June 2020
Volume 61, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2020
Using Artificial Intelligence (AI) to Classify Retinal Developmental Disorders
Author Affiliations & Notes
  • Helen Kuht
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Shuihua Wang
    Department of Mathematics, University of Leicester, Leicester, United Kingdom
  • Garima Nishad
    International Institute of Information Technology, India
  • Sharon George
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
  • Gail Maconachie
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Viral Sheth
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Zhanhan Tu
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Michael Hisaund
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Rebecca McLean
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Seema Teli
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Frank Proudlock
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Girish Varma
    International Institute of Information Technology, India
  • Yu-Dong Zhang
    Department of Informatics, University of Leicester, Leicester, United Kingdom
  • Irene Gottlob
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Mervyn George Thomas
    Ulverscroft Eye Unit, University of Leicester, Leicester, United Kingdom
    Department of Ophthalmology, University Hospitals of Leicester, United Kingdom
  • Footnotes
    Commercial Relationships   Helen Kuht, None; Shuihua Wang, None; Garima Nishad, None; Sharon George, None; Gail Maconachie, None; Viral Sheth, None; Zhanhan Tu, None; Michael Hisaund, None; Rebecca McLean, None; Seema Teli, None; Frank Proudlock, None; Girish Varma, None; Yu-Dong Zhang, None; Irene Gottlob, None; Mervyn Thomas, None
  • Footnotes
    Support  Medical Research Council, National Institute of Health Research, Ulverscroft Foundation, Fight for Sight
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 4030. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Helen Kuht, Shuihua Wang, Garima Nishad, Sharon George, Gail Maconachie, Viral Sheth, Zhanhan Tu, Michael Hisaund, Rebecca McLean, Seema Teli, Frank Proudlock, Girish Varma, Yu-Dong Zhang, Irene Gottlob, Mervyn George Thomas; Using Artificial Intelligence (AI) to Classify Retinal Developmental Disorders. Invest. Ophthalmol. Vis. Sci. 2020;61(7):4030.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Artificial intelligence (AI) is particularly effective in image recognition as demonstrated in radiology, pathology and recently ophthalmology. Foveal hypoplasia (FH) is a group of disorders characterised by arrested retinal development and often associated with infantile nystagmus. Identifying the degree of arrested retinal development using optical coherence tomography (OCT) is paramount as this information provides both diagnostic and prognostic value. To date, there are no AI systems available for paediatric OCT or childhood nystagmus. We aimed to develop a quick, automated AI system to accurately differentiate normal foveal structure and grades of FH in paediatric retinal OCT images.

Methods : We used the Leicester paediatric OCT database to obtain normal and abnormal developmental scans. This included scans with varying degrees of arrested retinal development (Grades 1-4 FH and atypical FH). Representative high yield training datasets (3040 foveal B-scans) were extracted from >20,000 volumetric B-scans. The foveal B-scans were subsequently segmented and annotated. A series of convolutional neural networks (AI algorithms: Densenet201 and Resnet50) were used to train and validate the AI system to differentiate between normal, grade 1-4 FH and atypical FH.

Results : Following training of the AI system, we performed validation on different pathologies. We achieved a binary and 6-point classification, by replacing the 1000-neuron fully connected (FC) layer with a new 2-neuron FC. The AI system was able to successfully differentiate normal and abnormal scans with a 97.68% accuracy. Furthermore, the six point classification system (normal, grade 1-4 FH and atypical FH) achieved a 93.54% validation accuracy.

Conclusions : Our study has, for the first time, demonstrated a successful outcome for classification of retinal developmental disorders using AI. These results provide proof-of-concept for the use of AI in paediatric ophthalmology. The introduction of this system will help to eliminate inter-examiner variability with interpretation of scans and increase time efficiency on busy clinics. This work has provided a strong foundation for prospective testing using our AI algorithm, thus bringing us closer to implementation of a real-time intelligent diagnostic system for paediatric OCT.

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1: Overview of our AI algorithm

Figure 1: Overview of our AI algorithm

 

Figure 2: Validation accuracy per epoch over time with the 6-point classification

Figure 2: Validation accuracy per epoch over time with the 6-point classification

×
×

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.

×