基于增量式学习的圆锥角膜分类算法  

Keratoconus classification algorithm based on incremental learning

作　　者：赖雨晴 刘凤连[1] 李婧 汪日伟 谭左平 LAI Yuqing;LIU Fenglian;LI Jing;WANG Riwei;TAN Zuoping(Key Laboratory on Computer Vision and Systems,Ministry of Education of China,Tianjin Key Laboratory on Intelligence Computing and Novel Software Technology,Tianjin University of Technology,Tianjin 300384,China;Zhejiang Women's Science and Technology Innovation Studios,Wenzhou University of Technology,Wenzhou,Zhejiang 325035,China)

机构地区：[1]天津理工大学计算机视觉与系统教育部重点实验室和天津市智能计算及软件新技术重点实验室,天津300384 [2]温州理工学院浙江省巾帼科技创新工作室,浙江温州325035

出　　处：《光电子．激光》2024年第8期880-884,共5页Journal of Optoelectronics·Laser

基　　金：南开大学眼科学研究院开放基金(NKYKD202209);温州市重大科技创新攻关项目(ZG2022011);温州理工学院科技计划研究重点项目(KY202204)资助项目。

摘　　要：圆锥角膜是一种进展性的角膜疾病,多发于青春期,会造成不规则散光以及视力下降,晚期致盲需进行角膜移植,因此圆锥角膜的早期精准筛查是阻止疾病进展避免恶化的必要条件。神经网络作为一种经典的算法是圆锥角膜诊断的有效工具。但随着圆锥角膜病例数据日益增长,为了充分利用新增数据,往往需要对所有样本重新训练,这将耗费大量的时间。为了解决上述问题,本文提出集成神经网络的增量式学习算法,以实现圆锥角膜的智能诊断。此外,本文还引入欠采样和代价敏感思想,用于解决已有增量式学习算法无法处理不均衡数据的问题。实验结果表明,本文提出的算法识别精度达到97%,并且所需训练时间短、存储空间少,因此本算法能够更高效地辅助圆锥角膜诊断。Keratoconus is a progressive corneal disease that mostly occurs in adolescence and can cause irregular astigmatism and vision loss.Late-stage blindness requires corneal transplantation.Therefore,early and accurate screening of keratoconus is necessary to prevent the progression of the disease and avoid deterioration.As a classic algorithm,neural network is an effective tool for keratoconus diagnosis.However,as the data of keratoconus cases grows day by day,in order to make full use of the new data,it is often necessary to retrain all samples,which will consume a lot of time.In order to solve the above problems,this article proposes an incremental learning algorithm integrating neural networks to achieve intelligent diagnosis of keratoconus.In addition,this article also introduces the ideas of undersampling and cost sensitivity to solve the problem that existing incremental learning algorithms cannot handle imbalanced data.Experimental results show that the recognition accuracy of the algorithm proposed in this article reaches 97%,and requires short training time and less storage space.Therefore,this algorithm can assist in the diagnosis of keratoconus more efficiently.

关 键 词：圆锥角膜 集成神经网络 增量学习 不平衡数据 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]