Department of Biostatistics, Faculty of Medicine, Izmir Katip Celebi University, Izmir, Turkey.
Department of Biostatistics, Faculty of Medicine, Eskisehir Osmangazi University, Eskisehir, Turkey.
Arq Bras Oftalmol. 2023 Apr 3;87(5):e20220124. doi: 10.5935/0004-2749.2022-0124. eCollection 2023.
This study aimed to evaluate the classification performance of pretrained convolutional neural network models or architectures using fundus image dataset containing eight disease labels.
A publicly available ocular disease intelligent recognition database has been used for the diagnosis of eight diseases. This ocular disease intelligent recognition database has a total of 10,000 fundus images from both eyes of 5,000 patients for the following eight diseases: healthy, diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, hypertension, myopia, and others. Ocular disease classification performances were investigated by constructing three pretrained convolutional neural network architectures including VGG16, Inceptionv3, and ResNet50 models with adaptive moment optimizer. These models were implemented in Google Colab, which made the task straight-forward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of the models, the dataset was divided into 70%, 10%, and 20% for training, validation, and testing, respectively. For each classification, the training images were augmented to 10,000 fundus images.
ResNet50 achieved an accuracy of 97.1%; sensitivity, 78.5%; specificity, 98.5%; and precision, 79.7%, and had the best area under the curve and final score to classify cataract (area under the curve = 0.964, final score = 0.903). By contrast, VGG16 achieved an accuracy of 96.2%; sensitivity, 56.9%; specificity, 99.2%; precision, 84.1%; area under the curve, 0.949; and final score, 0.857.
These results demonstrate the ability of the pretrained convolutional neural network architectures to identify ophthalmological diseases from fundus images. ResNet50 can be a good architecture to solve problems in disease detection and classification of glaucoma, cataract, hypertension, and myopia; Inceptionv3 for age-related macular degeneration, and other disease; and VGG16 for normal and diabetic retinopathy.
本研究旨在评估使用包含 8 种疾病标签的眼底图像数据集的预训练卷积神经网络模型或架构的分类性能。
使用公开的眼部疾病智能识别数据库进行 8 种疾病的诊断。该眼部疾病智能识别数据库共包含来自 5000 名患者双眼的 10000 张眼底图像，用于以下 8 种疾病：健康、糖尿病视网膜病变、青光眼、白内障、年龄相关性黄斑变性、高血压、近视和其他疾病。通过构建三个包括 VGG16、Inceptionv3 和 ResNet50 模型的预训练卷积神经网络架构，并使用自适应矩优化器，研究了眼部疾病的分类性能。这些模型在 Google Colab 中实现，使得任务变得简单，无需花费数小时安装环境和支持库。为了评估模型的有效性，将数据集分为 70%、10%和 20%用于训练、验证和测试。对于每种分类，将训练图像扩充到 10000 张眼底图像。
ResNet50 达到了 97.1%的准确率、78.5%的灵敏度、98.5%的特异性和 79.7%的精确率，并且在分类白内障方面具有最佳的曲线下面积和最终得分（曲线下面积=0.964，最终得分=0.903）。相比之下，VGG16 达到了 96.2%的准确率、56.9%的灵敏度、99.2%的特异性、84.1%的精确率、0.949 的曲线下面积和 0.857 的最终得分。
这些结果表明，预训练的卷积神经网络架构能够从眼底图像中识别眼科疾病。ResNet50 可以成为一种很好的架构，用于解决青光眼、白内障、高血压和近视等疾病的检测和分类问题；Inceptionv3 用于年龄相关性黄斑变性和其他疾病；VGG16 用于正常和糖尿病视网膜病变。
