Article Text

Download PDFPDF
Validation of a deep learning model for automatic detection and quantification of five OCT critical retinal features associated with neovascular age-related macular degeneration
  1. Federico Ricardi1,2,
  2. Jonathan Oakley3,
  3. Daniel Russakoff3,
  4. Giacomo Boscia1,2,
  5. Paolo Caselgrandi1,2,
  6. Francesco Gelormini1,2,
  7. Andrea Ghilardi1,2,
  8. Giulia Pintore1,2,
  9. Tommaso Tibaldi1,2,
  10. Paola Marolo1,2,
  11. Francesco Bandello4,5,
  12. Michele Reibaldi1,2,
  13. Enrico Borrelli1,2
  1. 1Department of Surgical Sciences, University of Turin, Turin, Italy
  2. 2Department of Ophthalmology, "City of Health and Science" Hospital, Turin, Italy
  3. 3Voxeleron Inc, Austin, Texas, USA
  4. 4Division of Head and Neck, Ophthalmology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy
  5. 5School of Medicine, Vita-Salute San Raffaele University, Milan, Italy
  1. Correspondence to Professor Enrico Borrelli, Department of Surgical Sciences, University of Turin, Turin, Italy; borrelli.enrico{at}yahoo.com

Abstract

Purpose To develop and validate a deep learning model for the segmentation of five retinal biomarkers associated with neovascular age-related macular degeneration (nAMD).

Methods 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients.

Results The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10).

Conclusions We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians’ assessments.

  • Imaging
  • Diagnostic tests/Investigation
  • Macula
  • Neovascularisation

Data availability statement

Data are available on reasonable request.

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 on reasonable request.

View Full Text

Footnotes

  • MR and EB are joint senior authors.

  • MR and EB contributed equally.

  • Contributors Study concept and design: FR, JO, MR and EB. Acquisition, analysis or interpretation of data: all authors. Drafting of the manuscript: FR, JO and EB. Critical revision of the manuscript for important intellectual content: all authors. Statistical analysis: JO and EB. Study supervision: EB and MR. Guarantor: EB

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • 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.