June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Convolutional neural network performances in detecting keratoconus using color and grayscale corneal curvature maps in different architectures
Author Affiliations & Notes
  • Lucas Orlandi Oliveira
    Institute of Physics of São Carlos, University of São Paulo, São Carlos, São Paulo, Brazil
  • Felipe Marques de Carvalho Taguchi
    Ophthalmology and Visual Sciences, Universidade Federal de Sao Paulo Escola Paulista de Medicina, Sao Paulo, SP, Brazil
  • Renato Feijó Evangelista
    Institute of Physics of São Carlos, University of São Paulo, São Carlos, São Paulo, Brazil
  • Edson Shizuo Mori
    Ophthalmology and Visual Sciences, Universidade Federal de Sao Paulo Escola Paulista de Medicina, Sao Paulo, SP, Brazil
  • Jarbas Caiado de Castro Neto
    Institute of Physics of São Carlos, University of São Paulo, São Carlos, São Paulo, Brazil
  • Wallace Chamon
    Ophthalmology and Visual Sciences, Universidade Federal de Sao Paulo Escola Paulista de Medicina, Sao Paulo, SP, Brazil
  • Footnotes
    Commercial Relationships   Lucas Oliveira None; Felipe Taguchi Johnson&Johnson, Code C (Consultant/Contractor), JTAG, Code I (Personal Financial Interest); Renato Evangelista None; Edson Mori None; Jarbas de Castro Neto JTAG, Code O (Owner); Wallace Chamon Johnson&Johnson, Code C (Consultant/Contractor), JTAG, Code I (Personal Financial Interest)
  • Footnotes
    Support   CAPES/PROEX 88887.631069/2021-00, CAPES/PROEX 88887.603275/2021-00, São Paulo Research Foundation (FAPESP) Grant #2021/01136-0, PIPE/FAPESP 2019/15216-5
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 5144. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Lucas Orlandi Oliveira, Felipe Marques de Carvalho Taguchi, Renato Feijó Evangelista, Edson Shizuo Mori, Jarbas Caiado de Castro Neto, Wallace Chamon; Convolutional neural network performances in detecting keratoconus using color and grayscale corneal curvature maps in different architectures. Invest. Ophthalmol. Vis. Sci. 2023;64(8):5144.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To create and test convolutional neural networks for the diagnosis of keratoconus and evaluate the importance of color information on their performances.

Methods : A total of 36,008 unique Scheimpflug corneal exams were used to evaluate different architectures of convolutional neural networks built from scratch in Python using Tensorflow. After defining the best network architecture, two networks were trained to analyze the axial map of the anterior corneal surface in both, colored and grayscale maps. The Topographic Keratoconus Classification index (TKC) provided by Pentacam was used as a label and the KC2-labeled maps were defined as keratoconus. Each model was trained using 3,000 images of normal and 3,000 keratoconic eyes, and then validated and tested on 1,000 images of each label.

Results : The evaluated network architectures varied in image size (32x32, 64x64, and 128x128 pixels), number of neurons per layer (width), number of layers (depth), and batch sizes (1, 8, 16, and 32 images) (figure 1). After multiple iterations, the optimal network was defined with images of 64x64 pixels in three convolutional layers, consisting of 128, 256, and 512 neurons, respectively. The first two layers were followed by a pooling layer, and the network structure was completed with five fully connected layers containing 1024, 512, 256, 128, and 64 neurons, respectively. The model trained with color images exhibited a sensitivity of 99.6% and specificity of 99.4%, with an Area Under the Curve (AUC) of 0.999890. The grayscale model showed sensitivity of 99.5%, specificity of 99.5%, and AUC = 0.999778 (figure 1). While there was no statistically significant difference in performance between the color and grayscale models, the feature maps indicate that they have distinct patterns of neural activation (figure 2).

Conclusions : The optimal architecture for the neural network was determined. The results support the hypothesis that it is possible to distinguish between normal and keratoconus-affected eyes using the axial map of the anterior corneal surface. The use of color did not impact significantly the network's performance, suggesting that this feature is not relevant to neuron activation.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Comparison of sensitivity, specificity and AUC between different training parameters.

Comparison of sensitivity, specificity and AUC between different training parameters.

 

Resulting feature maps for (a) color-maps model; and (b) grayscale-maps model.

Resulting feature maps for (a) color-maps model; and (b) grayscale-maps model.

×
×

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.

×