Abstract
Diabetic Retinopathy (DR) causes a significant health threat to the patient’s vision with diabetic disease, which may result in blindness in severe situations. Various automatic DR diagnosis models have been proposed along with the development of deep learning, while there always relies on a large scale annotated data to train the network. However, annotating medical fundus images is cost-expensive and requires well-trained professional doctors to identity the DR grades. To overcome this drawback, this paper focuses on utilizing the easily-obtained unlabeled data with the help of limited annotated data to identify DR grades accurately. Hence we proposes a semi-supervised retinal image classification method by a Hybrid Graph Convolutional Network (HGCN). This HGCN network designs a modularity-based graph learning module and integrates Convolutional Neural Network (CNN) features into the graph representation by graph convolutional network. The synthesized hybrid features are optimized by a semi-supervised classification task which is assisted by a similarity-based pseudo label estimator. Through the proposed HGCN method, the retinal image classification model can be trained efficiently by partially labeled samples and the complicated annotating work is not required for the most retinal images. The experimental results on MESSIDOR dataset demonstrate the favorable performance of HGCN on semi-supervised retinal image classification, and the fully labeled data training also achieves an obvious superiority to the state-of-the-art supervised learning methods.
Highlights
Diabetic Retinopathy (DR) can give rise to evitable blindness for diabetic patients in the whole world
RELATED WORK We review the related researches of retinal image classification which are partitioned by three aspects, including retina image classification, unsupervised medical image classification, and a brief introduction of graph convolutional network
Through this hybrid graph convolutional network, the structural influence inside retinal image samples is learned by the modularity-based graph learning and Graph Convolutional Network (GCN) process, and more discriminative information in unlabeled data is exploited by the clustering-based pseudo label producer to support ‘pseudo-supervised’ learning with labeled retinal images
Summary
Diabetic Retinopathy (DR) can give rise to evitable blindness for diabetic patients in the whole world. The diabetes has attacked around 210 million humans [29], and at least 10% of them have deteriorated into DR [25], [35]. The number of diabetic patients will be increased to 360 million by 2030 [36], that indicates DR will become a severe health issue in the decade. The associate editor coordinating the review of this manuscript and approving it for publication was Kang Li. The histopathological retinal delicate damage could cause the visual loss or permanent blindness when it is untreated in early stage, which makes most adults in developed areas exposed in the threaten of blindness. An efficient evaluating protocol of distinguishing retinopathy level in visual impairment is a significant requirement to avoid the permanent retinal deterioration
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
