Introducing Feature Attention Module on Convolutional Neural Network for Diabetic Retinopathy Detection

TL;DR

This paper introduces a feature attention module integrated with a pretrained VGG19 CNN to improve diabetic retinopathy detection accuracy, demonstrating significant performance gains on a standard dataset.

Contribution

The novel feature attention module enhances CNN focus on relevant image regions, improving DR detection accuracy over existing methods.

Findings

Achieved 95.70% accuracy on APTOS dataset.

Attention module improves detection performance compared to baseline.

Fusion of attention with CNN outperforms state-of-the-art approaches.

Abstract

Diabetic retinopathy (DR) is a leading cause of blindness among diabetic patients. Deep learning models have shown promising results in automating the detection of DR. In the present work, we propose a new methodology that integrates a feature attention module with a pretrained VGG19 convolutional neural network (CNN) for more accurate DR detection. Here, the pretrained net is fine-tuned with the proposed feature attention block. The proposed module aims to leverage the complementary information from various regions of fundus images to enhance the discriminative power of the CNN. The said feature attention module incorporates an attention mechanism which selectively highlights salient features from images and fuses them with the original input. The simultaneous learning of attention weights for the features and thereupon the combination of attention-modulated features within the feature attention block facilitates the network's ability to focus on relevant information while reducing the impact of noisy or irrelevant features. Performance of the proposed method has been evaluated on a widely used dataset for diabetic retinopathy classification e.g., the APTOS (Asia Pacific Tele-Ophthalmology Society) DR Dataset. Results are compared with/without attention module, as well as with other state-of-the-art approaches. Results confirm that the introduction of the fusion module (fusing of feature attention module with CNN) improves the accuracy of DR detection achieving an accuracy of 95.70%.