You are here

  • Home
  • Archive
  • Volume 108, Issue 12
  • Detection of glaucoma progression on longitudinal series of en-face macular optical coherence tomography angiography images with a deep learning model

Article Text

Article menu
Download PDFPDF
Glaucoma
Detection of glaucoma progression on longitudinal series of en-face macular optical coherence tomography angiography images with a deep learning model
  1. Vahid Mohammadzadeh1,2,
  2. Youwei Liang3,
  3. Sasan Moghimi1,
  4. Pengtao Xie3,
  5. Takashi Nishida1,
  6. Golnoush Mahmoudinezhad1,
  7. Medi Eslani1,
  8. Evan Walker1,
  9. Alireza Kamalipour1,
  10. Eleonora Micheletti4,
  11. Jo-Hsuan Wu1,
  12. Mark Christopher1,
  13. Linda M Zangwill1,
  14. Tara Javidi3,
  15. Robert N Weinreb1
  1. 1 Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, California, USA
  2. 2 Ophthalmology and Vision Science, University of Louisville, Louisville, Kentucky, USA
  3. 3 Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, California, USA
  4. 4 Department of Surgical & Clinical, Diagnostic and Pediatric Sciences, Section of Ophthalmology, University of Pavia, Pavia, Lombardia, Italy
  1. Correspondence to Dr Robert N Weinreb; rweinreb{at}ucsd.edu

Abstract

Background/aims To design a deep learning (DL) model for the detection of glaucoma progression with a longitudinal series of macular optical coherence tomography angiography (OCTA) images.

Methods 202 eyes of 134 patients with open-angle glaucoma with ≥4 OCTA visits were followed for an average of 3.5 years. Glaucoma progression was defined as having a statistically significant negative 24-2 visual field (VF) mean deviation (MD) rate. The baseline and final macular OCTA images were aligned according to centre of fovea avascular zone automatically, by checking the highest value of correlation between the two images. A customised convolutional neural network (CNN) was designed for classification. A comparison of the CNN to logistic regression model for whole image vessel density (wiVD) loss on detection of glaucoma progression was performed. The performance of the model was defined based on the confusion matrix of the validation dataset and the area under receiver operating characteristics (AUC).

Results The average (95% CI) baseline VF MD was −3.4 (−4.1 to −2.7) dB. 28 (14%) eyes demonstrated glaucoma progression. The AUC (95% CI) of the DL model for the detection of glaucoma progression was 0.81 (0.59 to 0.93). The sensitivity, specificity and accuracy (95% CI) of DL model were 67% (34% to 78%), 83% (42% to 97%) and 80% (52% to 95%), respectively. The AUC (95% CI) for the detection of glaucoma progression based on the logistic regression model was lower than the DL model (0.69 (0.50 to 0.88)).

Conclusion The optimised DL model detected glaucoma progression based on longitudinal macular OCTA images showed good performance. With external validation, it could enhance detection of glaucoma progression.

Trial registration number NCT00221897.

  • Glaucoma

Data availability statement

Data are available upon reasonable request. The datasets generated and/or analysed during the current study are available from the corresponding author on reasonable request.

https://doi.org/10.1136/bjo-2023-324528

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available upon reasonable request. The datasets generated and/or analysed during the current study are available from the corresponding author on reasonable request.

    View Full Text

    Footnotes

    • VM and YL are joint first authors.

    • VM and YL contributed equally.

    • Contributors VM involved in design and conduct of study, data collection, analysis and interpretation of data, writing, critical revision and approval of the manuscript. YL involved in design and conduct of study, analysis and interpretation of data, writing and critical revision. SM involved in design and conduct of study, data collection, analysis and interpretation of data, writing, critical revision and approval of the manuscript. PX involved in design and conduct of study, writing and critical revision. TN involved in data collection, analysis and interpretation of data, writing and critical revision. GM involved in data collection and writing. ME involved in data collection and writing. EW involved in analysis and interpretation of data and writing. AK involved in data collection and writing. EM involved in data collection and writing. J-HW involved in data collection and writing. MC involved in analysis and interpretation of data and writing. LMZ involved in design and conduct of study, data collection, analysis and interpretation of data, writing, critical revision and approval of the manuscript. TJ involved in design and conduct of study, analysis and interpretation of data, writing, critical revision and approval of the manuscript. RNW involved in design and conduct of study, data collection, analysis and interpretation of data, had access to the data, writing, critical revision and approval of the manuscript, controlled the decision to publish and overall guarantor of work.

    • Funding This work is supported by National Institutes of Health/National Eye Institute Grants R01EY034148, R01EY029058, R01EY011008, R01EY019869, R01EY027510, R01EY026574, P30EY022589; University of California Tobacco Related Disease Research Program (T31IP1511), Research to Prevent Blindness (an unrestricted grant), and participant retention incentive grants in the form of glaucoma medication at no cost from Novartis/Alcon Laboratories, Allergan, Akorn and Pfizer.

    • Disclaimer The sponsor or funding organisations had no role in the design or conduct of this research.

    • Competing interests VM: None; YL: None; SM: F: National Eye Institute; PX: None; TN: C: Topcon; GM: None; ME: None; EW: None; AK: F: Fight for Sight; EM: None; J-HW: None:, MC: F: National Eye Institute; LMZ: C: Abbvie Inc., Topcon; F: National Eye Institute, Carl Zeiss Meditec Inc., Heidelberg Engineering GmbH, Optovue Inc., Topcon Medical Systems Inc.; P: Zeiss Meditec, AISight Health (founder); TJ: None; RNW: C: Abbvie, Aerie Pharmaceuticals, Allergan, Amydis, Editas, Equinox, Eyenovia, Iantrek, Implandata, IOPtic, iSTAR Medical, Nicox, Santen, Tenpoint and Topcon; F: National Eye Institute, National Institute of Minority Health and Health Disparities, Heidelberg Engineering, Carl Zeiss Meditec, Konan Medical, Optovue, Zilia, Centervue, and Topcon; P: Toromedes, Carl Zeiss Meditec.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.