaging (Bellingham)."},{"key":"pone.0285488.ref005","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1118\/1.2826557","article-title":"Geometrical model\u2010based segmentation of the organs of sight on CT images.","volume":"35","author":"G Bekes","year":"2008","journal-title":"Med Phys"},{"key":"pone.0285488.ref006","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cmpb.2016.10.007","article-title":"Classification of CT brain images based on deep learning networks","volume":"138","author":"XW Gao","year":"2017","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0285488.ref007","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1016\/S0140-6736(18)31645-3","article-title":"Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study","volume":"392","author":"S Chilamkurthy","year":"2018","journal-title":"The Lancet"},{"key":"pone.0285488.ref008","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.media.2016.07.007","article-title":"Large-scale deep learning for computer-aided detection of mammographic lesions","volume":"35","author":"T Kooi","year":"2017","journal-title":"Med Image Anal"},{"key":"pone.0285488.ref009","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"Jama"},{"key":"pone.0285488.ref010","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1001\/jamaophthalmol.2018.4118","article-title":"Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration","volume":"136","author":"PM Burlina","year":"2018","journal-title":"JAMA Ophthalmol"},{"key":"pone.0285488.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-33013-w","article-title":"Development of a deep residual learning algorithm to screen for glaucoma from fundus photography","volume":"8","author":"N Shibata","year":"2018","journal-title":"Sci Rep"},{"key":"pone.0285488.ref012","doi-asserted-by":"crossref","first-page":"116442","DOI":"10.1016\/j.neuroimage.2019.116442","article-title":"Deep learning segmentation of orbital fat to calibrate conventional MRI for longitudinal studies.","volume":"208","author":"RA Brown","year":"2020","journal-title":"Neuroimage"},{"key":"pone.0285488.ref013","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.3174\/ajnr.A6538","article-title":"Fully automated segmentation of globes for volume quantification in CT images of orbits using deep learning.","volume":"41","author":"L Umapathy","year":"2020","journal-title":"Am J Neuroradiol"},{"key":"pone.0285488.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-93227-3","article-title":"A deep learning method for automatic segmentation of the bony orbit in MRI and CT images.","volume":"11","author":"J Hamwood","year":"2021","journal-title":"Sci Rep."},{"key":"pone.0285488.ref015","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T, editors. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention; 2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"pone.0285488.ref016","doi-asserted-by":"crossref","unstructured":"Noori M, Bahri A, Mohammadi K (Eds.). Attention-guided version of 2D UNet for automatic brain tumor segmentation. 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE); 2019.","DOI":"10.1109\/ICCKE48569.2019.8964956"},{"key":"pone.0285488.ref017","doi-asserted-by":"crossref","unstructured":"Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (Eds.). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV); 2018.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"pone.0285488.ref018","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":"V Badrinarayanan","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0285488.ref019","article-title":"HarDNet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean Dice and 86 fps.","author":"C-H Huang","year":"2021","journal-title":"arXiv"},{"key":"pone.0285488.ref020","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T, editors. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"pone.0285488.ref021","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.compbiomed.2019.05.002","article-title":"Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm","volume":"109","author":"M Buda","year":"2019","journal-title":"Comput Biol Med"},{"key":"pone.0285488.ref022","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G, (Eds.). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0285488.ref023","article-title":"Rethinking atrous convolution for semantic image segmentation.","author":"L-C Chen","year":"2017","journal-title":"arXiv"},{"key":"pone.0285488.ref024","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J, editors. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. Proceedings of the IEEE International Conference on Computer Vision; 2015.","DOI":"10.1109\/ICCV.2015.123"},{"key":"pone.0285488.ref025","first-page":"1412","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs.","author":"L-C Chen","year":"2014","journal-title":"arXiv"},{"key":"pone.0285488.ref026","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":"L-C Chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0285488.ref027","first-page":"229","article-title":"Pterygium tissues segmentation using densely connected DeepLab.","author":"S Abdani","year":"2020","journal-title":"IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE)."},{"key":"pone.0285488.ref028","first-page":"1","article-title":"Segmentation of kidney lesions with attention model based on DeepLab.","author":"A Wen","year":"2019","journal-title":"The 2019 Kidney Tumor Segmentation Challenge."},{"issue":"2","key":"pone.0285488.ref029","first-page":"458","article-title":"Semantic segmentation of lesions from dermoscopic images using Yolo-DeepLab networks.","volume":"34","author":"F Bagheri","year":"2021","journal-title":"Int J Eng"},{"key":"pone.0285488.ref030","doi-asserted-by":"crossref","first-page":"102023","DOI":"10.1016\/j.compmedimag.2021.102023","article-title":"Automated segmentation of epidermis in high-frequency ultrasound of pathological skin using a cascade of DeepLab v3+ networks and fuzzy connectedness.","volume":"95","author":"J Czajkowska","year":"2022","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0285488.ref031","doi-asserted-by":"crossref","unstructured":"Lucio DR, Laroca R, Severo E, Britto AS, Menotti D. Fully convolutional networks and generative adversarial networks applied to sclera segmentation. IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS). 2018: 1\u20137.","DOI":"10.1109\/BTAS.2018.8698597"},{"issue":"2","key":"pone.0285488.ref032","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s41095-019-0139-y","article-title":"Automated brain tumor segmentation on multi-modal MR image using SegNet","volume":"5","author":"S Alqazzaz","year":"2019","journal-title":"Comput Vis Media"},{"key":"pone.0285488.ref033","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1109\/YAC.2018.8406531","article-title":"SegNet-based gland segmentation from colon cancer histology images.","author":"J Tang","year":"2018","journal-title":"33rd Youth Academic Annual Conference of the Chinese Association of Automation (YAC)."},{"key":"pone.0285488.ref034","first-page":"317","article-title":"SegNet-based corpus callosum segmentation for brain magnetic resonance images (MRI).","author":"A Chandra","year":"2019","journal-title":"International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)."},{"key":"pone.0285488.ref035","first-page":"3552","article-title":"HarDNet: A low-memory traffic network","author":"P Chao","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"pone.0285488.ref036","first-page":"385","article-title":"Receptive field block net for accurate and fast object detection","author":"S Liu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"pone.0285488.ref037","doi-asserted-by":"crossref","first-page":"3721","DOI":"10.1002\/mp.14907","article-title":"Automated delineation of orbital abscess depicted on CT scan using deep learning.","volume":"48","author":"R Fu","year":"2021","journal-title":"Med Phys"},{"key":"pone.0285488.ref038","article-title":"Semantic segmentation using deep learning to extract total extraocular muscles and optic nerve from orbital computed tomography images.","author":"F Zhu","year":"2021","journal-title":"Optik"},{"key":"pone.0285488.ref039","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1097\/SCS.0000000000008198","article-title":"Deep Learning-Based CT Radiomics for Feature Representation and Analysis of Aging Characteristics of Asian Bony Orbit","volume":"33","author":"Z Li","year":"2022","journal-title":"J Craniofac Surg"},{"key":"pone.0285488.ref040","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1007\/s00276-022-02933-8","article-title":"Aging of Chinese bony orbit: automatic calculation based on UNet++ and connected component analysis.","volume":"44","author":"L Pan","year":"2022","journal-title":"Surg Radiol Anat."},{"key":"pone.0285488.ref041","article-title":"Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks.","volume":"12","author":"R Shanker","year":"2022","journal-title":"Diagnostics (Basel)."},{"key":"pone.0285488.ref042","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"D Ting","year":"2019","journal-title":"Br J Ophthalmol"},{"key":"pone.0285488.ref043","first-page":"285","article-title":"Development of a reliable method for orbit segmentation & measuring.","author":"M Becker","year":"2015","journal-title":"IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings."},{"key":"pone.0285488.ref044","doi-asserted-by":"crossref","first-page":"336","DOI":"10.3348\/kjr.2007.8.4.336","article-title":"The radiological spectrum of orbital pathologies that involve the lacrimal gland and the lacrimal fossa.","volume":"8","author":"W Jung","year":"2017","journal-title":"Korean J Radiol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0285488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T18:28:16Z","timestamp":1683743296000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0285488"}},"subtitle":[],"editor":[{"given":"Nour Eldeen Mahmoud","family":"Khalifa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,5,10]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,5,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0285488","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,10]]}}}