Detection and comparison of accuracy using LeNet with VGG16 for Macula disease using oct images

The macula OCT disease is investigated in this work by employing deep learning techniques like as LeNet and comparing the accuracy of these approaches to that of a VGG16 database. For the purpose of determining the accuracy of the Macula prediction in this study, the materials and methods that were employed were LeNet and the VGG16 algorithm, each of which contains twenty samples. The size of the sample was determined by use G power, with the pretest power set at 80 percent, and the alpha value set at 0.05. For the purpose of training the LeNet and VGG16 algorithms, the classification of macula OCT images was utilised as a way to train the data models. LeNet has a 67.25 percent accuracy rate, whereas VGG16 has a 22.36 percent accuracy rate. The results indicate that there is a statistically significant difference between the two models (p=0.001, p