Saad Mohamed H, Hashima Sherief, Sayed Wessam, El-Shazly Ehab H, Madian Ahmed H, Fouda Mostafa M
Radiation Engineering Department, National Center for Radiation Research and Technology (NCRRT), Egyptian Atomic Energy Authority, Cairo 11787, Egypt.
Engineering Department, Nuclear Research Center (NRC), Egyptian Atomic Energy Authority, Cairo 13759, Egypt.
Diagnostics (Basel). 2022 Dec 27;13(1):76. doi: 10.3390/diagnostics13010076.
Coronavirus disease (COVID-19) is a worldwide epidemic that poses substantial health hazards. However, COVID-19 diagnostic test sensitivity is still restricted due to abnormalities in specimen processing. Meanwhile, optimizing the highly defined number of convolutional neural network (CNN) hyperparameters (hundreds to thousands) is a useful direction to improve its overall performance and overcome its cons. Hence, this paper proposes an optimization strategy for obtaining the optimal learning rate and momentum of a CNN's hyperparameters using the grid search method to improve the network performance. Therefore, three alternative CNN architectures (GoogleNet, VGG16, and ResNet) were used to optimize hyperparameters utilizing two different COVID-19 radiography data sets (Kaggle (X-ray) and China national center for bio-information (CT)). These architectures were tested with/without optimizing the hyperparameters. The results confirm effective disease classification using the CNN structures with optimized hyperparameters. Experimental findings indicate that the new technique outperformed the previous in terms of accuracy, sensitivity, specificity, recall, F-score, false positive and negative rates, and error rate. At epoch 25, the optimized Resnet obtained high classification accuracy, reaching 98.98% for X-ray images and 98.78% for CT images.
冠状病毒病（COVID-19）是一种全球性流行病，会带来重大健康危害。然而，由于样本处理异常，COVID-19诊断测试的灵敏度仍然受到限制。同时，优化卷积神经网络（CNN）大量高度定义的超参数（数百到数千个）是提高其整体性能并克服其缺点的一个有用方向。因此，本文提出一种优化策略，使用网格搜索方法来获得CNN超参数的最优学习率和动量，以提高网络性能。为此，利用两个不同的COVID-19放射成像数据集（Kaggle（X射线）和中国国家生物信息中心（CT）），使用三种替代的CNN架构（GoogleNet、VGG16和ResNet）来优化超参数。对这些架构在优化超参数和未优化超参数的情况下进行了测试。结果证实，使用具有优化超参数的CNN结构可实现有效的疾病分类。实验结果表明，新技术在准确率、灵敏度、特异性、召回率、F分数、假阳性和假阴性率以及错误率方面均优于之前的技术。在第25个epoch时，优化后的Resnet获得了较高的分类准确率，X射线图像达到98.98%，CT图像达到98.78%。
