Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks.

Journal: Nature communications
Published Date: Aug 10, 2021

Abstract

Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

Authors

  • Ling-Ping Cen
    Guangdong Provincial Key Laboratory of Medical Immunology and Molecular Diagnostics, School of Medical Technology, Guangdong Medical University, Zhanjiang, China. cenlp@hotmail.com.
  • Jie Ji
    Network and Information Center, Shantou University, Shantou, Guangdong, China.
  • Jian-Wei Lin
    Joint Shantou International Eye Center of Shantou University, the Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Si-Tong Ju
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Hong-Jie Lin
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Tai-Ping Li
    Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Yun Wang
    Department of Anesthesiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People's Republic of China.
  • Jian-Feng Yang
    Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Yu-Fen Liu
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Shaoying Tan
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Li Tan
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Dongjie Li
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Yifan Wang
    School of Bioscience and Bioengineering, South China University of Technology, Guangzhou, China.
  • Dezhi Zheng
  • Yongqun Xiong
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Hanfu Wu
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Jingjing Jiang
    Department of Endocrinology and Metabolism, Fudan Institute of Metabolic Diseases, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Zhenggen Wu
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Dingguo Huang
    Joint Shantou International Eye Center of Shantou University, the Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Tingkun Shi
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Binyao Chen
    Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, 515000, Guangdong, China.
  • Jianling Yang
    Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Shantou University Medical College, Shantou, 515000, Guangdong, China.
  • Xiaoling Zhang
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Li Luo
    Department of Intensive Care Unit, First Affiliated Hospital, Chongqing Medical University, Chongqing 400016, China.
  • Chukai Huang
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Guihua Zhang
    Joint Shantou International Eye Center of Shantou University, the Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Yuqiang Huang
    Joint Shantou International Eye Centre of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Tsz Kin Ng
    Joint Shantou International Eye Center of Shantou University, the Chinese University of Hong Kong, Shantou, Guangdong, China.
  • Haoyu Chen
    Joint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, China.
  • Weiqi Chen
    School of Computer Science, University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK.
  • Chi Pui Pang
    Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong, Hong Kong.
  • Mingzhi Zhang
    Joint Shantou International Eye Center, Shantou University & the Chinese University of Hong Kong, Shantou, China. Electronic address: zmz@jsiec.org.

Keywords

External Resources

Popular Topics
Recent Journals