<![CDATA[Glaucoma is a chronic ocular disease characterized by progressive optic nerve damage and is one of the leading causes of irreversible blindness. Manual analysis of retinal fundus images is time-consuming, particularly under high clinical workloads. To improve the efficiency of clinical diagnostic workflows, this study aims to develop a glaucoma classification system using a hybrid deep learning model that integrates the ResNeXt architecture with a Convolutional Block Attention Module (CBAM). In the proposed approach, ResNeXt is employed to capture complex feature representations, while CBAM enhances feature extraction by directing the model’s attention to more informative spatial and channel-wise features. Performance evaluation demonstrates that the proposed model outperforms the baseline architecture. The standard ResNeXt model achieves an accuracy of 91.61%, an F1-score of 88.98%, and an AUC of 93.1%. In contrast, the ResNeXt model integrated with CBAM shows improved performance, attaining an accuracy of 92.70%, an F1-score of 90.60%, and an AUC of 95,6%. These results indicate that the integration of CBAM effectively enhances the sensitivity and robustness of the glaucoma classification model compared to the standard architecture.]]>
Copyrights © 2026
