{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T01:05:05Z","timestamp":1790211905567,"version":"4.1.0"},"reference-count":28,"publisher":"SPIE-Intl Soc Optical Eng","issue":"06","license":[{"start":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T00:00:00Z","timestamp":1696291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2023,10,3]]},"abstract":"<jats:p>PurposeRetinopathy of prematurity (ROP) is a retinal vascular disease affecting premature infants that can culminate in blindness within days if not monitored and treated. A disease stage for scrutiny and administration of treatment within ROP is \u201cplus disease\u201d characterized by increased tortuosity and dilation of posterior retinal blood vessels. The monitoring of ROP occurs via routine imaging, typically using expensive instruments ($50 to $140\u00a0K) that are unavailable in low-resource settings at the point of care.ApproachAs part of the smartphone-ROP program to enable referrals to expert physicians, fundus images are acquired using smartphone cameras and inexpensive lenses. We developed methods for artificial intelligence determination of plus disease, consisting of a preprocessing pipeline to enhance vessels and harmonize images followed by deep learning classification. A deep learning binary classifier (plus disease versus no plus disease) was developed using GoogLeNet.ResultsVessel contrast was enhanced by 90% after preprocessing as assessed by the contrast improvement index. In an image quality evaluation, preprocessed and original images were evaluated by pediatric ophthalmologists from the US and South America with years of experience diagnosing ROP and plus disease. All participating ophthalmologists agreed or strongly agreed that vessel visibility was improved with preprocessing. Using images from various smartphones, harmonized via preprocessing (e.g., vessel enhancement and size normalization) and augmented in physically reasonable ways (e.g., image rotation), we achieved an area under the ROC curve of 0.9754 for plus disease on a limited dataset.ConclusionsPromising results indicate the potential for developing algorithms and software to facilitate the usage of cell phone images for staging of plus disease.<\/jats:p>","DOI":"10.1117\/1.jmi.10.6.061107","type":"journal-article","created":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T04:47:38Z","timestamp":1696308458000},"page":"1-13","source":"Crossref","is-referenced-by-count":7,"title":["Image harmonization and deep learning automated classification of plus disease in retinopathy of prematurity"],"prefix":"10.1117","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0824-1485","authenticated-orcid":false,"given":"Ananya","family":"Subramaniam","sequence":"first","affiliation":[{"name":"Case Western Reserve Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5095-6401","authenticated-orcid":false,"given":"Faruk","family":"Orge","sequence":"additional","affiliation":[{"name":"Case Medical Ctr. Univ. Hospitals"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Douglass","sequence":"additional","affiliation":[{"name":"Case Western Reserve Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basak","family":"Can","sequence":"additional","affiliation":[{"name":"Case Medical Ctr. Univ. Hospitals"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillermo","family":"Monteoliva","sequence":"additional","affiliation":[{"name":"Hospital Italiano de San Justo Agustin Rocca"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evelin","family":"Fried","sequence":"additional","affiliation":[{"name":"Hospital Italiano de San Justo Agustin Rocca"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6713-4618","authenticated-orcid":false,"given":"Vanina","family":"Schbib","sequence":"additional","affiliation":[{"name":"Hospital de Ni\u00f1os Sor Maria Ludovica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriela","family":"Saidman","sequence":"additional","affiliation":[{"name":"Hospital Evita Pueblo de Berazategui"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brenda","family":"Pe\u00f1a","sequence":"additional","affiliation":[{"name":"Centro Integral de Salud Visual Daponte"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soledad","family":"Ulacia","sequence":"additional","affiliation":[{"name":"Ministerio de Salud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-5467","authenticated-orcid":false,"given":"Pedro","family":"Acevedo","sequence":"additional","affiliation":[{"name":"Fundaci\u00f3n Oftalmol\u00f3gica Nacional"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7780-4862","authenticated-orcid":false,"given":"Andrew M.","family":"Rollins","sequence":"additional","affiliation":[{"name":"Case Western Reserve Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-1463","authenticated-orcid":false,"given":"David L.","family":"Wilson","sequence":"additional","affiliation":[{"name":"Case Western Reserve Univ."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.5409\/wjcp.v5.i1.35"},{"key":"r2","article-title":"Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks | Neonatology | JAMA ophthalmology | JAMA network","author":"Brown","year":"2018"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(13)60178-6"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.4103\/0974-9233.63080"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1016\/j.oret.2020.04.022"},{"key":"r6","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2017.09.002"},{"key":"r7","first-page":"45","article-title":"Retinopathy of prematurity: it is time to take action","author":"Gilbert","year":"2017"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-019-1180-4"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.22608\/APO.201963"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.8.6.23"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.4103\/ijo.IJO_700_18"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1097\/APO.0000000000000303"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaapos.2005.11.019"},{"key":"r14","article-title":"RetCam Envision\u2122 ophthalmic imaging system"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.02.005"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-313156"},{"key":"r17","first-page":"2","article-title":"Circular Hough transform","author":"Pedersen","year":"2007"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1988.01060130517027"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962617"},{"key":"r20","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-018-0685-6"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.22608\/APO.201837"},{"key":"r22","article-title":"Economic impact of the use of anti-VEGF monotherapy or in combination with panretinal photocoagulation","year":"2019"},{"key":"r23","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2013-003471"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1007\/BF03178082"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.14257\/ijsip.2017.10.12.04"},{"key":"r26","article-title":"Parametric ROC curve","author":"Bantis","year":"2023"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"r28","doi-asserted-by":"publisher","DOI":"10.1117\/12.2613268"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-10\/issue-06\/061107\/Image-harmonization-and-deep-learning-automated-classification-of-plus-disease\/10.1117\/1.JMI.10.6.061107.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:28:13Z","timestamp":1790209693000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-10\/issue-06\/061107\/Image-harmonization-and-deep-learning-automated-classification-of-plus-disease\/10.1117\/1.JMI.10.6.061107.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,3]]},"references-count":28,"journal-issue":{"issue":"06","published-online":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.10.6.061107","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,3]]}}}