Duah Gifty, Nyarko Eric, Lotsi Anani
Department of Statistics and Actuarial Science, School of Physical and Mathematical Sciences, University of Ghana, Legon, Accra, Ghana.
PLoS One. 2025 Aug 1;20(8):e0327743. doi: 10.1371/journal.pone.0327743. eCollection 2025.
Retinal diseases, a significant global health concern, often lead to severe vision impairment and blindness, resulting in substantial functional and social limitations. This study explored a novel goal of developing and comparing the performance of multiple state-of-the-art convolutional neural network (CNN) models for the automated detection and classification of retinal diseases using optical coherence tomography (OCT) images.
The study utilized several models, including DenseNet121, ResNet50, Inception V3, MobileNet, and OCT images obtained from the WATBORG Eye Clinic, to detect and classify multiple retinal diseases such as glaucoma, macular edema, posterior vitreous detachment (PVD), and normal eye cases. The preprocessing techniques employed included data augmentation, resizing, and one-hot encoding. We also used the Gaussian Process-based Bayesian Optimization (GPBBO) approach to fine-tune the hyperparameters. Model performance was evaluated using the F1-Score, precision, recall, and area under the curve (AUC).
All the CNN models evaluated in this study demonstrated a strong capability to detect and classify various retinal diseases with high accuracy. MobileNet achieved the highest accuracy at 96% and AUC of 0.975, closely followed by DenseNet121, which had 95% accuracy and an AUC of 0.963. Inception V3 and ResNet50, while not as high in accuracy, showed potential in specific contexts, with 83% and 79% accuracy, respectively.
These results underscore the potential of advanced CNN models for diagnosing retinal diseases. With the exception of ResNet50, the other CNN models displayed accuracy levels that are comparable to other state-of-the-art deep learning models. Notably, MobileNet and DenseNet121 showed considerable promise for use in clinical settings, enabling healthcare practitioners to make rapid and accurate diagnoses of retinal diseases. Future research should focus on expanding datasets, integrating multi-modal data, exploring hybrid models, and validating these models in clinical environments to further enhance their performance and real-world applicability.
视网膜疾病是一个重大的全球健康问题，常常导致严重的视力损害和失明，造成显著的功能和社会限制。本研究探索了一个新目标，即开发并比较多个先进的卷积神经网络（CNN）模型，用于使用光学相干断层扫描（OCT）图像对视网膜疾病进行自动检测和分类。
该研究使用了多个模型，包括DenseNet121、ResNet50、Inception V3、MobileNet，以及从WATBORG眼科诊所获取的OCT图像，以检测和分类多种视网膜疾病，如青光眼、黄斑水肿、玻璃体后脱离（PVD）和正常眼病例。所采用的预处理技术包括数据增强、调整大小和独热编码。我们还使用了基于高斯过程的贝叶斯优化（GPBBO）方法来微调超参数。使用F1分数、精度、召回率和曲线下面积（AUC）评估模型性能。
本研究中评估的所有CNN模型都表现出以高精度检测和分类各种视网膜疾病的强大能力。MobileNet的准确率最高，为96%，AUC为0.975，紧随其后的是DenseNet121，其准确率为95%，AUC为0.963。Inception V3和ResNet50虽然准确率没有那么高，但在特定情况下显示出潜力，准确率分别为83%和79%。
这些结果强调了先进的CNN模型在诊断视网膜疾病方面的潜力。除了ResNet50之外，其他CNN模型的准确率水平与其他先进的深度学习模型相当。值得注意的是，MobileNet和DenseNet121在临床环境中显示出了很大的应用前景，使医疗从业者能够快速准确地诊断视网膜疾病。未来的研究应专注于扩大数据集、整合多模态数据、探索混合模型，并在临床环境中验证这些模型，以进一步提高它们的性能和实际应用价值。
