Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study
Objective To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).Design A diagnostic accuracy study.Setting A single-centre study.Participants A total of 304 keratoconic eye...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2019-09-01
|
| Series: | BMJ Open |
| Online Access: | https://bmjopen.bmj.com/content/9/9/e031313.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846149987797303296 |
|---|---|
| author | Nobuyuki Shoji Kazutaka Kamiya Yuji Ayatsuka Yudai Kato Fusako Fujimura Masahide Takahashi Yosai Mori Kazunori Miyata |
| author_facet | Nobuyuki Shoji Kazutaka Kamiya Yuji Ayatsuka Yudai Kato Fusako Fujimura Masahide Takahashi Yosai Mori Kazunori Miyata |
| author_sort | Nobuyuki Shoji |
| collection | DOAJ |
| description | Objective To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).Design A diagnostic accuracy study.Setting A single-centre study.Participants A total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes.Main outcome measures The diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map).Results Deep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage.Conclusions Deep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice.Clinical trial registration number 000034587. |
| format | Article |
| id | doaj-art-ca77d6bfc6a64476b55b46cfe199a910 |
| institution | Kabale University |
| issn | 2044-6055 |
| language | English |
| publishDate | 2019-09-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Open |
| spelling | doaj-art-ca77d6bfc6a64476b55b46cfe199a9102024-11-29T08:55:11ZengBMJ Publishing GroupBMJ Open2044-60552019-09-019910.1136/bmjopen-2019-031313Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy studyNobuyuki Shoji0Kazutaka Kamiya1Yuji Ayatsuka2Yudai Kato3Fusako Fujimura4Masahide Takahashi5Yosai Mori6Kazunori Miyata7Department of Ophthalmology, Kitasato University School of Medicine, Sagamihara, Kanagawa, JapanVisual Physiology, Kitasato University School of Allied Health Sciences, Sagamihara, Japan2 Cresco Ltd, Technology Laboratory, Tokyo, Japan2 Cresco Ltd, Technology Laboratory, Tokyo, Japan1 Visual Phisiology, School of Allied Health Sciences, Kitasato University, Sagamihara, Japan3 Department of Ophthalmology, School of Medicine, Kitasato University, Sagamihara, Japan4 Miyata Eye Hospital, Department of Ophthalmology, Miyakonojo, Japan6 Miyata Eye Hospital, Miyakonojo, JapanObjective To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).Design A diagnostic accuracy study.Setting A single-centre study.Participants A total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes.Main outcome measures The diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map).Results Deep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage.Conclusions Deep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice.Clinical trial registration number 000034587.https://bmjopen.bmj.com/content/9/9/e031313.full |
| spellingShingle | Nobuyuki Shoji Kazutaka Kamiya Yuji Ayatsuka Yudai Kato Fusako Fujimura Masahide Takahashi Yosai Mori Kazunori Miyata Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study BMJ Open |
| title | Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study |
| title_full | Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study |
| title_fullStr | Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study |
| title_full_unstemmed | Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study |
| title_short | Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study |
| title_sort | keratoconus detection using deep learning of colour coded maps with anterior segment optical coherence tomography a diagnostic accuracy study |
| url | https://bmjopen.bmj.com/content/9/9/e031313.full |
| work_keys_str_mv | AT nobuyukishoji keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT kazutakakamiya keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT yujiayatsuka keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT yudaikato keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT fusakofujimura keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT masahidetakahashi keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT yosaimori keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy AT kazunorimiyata keratoconusdetectionusingdeeplearningofcolourcodedmapswithanteriorsegmentopticalcoherencetomographyadiagnosticaccuracystudy |