{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T15:32:58Z","timestamp":1784734378285,"version":"3.55.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["R21EY030619"],"award-info":[{"award-number":["R21EY030619"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Age-related macular degeneration (AMD) and Stargardt disease are the leading causes of blindness for the elderly and young adults respectively. Geographic atrophy (GA) of AMD and Stargardt atrophy are their end-stage outcomes. Efficient methods for segmentation and quantification of these atrophic lesions are critical for clinical research. In this study, we developed a deep convolutional neural network (CNN) with a trainable self-attended mechanism for accurate GA and Stargardt atrophy segmentation. Compared with traditional post-hoc attention mechanisms which can only visualize CNN features, our self-attended mechanism is embedded in a fully convolutional network and directly involved in training the CNN to actively attend key features for enhanced algorithm performance. We applied the self-attended CNN on the segmentation of AMD and Stargardt atrophic lesions on fundus autofluorescence (FAF) images. Compared with a preexisting regular fully convolutional network (the U-Net), our self-attended CNN achieved 10.6% higher Dice coefficient and 17% higher IoU (intersection over union) for AMD GA segmentation, and a 22% higher Dice coefficient and a 32% higher IoU for Stargardt atrophy segmentation. With longitudinal image data having over a longer time, the developed self-attended mechanism can also be applied on the visual discovery of early AMD and Stargardt features.<\/jats:p>","DOI":"10.1038\/s41598-022-18785-6","type":"journal-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T10:03:17Z","timestamp":1661508197000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Automated segmentation and feature discovery of age-related macular degeneration and Stargardt disease via self-attended neural networks"],"prefix":"10.1038","volume":"12","author":[{"given":"Ziyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srinivas Reddy","family":"Sadda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihong Jewel","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,26]]},"reference":[{"issue":"9652","key":"18785_CR1","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.1016\/S0140-6736(08)61759-6","volume":"372","author":"HR Coleman","year":"2008","unstructured":"Coleman, H. R., Chan, C.-C., Ferris, F. L. & Chew, E. Y. Age-related macular degeneration. Lancet 372(9652), 1835\u20131845. https:\/\/doi.org\/10.1016\/S0140-6736(08)61759-6 (2008) (ISSN: 0140-6736).","journal-title":"Lancet"},{"issue":"29\u201330","key":"18785_CR2","doi-asserted-by":"publisher","first-page":"513","DOI":"10.3238\/arztebl.2020.0513","volume":"117","author":"A Stahl","year":"2020","unstructured":"Stahl, A. The diagnosis and treatment of age-related macular degeneration. Deutsches Arzteblatt Int. 117(29\u201330), 513\u2013520. https:\/\/doi.org\/10.3238\/arztebl.2020.0513 (2020) (ISSN: 1866-0452).","journal-title":"Deutsches Arzteblatt Int."},{"issue":"5035","key":"18785_CR3","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","volume":"254","author":"D Huang","year":"1991","unstructured":"Huang, D. et al. Optical coherence tomography. Science 254(5035), 1178\u20131181. https:\/\/doi.org\/10.1126\/science.1957169 (1991).","journal-title":"Science"},{"key":"18785_CR4","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.ajo.2006.06.015","volume":"142","author":"R Klein","year":"2006","unstructured":"Klein, R., Klein, B. E., Lee, K. E., Cruickshanks, K. J. & Gangnon, R. E. Changes in visual acuity in a population over a 15 year period: the Beaver Dam Eye Study. Am. J. Ophthalmol. 142, 539\u2013549 (2006).","journal-title":"Am. J. Ophthalmol."},{"issue":"4","key":"18785_CR5","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/j.ophtha.2015.12.009","volume":"123","author":"RW Strauss","year":"2016","unstructured":"Strauss, R. W. et al. The natural history of the progression of atrophy secondary to Stargardt disease (ProgStar) studies: Design and baseline characteristics: ProgStar report no. 1. Ophthalmology 123(4), 817\u2013828. https:\/\/doi.org\/10.1016\/j.ophtha.2015.12.009 (2016).","journal-title":"Ophthalmology"},{"key":"18785_CR6","volume-title":"Diagnosis and Management of Stargardt Disease","author":"N Mukherjee","year":"2014","unstructured":"Mukherjee, N. & Schuman, S. Diagnosis and Management of Stargardt Disease (American Academy of Ophthalmology, 2014)."},{"issue":"3","key":"18785_CR7","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1097\/IAE.0b013e318164a907","volume":"28","author":"S Schmitz-Valckenberg","year":"2008","unstructured":"Schmitz-Valckenberg, S., Holz, F. G., Bird, A. C. & Spaide, R. F. Fundus autofluores-cence imaging: Review and perspectives. En-US Retina 28(3), 385\u2013409. https:\/\/doi.org\/10.1097\/IAE.0b013e318164a907 (2008) (ISSN: 0275-004X).","journal-title":"En-US Retina"},{"issue":"10","key":"18785_CR8","doi-asserted-by":"publisher","first-page":"7640","DOI":"10.1167\/iovs.11-7457","volume":"52","author":"S Schmitz-Valckenberg","year":"2011","unstructured":"Schmitz-Valckenberg, S. et al. Semiautomated image processing method for identification and quantification of geographic atrophy in age-related macular degeneration. Invest. Ophthalmol. Vis. Sci. 52(10), 7640\u20137646 (2011).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"issue":"12","key":"18785_CR9","doi-asserted-by":"publisher","first-page":"2729","DOI":"10.1364\/BOE.4.002729","volume":"4","author":"Q Chen","year":"2013","unstructured":"Chen, Q., Leng, T., Zheng, L., Kutzscher, L. & Rubin, D. L. Semi-automatic geographic atrophy segmentation for SD-OCT images. Biomed. Opt. Exp. 4(12), 2729\u20132750 (2013).","journal-title":"Biomed. Opt. Exp."},{"key":"18785_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Z., Medioni, G. G., Hernandez, M., Hariri, A., Wu, X., & Sadda, S. R. Segmentation of the geographic atrophy in spectral-domain optical coherence tomography volume scans and fundus autofluorescene images. Invest. Ophthalmol. Vis. Sci. 54(13), 8375\u20138383 (2013) (proceedings of SPIE. Vol. 10950. 109501Q-8).","DOI":"10.1167\/iovs.13-12552"},{"key":"18785_CR11","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1097\/IAE.0000000000000069","volume":"34","author":"D Ramsey","year":"2014","unstructured":"Ramsey, D. et al. Automated image alignment and segmentation to follow progression of geographic atrophy in age-related macular degeneration. Retina 34, 1296\u20131307 (2014).","journal-title":"Retina"},{"key":"18785_CR12","doi-asserted-by":"publisher","first-page":"014501","DOI":"10.1117\/1.JMI.2.1.014501","volume":"2","author":"Z Hu","year":"2015","unstructured":"Hu, Z., Medioni, G. G., Hernandez, M. & Sadda, S. R. Automated segmentation of geographic atrophy in fundus autofluorescence images using supervised pixel classification. J. Med. Imag. 2, 014501 (2015).","journal-title":"J. Med. Imag."},{"key":"18785_CR13","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 [cs] (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"18785_CR14","unstructured":"LeCun, Y. & Bengio, Y. Convolutional networks for images, speech, and time-series. in The Handbook of Brain Theory and Neural Networks (Arbib, M. A. Ed.). (MIT Press, 1995)."},{"key":"18785_CR15","doi-asserted-by":"publisher","unstructured":"Hu, Z., Wang, Z., & Sadda, S. Automated segmentation of geographic atrophy using deep convolutional neural networks. In Proceedings of the SPIE Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575. 1057511. https:\/\/doi.org\/10.1117\/12.2287001 (2018).","DOI":"10.1117\/12.2287001"},{"key":"18785_CR16","doi-asserted-by":"publisher","unstructured":"Wang, Z., Sadda, S. R., & Hu, Z. Deep learning for automated screening and semantic segmentation of age-related and juvenile atrophic macular degeneration. in Medical Imaging 2019: Computer-Aided Diagnosis. Vol. 10950. 109501Q. https:\/\/doi.org\/10.1117\/12.2511538 (International Society for Optics and Photonics, 2019).","DOI":"10.1117\/12.2511538"},{"issue":"1","key":"18785_CR17","doi-asserted-by":"publisher","first-page":"10990","DOI":"10.1038\/s41598-019-47390-3","volume":"9","author":"S Saha","year":"2019","unstructured":"Saha, S. et al. Automated detection and classification of early AMD biomarkers using deep learning. Sci. Rep. 9(1), 10990. https:\/\/doi.org\/10.1038\/s41598-019-47390-3 (2019) (ISSN: 2045-2322).","journal-title":"Sci. Rep."},{"key":"18785_CR18","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.ajo.2020.03.042","volume":"216","author":"U Schmidt-Erfurth","year":"2020","unstructured":"Schmidt-Erfurth, U. et al. Role of deep learning-quantified hyperreflective foci for the prediction of geographic atrophy progression. Am. J. Ophthalmol. 216, 257\u2013270. https:\/\/doi.org\/10.1016\/j.ajo.2020.03.042 (2020) (ISSN: 1879-1891).","journal-title":"Am. J. Ophthalmol."},{"issue":"1","key":"18785_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/tvst.7.1.1","volume":"7","author":"Z Ji","year":"2018","unstructured":"Ji, Z., Chen, Q., Niu, S., Leng, T. & Rubin, D. L. Beyond retinal layers: A deep voting model for automated geographic atrophy segmentation in SD-OCT images. Transl. Vis. Sci. Technol. 7(1), 1. https:\/\/doi.org\/10.1167\/tvst.7.1.1 (2018).","journal-title":"Transl. Vis. Sci. Technol."},{"issue":"8","key":"18785_CR20","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1016\/j.ophtha.2020.02.009","volume":"127","author":"B Liefers","year":"2020","unstructured":"Liefers, B. et al. A deep learning model for segmentation of geographic atrophy to study its long-term natural history. Ophthalmology 127(8), 1086\u20131096. https:\/\/doi.org\/10.1016\/j.ophtha.2020.02.009 (2020) (ISSN 0161-6420).","journal-title":"Ophthalmology"},{"key":"18785_CR21","doi-asserted-by":"publisher","first-page":"3958","DOI":"10.1109\/IEMBS.2011.6090983","volume":"2011","author":"K Devisetti","year":"2011","unstructured":"Devisetti, K., Karnowski, T. P., Giancardo, L., Li, Y. & Chaum, E. Geographic atrophy segmentation in infrared and autofluorescent retina images using supervised learning. Ann. Int. Conf. IEEE Eng. Med. Biol. Soc. 2011, 3958\u20133961. https:\/\/doi.org\/10.1109\/IEMBS.2011.6090983 (2011).","journal-title":"Ann. Int. Conf. IEEE Eng. Med. Biol. Soc."},{"key":"18785_CR22","doi-asserted-by":"publisher","first-page":"16491","DOI":"10.1038\/s41598-020-73339-y","volume":"10","author":"J Charng","year":"2020","unstructured":"Charng, J. et al. Deep learning segmentation of hyperautofluorescent fleck lesions in Stargardt disease. Sci. Rep. 10, 16491 (2020).","journal-title":"Sci. Rep."},{"issue":"3","key":"18785_CR23","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1364\/BOE.449314","volume":"13","author":"Z Chu","year":"2022","unstructured":"Chu, Z. et al. Automatic geographic atrophy segmentation using optical attenuation in OCT scans with deep learning. Biomed. Opt. Exp. 13(3), 1328\u20131343. https:\/\/doi.org\/10.1364\/BOE.449314 (2022).","journal-title":"Biomed. Opt. Exp."},{"issue":"22","key":"18785_CR24","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402\u20132410. https:\/\/doi.org\/10.1001\/jama.2016.17216 (2016).","journal-title":"JAMA"},{"issue":"8","key":"18785_CR25","doi-asserted-by":"publisher","first-page":"3627","DOI":"10.1364\/BOE.8.003627","volume":"8","author":"AG Roy","year":"2017","unstructured":"Roy, A. G. et al. ReLayNet: Retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks. Biomed. Opt. Exp. 8(8), 3627\u20133642. https:\/\/doi.org\/10.1364\/BOE.8.003627 (2017).","journal-title":"Biomed. Opt. Exp."},{"issue":"5","key":"18785_CR26","doi-asserted-by":"publisher","first-page":"2732","DOI":"10.1364\/BOE.8.002732","volume":"8","author":"L Fang","year":"2017","unstructured":"Fang, L. et al. Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search. Biomed. Opt. Exp. 8(5), 2732\u20132744. https:\/\/doi.org\/10.1364\/BOE.8.002732 (2017).","journal-title":"Biomed. Opt. Exp."},{"key":"18785_CR27","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.neucom.2019.07.079","volume":"365","author":"K Hu","year":"2019","unstructured":"Hu, K. et al. Automatic segmentation of retinal layer boundaries in OCT images using multiscale convolutional neural network and graph search. Neurocomputing 365, 302\u2013313 (2019).","journal-title":"Neurocomputing"},{"key":"18785_CR28","doi-asserted-by":"publisher","first-page":"13298","DOI":"10.1038\/s41598-019-49816-4","volume":"9","author":"J Kugelman","year":"2019","unstructured":"Kugelman, J. et al. Automatic choroidal segmentation in OCT images using supervised deep learning methods. Sci. Rep. 9, 13298 (2019).","journal-title":"Sci. Rep."},{"issue":"7","key":"18785_CR29","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1364\/BOE.8.003292.PMID:28717568;PMCID:PMC5508829","volume":"8","author":"FG Venhuizen","year":"2017","unstructured":"Venhuizen, F. G. et al. Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks. Biomed. Opt. Exp. 8(7), 3292\u20133316. https:\/\/doi.org\/10.1364\/BOE.8.003292.PMID:28717568;PMCID:PMC5508829 (2017).","journal-title":"Biomed. Opt. Exp."},{"key":"18785_CR30","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D. & Fergus, R. Visualizing and Understanding Convolutional Networks. arXiv:1311.2901 [cs] (2013).","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"18785_CR31","doi-asserted-by":"publisher","first-page":"2689","DOI":"10.1002\/ail2.16","volume":"1","author":"S Saha","year":"2020","unstructured":"Saha, S., Wang, Z., Sadda, S., Kanagasingam, Y. & Hu, Z. Visualizing and understanding inherent featuresin SD-OCT for the progression of age-related macular degeneration using deconvolutional neural networks. Appl. AI Lett. 1, 2689\u20135595. https:\/\/doi.org\/10.1002\/ail2.16 (2020) (ISSN: 2689-5595).","journal-title":"Appl. AI Lett."},{"issue":"12","key":"18785_CR32","doi-asserted-by":"publisher","first-page":"3443","DOI":"10.1109\/JBHI.2020.2999588","volume":"24","author":"X Ma","year":"2020","unstructured":"Ma, X. et al. MS-CAM: Multi-scale class activation maps for weakly-supervised segmentation of geographic atrophy lesions in SD-OCT images. IEEE J. Biomed. Health Inform. 24(12), 3443\u20133455. https:\/\/doi.org\/10.1109\/JBHI.2020.2999588 (2020) (ISSN: 2168-2208).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"18785_CR33","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/ICCV.2017.74","volume":"2017","author":"RR Selvaraju","year":"2017","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization. IEEE Int. Conf. Comput. Vis. (ICCV) 2017, 618\u2013626. https:\/\/doi.org\/10.1109\/ICCV.2017.74 (2017).","journal-title":"IEEE Int. Conf. Comput. Vis. (ICCV)"},{"key":"18785_CR34","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M.J., Heinrich, M.P., Misawa, K., Mori, K., McDonagh, S.G., Hammerla, N.Y., Kainz, B., Glocker, B., & Rueckert, D. Attention U-Net: Learning Where to Look for the Pancreas. arXiv:1804.03999 [abs] (2018)."},{"key":"18785_CR35","unstructured":"Jetley, S., Lord, N.A., Lee, N., & Torr, P. Learn to pay attention. in International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyzbhfWRW (2018)"},{"key":"18785_CR36","doi-asserted-by":"crossref","unstructured":"Hernandez, M., Medioni, G. G., Hu, Z., & Sadda, S. R. Multimodal registration of multiple retinal images based on line structures. in 2015 IEEE Winter Conference on Applications of Computer Vision (WACV), 5\u20139 Jan 2015. 907\u2013914 (2015).","DOI":"10.1109\/WACV.2015.125"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-18785-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-18785-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-18785-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T17:03:16Z","timestamp":1727888596000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-18785-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,26]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["18785"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-18785-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,26]]},"assertion":[{"value":"8 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 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":"14565"}}