Deep Ensemble Learning Based Objective Grading of Macular Edema by Extracting Clinically Significant Findings from Fused Retinal Imaging Modalities

Abstract

Macular edema (ME) is a retinal condition in which central vision of a patient is affected. ME leads to accumulation of fluid in the surrounding macular region resulting in a swollen macula. Optical coherence tomography (OCT) and the fundus photography are the two widely used retinal examination techniques that can effectively detect ME. Many researchers have utilized retinal fundus and OCT imaging for detecting ME. However, to the best of our knowledge, no work is found in the literature that fuses the findings from both retinal imaging modalities for the effective and more reliable diagnosis of ME. In this paper, we proposed an automated framework for the classification of ME and healthy eyes using retinal fundus and OCT scans. The proposed framework is based on deep ensemble learning where the input fundus and OCT scans are recognized through the deep convolutional neural network (CNN) and are processed accordingly. The processed scans are further passed to the second layer of the deep CNN model, which extracts the required feature descriptors from both images. The extracted descriptors are then concatenated together and are passed to the supervised hybrid classifier made through the ensemble of the artificial neural networks, support vector machines and naïve Bayes. The proposed framework has been trained on 73,791 retinal scans and is validated on 5100 scans of publicly available Zhang dataset and Rabbani dataset. The proposed framework achieved the accuracy of 94.33% for diagnosing ME and healthy subjects and achieved the mean dice coefficient of 0.9019 ± 0.04 for accurately extracting the retinal fluids, 0.7069 ± 0.11 for accurately extracting hard exudates and 0.8203 ± 0.03 for accurately extracting retinal blood vessels against the clinical markings.

Performance of deep neural network-based artificial intelligence method in diabetic retinopathy screening: a systematic review and meta-analysis of diagnostic test accuracy

“…Moreover, our metaanalysis focused on studies that used fundus image as an examination method, the main shortcoming of which is that it could only produce 2D images, while the structure of retina is actually 3D. From the perspective of techniques, optical coherence tomography (OCT) that could capture the cross-sectional axial of retina through light coherence has an advantage of macular edema visualization and has largely supplanted fundus image in macular edema detection (51,52). Thus, algorithms should also be trained to interpret OCT images in order to better diagnose macular edema.…”

“…Thus, algorithms should also be trained to interpret OCT images in order to better diagnose macular edema. Furthermore, the artificial intelligence method that could make use of both fundus image and OCT might get better results (52).…”

Automatic Identification and Representation of the Cornea–Contact Lens Relationship Using AS-OCT Images

“…AS-OCT is based on the optical coherence tomography (OCT) capture technique, a widely used non-invasive imaging technology that provides high-detail transverse images (tomographies) of the main internal structures of the biological tissues [27,28,29]. Figure 3 illustrates a typical optical configuration of a basic OCT acquisition system.…”

Deep Neural Network Learning for Detection and Grading of Diabetic Retinopathy

“…Average pooling deals with the average of the values within the window size. The dropout layer carries out a model averaging by dropping a random set of units from the network while training [17]. It is a regularization technique which is applied to reduce overfitting in a network.…”