中文摘要：

眼底影像的自动分析是计算机辅助青光眼筛查和诊断的关键基础.为提高青光眼辅助诊断的准确性,基于彩色眼底图,提出一种聚合多通道特征的青光眼自动检测算法.首先基于多尺度分析技术,通过聚合多通道图像特征,从颜色分布、多尺度Gabor滤波和梯度方向分布等方面表示视盘形态和结构在彩色眼底图上的细微变化;然后设计基于随机森林的分类器,在青光眼数据集上训练分类器模型,并利用集成学习技术鉴别青光眼,从而实现一种基于图像特征的青光眼自动检测算法;最后在2个具有挑战性的青光眼公开数据集(RIM-ONEr2和Drishti_GS)上对青光眼检测算法进行测试和验证,分别得到了0.8690和0.8004的曲线下面积值.实验结果表明,该算法在保证青光眼检测敏感性的同时能够显著提高其特异性,对青光眼辅助筛查和诊断具有很好的参考价值.

英文摘要：

Automatic analysis of fundus images is the foundation of computer-aided glaucoma screening anddiagnosis.To improve the accuracy of glaucoma screening,a novel glaucoma detection method is proposedbased on the multi-channel feature aggregation in fundus images.Firstly,multi-channel features are computedbased on color distribution,multi-scale Gabor filters and oriented gradient histogram,and they describethe tiny changes in the morphology and structure of the optic disc.Secondly,a random forest classifieris developed to detect glaucoma based on the multi-channel features and ensemble learning technology.Finally,the glaucoma detection algorithm is tested on two challenging glaucoma datasetss and obtains valuesof the area under the curve with0.8690and0.8204,respectively.The experimental results show that theproposed method can improve sensitivity and specificity simultaneously.