Improved Microaneurysm Detection using Deep Neural Networks

Abstract

In this work, we propose a novel microaneurysm (MA) detection for early diabetic retinopathy screening using color fundus images. Since MA usually the first lesions to appear as an indicator of diabetic retinopathy, accurate detection of MA is necessary for treatment. Each pixel of the image is classified as either MA or non-MA using a deep neural network with dropout training procedure using maxout activation function. No preprocessing step or manual feature extraction is required. Substantial improvements over standard MA detection method based on the pipeline of preprocessing, feature extraction, classification followed by post processing is achieved. The presented method is evaluated in publicly available Retinopathy Online Challenge (ROC) and Diaretdb1v2 database and achieved state-of-the-art accuracy.

References in corpus (2)

• An ensemble-based system for automatic screening of diabetic retinopathy
• A Gaussian Scale Space Approach For Exudates Detection, Classification And Severity Prediction

Cited by in corpus (14)

• Deep image mining for diabetic retinopathy screening
• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• Retinal Microaneurysms Detection using Local Convergence Index Features
• Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
• Towards Ophthalmologist Level Accurate Deep Learning System for OCT Screening and Diagnosis
• An Unsupervised Method for Detection and Validation of The Optic Disc and The Fovea
• Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
• Rethinking Convolutional Semantic Segmentation Learning
• A comprehensive survey on computer-aided diagnostic systems in diabetic retinopathy screening
• Automated Detection of Microaneurysms in Color Fundus Images using Deep Learning with Different Preprocessing Approaches
• Point-of-Care Diabetic Retinopathy Diagnosis: A Standalone Mobile Application Approach
• Sparsely Activated Networks: A new method for decomposing and compressing data
• The Efficacy of Microaneurysms Detection With and Without Vessel Segmentation in Color Retinal Images
• Comparison Different Vessel Segmentation Methods in Automated Microaneurysms Detection in Retinal Images using Convolutional Neural Networks