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

Published on Jul 24, 2020in Artificial Intelligence in Medicine5.326
· DOI :10.1016/J.ARTMED.2020.101936
Gouenou Coatrieux28
Estimated H-index: 28
(École nationale supérieure des télécommunications de Bretagne),
Jian Yang142
Estimated H-index: 142
(BIT: Beijing Institute of Technology)
+ 6 AuthorsShuo Li41
Estimated H-index: 41
(UWO: University of Western Ontario)
Abstract 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.
📖 Papers frequently viewed together
2019ICIP: International Conference on Image Processing
7 Authors (Ziyuan Zhao, ..., Xin Xu)
#1Nadeem SalamatH-Index: 6
#2Malik Muhammad Saad Missen (The Islamia University of Bahawalpur Pakistan)H-Index: 9
Last. Aqsa Rashid (National University of Science and Technology)H-Index: 5
view all 3 authors...
Abstract The diabetic retinopathy is the main reason of vision loss in people. Medical experts recognize some clinical, geometrical and haemodynamic features of diabetic retinopathy. These features include the blood vessel area, exudates, microaneurysm, hemorrhages and neovascularization, etc. In Computer Aided Diagnosis (CAD) systems, these features are detected in fundus images using computer vision techniques. In this paper, we review the methods of low, middle and high level vision for autom...
#1Zifeng Wu (University of Adelaide)H-Index: 16
#2Chunhua Shen (University of Adelaide)H-Index: 94
Last. Anton van den Hengel (University of Adelaide)H-Index: 66
view all 3 authors...
Abstract The community has been going deeper and deeper in designing one cutting edge network after another, yet some works are there suggesting that we may have gone too far in this dimension. Some researchers unravelled a residual network into an exponentially wider one, and assorted the success of residual networks to fusing a large amount of relatively shallow models. Since some of their early claims are still not settled, we in this paper dig more on this topic, i.e., the unravelled view of...
#1Gen-Min Lin (NDHU: National Dong Hwa University)H-Index: 18
#2Mei-Juan Chen (NDHU: National Dong Hwa University)H-Index: 20
Last. Carol Y. Cheung (CUHK: The Chinese University of Hong Kong)H-Index: 68
view all 11 authors...
Entropy images, representing the complexity of original fundus photographs, may strengthen the contrast between diabetic retinopathy (DR) lesions and unaffected areas. The aim of this study is to compare the detection performance for severe DR between original fundus photographs and entropy images by deep learning. A sample of 21,123 interpretable fundus photographs obtained from a publicly available data set was expanded to 33,000 images by rotating and flipping. All photographs were transforme...
#1Prasanna Porwal (Shri Guru Gobind Singhji Institute of Engineering and Technology)H-Index: 6
#2Samiksha Pachade (Shri Guru Gobind Singhji Institute of Engineering and Technology)H-Index: 5
Last. Fabrice Meriaudeau (University of Burgundy)H-Index: 34
view all 7 authors...
Diabetic Retinopathy is the most prevalent cause of avoidable vision impairment, mainly affecting the working-age population in the world. Recent research has given a better understanding of the requirement in clinical eye care practice to identify better and cheaper ways of identification, management, diagnosis and treatment of retinal disease. The importance of diabetic retinopathy screening programs and difficulty in achieving reliable early diagnosis of diabetic retinopathy at a reasonable c...
Jul 1, 2018 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
#1Kang Zhou (ShanghaiTech University)H-Index: 7
#2Zaiwang GuH-Index: 12
Last. Jiang LiuH-Index: 36
view all 7 authors...
Diabetic Retinopathy (DR) is a non-negligible eye disease among patients with Diabetes Mellitus, and automatic retinal image analysis algorithm for the DR screening is in high demand. Considering the resolution of retinal image is very high, where small pathological tissues can be detected only with large resolution image and large local receptive field are required to identify those late stage disease, but directly training a neural network with very deep architecture and high resolution image ...
#1Ozan OktayH-Index: 24
#2Jo SchlemperH-Index: 17
Last. Daniel RueckertH-Index: 116
view all 12 authors...
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input image while highlighting salient features useful for a specific task. This enables us to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs). AGs can be easily integrated into standard...
The high-pace rise in advanced computing and imaging systems has given rise to a new research dimension called computer-aided diagnosis (CAD) system for various biomedical purposes. CAD-based diabetic retinopathy (DR) can be of paramount significance to enable early disease detection and diagnosis decision. Considering the robustness of deep neural networks (DNNs) to solve highly intricate classification problems, in this paper, AlexNet DNN, which functions on the basis of convolutional neural n...
#1Xuanhan Wang (University of Electronic Science and Technology of China)H-Index: 5
#2Lianli Gao (University of Electronic Science and Technology of China)H-Index: 30
Last. Heng Tao Shen (UQ: University of Queensland)H-Index: 72
view all 4 authors...
Human activity recognition in videos with convolutional neural network (CNN) features has received increasing attention in multimedia understanding. Taking videos as a sequence of frames, a new record was recently set on several benchmark datasets by feeding frame-level CNN sequence features to long short-term memory (LSTM) model for video activity recognition. This recurrent model-based visual recognition pipeline is a natural choice for perceptual problems with time-varying visual input or seq...
#1Justin Salamon (NYU: New York University)H-Index: 30
#2Juan Pablo Bello (NYU: New York University)H-Index: 42
The ability of deep convolutional neural networks (CNNs) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family of high-capacity models. This study has two primary contributions: first, we propose a deep CNN architecture for environmental sound classification. Second, we propose the use of audio data augmentation for overcoming the problem of data sc...
#1Varun Gulshan (Google)H-Index: 8
#2Lily Peng (Google)H-Index: 32
Last. Dale R. Webster (Google)H-Index: 24
view all 15 authors...
Importance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. Design and Sett...
Cited By10
Diabetic retinopathy (DR) is one of the major blindness-causing diseases current-ly known. Automatic grading of DR using deep learning methods not only speeds up the diagnosis of the disease but also reduces the rate of misdiagnosis. However, problems such as insufficient samples and imbalanced class distribu-tion in DR datasets have constrained the improvement of grading performance. In this paper, we introduce the idea of multi-stage transfer into the grading task of DR. The new transfer learn...
#1Tahira Nazir (University of Engineering and Technology)H-Index: 4
#2Marriam Nawaz (University of Engineering and Technology)H-Index: 3
Last. Amir Hussain (Edinburgh Napier University)H-Index: 61
view all 10 authors...
Diabetic retinopathy (DR) is an eye disease that alters the blood vessels of a person suffering from diabetes. Diabetic macular edema (DME) occurs when DR affects the macula, which causes fluid accumulation in the macula. Efficient screening systems require experts to manually analyze images to recognize diseases. However, due to the challenging nature of the screening method and lack of trained human resources, devising effective screening-oriented treatment is an expensive task. Automated syst...
#2B. KarthikeyanH-Index: 9
view all 4 authors...
#1N. Deepa (Saveetha University)H-Index: 5
#2T. Devi (Saveetha University)H-Index: 7
Hypertensive retinopathy (HR)is one of the severe damages caused in retinal vascular due to the hectic and abnormal upset in a human life. These damages are taken in a clinical sample by monitoring the presence and importance of all parameters that shows the increasing rate. Retina as main features for finding the variation which takes a longer duration to fix the diseases and impact in arteriolar construction and optic disk edema. In this work, a enhanced transfer learning-convolutional neural ...
#1Víctor Vives-Boix (University of Alicante)H-Index: 2
#2Daniel Ruiz-Fernandez (University of Alicante)H-Index: 8
Abstract Background and objectives: Diabetic retinopathy is a type of diabetes that causes vascular changes that can lead to blindness. The ravages of this disease cannot be reversed, so early detection is essential. This work presents an automated method for early detection of this disease using fundus colored images. Methods: A bio-inspired approach is proposed on synaptic metaplasticity in convolutional neural networks. This biological phenomenon is known to directly interfere in both learnin...
#1Jinho ParkH-Index: 5
#2Heegwang KimH-Index: 3
Last. Joonki PaikH-Index: 32
view all 3 authors...
#1Fahd S. AlharithiH-Index: 1
#2Ahmed H. AlmulihiH-Index: 1
Last. Nizar BouguilaH-Index: 49
view all 5 authors...
In this paper, we propose a novel hybrid discriminative learning approach based on shifted-scaled Dirichlet mixture model (SSDMM) and Support Vector Machines (SVMs) to address some challenging problems of medical data categorization and recognition. The main goal is to capture accurately the intrinsic nature of biomedical images by considering the desirable properties of both generative and discriminative models. To achieve this objective, we propose to derive new data-based SVM kernels generate...
#1Mili Rosline Mathews (Thangal Kunju Musaliar College of Engineering, Kollam)H-Index: 1
#2S. M. Anzar (Thangal Kunju Musaliar College of Engineering, Kollam)H-Index: 6
#1Phat K. HuynhH-Index: 1
#2Arveity R. Setty (Sanford Health)H-Index: 1
Last. Trung Q. LeH-Index: 9
view all 4 authors...
Abstract Disease pathogenesis, a type of domain knowledge about biological mechanisms leading to diseases, has not been adequately encoded in machine-learning-based medical diagnostic models because of the inter-patient variabilities and complex dependencies of the underlying pathogenetic mechanisms. We propose 1) a novel pathogenesis probabilistic graphical model (PPGM) to quantify the dynamics underpinning patient-specific data and pathogenetic domain knowledge, 2) a Bayesian-based inference p...
One of the commonly found medical conditions in people with type 1 or 2 diabetes is Diabetic Retinopathy (DR). It is mostly asymptomatic in its early stages and can lead to both central and side vision loss if left untreated. The five stages of this disease include normal (no DR), mild stage non-proliferative DR, moderate stage non-proliferative DR, severe stage non-proliferative DR, and proliferative DR. This condition is generally diagnosed by a highly trained ophthalmologist by examining the ...
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.