Abstract
Diabetic Macular Edema (DME) is an advanced stage of Diabetic Retinopathy (DR) and can lead to permanent vision loss. Currently, it affects 26.7 million people globally and on account of such a huge number of DME cases and the limited number of ophthalmologists, it is desirable to automate the diagnosis process. Computer-assisted, deep learning based diagnosis could help in early detection, following which precision medication can help to mitigate the vision loss. Method: In order to automate the screening of DME, we propose a novel DMENet Algorithm which is built on the pillars of Convolutional Neural Networks (CNNs). DMENet analyses the preprocessed color fundus images and passes it through a two-stage pipeline. The first stage detects the presence or absence of DME whereas the second stage takes only the positive cases and grades the images based on severity. In both the stages, we use a novel Hierarchical Ensemble of CNNs (HE-CNN). This paper uses two of the popular publicly available datasets IDRiD and MESSIDOR for classification. Preprocessing on the images is performed using morphological opening and gaussian kernel. The dataset is augmented to solve the class imbalance problem for better performance of the proposed model. Results: The proposed methodology achieved an average Accuracy of 96.12%, Sensitivity of 96.32%, Specificity of 95.84%, and F−1 score of 0.9609 on MESSIDOR and IDRiD datasets. Conclusion: These excellent results establish the validity of the proposed methodology for use in DME screening and solidifies the applicability of the HE-CNN classification technique in the domain of biomedical imaging.
Highlights
Diabetic Macular Edema (DME) is a complication of Diabetic Retinopathy (DR), and it usually occurs when vessels in the central part of the macula are affected by the fluid accretion [1]
We performed an array of analysis ranging from evaluating the proposed HE-Convolutional Neural Networks (CNNs) ensemble technique in each stage of DMENet pipeline, comparative evaluation of the DMENet methodology with existing computer-aided solutions, analyzing performance of CNNs vs. proposed Hierarchical Ensemble of CNNs (HE-CNN) technique, comparative study of HE-CNN with other existing ensemble techniques and analyzing the performance of DMENet vs. tri-class classification (Grade 0, Grade 1 and Grade 2) solutions
Soft-Ensemble employs several parallel CNN branches, where feature maps are concatenated at the end of each convolutional branch and fully-connected layer processes all the features [57], [58]
Summary
Diabetic Macular Edema (DME) is a complication of Diabetic Retinopathy (DR), and it usually occurs when vessels in the central part of the macula are affected by the fluid accretion [1]. Diabetes currently affects more than 425 million people worldwide and is expected to affect an estimated 520 million by 2025. It is estimated that 10% of people who suffer from some form of Diabetes are at the risk of DME. CNNs are fundamentally made of three types of layers, namely convolutional, pooling, and fully-connected layers. The convolutional layer is composed of a set of convolutional kernels that are responsible to learn the patterns or specific features from the input. These kernels compute different feature maps and each neuron in a feature map is associated with a region of neighboring neurons of the previous layer.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
