Keratoconus detection of changes using deep learning of colour-coded maps

Simple item page
dc.contributor.authorChen, Xu
dc.contributor.authorZhao, Jiaxin
dc.contributor.authorIselin, Katja C.
dc.contributor.authorBorroni, Davide
dc.contributor.authorRomano, Davide
dc.contributor.authorGokul, Akilesh
dc.contributor.authorMcGhee, Charles N.J.
dc.contributor.authorZhao, Yitian
dc.contributor.authorSedaghat, Mohammad Reza
dc.contributor.authorMomeni-Moghaddam, Hamed
dc.contributor.authorZiaei, Mohammed
dc.contributor.authorKaye, Stephen
dc.contributor.authorRomano, Vito
dc.contributor.authorZheng, Yalin
dc.date.accessioned2025-01-02T12:55:01Z
dc.date.available2025-01-02T12:55:01Z
dc.date.issued2021-07-13
dc.descriptionPublisher Copyright: © Authors 2021
dc.description.abstractObjective To evaluate the accuracy of convolutional neural networks technique (CNN) in detecting keratoconus using colour-coded corneal maps obtained by a Scheimpflug camera. Design Multicentre retrospective study. Methods and analysis We included the images of keratoconic and healthy volunteers' eyes provided by three centres: Royal Liverpool University Hospital (Liverpool, UK), Sedaghat Eye Clinic (Mashhad, Iran) and The New Zealand National Eye Center (New Zealand). Corneal tomography scans were used to train and test CNN models, which included healthy controls. Keratoconic scans were classified according to the Amsler-Krumeich classification. Keratoconic scans from Iran were used as an independent testing set. Four maps were considered for each scan: axial map, anterior and posterior elevation map, and pachymetry map. Results A CNN model detected keratoconus versus health eyes with an accuracy of 0.9785 on the testing set, considering all four maps concatenated. Considering each map independently, the accuracy was 0.9283 for axial map, 0.9642 for thickness map, 0.9642 for the front elevation map and 0.9749 for the back elevation map. The accuracy of models in recognising between healthy controls and stage 1 was 0.90, between stages 1 and 2 was 0.9032, and between stages 2 and 3 was 0.8537 using the concatenated map. Conclusion CNN provides excellent detection performance for keratoconus and accurately grades different severities of disease using the colour-coded maps obtained by the Scheimpflug camera. CNN has the potential to be further developed, validated and adopted for screening and management of keratoconus.en
dc.description.statusPeer reviewed
dc.format.extent246787
dc.identifier.citationChen, X, Zhao, J, Iselin, K C, Borroni, D, Romano, D, Gokul, A, McGhee, C N J, Zhao, Y, Sedaghat, M R, Momeni-Moghaddam, H, Ziaei, M, Kaye, S, Romano, V & Zheng, Y 2021, 'Keratoconus detection of changes using deep learning of colour-coded maps', BMJ Open Ophthalmology, vol. 6, no. 1, e000824. https://doi.org/10.1136/bmjophth-2021-000824
dc.identifier.doi10.1136/bmjophth-2021-000824
dc.identifier.issn2397-3269
dc.identifier.urihttps://dspace.rsu.lv/jspui/handle/123456789/17004
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85110305777&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofBMJ Open Ophthalmology
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectcornea
dc.subjectimaging
dc.subject3.2 Clinical medicine
dc.subject1.1. Scientific article indexed in Web of Science and/or Scopus database
dc.subjectOphthalmology
dc.titleKeratoconus detection of changes using deep learning of colour-coded mapsen
dc.type/dk/atira/pure/researchoutput/researchoutputtypes/contributiontojournal/article

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Keratoconus_detection_of_changes.pdf
Size:
241 KB
Format:
Adobe Portable Document Format
Download

Collections

Research outputs from Pure / Zinātniskās darbības rezultāti no ZDIS Pure