School of Software Engineering, Xiamen University of Technology, Xiamen 361024, China.
School of Opto-electronic and Communications Engineering, Xiamen University of Technology, Xiamen 361024, China.
J Healthc Eng. 2021 May 5;2021:5549779. doi: 10.1155/2021/5549779. eCollection 2021.
The automatic diagnosis of various retinal diseases based on fundus images is important in supporting clinical decision-making. Convolutional neural networks (CNNs) have achieved remarkable results in such tasks. However, their high expression ability possibly leads to overfitting. Therefore, data augmentation (DA) techniques have been proposed to prevent overfitting while enriching datasets. Recent CNN architectures with more parameters render traditional DA techniques insufficient. In this study, we proposed a new DA strategy based on multimodal fusion (DAMF) which could integrate the standard DA method, data disrupting method, data mixing method, and autoadjustment method to enhance the image data in the training dataset to create new training images. In addition, we fused the results of the classifier by voting on the basis of DAMF, which further improved the generalization ability of the model. The experimental results showed that the optimal DA mode could be matched to the image dataset through our DA strategy. We evaluated DAMF on the iChallenge-PM dataset. At last, we compared training results between 12 DAMF processed datasets and the original training dataset. Compared with the original dataset, the optimal DAMF achieved an accuracy increase of 2.85% on iChallenge-PM.
基于眼底图像的各种视网膜疾病的自动诊断在支持临床决策中非常重要。卷积神经网络（CNN）在这些任务中取得了显著的成果。然而，它们的高表达能力可能导致过拟合。因此，提出了数据增强（DA）技术来防止过拟合，同时丰富数据集。具有更多参数的最新 CNN 架构使得传统的 DA 技术不足。在这项研究中，我们提出了一种新的基于多模态融合（DAMF）的 DA 策略，该策略可以整合标准的 DA 方法、数据破坏方法、数据混合方法和自动调整方法，以增强训练数据集中的图像数据，创建新的训练图像。此外，我们根据 DAMF 通过投票融合分类器的结果，进一步提高了模型的泛化能力。实验结果表明，通过我们的 DA 策略可以将最优的 DA 模式匹配到图像数据集。我们在 iChallenge-PM 数据集上评估了 DAMF。最后，我们比较了 12 个经过 DAMF 处理的数据集和原始训练数据集的训练结果。与原始数据集相比，最优的 DAMF 在 iChallenge-PM 上的准确率提高了 2.85%。
