Article Text

Download PDFPDF
AI-based clinical assessment of optic nerve head robustness superseding biomechanical testing
  1. Fabian A Braeu1,2,3,
  2. Thanadet Chuangsuwanich1,3,
  3. Tin A Tun4,5,
  4. Shamira Perera4,5,
  5. Rahat Husain4,5,
  6. Alexandre H Thiery6,
  7. Tin Aung1,4,5,7,
  8. George Barbastathis2,8,
  9. Michaël J A Girard3,7,9
  1. 1 Yong Loo Lin School of Medicine, National University of Singapore, Singapore
  2. 2 Singapore-MIT Alliance for Research and Technology, Singapore
  3. 3 Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore
  4. 4 Singapore Eye Research Institute, Singapore
  5. 5 Singapore National Eye Centre, Singapore
  6. 6 Statistics and Applied Probability, National University of Singapore, Singapore
  7. 7 Duke-NUS Graduate Medical School, Singapore
  8. 8 Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
  9. 9 Institute for Molecular and Clinical Ophthalmology, Basel, Switzerland
  1. Correspondence to Dr Michaël J A Girard, Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore, Singapore; mgirard{at}ophthalmic.engineering

Abstract

Background/aims To use artificial intelligence (AI) to: (1) exploit biomechanical knowledge of the optic nerve head (ONH) from a relatively large population; (2) assess ONH robustness (ie, sensitivity of the ONH to changes in intraocular pressure (IOP)) from a single optical coherence tomography (OCT) volume scan of the ONH without the need for biomechanical testing and (3) identify what critical three-dimensional (3D) structural features dictate ONH robustness.

Methods 316 subjects had their ONHs imaged with OCT before and after acute IOP elevation through ophthalmo-dynamometry. IOP-induced lamina cribrosa (LC) deformations were then mapped in 3D and used to classify ONHs. Those with an average effective LC strain superior to 4% were considered fragile, while those with a strain inferior to 4% robust. Learning from these data, we compared three AI algorithms to predict ONH robustness strictly from a baseline (undeformed) OCT volume: (1) a random forest classifier; (2) an autoencoder and (3) a dynamic graph convolutional neural network (DGCNN). The latter algorithm also allowed us to identify what critical 3D structural features make a given ONH robust.

Results All three methods were able to predict ONH robustness from a single OCT volume scan alone and without the need to perform biomechanical testing. The DGCNN (area under the curve (AUC): 0.76±0.08) outperformed the autoencoder (AUC: 0.72±0.09) and the random forest classifier (AUC: 0.69±0.05). Interestingly, to assess ONH robustness, the DGCNN mainly used information from the scleral canal and the LC insertion sites.

Conclusions We propose an AI-driven approach that can assess the robustness of a given ONH solely from a single OCT volume scan of the ONH, and without the need to perform biomechanical testing. Longitudinal studies should establish whether ONH robustness could help us identify fast visual field loss progressors.

Precis Using geometric deep learning, we can assess optic nerve head robustness (ie, sensitivity to a change in IOP) from a standard OCT scan that might help to identify fast visual field loss progressors.

  • glaucoma
  • optic nerve
  • imaging
  • intraocular pressure

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

  • Contributors Study conception and design: FAB, TC, TA, GB and MJAG; data collection: FAB, TAT, SP, RH and TA; analysis and interpretation of results: FAB, AHT and MJAG; draft manuscript preparation: FAB and MJAG; guarantor: MJAG. All authors reviewed the results and approved the final version of the manuscript.

  • Funding We acknowledge funding from (1) the donors of the National Glaucoma Research, a programme of the BrightFocus Foundation, for support of this research (G2021010S (MJAG)); (2) SingHealth Duke-NUS Academic Medicine Research Grant (SRDUKAMR21A6 (MJAG)); (3) the ‘Retinal Analytics through Machine learning aiding Physics (RAMP)’ project that is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its Intra-Create Thematic Grant ‘Intersection Of Engineering And Health’ - NRF2019-THE002-0006 awarded to the Singapore MIT Alliance for Research and Technology (SMART) Centre (MJAG/AT/GB); (4) the ‘Tackling & Reducing Glaucoma Blindness with Emerging Technologies (TARGET)’ project that is supported by the National Medical Research Council (NMRC), Singapore (MOH-OFLCG21jun-0003 (MJAG)).

  • Competing interests MJAG and AHT are the co-founders of the AI start-up company Abyss Processing.

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

Linked Articles

  • Highlights from this issue
    Frank Larkin