{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:07:03Z","timestamp":1790269623839,"version":"4.1.0"},"reference-count":48,"publisher":"SPIE-Intl Soc Optical Eng","issue":"04","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST106-2218-E-010-004-MY3"],"award-info":[{"award-number":["MOST106-2218-E-010-004-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST109-2314-B-010-027"],"award-info":[{"award-number":["MOST109-2314-B-010-027"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST110-2314-B-A49A-529"],"award-info":[{"award-number":["MOST110-2314-B-A49A-529"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2022,7,25]]},"abstract":"<jats:p>Purpose: Retinopathy screening via digital imaging is promising for early detection and timely treatment, and tracking retinopathic abnormality over time can help to reveal the risk of disease progression. We developed an innovative physician-oriented artificial intelligence-facilitating diagnosis aid system for retinal diseases for screening multiple retinopathies and monitoring the regions of potential abnormality over time.Approach: Our dataset contains 4908 fundus images from 304 eyes with image-level annotations, including diabetic retinopathy, age-related macular degeneration, cellophane maculopathy, pathological myopia, and healthy control (HC). The screening model utilized a VGG-based feature extractor and multiple-binary convolutional neural network-based classifiers. Images in time series were aligned via affine transforms estimated through speeded-up robust features. Heatmaps of retinopathy were generated from the feature extractor using gradient-weighted class activation mapping++, and individual candidate retinopathy sites were identified from the heatmaps using clustering algorithm. Nested cross-validation with a train-to-test split of 80% to 20% was used to evaluate the performance of the screening model.Results: Our screening model achieved 99% accuracy, 93% sensitivity, and 97% specificity in discriminating between patients with retinopathy and HCs. For discriminating between types of retinopathy, our model achieved an averaged performance of 80% accuracy, 78% sensitivity, 94% specificity, 79% F1-score, and Cohen\u2019s kappa coefficient of 0.70. Moreover, visualization results were also shown to provide reasonable candidate sites of retinopathy.Conclusions: Our results demonstrated the capability of the proposed model for extracting diagnostic information of the abnormality and lesion locations, which allows clinicians to focus on patient-centered treatment and untangles the pathological plausibility hidden in deep learning models.<\/jats:p>","DOI":"10.1117\/1.jmi.9.4.044501","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T12:44:50Z","timestamp":1658753090000},"page":"1-17","source":"Crossref","is-referenced-by-count":6,"title":["PADAr: physician-oriented artificial intelligence-facilitating diagnosis aid for retinal diseases"],"prefix":"10.1117","volume":"9","author":[{"given":"Po-Kang","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hsien","family":"Chiu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiu-Jung","family":"Huang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chien-Yao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science - Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei-Lien","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Information Science - Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da-Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science - Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Yuan","family":"Mark Liao","sequence":"additional","affiliation":[{"name":"Institute of Information Science - Academia Sinica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chieh-Hsiung","family":"Kuan","sequence":"additional","affiliation":[{"name":"National Taiwan Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Yen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3819-853X","authenticated-orcid":false,"given":"Li-Fen","family":"Chen","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2013.10.007"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9394(01)01218-1"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.3109\/08820530009040000"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2012.04.001"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1111\/aos.13976"},{"key":"r6","first-page":"198","article-title":"Classification of artery and vein in retinal fundus images based on the context-dependent features","author":"Yan"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1167\/Iovs.16-19964"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0187336"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4608-y"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.05.001"},{"key":"r11","first-page":"799","article-title":"Automated diabetic retinopathy detection using radial basis function","author":"Kamble","year":"2020"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-015-2059-9"},{"key":"r13","first-page":"839","article-title":"Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"r14","first-page":"469","article-title":"Fundus image classification and retinal disease localization with limited supervision","author":"Meng"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-016-0640-0"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2015.7319674"},{"key":"r18","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan","year":"2015"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"r20","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"r22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"r23","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-6-10"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_5"},{"key":"r28","first-page":"474","author":"Zuiderveld","year":"1994"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"r30","first-page":"331","article-title":"Fast approximate nearest neighbors with automatic algorithm configuration","author":"Muja","year":"2009"},{"key":"r31","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1999.0832"},{"key":"r32","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"r33","author":"Kaufman","year":"2009"},{"key":"r34","author":"Han","year":"2011"},{"key":"r35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.02.008"},{"key":"r36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296646"},{"key":"r37","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2019.2004"},{"key":"r38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.03.016"},{"key":"r39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103537"},{"key":"r40","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102600"},{"key":"r41","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102329"},{"key":"r42","first-page":"1271","article-title":"Retinal Image Processing and Classification Using Convolutional Neural Networks","author":"Rajan","year":"2019"},{"key":"r43","doi-asserted-by":"publisher","DOI":"10.2337\/dc18-0148"},{"key":"r44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfma.2020.03.024"},{"key":"r45","doi-asserted-by":"crossref","DOI":"10.5772\/7618","article-title":"Quality assessment of retinal fundus images using elliptical local vessel density","author":"Giancardo","year":"2010"},{"key":"r46","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3043495"},{"key":"r47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.02.037"},{"key":"r48","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0172-3"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-9\/issue-04\/044501\/PADAr--physician-oriented-artificial-intelligence-facilitating-diagnosis-aid-for\/10.1117\/1.JMI.9.4.044501.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:40:22Z","timestamp":1790268022000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-9\/issue-04\/044501\/PADAr--physician-oriented-artificial-intelligence-facilitating-diagnosis-aid-for\/10.1117\/1.JMI.9.4.044501.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,25]]},"references-count":48,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2022,7,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.9.4.044501","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,25]]}}}