Multi-task deep learning for predicting metabolic syndrome from retinal fundus images in a Japanese health checkup dataset.

Journal: PloS one
Published Date: Aug 21, 2025

Abstract

BACKGROUND: Retinal fundus images provide a noninvasive window into systemic health, offering opportunities for early detection of metabolic disorders such as metabolic syndrome (METS).

Authors

  • Tohru Itoh
    Advanced Photonics Technology Development Group, RIKEN Center for Advanced Photonics, Wako, Saitama, Japan.
  • Koichi Nishitsuka
    Advanced Photonics Technology Development Group, RIKEN Center for Advanced Photonics, Wako, Saitama, Japan.
  • Yasufumi Fukuma
    Advanced Photonics Technology Development Group, RIKEN Center for Advanced Photonics, Wako, Saitama, Japan.
  • Satoshi Wada
    Advanced Photonics Technology Development Group, RIKEN Center for Advanced Photonics, Wako, Saitama, Japan.

Keywords

External Resources

Popular Topics
Recent Journals