Equitable Deep Learning for Diabetic Retinopathy Detection Using Multidimensional Retinal Imaging With Fair Adaptive Scaling.

Journal: Translational vision science & technology
Published Date:

Abstract

PURPOSE: To investigate the fairness of existing deep models for diabetic retinopathy (DR) detection and introduce an equitable model to reduce group performance disparities.

Authors

  • Min Shi
    School of Education, Fuzhou University of International Studies and Trade, 350000, China.
  • Muhammad Muneeb Afzal
    Tandon School of Engineering, New York University, New York, NY, USA.
  • Hao Huang
    School of Information Science and Engineering, Xinjiang University, Shangli Road, Urumqi 830046, China.
  • Congcong Wen
    Laboratory Animal Centre, Wenzhou Medical University, Wenzhou 325027, China.
  • Yan Luo
    School of Public Health and Management, Research Center for Medicine and Social Development, Innovation Center for Social risk Governance in Health, Chongqing Medical University, Chongqing 400016, China.
  • Muhammad Osama Khan
    Tandon School of Engineering, New York University, New York, NY, USA.
  • Yu Tian
    Key Laboratory of Development and Maternal and Child Diseases of Sichuan Province, Department of Pediatrics, Sichuan University, Chengdu, China.
  • Leo Kim
    Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA.
  • Yi Fang
    Department of Neurosurgery, The Fuzhou General Hospital, Fuzhou, China.
  • Mengyu Wang
    Schepens Eye Research Institute, Harvard Medical School, Boston, Massachusetts.