[Detection of microaneurysms in fundus images based on improved YOLOv4 with SENet embedded].

Microaneurysm is the initial symptom of diabetic retinopathy. Eliminating this lesion can effectively prevent diabetic retinopathy in the early stage. However, due to the complex retinal structure and the different brightness and contrast of fundus image because of different factors such as patients, environment and acquisition equipment, the existing detection algorithms are difficult to achieve the accurate detection and location of the lesion. Therefore, an improved detection algorithm of you only look once (YOLO) v4 with Squeeze-and-Excitation networks (SENet) embedded was proposed. Firstly, an improved and fast fuzzy c-means clustering algorithm was used to optimize the anchor parameters of the target samples to improve the matching degree between the anchors and the feature graphs; Then, the SENet attention module was embedded in the backbone network to enhance the key information of the image and suppress the background information of the image, so as to improve the confidence of microaneurysms; In addition, an spatial pyramid pooling was added to the network neck to enhance the acceptance domain of the output characteristics of the backbone network, so as to help separate important context information; Finally, the model was verified on the Kaggle diabetic retinopathy dataset and compared with other methods. The experimental results showed that compared with other YOLOv4 network models with various structures, the improved YOLOv4 network model could significantly improve the automatic detection results such as F-score which increased by 12.68%; Compared with other network models and methods, the automatic detection accuracy of the improved YOLOv4 network model with SENet embedded was obviously better, and accurate positioning could be realized. Therefore, the proposed YOLOv4 algorithm with SENet embedded has better performance, and can accurately and effectively detect and locate microaneurysms in fundus images.微动脉瘤是糖尿病视网膜病变的初期症状，消除该病灶可在早期非常有效地预防糖尿病视网膜病变。但由于视网膜结构复杂，同时眼底图像的成像由于患者、环境、采集设备等因素的不同会存在不同的亮度和对比度，现有的微动脉瘤检测算法难以实现该病灶的精确检测和定位，为此本文提出嵌入SENet（squeeze-and-excitation networks）的改进YOLO（you only look once）v4自动检测算法。该算法在YOLOv4网络基础上，首先通过使用一种改进的快速模糊C均值聚类算法对目标样本进行先验框参数优化，以提高先验框与特征图的匹配度；然后，在主干网络嵌入SENet模块，通过强化关键信息，抑制背景信息，提高微动脉瘤的置信度；此外，还在网络颈部增加空间金字塔池化结构以增强主干网络输出特征的接受域，从而有助于分离出重要的上下文信息；最后，在Kaggle数据集上进行模型验证，并与其他方法进行对比。实验结果表明，与其他各种结构的YOLOv4网络模型相比，所提出的嵌入SENet的改进YOLOv4网络模型能显著提高检测结果（与原始YOLOv4相比F-score提升了12.68%）；与其他网络模型以及方法相比，所提出的嵌入SENet的改进YOLOv4网络模型的自动检测精度明显更优，且可实现精准定位。故本文所提出的嵌入SENet的改进YOLOv4算法性能较优，能准确、有效地检测并定位出眼底图像中的微动脉瘤。.