Comparative performance of deep learning architectures for diabetic peripheral neuropathy detection using corneal confocal microscopy: a retrospective single-centre study.

Journal: BMJ open
Published Date:

Abstract

OBJECTIVES: This study aims to develop a deep learning algorithm (DLA) using the InceptionV3 architecture for effective diabetic peripheral neuropathy (DPN) screening via corneal confocal microscopy (CCM) images.

Authors

  • Wenqu Chen
    Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China.
  • Yuyang Deng
    Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China.
  • Weihuang Xu
    Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China.
  • Jianzhang Hu
    Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China ophhjz@163.com.