Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network

Zhan Wu (1) , Gonglei Shi (2) , Yang Chen (1, 2, 3) , Fei Shi (4) , Xinjian Chen (4) , Gouenou Coatrieux (5) , Jian Yang (6) , Limin M. Luo (1, 2, 3) , Shuo Li (7)

1 SEU - Nanjing Southeast University
2 LIST - Laboratory of Image Science and Technology [Nanjing]
3 CRIBS - Centre de Recherche en Information Biomédicale sino-français
4 Soochow University
5 Optimisation Continue des Actions Thérapeutiques par l'Intégration d'Informations Multimodales
6 BIT - Beijing Institute of Technology
7 UWO - University of Western Ontario

Diabetic retinopathy (DR) is the most common eye complication of diabetes and one of the leading causes of blindness and vision impairment. Automated and accurate DR grading is of great significance for the timely and effective treatment of fundus diseases. Current clinical methods remain subject to potential time-consumption and high-risk. In this paper, a hierarchically Coarse-to-fine network (CF-DRNet) is proposed as an automatic clinical tool to classify five stages of DR severity grades using convolutional neural networks (CNNs). The CF-DRNet conforms to the hierarchical characteristic of DR grading and effectively improves the classification performance of five-class DR grading, which consists of the following: (1) The Coarse Network performs two-class classification including No DR and DR, where the attention gate module highlights the salient lesion features and suppresses irrelevant background information. (2) The Fine Network is proposed to classify four stages of DR severity grades of the grade DR from the Coarse Network including mild, moderate, severe non-proliferative DR (NPDR) and proliferative DR (PDR). Experimental results show that proposed CF-DRNet outperforms some state-of-art methods in the publicly available IDRiD and Kaggle fundus image datasets. These results indicate our method enables an efficient and reliable DR grading diagnosis in clinic.

Mots clés: Coarse-to-fine classification; Convolutional neural networks; Diabetic retinopathy grading; Fundus images

Domaines: Organes des sens; Ingénierie biomédicale; Réseau de neurones [cs.NE]

Zhan Wu, Gonglei Shi, Yang Chen, Fei Shi, Xinjian Chen, et al.. Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network. Artificial Intelligence in Medicine, 2020, 108, pp.101936. ⟨10.1016/j.artmed.2020.101936⟩. ⟨hal-02960951⟩