Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin Province, China.
College of Computer Science and Technology, Jilin University, Changchun, Jilin Province, China.
Retina. 2022 Jun 1;42(6):1095-1102. doi: 10.1097/IAE.0000000000003434.
To solve the problem of automatic grading of macular edema in retinal images in a more stable and reliable way and reduce the workload of ophthalmologists, an automatic detection and grading method of diabetic macular edema based on a deep neural network is proposed.
The enhanced green channels of fundus images are input into the YOLO network for training and testing. Diabetic macular edema is graded according to the distance of the macula and hard exudate. We used multiscale feature fusion to form more comprehensive features on different grain images to improve the effect of hard exudate detection. We adopted K-means++ algorithm to cluster anchor box size and use loss of the original network to guide the regression of hard exudate bounding box and improve the regression accuracy of anchor boxes. We increased the diversity of samples for sample training by data augmentation, including cropping, flipping, and rotating of fundus images, so that each batch of training data can better represent the distribution of samples.
The detection accuracy of the proposed method can reach 96% on the MESSIDOR data set. The detection rates of hard exudate with high, median, and low probability are 100%, 79.12%, and 60.40%, respectively.
The proposed method exhibits a very good detection stability on healthy and diseased fundus images.
为了更稳定、可靠地解决视网膜图像中黄斑水肿的自动分级问题，减少眼科医生的工作量，提出了一种基于深度神经网络的糖尿病性黄斑水肿自动检测和分级方法。
将眼底图像的增强绿色通道输入 YOLO 网络进行训练和测试。根据黄斑和硬性渗出物的距离对糖尿病性黄斑水肿进行分级。我们采用多尺度特征融合在不同粒度的图像上形成更全面的特征，以提高硬性渗出物检测的效果。我们采用 K-means++算法对锚框大小进行聚类，并利用原始网络的损失来引导硬性渗出物边界框的回归，提高锚框的回归精度。通过数据增强增加样本的多样性，包括眼底图像的裁剪、翻转和旋转，使每批训练数据能够更好地代表样本的分布。
该方法在 MESSIDOR 数据集上的检测准确率可达 96%。高、中、低概率硬性渗出物的检测率分别为 100%、79.12%和 60.40%。
该方法在健康和患病眼底图像上表现出非常好的检测稳定性。
