[论文解读] Development of a Machine-Learning System to Classify Lung CT Scan Images into Normal/COVID-19 Class

Seifedine Kadry, V. Rajinikanth+4 more|arXiv (Cornell University)|Apr 24, 2020

COVID-19 diagnosis using AI参考文献 53被引用 33

一句话总结

本文提出使用 Chaotic Bat Algorithm 和 Kapur’s Entropy 阈值法来提升肺部 CT 层级，然后进行特征提取/选择及两类分类器，使用融合特征向量的 SVM 最高可达 89.80% 的准确率。

ABSTRACT

Recently, the lung infection due to Coronavirus Disease (COVID-19) affected a large human group worldwide and the assessment of the infection rate in the lung is essential for treatment planning. This research aims to propose a Machine-Learning-System (MLS) to detect the COVID-19 infection using the CT scan Slices (CTS). This MLS implements a sequence of methods, such as multi-thresholding, image separation using threshold filter, feature-extraction, feature-selection, feature-fusion and classification. The initial part implements the Chaotic-Bat-Algorithm and Kapur's Entropy (CBA+KE) thresholding to enhance the CTS. The threshold filter separates the image into two segments based on a chosen threshold 'Th'. The texture features of these images are extracted, refined and selected using the chosen procedures. Finally, a two-class classifier system is implemented to categorize the chosen CTS (n=500 with a pixel dimension of 512x512x1) into normal/COVID-19 group. In this work, the classifiers, such as Naive Bayes (NB), k-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF) and Support Vector Machine with linear kernel (SVM) are implemented and the classification task is performed using various feature vectors. The experimental outcome of the SVM with Fused-Feature-Vector (FFV) helped to attain a detection accuracy of 89.80%.

研究动机与目标

• 快速 COVID-19 从 CT 扫描中检测以用于治疗规划和分诊的需求动机。
• 提出一个能够增强 CT 切片并提取辨别性纹理特征的机器学习工作流。
• 评估多种分类器以识别 Normal 与 COVID-19 分类的有效模型。

提出的方法

• 应用 Chaotic Bat Algorithm 和 Kapur’s Entropy 阈值化来增强 CT 切片。
• 执行基于阈值的图像分离，在选定阈值 Th 处创建两个分段。
• 从分割图像中提取、提炼并选择纹理特征。
• 通过融合方案融合特征向量并训练一个两类分类器。
• 在各种特征向量下评估 Naive Bayes、KNN、Decision Tree、Random Forest，以及线性 SVM。

实验结果

研究问题

• RQ1 阈值化增强结合纹理特征是否能够有效区分 Normal 与 COVID-19 CT 切片？
• RQ2 在给定数据集上，哪种分类器及特征向量配置能够获得最高的 Normal/ COVID-19 分类准确率？

主要发现

• 使用融合特征向量的 SVM 达到 89.80% 的检测准确率。
• 本研究测试了多种分类器，发现在 NB、KNN、DT、RF 与 SVM 的组合中，SVM（FFV）表现最好。
• 所用 CT 切片数据集：n=500，大小为 512x512x1。