{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T03:34:56Z","timestamp":1771644896188,"version":"3.50.1"},"reference-count":51,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T00:00:00Z","timestamp":1620172800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xiamen Science and Technology Program","award":["3502Z20183047"],"award-info":[{"award-number":["3502Z20183047"]}]},{"name":"Xiamen Science and Technology Program","award":["NGII20170620"],"award-info":[{"award-number":["NGII20170620"]}]},{"name":"China Education Research Network","award":["3502Z20183047"],"award-info":[{"award-number":["3502Z20183047"]}]},{"name":"China Education Research Network","award":["NGII20170620"],"award-info":[{"award-number":["NGII20170620"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Healthcare Engineering"],"published-print":{"date-parts":[[2021,5,5]]},"abstract":"<jats:p>The automatic diagnosis of various retinal diseases based on fundus images is important in supporting clinical decision-making. Convolutional neural networks (CNNs) have achieved remarkable results in such tasks. However, their high expression ability possibly leads to overfitting. Therefore, data augmentation (DA) techniques have been proposed to prevent overfitting while enriching datasets. Recent CNN architectures with more parameters render traditional DA techniques insufficient. In this study, we proposed a new DA strategy based on multimodal fusion (DAMF) which could integrate the standard DA method, data disrupting method, data mixing method, and autoadjustment method to enhance the image data in the training dataset to create new training images. In addition, we fused the results of the classifier by voting on the basis of DAMF, which further improved the generalization ability of the model. The experimental results showed that the optimal DA mode could be matched to the image dataset through our DA strategy. We evaluated DAMF on the iChallenge-PM dataset. At last, we compared training results between 12 DAMF processed datasets and the original training dataset. Compared with the original dataset, the optimal DAMF achieved an accuracy increase of 2.85% on iChallenge-PM.<\/jats:p>","DOI":"10.1155\/2021\/5549779","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T22:05:25Z","timestamp":1620338725000},"page":"1-15","source":"Crossref","is-referenced-by-count":15,"title":["Pathological Myopia Image Recognition Strategy Based on Data Augmentation and Model Fusion"],"prefix":"10.1155","volume":"2021","author":[{"given":"Jianfeng","family":"Cui","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0349-1127","authenticated-orcid":true,"given":"Xiaoyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Opto-electronic and Communications Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feibing","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Opto-electronic and Communications Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-2043","authenticated-orcid":true,"given":"Chin-Ling","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China"},{"name":"School of Information Engineering, Changchun Sci-Tech University, Changchun 130600, China"},{"name":"Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung 41349, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-7644-7_21"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1097\/apo.0000000000000230"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2013.08.010"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.12-10106"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2016.01.006"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.18-24032"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8491-2_1"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.295.18.2158"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(12)60272-4"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2003.05.011"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.04.022"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.01.035"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.3109\/09286580903450346"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2010.09.032"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0307-0"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/5278196"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0305-z"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.18-23887"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-313173"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6319581"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1111\/ceo.13381"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1007\/s12194-017-0406-5"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.2337\/dc18-0147"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3005152"},{"key":"27","article-title":"Robust retinal vessel segmentation from a data augmentation perspective","author":"X. Sun","year":"2020"},{"key":"28","first-page":"1","article-title":"Automatic detection of pathological myopia and high myopia on fundus images","author":"S. a. C. Dai"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2018.2838550"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1038\/srep41545"},{"key":"31","first-page":"1742","article-title":"Pathological myopia detection from selective fundus image features","author":"Z. Zhang"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-017-0420-1"},{"issue":"7","key":"33","article-title":"A review on image enhancement techniques","volume":"2","author":"H. A\u010dkar","year":"2017","journal-title":"International Journal of Engineering and Applied Computer Science (IJEACS)"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1159\/000329597"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39804-2_12"},{"key":"36","article-title":"A comprehensive analysis of fusion-based image enhancement techniques","author":"A. S. Parihar"},{"key":"37","doi-asserted-by":"crossref","article-title":"Empirical aspect of big data to enhance medical images using HIPI","author":"A. Maheshwari","DOI":"10.1109\/ICCONS.2018.8663053"},{"key":"38","article-title":"Xception: deep learning with depthwise separable convolutions","author":"F. c. c. o. Chollet","year":"2017"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"40","article-title":"Deep residual learning for image recognition","author":"K. He","year":"2015"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.05.031"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2019.2935128"},{"key":"43","article-title":"Mixup: beyond empirical risk minimization","author":"H. Zhang","year":"2018"},{"key":"44","article-title":"Neural architecture search with reinforcement learning","author":"B. Zoph","year":"2017"},{"key":"45","article-title":"AutoAugment: learning augmentation policies from data","author":"E. D. Cubuk","year":"2019"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2018.2791488"},{"key":"47","article-title":"Accelerating deep network training by reducing internal covariate shift","author":"B. Normalization","year":"2015"},{"key":"48","article-title":"A simple framework for contrastive learning of visual representations","author":"T. Chen"},{"key":"49","article-title":"Building high-level features using large scale unsupervised learning","author":"Q. V. Le"},{"key":"50","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"51","article-title":"Unsupervised feature learning via non-parametric instance discrimination","author":"Z. Wu"}],"container-title":["Journal of Healthcare Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/jhe\/2021\/5549779.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jhe\/2021\/5549779.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jhe\/2021\/5549779.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T22:05:34Z","timestamp":1620338734000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/jhe\/2021\/5549779\/"}},"subtitle":[],"editor":[{"given":"Hao-Chun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,5,5]]},"references-count":51,"alternative-id":["5549779","5549779"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5549779","relation":{},"ISSN":["2040-2309","2040-2295"],"issn-type":[{"value":"2040-2309","type":"electronic"},{"value":"2040-2295","type":"print"}],"subject":[],"published":{"date-parts":[[2021,5,5]]}}}