Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Prediction of axial length from macular optical coherence tomography using deep learning model
Author Affiliations & Notes
  • Richul Oh
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Myeongkyun Kang
    Robotics and Mechatronics Engineering, Daegu-Gyeongbuk Institute of Science & Technology, Daegu, Daegu, Korea (the Republic of)
  • Eun Kyoung Lee
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Kunho Bae
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Un Chul Park
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Kyu Hyung Park
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Chang Ki Yoon
    Ophthalmology, Seoul National University Hospital, Jongno-gu, Seoul, Korea (the Republic of)
  • Footnotes
    Commercial Relationships   Richul Oh None; Myeongkyun Kang None; Eun Kyoung Lee None; Kunho Bae None; Un Chul Park None; Kyu Hyung Park None; Chang Ki Yoon None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2340. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Richul Oh, Myeongkyun Kang, Eun Kyoung Lee, Kunho Bae, Un Chul Park, Kyu Hyung Park, Chang Ki Yoon; Prediction of axial length from macular optical coherence tomography using deep learning model. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2340.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning model for predicting axial lengths (AL) of eyes using optical coherence tomography (OCT) images.

Methods : We retrospectively included patients with axial length (AL) measurements and OCT images taken within 3 months. We utilized a five-fold cross-validation with the ResNet 152 architecture, incorporating horizontal OCT images, vertical OCT images, and dual-input images. The mean absolute error (MAE), R-squared (R2), and the percentages of eyes within error ranges of ±1.0, ±2.0, and ±3.0 mm were calculated.

Results : A total of 9,064 eyes of 5,349 patients (total image number of 18,128) were included in the analysis. The average AL of the eyes was 24.35 ± 2.03 (range: 20.53 – 37.07). Using horizontal OCT images, deep learning models predicted AL with MAE of and R2 of 0.704 and 0.784, respectively. Using vertical OCT images, deep learning models predicted AL with MAE of and R2 of 0.698 and 0.785, respectively. Using both horizontal and vertical OCT images, dual-input models predicted AL with MAE of R2 of 0.662 and 0.809, respectively. The dual-input models showed 89.33 %, 98.49 %, and 99.56 % accuracy in error margins of ±1.0, ±2.0, and ±3.0 mm.

Conclusions : A deep learning-based model accurately predicts AL from OCT images. The dual-input model showed the best performance, demonstrating the potential of macular OCT images in AL prediction.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Figure 2. Heatmap analysis of gradient-weighted regression activation mapping (Grad-RAM) for myopic eyes with axial length greater than 26.5 mm. (A–I) Nine optical coherence tomography (OCT) images were randomly selected among eye with good prediction outcome (absolute prediction error less than 0.5 mm). For each image, the left one is a horizontal section OCT image and the right one is a vertical section OCT image.

Figure 2. Heatmap analysis of gradient-weighted regression activation mapping (Grad-RAM) for myopic eyes with axial length greater than 26.5 mm. (A–I) Nine optical coherence tomography (OCT) images were randomly selected among eye with good prediction outcome (absolute prediction error less than 0.5 mm). For each image, the left one is a horizontal section OCT image and the right one is a vertical section OCT image.

×
×

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.

×