Improved Microaneurysm Detection using Deep Neural Networks

TL;DR

This paper introduces a deep neural network approach for early diabetic retinopathy screening by accurately detecting microaneurysms in fundus images, eliminating manual feature extraction and preprocessing.

Contribution

A novel deep neural network model with dropout and maxout activation for microaneurysm detection that outperforms traditional methods without preprocessing.

Findings

Achieved state-of-the-art accuracy on ROC and Diaretdb1v2 datasets.

No preprocessing or manual feature extraction needed.

Substantial improvement over standard detection pipelines.

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.