基于改进YOLOv5的眼底出血点检测算法  

Fundus Hemorrhagic Spot Detection Algorithm Based on Improved YOLOv5

作　　者：吕辉[1] 吕卫峰 LU Hui;L Weifeng(College of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo Henan 454150,China)

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454150

出　　处：《广西师范大学学报（自然科学版）》2024年第3期99-107,共9页Journal of Guangxi Normal University:Natural Science Edition

基　　金：河南省自然科学基金(242300420283);河南省科技攻关项目(232102210171);河南省高校基本科研业务费专项资金项目(NSFRF230622,NSFRF240819)

摘　　要：糖尿病视网膜病变眼底图像中出血点病灶尺寸小且分布密集,导致现有算法难以实现该病灶的精确检测及定位。本文提出一种RCA-YOLO出血病灶检测算法,算法在YOLOv5s基础上,首先在主干网络中使用RCA-Net模块,使网络在获得各通道间联系的同时保留目标病灶的位置信息,增强网络对出血区域的特征提取及定位能力;然后在特征融合阶段采用轻量化特征金字塔网络Tiny-BiFPN,在减少网络参数量的同时,实现高效率的多尺度特征融合;最后提出小目标特征增强模块,提升算法对小出血点病灶的检测精度。实验结果表明,改进后的RCA-YOLO算法能够准确地检测并定位出血点病灶,平均检测准确率(mAP)可达79.3%,较YOLOv5s算法提高了9.5个百分点,其检测结果同样优于Faster R-CNN、YOLOv6s、YOLOv7和YOLOv8s等主流算法。The small size and dense distribution of bleeding point lesions in the fundus image of diabetic retinopathy make it difficult for the existing algorithms to achieve accurate detection and localization of the lesions.A RCA-YOLO bleeding lesion detection algorithm is proposed.Based on YOLOv5s,the RCA-Net module is first used in the backbone network,so that the network can obtain the connection between each channel while retaining the location information of the target lesion,and enhance the feature extraction and localization ability of the network for the bleeding area.In the feature fusion stage,the lightweight feature pyramid network Tiny-BiFPN is adopted to reduce the number of network parameters and achieve high-efficiency multi-scale feature fusion.Finally,a small target feature enhancement module is proposed to improve the detection accuracy of the algorithm for small bleeding point lesions.The experimental results show that the improved RCA-YOLO algorithm can accurately detect and locate bleeding point lesions,and the average detection accuracy(mAP)can reach 79.3%,which is 9.5 percentage points higher than that of YOLOv5s algorithm,and its detection results are also better than mainstream algorithms such as Faster R-CNN,YOLOv6s,YOLOv7 and YOLOv8s.

关 键 词：眼底图像 糖尿病视网膜病变 目标检测 出血病灶 特征融合 

分 类 号：R587.2[医药卫生—内分泌] R774.1[医药卫生—内科学] TP183[医药卫生—临床医学] TP391.41[自动化与计算机技术—控制理论与控制工程]