Article Text

Original research
Diagnostic accuracy of code-free deep learning for detection and evaluation of posterior capsule opacification
  1. Josef Huemer1,2,
  2. Martin Kronschläger3,
  3. Manuel Ruiss3,
  4. Dawn Sim1,
  5. Pearse A Keane1,2,4,
  6. Oliver Findl3,
  7. Siegfried K Wagner1,2,4
  1. 1Department of Medical Retina, Moorfields Eye Hospital NHS Foundation Trust, London, UK
  2. 2NIHR Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK
  3. 3VIROS-Vienna Institute for Research in Ocular Surgery, a Karl Landsteiner Institute, Hanusch Hospital, Vienna, Austria
  4. 4Institute of Ophthalmology, UCL, London, UK
  1. Correspondence to Siegfried K Wagner; S.wagner{at}ucl.ac.uk

Abstract

Objective To train and validate a code-free deep learning system (CFDLS) on classifying high-resolution digital retroillumination images of posterior capsule opacification (PCO) and to discriminate between clinically significant and non-significant PCOs.

Methods and analysis For this retrospective registry study, three expert observers graded two independent datasets of 279 images three separate times with no PCO to severe PCO, providing binary labels for clinical significance. The CFDLS was trained and internally validated using 179 images of a training dataset and externally validated with 100 images. Model development was through Google Cloud AutoML Vision. Intraobserver and interobserver variabilities were assessed using Fleiss kappa (κ) coefficients and model performance through sensitivity, specificity and area under the curve (AUC).

Results Intraobserver variability κ values for observers 1, 2 and 3 were 0.90 (95% CI 0.86 to 0.95), 0.94 (95% CI 0.90 to 0.97) and 0.88 (95% CI 0.82 to 0.93). Interobserver agreement was high, ranging from 0.85 (95% CI 0.79 to 0.90) between observers 1 and 2 to 0.90 (95% CI 0.85 to 0.94) for observers 1 and 3. On internal validation, the AUC of the CFDLS was 0.99 (95% CI 0.92 to 1.0); sensitivity was 0.89 at a specificity of 1. On external validation, the AUC was 0.97 (95% CI 0.93 to 0.99); sensitivity was 0.84 and specificity was 0.92.

Conclusion This CFDLS provides highly accurate discrimination between clinically significant and non-significant PCO equivalent to human expert graders. The clinical value as a potential decision support tool in different models of care warrants further research.

  • diagnostic tests/investigation
  • imaging
  • lens and zonules

Data availability statement

Data are available upon request. Interested parties should contact JH.

https://creativecommons.org/licenses/by/4.0/

This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https://creativecommons.org/licenses/by/4.0/.

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 request. Interested parties should contact JH.

View Full Text

Supplementary material

  • Supplementary Data

    This web only file has been produced by the BMJ Publishing Group from an electronic file supplied by the author(s) and has not been edited for content.

Footnotes

  • JH and MK contributed equally.

  • Contributors All listed authors contributed to the conception or design of the work; or the acquisition, analysis or interpretation of data for the work; drafted or revised the work critically for important intellectual content; and finally approved this version to be published and agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. SKW is responsible for the overall content as guarantor.

  • Funding SKW is supported by a MRC clinical research training fellowship (MR/TR000953/1). PAK is supported by a Moorfields Eye Charity Career Development Award (R190028A) and a UK Research & Innovation Future Leaders Fellowship (MR/T019050/1).

  • Competing interests JH received travel grants from Bayer, speaker fees from Carl Zeiss Meditec AG and Bayer, and served on advisory boards for Roche outside of this work. DS received speaker fees from Allergan, Bayer, Novartis and Haag Streit. PAK acted as a consultant for DeepMind, Roche, Novartis and Apellis; was an equity owner in Big Picture Medical; and received speaker fees from Heidelberg Engineering, Topcon, Allergan and Bayer. OF is a scientific advisor to Alcon, Carl Zeiss Meditec AG, Croma Pharma, Johnson & Johnson and Merck.

  • 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.