Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study

Friso G. Heslinga*, Josien P. W. Pluim, A. J. H. M. Houben, Miranda T. Schram, Ronald M. A. Henry, Coen D. A. Stehouwer, Marleen J. van Greevenbroek, Tos T. J. M. Berendschot, Mitko Veta

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [+/- 0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [+/- 0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.

Original languageEnglish
Title of host publicationMedical Imaging 2020: Computer-Aided Diagnosis
PublisherSPIE-Society of Photo-Optical Instrumentation Engineers
Number of pages6
DOIs
Publication statusPublished - 2020
EventConference on Medical Imaging - Computer-Aided Diagnosis - Houston, United States
Duration: 16 Feb 202019 Feb 2020

Publication series

SeriesProceedings of SPIE - The International Society for Optical Engineering
Volume11314
ISSN0277-786X

Conference

ConferenceConference on Medical Imaging - Computer-Aided Diagnosis
Country/TerritoryUnited States
CityHouston
Period16/02/2019/02/20

Keywords

  • Deep Learning
  • Retinal Image Analysis
  • Type 2 Diabetes
  • Classification Uncertainty
  • The Maastricht Study
  • PREDICTION
  • MORTALITY

Fingerprint

Dive into the research topics of 'Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study'. Together they form a unique fingerprint.

Cite this