Department of Computer Science, Shiv Nadar University, Noida, UP, India.
PLoS One. 2020 Feb 10;15(2):e0220677. doi: 10.1371/journal.pone.0220677. eCollection 2020.
Diabetic Macular Edema (DME) is an advanced stage of Diabetic Retinopathy (DR) and can lead to permanent vision loss. Currently, it affects 26.7 million people globally and on account of such a huge number of DME cases and the limited number of ophthalmologists, it is desirable to automate the diagnosis process. Computer-assisted, deep learning based diagnosis could help in early detection, following which precision medication can help to mitigate the vision loss.
In order to automate the screening of DME, we propose a novel DMENet Algorithm which is built on the pillars of Convolutional Neural Networks (CNNs). DMENet analyses the preprocessed color fundus images and passes it through a two-stage pipeline. The first stage detects the presence or absence of DME whereas the second stage takes only the positive cases and grades the images based on severity. In both the stages, we use a novel Hierarchical Ensemble of CNNs (HE-CNN). This paper uses two of the popular publicly available datasets IDRiD and MESSIDOR for classification. Preprocessing on the images is performed using morphological opening and gaussian kernel. The dataset is augmented to solve the class imbalance problem for better performance of the proposed model.
The proposed methodology achieved an average Accuracy of 96.12%, Sensitivity of 96.32%, Specificity of 95.84%, and F-1 score of 0.9609 on MESSIDOR and IDRiD datasets.
These excellent results establish the validity of the proposed methodology for use in DME screening and solidifies the applicability of the HE-CNN classification technique in the domain of biomedical imaging.
目的：为了实现 DME 的自动化筛查，我们提出了一种新的 DMENet 算法，该算法建立在卷积神经网络 (CNN) 的基础上。DMENet 分析预处理的彩色眼底图像，并通过两阶段流水线进行处理。第一阶段检测 DME 是否存在，第二阶段仅对阳性病例进行处理，并根据严重程度对图像进行分级。在这两个阶段中，我们都使用了一种新的分层 CNN 集成 (HE-CNN)。本文使用了两个流行的公开可用数据集 IDRiD 和 MESSIDOR 进行分类。使用形态学开运算和高斯核对图像进行预处理。通过数据增强来解决类别不平衡问题，以提高所提出模型的性能。
结果：在 MESSIDOR 和 IDRiD 数据集上，所提出的方法的平均准确率为 96.12%，灵敏度为 96.32%，特异性为 95.84%，F1 得分为 0.9609。
结论：这些优异的结果证明了所提出的方法在 DME 筛查中的有效性，并证实了 HE-CNN 分类技术在生物医学成像领域的适用性。
