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

•For the first time, a hierarchically Coarse-to-fine diabetic retinopathy (DR) network (CF-DRNet) is proposed and this network can enables a hierarchically five-stage grading using convolutional neural networks.•The proposed CF-DRNet consists of the pre-trained Coarse Network and the pre-trained Fin...

Full description

Saved in:

Bibliographic Details
Published in:	Artificial intelligence in medicine Vol. 108; p. 101936
Main Authors:	Wu, Zhan, Shi, Gonglei, Chen, Yang, Shi, Fei, Chen, Xinjian, Coatrieux, Gouenou, Yang, Jian, Luo, Limin, Li, Shuo
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.08.2020 Elsevier
Subjects:	Bioengineering Coarse-to-fine classification Computer Science Convolutional neural networks Diabetic retinopathy grading Fundus images Human health and pathology Life Sciences Neural and Evolutionary Computing Sensory Organs Coarse-to-fine classification Diabetic retinopathy grading Convolutional neural networks Fundus images
ISSN:	0933-3657, 1873-2860, 1873-2860
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•For the first time, a hierarchically Coarse-to-fine diabetic retinopathy (DR) network (CF-DRNet) is proposed and this network can enables a hierarchically five-stage grading using convolutional neural networks.•The proposed CF-DRNet consists of the pre-trained Coarse Network and the pre-trained Fine Network. The Coarse Network performs two-class classification and the Fine Network further performs four- class classification DR severity grades.•The self-gated soft-attention mechanism modules are introduced in the pre-trained Coarse Network for two-class classification to effectively highlight the lesion features and suppress irrelevant information. 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.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0933-3657 1873-2860 1873-2860
DOI:	10.1016/j.artmed.2020.101936