{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:25:14Z","timestamp":1784834714924,"version":"3.55.0"},"reference-count":75,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T00:00:00Z","timestamp":1622419200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational and Mathematical Methods in Medicine"],"published-print":{"date-parts":[[2021,5,31]]},"abstract":"<jats:p>Diabetic retinopathy occurs as a result of the harmful effects of diabetes on the eyes. Diabetic retinopathy is also a disease that should be diagnosed early. If not treated early, vision loss may occur. It is estimated that one third of more than half a million diabetic patients will have diabetic retinopathy by the 22nd century. Many effective methods have been proposed for disease detection with deep learning. In this study, unlike other studies, a deep learning-based method has been proposed in which diabetic retinopathy lesions are detected automatically and independently of datasets, and the detected lesions are classified. In the first stage of the proposed method, a data pool is created by collecting diabetic retinopathy data from different datasets. With Faster RCNN, lesions are detected, and the region of interests are marked. The images obtained in the second stage are classified using the transfer learning and attention mechanism. The method tested in Kaggle and MESSIDOR datasets reached 99.1% and 100% ACC and 99.9% and 100% AUC, respectively. When the obtained results are compared with other results in the literature, it is seen that more successful results are obtained.<\/jats:p>","DOI":"10.1155\/2021\/9928899","type":"journal-article","created":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T03:30:34Z","timestamp":1622518234000},"page":"1-13","source":"Crossref","is-referenced-by-count":51,"title":["An Effective Method for Detecting and Classifying Diabetic Retinopathy Lesions Based on Deep Learning"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4714-8523","authenticated-orcid":true,"given":"Abd\u00fcssamed","family":"Erciyas","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Gazi University, Ankara, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8762-5091","authenticated-orcid":true,"given":"Necaattin","family":"Bar\u0131\u015f\u00e7\u0131","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gazi University, Ankara, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","reference":[{"key":"1","first-page":"681","article-title":"Modified Alexnet architecture for classification of diabetic retinopathy images","volume":"107","author":"R. S. Biyani","year":"2018","journal-title":"Biomedicine and Pharmacotherapy"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.03.004"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2018.11.024"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1136\/qhc.9.2.137"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1984.01040030398010"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101561"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-018-5695-z"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"9","volume-title":"Imagenet Classification with Deep Convolutional Neural Networks","author":"A. Krizhevsky","year":"2012"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2009.5206848"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.308"},{"key":"13","article-title":"Very deep convolutional networks for large-scale image recognition, The 3rd International Conference on Learning Representations (ICLR2015)","author":"K. Simonyan"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.243"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.81"},{"key":"17","unstructured":"GirshickR. B.Fast R-CNN2015CoRRhttps:\/\/arxiv.org\/abs\/1504.08083"},{"key":"18","first-page":"1080","article-title":"Contextual action recognition with r\u2217 cnn","author":"G. Gkioxari"},{"key":"19","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks, CoRR","author":"S. Ren"},{"key":"20","unstructured":"HeK.GkioxariG.Doll\u00e1rP.GirshickR.Mask R-CNN2017CoRRhttps:\/\/arxiv.org\/abs\/1703.06870"},{"key":"21","unstructured":"LiuW.AnguelovD.ErhanD.SzegedyC.ReedS.FuC.-Y.BergA. C.SSD: single shot multibox detector2015CoRRhttps:\/\/arxiv.org\/abs\/1512.02325"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"23","volume-title":"Deep medicine: how artificial intelligence can make healthcare human again","author":"E. Topol","year":"2019"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180031"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2833635"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"27","article-title":"Deep learning in medical image registration: asurvey","author":"G. Haskins","year":"2019"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-2495"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1717139115"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5552743"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8839376"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.429"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.21227\/H25W98"},{"key":"35","author":"Kaggle Diabetic Retinopathy Detection Competition"},{"issue":"3, article 25","key":"36","article-title":"Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening","volume":"3","author":"T. Li","year":"2018","journal-title":"Data"},{"key":"37","author":"MESSIDOR dataset"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(03)00475-5"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.10.009"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2013.10.007"},{"key":"42","unstructured":"ZhangM.Blood Vessel Detection in Retinal Images and Its Application in Diabetic Retinopathy Screening, [Ph.D. thesis]2008College Station, TX, USATexas University"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.07.009"},{"key":"44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2013.11.014"},{"key":"45","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2008.08.009"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1007\/BF02169209"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2011.2106509"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8841927"},{"key":"49","first-page":"105741U","article-title":"Automatic localization and segmentation of optical disk based on faster r-cnn and level set in fundus image","volume-title":"Medical Imaging 2018: Image Processing","author":"D. Zhang","year":"2018"},{"key":"50","doi-asserted-by":"publisher","DOI":"10.17077\/omia.1042"},{"key":"51","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1007\/978-3-319-67561-9_15","article-title":"Optic disc detection via deep learning in fundus images","volume-title":"Fetal, Infant and Ophthalmic Medical Image Analysis","author":"P. Xu","year":"2017"},{"key":"52","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.16-19964"},{"key":"53","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2526689"},{"key":"54","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"55","doi-asserted-by":"publisher","DOI":"10.1186\/s41074-017-0023-6"},{"key":"56","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.02.008"},{"key":"57","volume-title":"Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection","author":"Z. Wang","year":"2017"},{"key":"58","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461427"},{"key":"59","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-017-0047-y"},{"key":"60","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.04.012"},{"key":"61","doi-asserted-by":"publisher","DOI":"10.1111\/j.1755-3768.2016.0635"},{"key":"62","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.07.014"},{"key":"63","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8864698"},{"key":"64","article-title":"InceptionV3 for Retinopathy GPU-HR"},{"key":"65","first-page":"1","article-title":"Very deep convolutional networksfor large-scale image recognition","author":"K. Simonyan","year":"2014"},{"key":"66","article-title":"DeepID3: Face Recognition with Very Deep Neural Networks","author":"Y. Sun","year":"2015"},{"key":"67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248055"},{"key":"68","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","volume-title":"AAAI","author":"C. Szegedy","year":"2017"},{"key":"69","article-title":"Learning transferable architectures for scalable image recognition","author":"B. Zoph","year":"2017"},{"key":"70","article-title":"MobileNet: efficient convolutional neural networks for mobile applications","author":"A. G. Howard","year":"2017"},{"key":"71","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"C. Szegedy"},{"key":"72","article-title":"R-CNNs for Pose Estimation and Action Detection","author":"G. Gkioxari"},{"key":"73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.56"},{"key":"75","doi-asserted-by":"publisher","DOI":"10.1016\/1352-2310(94)00210-C"}],"container-title":["Computational and Mathematical Methods in Medicine"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9928899.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9928899.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9928899.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T06:31:41Z","timestamp":1672295501000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cmmm\/2021\/9928899\/"}},"subtitle":[],"editor":[{"given":"Venkatesan","family":"Rajinikanth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,5,31]]},"references-count":75,"alternative-id":["9928899","9928899"],"URL":"https:\/\/doi.org\/10.1155\/2021\/9928899","relation":{},"ISSN":["1748-6718","1748-670X"],"issn-type":[{"value":"1748-6718","type":"electronic"},{"value":"1748-670X","type":"print"}],"subject":[],"published":{"date-parts":[[2021,5,31]]}}}