Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review

Transl Vis Sci Technol. 2020 Feb 18;9(2):11. doi: 10.1167/tvst.9.2.11.

Abstract

Artificial intelligence (AI)-based automated classification and segmentation of optical coherence tomography (OCT) features have become increasingly popular. However, its 3-dimensional volumetric nature has made developing an algorithm that generalizes across all patient populations and OCT devices challenging. Several recent studies have reported high diagnostic performances of AI models; however, significant methodological challenges still exist in applying these models in real-world clinical practice. Lack of large-image datasets from multiple OCT devices, nonstandardized imaging or post-processing protocols between devices, limited graphics processing unit capabilities for exploiting 3-dimensional features, and inconsistency in the reporting metrics are major hurdles in enabling AI for OCT analyses. We discuss these issues and present possible solutions.

Keywords: artificial intelligence; deep learning; optical coherence tomography.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't
  • Review

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Deep Learning*
  • Humans
  • Retinal Diseases* / diagnostic imaging
  • Tomography, Optical Coherence*