{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T15:57:01Z","timestamp":1782143821146,"version":"3.54.5"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["21H03095"],"award-info":[{"award-number":["21H03095"]}]},{"name":"JSPS KAKENHI","award":["22K16975"],"award-info":[{"award-number":["22K16975"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Aim\/background<\/jats:title>\n<jats:p>To aim of this study is to develop an artificial intelligence (AI) that aids in the thought process by providing retinal clinicians with clinically meaningful or abnormal findings rather than just a final diagnosis, i.e., a \u201cwayfinding AI.\u201d<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Spectral domain optical coherence tomography B-scan images were classified into 189 normal and 111 diseased eyes. These were automatically segmented using a deep-learning based boundary-layer detection model. During segmentation, the AI model calculates the probability of the boundary surface of the layer for each A-scan. If this probability distribution is not biased toward a single point, layer detection is defined as ambiguous. This ambiguity was calculated using entropy, and a value referred to as the ambiguity index was calculated for each OCT image. The ability of the ambiguity index to classify normal and diseased images and the presence or absence of abnormalities in each layer of the retina were evaluated based on the area under the curve (AUC). A heatmap, i.e., an ambiguity-map, of each layer, that changes the color according to the ambiguity index value, was also created.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>The ambiguity index of the overall retina of the normal and disease-affected images (mean \u00b1 SD) were 1.76 \u00b1 0.10 and 2.06 \u00b1 0.22, respectively, with a significant difference (p &lt; 0.05). The AUC used to distinguish normal and disease-affected images using the ambiguity index was 0.93, and was 0.588 for the internal limiting membrane boundary, 0.902 for the nerve fiber layer\/ganglion cell layer boundary, 0.920 for the inner plexiform layer\/inner nuclear layer boundary, 0.882 for the outer plexiform layer\/outer nuclear layer boundary, 0.926 for the ellipsoid zone line, and 0.866 for the retinal pigment epithelium\/Bruch\u2019s membrane boundary. Three representative cases reveal the usefulness of an ambiguity map.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>The present AI algorithm can pinpoint abnormal retinal lesions in OCT images, and its localization is known at a glance when using an ambiguity map. This will help diagnose the processes of clinicians as a wayfinding tool.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0283214","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T17:29:33Z","timestamp":1679938173000},"page":"e0283214","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Wayfinding artificial intelligence to detect clinically meaningful spots of retinal diseases: Artificial intelligence to help retina specialists in real world practice"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2208-2118","authenticated-orcid":true,"given":"Hideki","family":"Shiihara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shozo","family":"Sonoda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroto","family":"Terasaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuki","family":"Fujiwara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryoh","family":"Funatsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yousuke","family":"Shiba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiki","family":"Kumagai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoto","family":"Honda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0287-3801","authenticated-orcid":true,"given":"Taiji","family":"Sakamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"issue":"7553","key":"pone.0283214.ref001","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning.","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"issue":"22","key":"pone.0283214.ref002","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"13","key":"pone.0283214.ref003","doi-asserted-by":"crossref","first-page":"5200","DOI":"10.1167\/iovs.16-19964","article-title":"Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning","volume":"57","author":"MD Abr\u00e0moff","year":"2016","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"7","key":"pone.0283214.ref004","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1016\/j.ophtha.2017.02.008","article-title":"Automated identification of diabetic retinopathy using deep learning","volume":"124","author":"R Gargeya","year":"2017","journal-title":"Ophthalmology"},{"issue":"22","key":"pone.0283214.ref005","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes","volume":"318","author":"DSW Ting","year":"2017","journal-title":"JAMA"},{"issue":"11","key":"pone.0283214.ref006","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1001\/jamaophthalmol.2017.3782","article-title":"Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks","volume":"135","author":"PM Burlina","year":"2017","journal-title":"JAMA Ophthalmol"},{"issue":"12","key":"pone.0283214.ref007","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1001\/jamaophthalmol.2018.4118","article-title":"Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration","volume":"136","author":"PM Burlina","year":"2018","journal-title":"JAMA Ophthalmol"},{"issue":"8","key":"pone.0283214.ref008","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","article-title":"Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs","volume":"125","author":"Z Li","year":"2018","journal-title":"Ophthalmology"},{"key":"pone.0283214.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.preteyeres.2018.07.004","article-title":"Artificial intelligence in retina","volume":"67","author":"U Schmidt-Erfurth","year":"2018","journal-title":"Prog Retin Eye Res"},{"issue":"9","key":"pone.0283214.ref010","doi-asserted-by":"crossref","first-page":"1410","DOI":"10.1016\/j.ophtha.2018.02.037","article-title":"A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography","volume":"125","author":"F Grassmann","year":"2018","journal-title":"Ophthalmology"},{"issue":"7","key":"pone.0283214.ref011","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1001\/jamaophthalmol.2018.1934","article-title":"Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks","volume":"136","author":"JM Brown","year":"2018","journal-title":"JAMA Ophthalmol"},{"issue":"7623","key":"pone.0283214.ref012","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/538020a","article-title":"Can we open the black box of AI?","volume":"538","author":"D. Castelvecchi","year":"2016","journal-title":"Nature"},{"issue":"3","key":"pone.0283214.ref013","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1001\/jamaophthalmol.2018.6035","article-title":"Visualizing deep learning models for the detection of referable diabetic retinopathy and glaucoma","volume":"137","author":"S Keel","year":"2019","journal-title":"JAMA Ophthalmol"},{"issue":"2","key":"pone.0283214.ref014","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"DSW Ting","year":"2019","journal-title":"Br J Ophthalmol"},{"issue":"24","key":"pone.0283214.ref015","doi-asserted-by":"crossref","first-page":"2467","DOI":"10.1001\/jama.2021.22396","article-title":"Next-Generation Artificial Intelligence for Diagnosis: From Predicting Diagnostic Labels to \u201cWayfinding\u201d.","volume":"326","author":"J Adler-Milstein","year":"2021","journal-title":"JAMA"},{"issue":"9","key":"pone.0283214.ref016","doi-asserted-by":"crossref","first-page":"OCT1","DOI":"10.1167\/iovs.16-19963","article-title":"The Development, Commercialization, and Impact of Optical Coherence Tomography","volume":"57","author":"J Fujimoto","year":"2016","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"1","key":"pone.0283214.ref017","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TMI.2019.2919951","article-title":"Exploiting epistemic uncertainty of anatomy segmentation for anomaly detection in retinal OCT","volume":"39","author":"P Seeb\u00f6ck","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"issue":"5","key":"pone.0283214.ref018","doi-asserted-by":"crossref","first-page":"e0251553","DOI":"10.1371\/journal.pone.0251553","article-title":"Artificial intelligence for classifying uncertain images by humans in determining choroidal vascular running pattern and comparisons with automated classification between artificial intelligence","volume":"16","author":"S Sonoda","year":"2021","journal-title":"PLOS ONE"},{"key":"pone.0283214.ref019","doi-asserted-by":"crossref","first-page":"106732","DOI":"10.1016\/j.cmpb.2022.106732","article-title":"DilUnet: A U-net based architecture for blood vessels segmentation","volume":"218","author":"S Hussain","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0283214.ref020","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T, editors. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, Cham. 2015;234\u2013231. doi: 10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"pone.0283214.ref021","first-page":"120","article-title":"Fully Convolutional Boundary Regression for Retina OCT Segmentation.","volume":"11764","author":"Y He","year":"2019","journal-title":"Med Image Comput Comput Assist Interv."},{"issue":"4","key":"pone.0283214.ref022","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.oret.2016.12.009","article-title":"Deep learning is effective for classifying normal versus age-related macular degeneration OCT images.","volume":"1","author":"CS Lee","year":"2017","journal-title":"Ophthalmol Retina"},{"issue":"9","key":"pone.0283214.ref023","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"J De Fauw","year":"2018","journal-title":"Nat Med"},{"issue":"9","key":"pone.0283214.ref024","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1136\/bjophthalmol-2020-317817","article-title":"Computer-aided detection and abnormality score for the outer retinal layer in optical coherence tomography","volume":"106","author":"TH Rim","year":"2021","journal-title":"Br J Ophthalmol"},{"key":"pone.0283214.ref025","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1038\/s41591-020-0867-7","article-title":"Predicting conversion to wet age-related macular degeneration using deep learning","volume":"26","author":"J Yim","year":"2020","journal-title":"Nat Med"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0283214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T17:30:06Z","timestamp":1679938206000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0283214"}},"subtitle":[],"editor":[{"given":"Wei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":25,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0283214","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]}}}