基于双视图特征融合的糖尿病视网膜病变分级  

Diabetic retinopathy grading based on dual-view image feature fusion

作　　者：姜璐璐 孙司琦 邹海东 陆丽娜[2,6] 冯瑞 JIANG Lulu;SUN Siqi;ZOU Haidong;LU Lina;FENG Rui(Academy for Engineering and Technology,Fudan University,Shanghai 200433,China;Shanghai Engineering Research Center of Precise Diagnosis and Treatment of Eye Diseases,Shanghai 200080,China;School of Computer Science,Shanghai Key Laboratory of Intelligent Information Processing,Fudan University,Shanghai 200433,China;Shanghai Collaborative Innovation Center of Intelligent Visual Computing,Fudan University,Shanghai 200433,China;Shanghai General Hospital,Shanghai 200080,China;Shanghai Eye Disease Prevention Center,Shanghai 200040,China)

机构地区：[1]复旦大学工程与应用技术研究院,上海200433 [2]上海市眼科疾病精准诊疗工程技术研究中心,上海200080 [3]复旦大学计算机科学技术学院上海市智能信息处理重点实验室,上海200433 [4]复旦大学上海市智能视觉计算协同创新中心,上海200433 [5]上海交通大学附属第一人民医院,上海200080 [6]上海市眼病防治中心,上海200040

出　　处：《华东师范大学学报（自然科学版）》2023年第6期39-48,共10页Journal of East China Normal University(Natural Science)

基　　金：国家自然科学基金(62172101);上海市科委项目(19DZ2250100,20DZ1100205)。

摘　　要：基于双视图眼底图像的诊断方法被广泛应用于糖尿病视网膜病变(diabetic retinopathy,DR)的筛查,该方法可以有效地解决单视角下图像遮挡和视场受限的问题.针对如何有效融合不同视图信息来提高DR分级准确率,提出了一种基于注意力机制的多视角图像之间特征融合的学习方法.针对眼底图像中病灶占比率较小的问题,引入了自注意力机制以加强局部病灶特征的学习;针对双视图眼底图像分类场景,提出了一种跨视图注意力机制,有效地利用了双视图之间的信息.在内部数据集DFiD和公开数据集DeepDR上进行的实验,验证了所提方法能够有效提高DR分级精度,可用于大规模DR筛查,辅助医生实现高效诊断.The diagnostic method based on dual-view fundus imaging is widely used in diabetic retinopathy(DR)screening.This method effectively solves the problems of image occlusion and limited field of view under single-view.This paper proposes a learning method of feature fusion between dual-view images based on the attention mechanism to improve the accuracy of DR classification by effectively integrating different view information.Due to the small proportion of lesions in fundus images,the self-attention mechanism was introduced to enhance the learning of local lesion features.Moreover,a cross-attention mechanism is proposed to effectively utilize information between dual-view images to improve the classification of dual-view fundus images.Experiments were performed on the internal DFiD dataset and public DeepDRiD dataset.The proposed method can effectively improve the accuracy of DR classification and can be used for large-scale DR screening to assist doctors in achieving an efficient diagnosis.

关 键 词：眼底图像 特征融合 双视图融合 注意力机制 糖尿病视网膜病变 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]