Department of Ophthalmology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand.
Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand.
Sci Rep. 2024 Jul 10;14(1):15899. doi: 10.1038/s41598-024-67121-7.
Cytomegalovirus retinitis (CMVR) is a significant cause of vision loss. Regular screening is crucial but challenging in resource-limited settings. A convolutional neural network is a state-of-the-art deep learning technique to generate automatic diagnoses from retinal images. However, there are limited numbers of CMVR images to train the model properly. Transfer learning (TL) is a strategy to train a model with a scarce dataset. This study explores the efficacy of TL with different pre-trained weights for automated CMVR classification using retinal images. We utilised a dataset of 955 retinal images (524 CMVR and 431 normal) from Siriraj Hospital, Mahidol University, collected between 2005 and 2015. Images were processed using Kowa VX-10i or VX-20 fundus cameras and augmented for training. We employed DenseNet121 as a backbone model, comparing the performance of TL with weights pre-trained on ImageNet, APTOS2019, and CheXNet datasets. The models were evaluated based on accuracy, loss, and other performance metrics, with the depth of fine-tuning varied across different pre-trained weights. The study found that TL significantly enhances model performance in CMVR classification. The best results were achieved with weights sequentially transferred from ImageNet to APTOS2019 dataset before application to our CMVR dataset. This approach yielded the highest mean accuracy (0.99) and lowest mean loss (0.04), outperforming other methods. The class activation heatmaps provided insights into the model's decision-making process. The model with APTOS2019 pre-trained weights offered the best explanation and highlighted the pathologic lesions resembling human interpretation. Our findings demonstrate the potential of sequential TL in improving the accuracy and efficiency of CMVR diagnosis, particularly in settings with limited data availability. They highlight the importance of domain-specific pre-training in medical image classification. This approach streamlines the diagnostic process and paves the way for broader applications in automated medical image analysis, offering a scalable solution for early disease detection.
巨细胞病毒视网膜炎（CMVR）是导致视力丧失的重要原因。在资源有限的环境中，定期筛查至关重要，但具有挑战性。卷积神经网络是一种最先进的深度学习技术，可从视网膜图像生成自动诊断。然而，用于适当训练模型的 CMVR 图像数量有限。迁移学习（TL）是使用稀缺数据集训练模型的策略。本研究探讨了使用来自不同预先训练权重的 TL 进行使用视网膜图像的自动 CMVR 分类的效果。我们利用 2005 年至 2015 年期间在玛希隆大学 Siriraj 医院收集的 955 张视网膜图像（524 张 CMVR 和 431 张正常）数据集。使用 Kowa VX-10i 或 VX-20 眼底相机处理图像，并进行扩充以进行训练。我们采用 DenseNet121 作为骨干模型，比较了在 ImageNet、APTOS2019 和 CheXNet 数据集上预训练权重的 TL 的性能。根据准确性、损失和其他性能指标评估模型，不同预训练权重的微调深度不同。研究发现，TL 显著增强了 CMVR 分类中的模型性能。在将权重从 ImageNet 依次转移到 APTOS2019 数据集后，再应用于我们的 CMVR 数据集，可获得最佳结果。这种方法产生了最高的平均准确率（0.99）和最低的平均损失（0.04），优于其他方法。类激活热图提供了模型决策过程的见解。使用 APTOS2019 预训练权重的模型提供了最佳解释，并突出了类似于人类解释的病理病变。我们的研究结果表明，在数据可用性有限的情况下，顺序 TL 具有提高 CMVR 诊断准确性和效率的潜力。它们突出了在医学图像分类中进行特定领域预训练的重要性。这种方法简化了诊断过程，并为在自动医学图像分析中的更广泛应用铺平了道路，为早期疾病检测提供了可扩展的解决方案。
