Article Text

Download PDFPDF
Discriminating glaucomatous and compressive optic neuropathy on spectral-domain optical coherence tomography with deep learning classifier
  1. Jinho Lee1,2,
  2. Jin-Soo Kim3,
  3. Haeng Jin Lee1,4,
  4. Seong-Joon Kim1,4,
  5. Young Kook Kim1,2,
  6. Ki Ho Park1,2,
  7. Jin Wook Jeoung1,2
  1. 1 Department of Ophthalmology, Seoul National University College of Medicine, Seoul, Republic of Korea
  2. 2 Division of Glaucoma, Department of Ophthalmology, Seoul National University Hospital, Seoul, Republic of Korea
  3. 3 Department of Ophthalmology, Hallym University Chuncheon Sacred Heart Hospital, Chuncheon, Republic of Korea
  4. 4 Division of Neuro-Ophthalmology, Department of Ophthalmology, Seoul National University Hospital, Seoul, Republic of Korea
  1. Correspondence to Professor Jin Wook Jeoung, Department of Ophthalmology, Seoul National University Hospital, Seoul 03080, Republic of Korea; neuroprotect{at}


Background/aims To assess the performance of a deep learning classifier for differentiation of glaucomatous optic neuropathy (GON) from compressive optic neuropathy (CON) based on ganglion cell–inner plexiform layer (GCIPL) and retinal nerve fibre layer (RNFL) spectral-domain optical coherence tomography (SD-OCT).

Methods Eighty SD-OCT image sets from 80 eyes of 80 patients with GON along with 81 SD-OCT image sets from 54 eyes of 54 patients with CON were compiled for the study. The bottleneck features extracted from the GCIPL thickness map, GCIPL deviation map, RNFL thickness map and RNFL deviation map were used as predictors for the deep learning classifier. The area under the receiver operating characteristic curve (AUC) was calculated to validate the diagnostic performance. The AUC with the deep learning classifier was compared with those for conventional diagnostic parameters including temporal raphe sign, SD-OCT thickness profile and standard automated perimetry.

Results The deep learning system achieved an AUC of 0.990 (95% CI 0.982 to 0.999) with a sensitivity of 97.9% and a specificity of 92.6% in a fivefold cross-validation testing, which was significantly larger than the AUCs with the other parameters: 0.804 (95% CI 0.737 to 0.872) with temporal raphe sign, 0.815 (95% CI 0.734 to 0.896) with superonasal GCIPL and 0.776 (95% CI 0.691 to 0.860) with superior GCIPL thicknesses (all p<0.001).

Conclusion The deep learning classifier can outperform the conventional diagnostic parameters for discrimination of GON and CON on SD-OCT.

  • glaucoma
  • optic nerve

Statistics from

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.


  • Contributors Design and conduct of the study: JL, JWJ. Collection of data: H-JL, S-JK, YKK, KHP, JWJ. Analysis and interpretation of data: JL, J-SK, H-JL, S-JK. Writing the article: JL, JWJ. Critical revision of the article: JL, J-SK, H-JL, S-JK, YKK, KHP. All authors agreed to final approval of the work and account for its integrity.

  • 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.

  • Patient consent for publication Not required.

  • Ethics approval This study was approved by the Institutional Review Board of Seoul National University Hospital.

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

  • Data availability statement De-identified patient data can be shared on reasonable request.

Linked Articles

  • At a glance
    Keith Barton James Chodosh Jost B Jonas