Abstract:
In this paper, a novel strategy to perform high-dimensional feature selection using an evolutionary algorithm for the automatic classification of coronary stenosis is introduced. The method involves a feature extraction stage to form a bank of 473 features considering different types such as intensity, texture and shape. The feature selection task is carried out on a high-dimensional feature bank, where the search space is denoted by O(2n) and n=473. The proposed evolutionary search strategy was compared in terms of the Jaccard coefficient and accuracy classification with different state-of-the-art methods. The highest feature selection rate, along with the best classification performance, was obtained with a subset of four features, representing a 99% discrimination rate. In the last stage, the feature subset was used as input to train a support vector machine using an independent testing set. The classification of coronary stenosis cases involves a binary classification type by considering positive and negative classes. The highest classification performance was obtained with the four-feature subset in terms of accuracy (0.86) and Jaccard coefficient (0.75) metrics. In addition, a second dataset containing 2788 instances was formed from a public image database, obtaining an accuracy of 0.89 and a Jaccard Coefficient of 0.80. Finally, based on the performance achieved with the four-feature subset, they can be suitable for use in a clinical decision support system.
摘要:
在本文中,介绍了一种使用进化算法进行高维特征选择以自动分类冠状动脉狭窄的新策略.该方法涉及特征提取阶段,以形成473个特征库,考虑到不同类型,例如强度,纹理和形状。在高维特征库上执行特征选择任务,其中搜索空间由O(2n)表示,n=473。在Jaccard系数和精度分类方面,使用不同的最新方法对所提出的进化搜索策略进行了比较。最高的功能选择率,以及最佳的分类性能,是用四个特征的子集获得的,代表99%的歧视率。在最后阶段,特征子集被用作输入,使用独立的测试集训练支持向量机.冠状动脉狭窄病例的分类涉及通过考虑阳性和阴性类别的二元分类类型。在准确度(0.86)和Jaccard系数(0.75)度量方面,四特征子集获得了最高的分类性能。此外,包含2788个实例的第二个数据集是由公共图像数据库形成的,获得0.89的精度和0.80的Jaccard系数。最后,基于四特征子集实现的性能,它们可以适用于临床决策支持系统。