Xiao Zhang1,2, Fan Li3, Donghong Li4, Qijie Wei4, Xiaoxu Han1,2, Bilei Zhang1,2, Huan Chen1,2, Yongpeng Zhang5, Bin Mo5, Bojie Hu6, Dayong Ding4, Xirong Li3, Weihong Yu7,8, Youxin Chen9,10. 1. Department of Ophthalmology, Union Medical College Hospital, Chinese Academy of Medical Sciences, PekingBeijing, China. 2. Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China. 3. Key Lab of Data Engineering and Knowledge Engineering, Renmin University of China, Beijing, China. 4. Vistel AI Lab, Visionary Intelligence Ltd, Beijing, China. 5. Ophthalmology and Visual Science Key Lab, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, BeijingBeijing, China. 6. Department of Retina, Tianjin Medical University Eye Hospital, Tianjin, China. 7. Department of Ophthalmology, Union Medical College Hospital, Chinese Academy of Medical Sciences, PekingBeijing, China. yuweihong.pumch@vip.126.com. 8. Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China. yuweihong.pumch@vip.126.com. 9. Department of Ophthalmology, Union Medical College Hospital, Chinese Academy of Medical Sciences, PekingBeijing, China. chenyouxinpumch@163.com. 10. Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China. chenyouxinpumch@163.com.
Abstract
PURPOSE: The purpose of this study is to develop and validate the intelligent diagnosis of severe DR with lesion recognition based on color fundus photography. METHODS: The Kaggle public dataset for DR grading is used in the project, including 53,576 fundus photos in the test set, 28,101 in the training set, and 7,025 in the validation set. We randomly select 4,192 images for lesion annotation. Inception V3 structure is adopted as the classification algorithm. Both 299 × 299 pixel images and 896 × 896 pixel images are used as the input size. ROC curve, AUC, sensitivity, specificity, and their harmonic mean are used to evaluate the performance of the models. RESULTS: The harmonic mean and AUC of the model of 896 × 896 input are higher than those of the 299 × 299 input model. The sensitivity, specificity, harmonic mean, and AUC of the method with 896 × 896 resolution images as input for severe DR are 0.925, 0.907, 0.916, and 0.968, respectively. The prediction error mainly occurs in moderate NPDR, and cases with more hard exudates and cotton wool spots are easily predicted as severe cases. Cases with preretinal hemorrhage and vitreous hemorrhage are easily identified as severe cases, and IRMA is the most difficult lesion to recognize. CONCLUSIONS: We have studied the intelligent diagnosis of severe DR based on color fundus photography. This artificial intelligence-based technology offers a possibility to increase the accessibility and efficiency of severe DR screening.
PURPOSE: The purpose of this study is to develop and validate the intelligent diagnosis of severe DR with lesion recognition based on color fundus photography. METHODS: The Kaggle public dataset for DR grading is used in the project, including 53,576 fundus photos in the test set, 28,101 in the training set, and 7,025 in the validation set. We randomly select 4,192 images for lesion annotation. Inception V3 structure is adopted as the classification algorithm. Both 299 × 299 pixel images and 896 × 896 pixel images are used as the input size. ROC curve, AUC, sensitivity, specificity, and their harmonic mean are used to evaluate the performance of the models. RESULTS: The harmonic mean and AUC of the model of 896 × 896 input are higher than those of the 299 × 299 input model. The sensitivity, specificity, harmonic mean, and AUC of the method with 896 × 896 resolution images as input for severe DR are 0.925, 0.907, 0.916, and 0.968, respectively. The prediction error mainly occurs in moderate NPDR, and cases with more hard exudates and cotton wool spots are easily predicted as severe cases. Cases with preretinal hemorrhage and vitreous hemorrhage are easily identified as severe cases, and IRMA is the most difficult lesion to recognize. CONCLUSIONS: We have studied the intelligent diagnosis of severe DR based on color fundus photography. This artificial intelligence-based technology offers a possibility to increase the accessibility and efficiency of severe DR screening.