融合Grad-CAM和卷积神经网络的COVID-19检测算法  

COVID-19 Detection Algorithm Combining Grad-CAM and Convolutional Neural Network

作　　者：朱炳宇 刘朕 张景祥[1] ZHU Bingyu;LIU Zhen;ZHANG Jingxiang(School of Science,Jiangnan University,Wuxi,Jiangsu 214122,China)

机构地区：[1]江南大学理学院,江苏无锡214122

出　　处：《计算机科学与探索》2022年第9期2108-2120,共13页Journal of Frontiers of Computer Science and Technology

基　　金：国家自然科学基金(61772239,11804123)。

摘　　要：新型冠状病毒肺炎(COVID-19)检测中胸部X射线(CXR图像)和电子计算机断层扫描(CT)图像是两种主要技术手段,为医生诊断提供了重要依据。针对当前卷积神经网络(CNN)在医学放射性图像中检测COVID-19的准确率不高、算法复杂、无法标记特征区域的问题,提出了一种融合梯度加权类激活映射(GradCAM)颜色可视化和卷积神经网络的算法(GCCV-CNN),对COVID-19阳性患者、COVID-19阴性患者、普通肺炎患者以及正常人的肺部CXR图像和CT扫描图像进行快速分类。通过定位到CXR图像和CT扫描图像中CNN进行分类的关键区域,再综合深度学习算法得到更准确的检测结果。为验证GCCV-CNN算法的有效性,分别在3个COVID-19阳性患者数据集上进行实验,并与已有算法进行比较。结果表明该算法对COVID-19阳性患者的CXR图像和CT扫描图像分类性能优于“新冠网络”(COVID-Net)算法及迁移学习新冠网络(DeTraCNet)算法,准确率最高达98.06%,速度更快的同时还具有较好的鲁棒性。In the detection of COVID-19, chest X-ray(CXR) images and CT scan images are two main technical methods, which provide an important basis for doctors’ diagnosis. Currently, convolutional neural network(CNN) in detecting the COVID-19 medical radioactive images has problems of low accuracy, complex algorithms, and inability to mark feature regions. In order to solve these problems, this paper proposes an algorithm combining Grad-CAM color visualization and convolutional neural network(GCCV-CNN). The algorithm can quickly classify lung X-ray images and CT scan images of COVID-19-positive patients, COVID-19-negative patients, general pneumonia patients and healthy people. At the same time, it can quickly locate the critical area in X-ray images and CT images. Finally, the algorithm can get more accurate detection results through the synthesis of deep learning algorithms. In order to verify the effectiveness of the GCCV-CNN algorithm, experiments are performed on three COVID-19-positive patient datasets and it is compared with existing algorithms. The results show that the classification performance of the algorithm is better than the COVID-Net algorithm and the DeTraC-Net algorithm. The GCCV-CNN algorithm achieves a high accuracy of 98.06%, which is faster and more robust.

关 键 词：CXR图像 CT扫描图像 COVID-19 Grad-CAM 融合Grad-CAM颜色可视化和CNN的算法(GCCV-CNN) 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]