基于多任务学习的眼底图像红色病变点分割  

Red Lesion Segmentation of Fundus Image with Multi-task Learning

作　　者：郭松 李涛[2,3] 李宁[1] 康宏 张玉军 王恺[1] GUO Song;LI Tao;LI Ning;KANG Hong;ZHANG Yu-Jun;WANG Kai(College of Computer Science,Nankai University,Tianjin 300350,China;Tianjin Key Laboratory of Network and Data Science Technology(Nankai University),Tianjin 300350,China;State Key Laboratory of Computer Architecture(Chinese Academy of Sciences),Beijing 100190,China;Beijing Shanggong Medical Technology Co.Ltd.,Beijing 100176,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]南开大学计算机学院,天津300350 [2]天津市网络与数据安全技术重点实验室(南开大学),天津300350 [3]计算机体系结构国家重点实验室(中国科学院),北京100190 [4]北京上工医信科技有限公司,北京100176 [5]中国科学院计算技术研究所,北京100190

出　　处：《软件学报》2021年第11期3646-3658,共13页Journal of Software

基　　金：国家自然科学基金(61872200);国家重点研发计划(2016YFC0400709,2018YFB2100300);天津市自然科学基金(18YFYZCG00060,19JCZDJC31600);天津市教学成果奖重点培育项目(PYGJ-018)。

摘　　要：糖尿病性视网膜病变(糖网病)是导致成年人视觉损失的主要因素之一.早期的眼底筛查可以显著降低这种视觉损失的可能性.彩色眼底图像由于具有采集便利、对人体无伤害等特点,常被用于大规模的眼底筛查工作.对眼底图像中的红色病变点而言,微动脉瘤是轻度非增殖性糖网病的主要标志,出血点与中度及重度非增殖性糖网病的诊断有关,因此,眼底图像中出血点和微动脉瘤的准确分割对糖网病分级诊断具有重要参考价值.提出一种基于多任务学习的分割模型Red-Seg来对出血点和微动脉瘤进行分割.该网络包含两个分支,每个分支处理一种病变点.设计了一种两阶段训练算法,并且两个阶段使用不同的损失函数:第1阶段使用改进的Top-k带权交叉熵损失函数,将模型训练集中在难分样本上;第2阶段将最小化假阳性和假阴性作为Red-Seg模型训练的优化目标,进一步减少病变点误分.最后,在IDRiD数据集上进行模型验证,并与其他病变点分割方法进行对比.实验结果表明,在应用Red-Seg模型进行微动脉瘤和出血点红色病变点分割时,两阶段训练算法可以显著减少病变点误分情况,尤其是出血点分割的准确率和召回率都提高2.8%.同时,与HED、FCRN、DeepLabv3+和L-Seg等图像级分割模型相比,Red-Seg模型在微动脉瘤分割上获得了更好的AUC_PR.Diabetic retinopathy(DR)is the leading cause of vision loss for adult individuals,and early fundus screening can significantly reduce this visual loss.Color fundus image is often used in large-scale fundus screening due to the acquisition convenience and its human-harmless.As a kind of red lesions in fundus images,the appearance of microaneurysms is the main marker of mild non-proliferative DR,and hemorrhage,as another kind of red lesions,is related to moderate and severe non-proliferative DR.So that red lesions in fundus images are important indicators for the screening of DR.This study proposes a multi-task network,named Red-Seg,for red lesion segmentation.The network contains two individual branches,each is used for one kind of lesion segmentation.Meantime,a two-stage training algorithm is presented where different loss functions are used in different stages.In the first stage,modified Top-k balanced cross-entropy loss is used to push the network focuses on hard-to-classify samples.And,in the second stage,false positive and false negative are integrated as loss function into training to reduce misclassification further.At last,extensive experiments are employed on the IDRiD dataset,and the lesion segmentation results are compared with other methods.Experimental results show that proposed two-stage training algorithm can lead to much higher precision and recall,which means this method can reduce misclassification in some certain.Specifically for hemorrhage segmentation,both recall and precision increased by at least 2.8%.Meanwhile,compared with other image-level lesion segmentation models,such as HED,FCRN,DeepLabv3+,and L-Seg,Red-Seg achieves much higher AUC_PR on microaneurysm segmentation.

关 键 词：眼底图像 糖网病 微动脉瘤分割 出血点分割 多任务学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]