{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T23:50:38Z","timestamp":1792021838111,"version":"4.4.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T00:00:00Z","timestamp":1611187200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T00:00:00Z","timestamp":1611187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Glaucoma, a leading cause of blindness, is a multifaceted disease with several patho-physiological features manifesting in single fundus images (e.g., optic nerve cupping) as well as fundus videos (e.g., vascular pulsatility index). Current convolutional neural networks (CNNs) developed to detect glaucoma are all based on spatial features embedded in an image. We developed a combined CNN and recurrent neural network (RNN) that not only extracts the spatial features in a fundus image but also the temporal features embedded in a fundus video (i.e., sequential images). A total of 1810 fundus images and 295 fundus videos were used to train a CNN and a combined CNN and Long Short-Term Memory RNN. The combined CNN\/RNN model reached an average F-measure of 96.2% in separating glaucoma from healthy eyes. In contrast, the base CNN model reached an average F-measure of only 79.2%. This proof-of-concept study demonstrates that extracting spatial and temporal features from fundus videos using a combined CNN and RNN, can markedly enhance the accuracy of glaucoma detection.<\/jats:p>","DOI":"10.1038\/s41598-021-81554-4","type":"journal-article","created":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T11:03:39Z","timestamp":1611227019000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":132,"title":["A combined convolutional and recurrent neural network for enhanced glaucoma detection"],"prefix":"10.1038","volume":"11","author":[{"given":"Soheila","family":"Gheisari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahar","family":"Shariflou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Phu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul J.","family":"Kennedy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Agar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Kalloniatis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. Mojtaba","family":"Golzan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"81554_CR1","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1111\/j.1442-9071.2012.02773.x","volume":"40","author":"RJ Casson","year":"2012","unstructured":"Casson, R. J., Chidlow, G., Wood, J. P., Crowston, J. G. & Goldberg, I. Definition of glaucoma: Clinical and experimentalconcepts. Clin. Exp. Ophthalmol. 40, 341\u2013349. https:\/\/doi.org\/10.1111\/j.1442-9071.2012.02773.x (2012).","journal-title":"Clin. Exp. Ophthalmol."},{"issue":"1","key":"81554_CR2","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1038\/nrdp.2016.67","volume":"2","author":"RN Weinreb","year":"2016","unstructured":"Weinreb, R. N. et al. Primary open-angle glaucoma. Nat. Rev. Dis. Primers 2(1), 160\u2013167. https:\/\/doi.org\/10.1038\/nrdp.2016.67 (2016).","journal-title":"Nat. Rev. Dis. Primers"},{"key":"81554_CR3","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1016\/j.ajo.2004.04.054","volume":"138","author":"R Weinreb","year":"2004","unstructured":"Weinreb, R. et al. Risk assessment in the management of patients with ocular hypertension. Am. J. Ophthalmol. 138, 458\u2013467. https:\/\/doi.org\/10.1016\/j.ajo.2004.04.054 (2004).","journal-title":"Am. J. Ophthalmol."},{"key":"81554_CR4","first-page":"940","volume":"2","author":"H Wiley","year":"2012","unstructured":"Wiley, H. & Iii, F. Nonproliferative diabetic retinopathy and diabetic macular edema. Retina Fifth Edn. 2, 940\u2013968 (2012).","journal-title":"Retina Fifth Edn."},{"key":"81554_CR5","first-page":"181","volume":"100","author":"GL Spaeth","year":"2002","unstructured":"Spaeth, G. L. et al. The disc damage likelihood scale: Reproducibility of a new method of estimating the amount of optic nerve damage caused by glaucoma. Trans. Am. Ophthalmol. Soc. 100, 181\u2013186 (2002).","journal-title":"Trans. Am. Ophthalmol. Soc."},{"issue":"6","key":"81554_CR6","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1136\/bjo.83.6.664","volume":"83","author":"DF Garway-Heath","year":"1999","unstructured":"Garway-Heath, D. F. et al. Inter- and intraobserver variation in the analysis of optic disc images: Comparison of the Heidelberg retina tomograph and computer assisted planimetry. Br. J. Ophthalmol. 83(6), 664\u2013669. https:\/\/doi.org\/10.1136\/bjo.83.6.664 (1999).","journal-title":"Br. J. Ophthalmol."},{"issue":"4","key":"81554_CR7","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/s1350-9462(02)00008-3","volume":"21","author":"J Flammer","year":"2002","unstructured":"Flammer, J. et al. The impact of ocular blood flow in glaucoma. Prog. Retina Eye Res. 21(4), 359\u2013393. https:\/\/doi.org\/10.1016\/s1350-9462(02)00008-3 (2002).","journal-title":"Prog. Retina Eye Res."},{"key":"81554_CR8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3109\/02713683.2010.530731","volume":"36","author":"SM Golzan","year":"2011","unstructured":"Golzan, S. M., Graham, S., Leaney, J. & Avolio, A. Dynamic association between intraocular pressure and spontaneous pulsations of retinal veins. Curr. Eye Res. 36, 53\u201359. https:\/\/doi.org\/10.3109\/02713683.2010.530731 (2011).","journal-title":"Curr. Eye Res."},{"issue":"9","key":"81554_CR9","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.1167\/iovs.14-15104","volume":"55","author":"WH Morgan","year":"2014","unstructured":"Morgan, W. H. et al. Photoplethysmographic measurement of various retinal vascular pulsation parameters and measurement of the venous phase delay. Investig. Ophthalmol. Vis. Sci. 55(9), 5998\u20136006. https:\/\/doi.org\/10.1167\/iovs.14-15104 (2014).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"issue":"6","key":"81554_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0128433","volume":"10","author":"SM Golzan","year":"2015","unstructured":"Golzan, S. M., Morgan, W. H., Georgevsky, D. & Graham, S. L. Correlation of retinal nerve fibre layer thickness and spontaneous retinal venous pulsations in glaucoma and normal controls. PLoS ONE 10(6), 1\u201312. https:\/\/doi.org\/10.1371\/journal.pone.0128433 (2015).","journal-title":"PLoS ONE"},{"issue":"8","key":"81554_CR11","first-page":"734","volume":"58","author":"SM Golzan","year":"2017","unstructured":"Golzan, S. M., Georgevsky, D., Bowd, C., Weinreb, R. & Graham, S. Visual field sensitivity is decreased with reduced spontaneous venous pulsation in glaucoma eyes. Investig. Ophthalmol. Vis. Sci. 58(8), 734 (2017).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"81554_CR12","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.preteyeres.2016.06.003","volume":"55","author":"WH Morgan","year":"2016","unstructured":"Morgan, W. H., Hazelton, M. L. & Yu, D.-Y. Retinal venous pulsation: Expanding our understanding and use of this enigmatic phenomenon. Prog. Retina Eye Res. 55, 82\u2013107. https:\/\/doi.org\/10.1016\/j.preteyeres.2016.06.003 (2016).","journal-title":"Prog. Retina Eye Res."},{"key":"81554_CR13","doi-asserted-by":"crossref","unstructured":"Cheriguene, S., Azizi, N., Djellali, H., Bunakhla, O., Aldwairi, M. and Ziani, A. New computer aided diagnosis system for glaucoma disease based on twin support vector machine. In International Conference on Embedded Distributed Systems (EDiS), pp. 1\u20136, (2017).","DOI":"10.1109\/EDIS.2017.8284039"},{"key":"81554_CR14","doi-asserted-by":"crossref","unstructured":"Al-Bander, B., Al-Nuaimy, W., Al-Taee, M. A. and Zheng, Y. Automated glaucoma diagnosis using deep learning approach. In 14th International Multi-Conference on Systems, Signals & Devices (SSD), pp. 207\u2013210 (2017).","DOI":"10.1109\/SSD.2017.8166974"},{"key":"81554_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-35044-9","author":"M Christopher","year":"2018","unstructured":"Christopher, M. et al. Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-018-35044-9 (2018).","journal-title":"Sci. Rep."},{"issue":"29","key":"81554_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-019-0649-y","volume":"18","author":"A Diaz-Pinto","year":"2019","unstructured":"Diaz-Pinto, A., Morales, S., Naranjo, V., Thomas, K. & Mossi, J. M. CNNs for automatic glaucoma assessment using fundus images: An extensive validation. BioMed. Eng. 18(29), 1\u201319. https:\/\/doi.org\/10.1186\/s12938-019-0649-y (2019).","journal-title":"BioMed. Eng."},{"issue":"8","key":"81554_CR17","doi-asserted-by":"publisher","first-page":"3276","DOI":"10.1167\/iovs.06-0072","volume":"47","author":"SC Huynh","year":"2006","unstructured":"Huynh, S. C., Wang, X. Y., Rochtchina, E., Crowston, J. G. & Mitchell, P. Distribution of optic disc parameters measured by OCT: Findings from a population-based study of 6-year-old Australian children. Investig. Ophthalmol. Vis. Sci. 47(8), 3276\u20133285. https:\/\/doi.org\/10.1167\/iovs.06-0072 (2006).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"issue":"2","key":"81554_CR18","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1097\/ICU.0000000000000548","volume":"30","author":"NYQ Tan","year":"2019","unstructured":"Tan, N. Y. Q., Sng, C. C. A. & Ang, M. Myopic optic disc changes and its role in glaucoma. Curr. Opin. Ophthalmol. 30(2), 89\u201396 (2019).","journal-title":"Curr. Opin. Ophthalmol."},{"key":"81554_CR19","doi-asserted-by":"crossref","unstructured":"Orlando, J., Prokofyeva, E., Fresno, M., and Blaschko, M. Convolutional neural network transfer for automated glaucoma identification. In International Symposium on Medical Information Processing and Analysis, pp. 241\u2013250 (2017).","DOI":"10.1117\/12.2255740"},{"key":"81554_CR20","unstructured":"Simonyan, K. and Zisserman, A. Very deep convolutional networks for large image recognition. In International Conference Learning Representation, pp. 1\u201314 (2015)."},{"key":"81554_CR21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S. and Vanhoucke, V. Inception-v4, inception-ResNet and the impact of residual connections on learning, In Computer Vision and Pattern Recognition (CVPR) 2016.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"81554_CR22","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"L Geert","year":"2017","unstructured":"Geert, L. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005 (2017).","journal-title":"Med. Image Anal."},{"issue":"8","key":"81554_CR23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"81554_CR24","doi-asserted-by":"publisher","unstructured":"Ribeiro, M. T., Singh, S. and Guestrin, C. Why should I trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016). https:\/\/doi.org\/10.18653\/v1\/N16-3020.","DOI":"10.18653\/v1\/N16-3020"},{"key":"81554_CR25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0128433","author":"SM Golzan","year":"2015","unstructured":"Golzan, S. M., Morgan, W. H., Georgevsky, D. & Graham, S. L. \"Correlation of retinal nerve fibre layer thickness and spontaneous retinal venous pulsations in glaucoma and normal controls. PLoS ONE https:\/\/doi.org\/10.1371\/journal.pone.0128433 (2015).","journal-title":"PLoS ONE"},{"key":"81554_CR26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/bs.pbr.2015.06.002","volume":"221","author":"JB Jonas","year":"2015","unstructured":"Jonas, J. B., Ritch, R. & Panda-Jonas, S. Cerebrospinal fluid pressure in the pathogenesis of glaucoma. Prog. Brain Res. 221, 33\u201347 (2015).","journal-title":"Prog. Brain Res."},{"issue":"2","key":"81554_CR27","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1097\/IJG.0000000000001421","volume":"29","author":"DA Price","year":"2020","unstructured":"Price, D. A., Harris, A., Siesky, B. & Mathew, S. The influence of translaminar pressure gradient and intracranial pressure in glaucoma: A review. J. Glaucoma 29(2), 141\u2013146 (2020).","journal-title":"J. Glaucoma"},{"key":"81554_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0214875","author":"JC Wen","year":"2018","unstructured":"Wen, J. C. et al. Forecasting future humphrey visual fields using deep learning. PLoS ONE https:\/\/doi.org\/10.1371\/journal.pone.0214875 (2018).","journal-title":"PLoS ONE"},{"issue":"9","key":"81554_CR29","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","volume":"24","author":"J De Fauw","year":"2018","unstructured":"De Fauw, J. et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24(9), 1342\u20131350 (2018).","journal-title":"Nat. Med."},{"key":"81554_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.preteyeres.2018.07.004","volume":"67","author":"U Schmidt-Erfurth","year":"2018","unstructured":"Schmidt-Erfurth, U., Sadeghipour, A., Gerendas, B. S., Waldstein, S. M. & Bogunovi\u0107, H. Artificial intelligence in retina. Prog. Retinal Eye Res. 67, 1\u201329. https:\/\/doi.org\/10.1016\/j.preteyeres.2018.07.004 (2018).","journal-title":"Prog. Retinal Eye Res."},{"key":"81554_CR31","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1111\/ceo.13381","volume":"47","author":"D Hogarty","year":"2018","unstructured":"Hogarty, D., Mackey, D. & Hewitt, A. Current state and future prospects of artificial intelligence in ophthalmology: A review: Artificial intelligence in ophthalmology. Clin. Exp. Ophthalmol. 47, 128\u2013139. https:\/\/doi.org\/10.1111\/ceo.13381 (2018).","journal-title":"Clin. Exp. Ophthalmol."},{"key":"81554_CR32","doi-asserted-by":"crossref","unstructured":"Devasia, T., Jacob, K. and Thomas, T. Automatic early stage glaucoma detection using cascade correlation neural network. In Second International Conference on Smart Computing and Informatics (SCI), pp. 659\u2013669, (2019).","DOI":"10.1007\/978-981-13-1921-1_64"},{"issue":"2","key":"81554_CR33","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1097\/ICU.0000000000000552","volume":"30","author":"C Zheng","year":"2019","unstructured":"Zheng, C., Johnson, T. V., Garg, A. & Boland, M. V. Artificial intelligence in glaucoma. Curr. Opin. Ophthalmol. 30(2), 97\u2013103 (2019).","journal-title":"Curr. Opin. Ophthalmol."},{"issue":"1","key":"81554_CR34","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.ogla.2018.04.002","volume":"1","author":"S Liu","year":"2018","unstructured":"Liu, S. et al. A deep learning-based algorithm identifies glaucomatous discs using monoscopic fundus photographs. Ophthalmol. Glaucoma 1(1), 15\u201322 (2018).","journal-title":"Ophthalmol. Glaucoma"},{"issue":"4","key":"81554_CR35","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/j.ophtha.2018.12.033","volume":"126","author":"FA Medeiros","year":"2019","unstructured":"Medeiros, F. A., Jammal, A. A. & Thompson, A. C. From machine to machine: An oct-trained deep learning algorithm for objective quantification of glaucomatous damage in fundus photographs. Ophthalmology 126(4), 513\u2013521. https:\/\/doi.org\/10.1016\/j.ophtha.2018.12.033 (2019).","journal-title":"Ophthalmology"},{"issue":"1","key":"81554_CR36","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3109\/02713683.2010.530731","volume":"36","author":"SM Golzan","year":"2011","unstructured":"Golzan, S. M., Graham, S. L., Leaney, J. & Avolio, A. Dynamic association between intraocular pressure and spontaneous pulsations of retinal veins. Curr. Eye Res. 36(1), 53\u201359. https:\/\/doi.org\/10.3109\/02713683.2010.530731 (2011).","journal-title":"Curr. Eye Res."},{"issue":"1","key":"81554_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1001\/archopht.122.1.22","volume":"122","author":"LM Zangwill","year":"2004","unstructured":"Zangwill, L. M. et al. Racial differences in optic disc topography: Baseline results from the confocal scanning laser ophthalmoscopy ancillary study to the ocular hypertension treatment study. JAMA Ophthalmol. 122(1), 22\u201328. https:\/\/doi.org\/10.1001\/archopht.122.1.22 (2004).","journal-title":"JAMA Ophthalmol."},{"key":"81554_CR38","unstructured":"Ervin, A. M., et al. Screening for glaucoma comparative effectiveness. Agency for Healthcare Research and Quality,\u00a0Report No.: 12-EHC037-EF., 2012."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81554-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81554-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81554-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T02:37:23Z","timestamp":1670035043000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-81554-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,21]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["81554"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-81554-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,21]]},"assertion":[{"value":"22 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2021","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":"1945"}}