June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
A machine learning solution to predict foveal development and visual prognosis in retinal developmental disorders
Author Affiliations & Notes
  • Helen Jane Kuht
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Garima Nishad
    International Institute of Information Technology Hyderabad, Gachibowli, India
  • Sharon S-H Wang
    Department of Mathematics, University of Leicester, Leicester, Leicestershire, United Kingdom
    Department of Informatics, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Gail Maconachie
    Academic Unit of Ophthalmology and Orthoptics, The University of Sheffield, Sheffield, Sheffield, United Kingdom
  • Viral Sheth
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Zhanhan Tu
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Michael Hisaund
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Rebecca J McLean
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Ravi Purohit
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Seema Teli
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Frank A Proudlock
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Yu-Dong Zhang
    Department of Informatics, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Irene Gottlob
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Girish Varma
    International Institute of Information Technology Hyderabad, Gachibowli, India
  • Mervyn G Thomas
    Ulverscroft Eye Unit, Ophthalmology Department, University of Leicester, Leicester, Leicestershire, United Kingdom
  • Footnotes
    Commercial Relationships   Helen Kuht, None; Garima Nishad, None; Sharon Wang, None; Gail Maconachie, None; Viral Sheth, None; Zhanhan Tu, Leica Microsystems (C); Michael Hisaund, None; Rebecca McLean, None; Ravi Purohit, None; Seema Teli, None; Frank Proudlock, Leica Microsystems (C); Yu-Dong Zhang, None; Irene Gottlob, None; Girish Varma, None; Mervyn Thomas, Leica Microsystems (C)
  • Footnotes
    Support  MRC (MC_PC_17171), NIHR (CL-2017-11-003), Ulverscroft Foundation and Fight for Sight (5009/5010 and 24NN181)
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 2739. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Helen Jane Kuht, Garima Nishad, Sharon S-H Wang, Gail Maconachie, Viral Sheth, Zhanhan Tu, Michael Hisaund, Rebecca J McLean, Ravi Purohit, Seema Teli, Frank A Proudlock, Yu-Dong Zhang, Irene Gottlob, Girish Varma, Mervyn G Thomas; A machine learning solution to predict foveal development and visual prognosis in retinal developmental disorders. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2739.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Detecting and grading abnormal retinal development has important diagnostic and prognostic implications in children. The foveal hypoplasia (FH) grading system is based on the stage at which retinal development ceases, and can be described as grade 1 to 4 FH and atypical FH. Correctly identifying the degree of arrested retinal development requires an understanding of the retinal developmental sequence and thus can be challenging for the non-expert. We therefore proposed the development of the first artificial intelligence (AI) based system to accurately identify and grade FH using optical coherence tomography (OCT).

Methods : A representative sample (n=5078) of paediatric OCT scans demonstrating varying degrees of arrested retinal development (normal, grade 1-4 FH and atypical FH) were obtained from the Leicester paediatric OCT database. Foveal scans were acquired from table mounted OCT (n=3037) (Copernicus, Optopol Technology S.A., Poland) and handheld OCT (n=2041) (Envisu 2300; Leica Microsystems, Germany) devices to ensure a high-performing, device agnostic system. The foveal B-scans were extracted, annotated, and segmented. A high-yield training dataset (n=3555) was inputted through a customised convolutional neural network (CNN) (Resnet50) for the training stage. Following the training and fine-tuning of the customised Resnet50, a validation stage to test the accuracy of the model was implemented. The foveal scans in this stage were new and unseen scans to the CNN.

Results : Our binary classification (normal and abnormal foveal morphology) and six-point classification (normal, grade 1-4 FH and atypical FH) achieved 98.1% and 95.0% validation accuracy, respectively.

Conclusions : We have demonstrated, for the first time, the proof-of-concept for the use of a device agnostic, automated AI system in paediatric OCT interpretation. Our system can help to eliminate inter-examiner variability and augment the clinical pathway by increasing time efficiency during busy clinics. The introduction of OCT to routine clinical assessment is imminent. Therefore, our AI system provides a strong foundation for the development of a real-time, frontline diagnostic tool for retinal developmental disorders.

This is a 2021 ARVO Annual Meeting abstract.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×