A Dual Attention-aided DenseNet-121 for Classification of Glaucoma from Fundus Images

TL;DR

This paper introduces an attention-enhanced DenseNet-121 model that effectively classifies glaucoma from fundus images, outperforming existing methods through the integration of spatial and channel attention modules.

Contribution

The novel dual attention mechanism integrated into DenseNet-121 improves glaucoma classification accuracy on fundus images, with comprehensive ablation studies validating each component's effectiveness.

Findings

Outperforms state-of-the-art models on RIM-ONE and ACRIMA datasets

Attention modules significantly enhance feature extraction

Ablation studies confirm the contribution of each component

Abstract

Deep learning and computer vision methods are nowadays predominantly used in the field of ophthalmology. In this paper, we present an attention-aided DenseNet-121 for classifying normal and glaucomatous eyes from fundus images. It involves the convolutional block attention module to highlight relevant spatial and channel features extracted by DenseNet-121. The channel recalibration module further enriches the features by utilizing edge information along with the statistical features of the spatial dimension. For the experiments, two standard datasets, namely RIM-ONE and ACRIMA, have been used. Our method has shown superior results than state-of-the-art models. An ablation study has also been conducted to show the effectiveness of each of the components. The code of the proposed work is available at: https://github.com/Soham2004GitHub/DADGC.