<![CDATA[Cataract is one of the leading causes of blindness worldwide and requires early detection to prevent vision deterioration. Advances in artificial intelligence, particularly deep learning, have enabled the development of automated systems for medical image classification. However, conventional Convolutional Neural Networks (CNNs) tend to lose important spatial information due to pooling operations, which may affect classification performance. This study aims to analyze the accuracy of the Capsule Network (CapsNet) method for cataract classification using fundus images. The proposed method employs image preprocessing techniques, including resizing, data augmentation, and normalization, before training the CapsNet model. The model was developed using Python and the PyTorch framework. Performance evaluation was conducted using a Confusion Matrix and several metrics, namely Accuracy, Precision, Recall, Specificity, F1-score, and Area Under the Curve (AUC). Experimental results showed that the model achieved a training accuracy of 86.29% and a best validation accuracy of 81.34%. Furthermore, testing on 1,813 fundus images resulted in an accuracy of 89.85%, precision of 94.56%, recall of 84.53%, specificity of 95.15%, F1-score of 89.26%, AUC-ROC of 95.27%, and Average Precision (AP) of 94.71%. These findings indicate that CapsNet is capable of effectively classifying cataract fundus images. Although the obtained performance is consistent with the theoretical capability of CapsNet to preserve spatial relationships among image features, this capability was not directly evaluated in the present study.]]>
Copyrights © 2026
