Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm
Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm
复制标题
计算机辅助微动脉瘤检测中不平衡数据学习的基于集成的自适应过采样方法
DOI：
10.1016/j.compmedimag.2016.07.011
复制
发表时间：
2017-01-01
影响因子：
5.7
通讯作者：
Zaiane, Osmar
中科院分区：
文献类型：
--
作者：
Ren, Fulong;Cao, Peng;Zaiane, Osmar
糖尿病视网膜病变（DR）是一种进行性疾病，早期发现对于挽救患者的视力至关重要。DR的自动筛查系统可以帮助减少因DR而完全失明的机会，同时降低眼科医生的工作量。DR的早期症状是微动脉瘤（MAs）。然而，由于检测算法具有很高的灵敏度，目前的MA检测方案似乎报告了许多假阳性。在初始MAs识别步骤中，不可避免地会有一些非MAs结构被标记为MAs。这是一个典型的“阶级失衡问题”。类不平衡数据对传统分类器的性能有不利影响。在这项工作中，我们提出了一种基于集成的自适应过采样算法来克服假阳性减少中的类不平衡问题，并使用Boosting， Bagging， Random子空间作为集成框架来改进微动脉瘤检测。我们提出的基于集合的过采样方法结合了自适应过采样和集合的强度。集成和自适应过采样融合的目的是减少由不平衡数据引入的归纳偏差，提高极限学习机（ELM）的泛化分类性能。实验结果表明，我们的ASOBoost方法比现有的许多类失衡学习方法具有更高的ROC曲线下面积（AUC）和g均值。(C) 2016 Elsevier Ltd.版权所有。
Diabetic retinopathy (DR) is a progressive disease, and its detection at an early stage is crucial for saving a patient's vision. An automated screening system for DR can help in reduce the chances of complete blindness due to DR along with lowering the work load on ophthalmologists. Among the earliest signs of DR are microaneurysms (MAs). However, current schemes for MA detection appear to report many false positives because detection algorithms have high sensitivity. Inevitably some non-MAs structures are labeled as MAs in the initial MAs identification step. This is a typical "class imbalance problem". Class imbalanced data has detrimental effects on the performance of conventional classifiers. In this work, we propose an ensemble based adaptive over-sampling algorithm for overcoming the class imbalance problem in the false positive reduction, and we use Boosting, Bagging, Random subspace as the ensemble framework to improve microaneurysm detection. The ensemble based over-sampling methods we proposed combine the strength of adaptive over-sampling and ensemble. The objective of the amalgamation of ensemble and adaptive over-sampling is to reduce the induction biases introduced from imbalanced data and to enhance the generalization classification performance of extreme learning machines (ELM). Experimental results show that our ASOBoost method has higher area under the ROC curve (AUC) and G-mean values than many existing class imbalance learning methods. (C) 2016 Elsevier Ltd. All rights reserved.