Fig. 10

Confusion matrices showcasing classification results for OCT images into four categories (Normal, CNV, DME, Drusen) utilizing the (a). InceptionV3, (b). DenseNet201, and (c). InceptionResNetV2 models. Each matrix highlights true positives, false positives, false negatives, and true negatives for each class, with DenseNet201 and InceptionResNetV2 demonstrating superior accuracy and minimal misclassifications compared to InceptionV3.