{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T21:04:30Z","timestamp":1794258270506,"version":"4.9.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U20A20363"],"award-info":[{"award-number":["U20A20363"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province, China","doi-asserted-by":"crossref","award":["LH2020H039"],"award-info":[{"award-number":["LH2020H039"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Higher Education Reform Project of Heilongjiang Province, China","award":["SJGY20180332"],"award-info":[{"award-number":["SJGY20180332"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Diabetes can cause microvessel impairment. However, these conjunctival pathological changes are not easily recognized, limiting their potential as independent diagnostic indicators. Therefore, we designed a deep learning model to explore the relationship between conjunctival features and diabetes, and to advance automated identification of diabetes through conjunctival images. Images were collected from patients with type 2 diabetes and healthy volunteers. A hierarchical multi-tasking network model (HMT-Net) was developed using conjunctival images, and the model was systematically evaluated and compared with other algorithms. The sensitivity, specificity, and accuracy of the HMT-Net model to identify diabetes were 78.70%, 69.08%, and 75.15%, respectively. The performance of the HMT-Net model was significantly better than that of ophthalmologists. The model allowed sensitive and rapid discrimination by assessment of conjunctival images and can be potentially useful for identifying diabetes.<\/jats:p>","DOI":"10.1038\/s41598-021-04006-z","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T11:03:21Z","timestamp":1641553401000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Identifying diabetes from conjunctival images using a novel hierarchical multi-task network"],"prefix":"10.1038","volume":"12","author":[{"given":"Xinyue","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjie","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangqing","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayue","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanpeng","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,7]]},"reference":[{"key":"4006_CR1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41551-019-0487-z","volume":"4","author":"A Mitani","year":"2020","unstructured":"Mitani, A. et al. Detection of anaemia from retinal fundus images via deep learning. Nat. Biomed. Eng. 4, 18\u201327. https:\/\/doi.org\/10.1038\/s41551-019-0487-z (2020).","journal-title":"Nat. Biomed. Eng."},{"key":"4006_CR2","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158\u2013164. https:\/\/doi.org\/10.1038\/s41551-018-0195-0 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"4006_CR3","doi-asserted-by":"publisher","first-page":"e88","DOI":"10.1016\/S2589-7500(20)30288-0","volume":"3","author":"W Xiao","year":"2021","unstructured":"Xiao, W. et al. Screening and identifying hepatobiliary diseases through deep learning using ocular images: a prospective, multicentre study. Lancet Digit. Heal. 3, e88\u2013e97. https:\/\/doi.org\/10.1016\/S2589-7500(20)30288-0 (2021).","journal-title":"Lancet Digit. Heal."},{"key":"4006_CR4","doi-asserted-by":"publisher","first-page":"6249","DOI":"10.1364\/boe.399473","volume":"11","author":"C Banbury","year":"2020","unstructured":"Banbury, C. et al. Spectroscopic detection of traumatic brain injury severity and biochemistry from the retina. Biomed. Opt. Express. 11, 6249\u20136261. https:\/\/doi.org\/10.1364\/boe.399473 (2020).","journal-title":"Biomed. Opt. Express."},{"key":"4006_CR5","unstructured":"International Diabetes Federation. IDF diabetes atlas. 9th edn, (International Diabetes Federation, 2019)."},{"key":"4006_CR6","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/CH-2010-1374","volume":"47","author":"WJ To","year":"2011","unstructured":"To, W. J., Telander, D. G., Lloyd, M. E., Chen, P. C. & Cheung, A. T. Correlation of conjunctival microangiopathy with retinopathy in type-2 diabetes mellitus (T2DM) patients. Clin. Hemorheol. Microcirc. 47, 131\u2013141. https:\/\/doi.org\/10.3233\/CH-2010-1374 (2011).","journal-title":"Clin. Hemorheol. Microcirc."},{"key":"4006_CR7","doi-asserted-by":"publisher","first-page":"285","DOI":"10.3233\/CH-2009-1199","volume":"42","author":"AT Cheung","year":"2009","unstructured":"Cheung, A. T. et al. Correlation of microvascular abnormalities and endothelial dysfunction in Type-1 Diabetes Mellitus (T1DM): a real-time intravital microscopy study. Clin. Hemorheol. Microcirc. 42, 285\u2013295. https:\/\/doi.org\/10.3233\/CH-2009-1199 (2009).","journal-title":"Clin. Hemorheol. Microcirc."},{"key":"4006_CR8","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1109\/TMI.2015.2486619","volume":"35","author":"MM Khansari","year":"2016","unstructured":"Khansari, M. M., Wanek, J., Felder, A. E., Camardo, N. & Shahidi, M. Automated assessment of hemodynamics in the conjunctival microvasculature network. IEEE Trans. Med. Imaging 35, 605\u2013611. https:\/\/doi.org\/10.1109\/TMI.2015.2486619 (2016).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4006_CR9","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1364\/BOE.7.002597","volume":"7","author":"MM Khansari","year":"2016","unstructured":"Khansari, M. M. et al. Automated fine structure image analysis method for discrimination of diabetic retinopathy stage using conjunctival microvasculature images. Biomed. Opt. Express. 7, 2597\u20132606. https:\/\/doi.org\/10.1364\/BOE.7.002597 (2016).","journal-title":"Biomed. Opt. Express."},{"key":"4006_CR10","doi-asserted-by":"publisher","DOI":"10.4172\/2155-9570.1000400","author":"N Stuebiger","year":"2015","unstructured":"Stuebiger, N., Smiddy, W., Wang, J., Jiang, H. & DeBuc, D. C. Assesment of conjunctival microangiopathy in a patient with diabetes mellitus using the retinal function imager. J. Clin. Exp. Ophthalmol. https:\/\/doi.org\/10.4172\/2155-9570.1000400 (2015).","journal-title":"J. Clin. Exp. Ophthalmol."},{"key":"4006_CR11","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1109\/JBHI.2020.2991043","volume":"24","author":"AS Panayides","year":"2020","unstructured":"Panayides, A. S. et al. AI in medical imaging informatics: current challenges and future directions. IEEE J. Biomed. Health Inform. 24, 1837\u20131857. https:\/\/doi.org\/10.1109\/JBHI.2020.2991043 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"4006_CR12","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"H-C Shin","year":"2016","unstructured":"Shin, H.-C. et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging. 35, 1285\u20131298 (2016).","journal-title":"IEEE Trans. Med. Imaging."},{"key":"4006_CR13","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1161\/01.cir.14.3.386","volume":"14","author":"J Ditzel","year":"1956","unstructured":"Ditzel, J. Angioscopic changes in the smaller blood vessels in diabetes mellitus and their relationship to aging. Circulation 14, 386\u2013397. https:\/\/doi.org\/10.1161\/01.cir.14.3.386 (1956).","journal-title":"Circulation"},{"key":"4006_CR14","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.mjafi.2017.01.005","volume":"73","author":"MA Khan","year":"2017","unstructured":"Khan, M. A. et al. A clinical correlation of conjunctival microangiopathy with grades of retinopathy in type 2 diabetes mellitus. Med. J. Armed Forces India 73, 261\u2013266. https:\/\/doi.org\/10.1016\/j.mjafi.2017.01.005 (2017).","journal-title":"Med. J. Armed Forces India"},{"key":"4006_CR15","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.mvr.2018.01.007","volume":"118","author":"MM Khansari","year":"2018","unstructured":"Khansari, M. M., Tan, M., Karamian, P. & Shahidi, M. Inter-visit variability of conjunctival microvascular hemodynamic measurements in healthy and diabetic retinopathy subjects. Microvasc. Res. 118, 7\u201311. https:\/\/doi.org\/10.1016\/j.mvr.2018.01.007 (2018).","journal-title":"Microvasc. Res."},{"key":"4006_CR16","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1364\/BOE.7.002597","volume":"7","author":"MM Khansari","year":"2016","unstructured":"Khansari, M. M. et al. Automated fine structure image analysis method for discrimination of diabetic retinopathy stage using conjunctival microvasculature images. Biomed. Opt. Express 7, 2597\u20132606. https:\/\/doi.org\/10.1364\/BOE.7.002597 (2016).","journal-title":"Biomed. Opt. Express"},{"key":"4006_CR17","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778."},{"key":"4006_CR18","unstructured":"Simonyan, K. & Zisserman, A. In IEEE Conference on Computer Vision & Pattern Recognition. (IEEE)."},{"key":"4006_CR19","unstructured":"Howard, A. G. et al. In IEEE Conference on Computer Vision & Pattern Recognition. (IEEE)."},{"key":"4006_CR20","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J. & Li, F. F. In IEEE Conference on Computer Vision & Pattern Recognition."},{"key":"4006_CR21","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G. & Wu, E. In IEEE Transactions on Pattern Analysis and Machine Intelligence. 7132\u20137141 (IEEE)."},{"key":"4006_CR22","unstructured":"Paszke, A. et al. In Advances in neural information processing systems. 8026\u20138037."},{"key":"4006_CR23","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1056\/NEJM195404082501401","volume":"250","author":"J Ditzel","year":"1954","unstructured":"Ditzel, J. & Sagild, U. Morphologic and hemodynamic change in the smaller blood vessels in dibetes melllitus. N Engl. J. Med. 250, 587\u2013594 (1954).","journal-title":"N Engl. J. Med."},{"key":"4006_CR24","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1097\/icl.0000000000000146","volume":"42","author":"L Wang","year":"2016","unstructured":"Wang, L. et al. Vessel sampling and blood flow velocity distribution with vessel diameter for characterizing the human bulbar conjunctival microvasculature. Eye Contact Lens Sci. Clin. Pract. 42, 135\u2013140. https:\/\/doi.org\/10.1097\/icl.0000000000000146 (2016).","journal-title":"Eye Contact Lens Sci. Clin. Pract."},{"key":"4006_CR25","doi-asserted-by":"publisher","first-page":"358","DOI":"10.4158\/ep.7.5.358","volume":"7","author":"AT Cheung","year":"2001","unstructured":"Cheung, A. T., Ramanujam, S., Greer, D. A., Kumagai, L. F. & Aoki, T. T. Microvascular abnormalities in the bulbar conjunctiva of patients with type 2 diabetes mellitus. Endocr. Pract. 7, 358\u2013363. https:\/\/doi.org\/10.4158\/ep.7.5.358 (2001).","journal-title":"Endocr. Pract."},{"key":"4006_CR26","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.mjafi.2017.01.005","volume":"73","author":"MA Khan","year":"2017","unstructured":"Khan, M. A. et al. A clinical correlation of conjunctival microangiopathy with grades of retinopathy in type 2 diabetes mellitus. Med. J. Armed. Forces India 73, 261\u2013266. https:\/\/doi.org\/10.1016\/j.mjafi.2017.01.005 (2017).","journal-title":"Med. J. Armed. Forces India"},{"key":"4006_CR27","doi-asserted-by":"publisher","first-page":"45916","DOI":"10.1038\/srep45916","volume":"7","author":"MM Khansari","year":"2017","unstructured":"Khansari, M. M. et al. Assessment of conjunctival microvascular hemodynamics in stages of diabetic microvasculopathy. Sci. Rep. 7, 45916. https:\/\/doi.org\/10.1038\/srep45916 (2017).","journal-title":"Sci. Rep."},{"key":"4006_CR28","doi-asserted-by":"publisher","first-page":"232","DOI":"10.7150\/thno.28447","volume":"9","author":"DK Hwang","year":"2019","unstructured":"Hwang, D. K. et al. Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics 9, 232\u2013245. https:\/\/doi.org\/10.7150\/thno.28447 (2019).","journal-title":"Theranostics"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-04006-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-04006-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-04006-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T19:29:05Z","timestamp":1669318145000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-04006-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,7]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["4006"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-04006-z","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,7]]},"assertion":[{"value":"18 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"264"}}