Department of Statistics, Institute of Science, Hacettepe University, Ankara, Turkey.
Institute of Biomedicine, Faculty of Medicine, University of Turku, Turku, Finland.
Big Data. 2023 Dec;11(6):420-436. doi: 10.1089/big.2022.0042. Epub 2023 Mar 16.
Coronavirus disease 2019 (COVID-19) is spreading rapidly around the world. Therefore, the classification of computed tomography (CT) scans alleviates the workload of experts, whose workload increased considerably during the pandemic. Convolutional neural network (CNN) architectures are successful for the classification of medical images. In this study, we have developed a new deep CNN architecture called OzNet. Moreover, we have compared it with pretrained architectures namely AlexNet, DenseNet201, GoogleNet, NASNetMobile, ResNet-50, SqueezeNet, and VGG-16. In addition, we have compared the classification success of three preprocessing methods with raw CT scans. We have not only classified the raw CT scans, but also have performed the classification with three different preprocessing methods, which are discrete wavelet transform (DWT), intensity adjustment, and gray to color red, green, blue image conversion on the data sets. Furthermore, it is known that the architecture's performance increases with the use of DWT preprocessing method rather than using the raw data set. The results are extremely promising with the CNN algorithms using the COVID-19 CT scans processed with the DWT. The proposed DWT-OzNet has achieved a high classification performance of more than 98.8% for each calculated metric.
2019 年冠状病毒病（COVID-19）正在全球迅速传播。因此，计算机断层扫描（CT）扫描的分类减轻了专家的工作量，在大流行期间，专家的工作量大大增加。卷积神经网络（CNN）架构在医学图像分类方面取得了成功。在这项研究中，我们开发了一种名为 OzNet 的新的深度 CNN 架构。此外，我们将其与预训练的架构（即 AlexNet、DenseNet201、GoogleNet、NASNetMobile、ResNet-50、SqueezeNet 和 VGG-16）进行了比较。此外，我们还比较了三种预处理方法与原始 CT 扫描的分类成功率。我们不仅对原始 CT 扫描进行了分类，而且还对三种不同的预处理方法（离散小波变换（DWT）、强度调整以及灰度到红、绿、蓝图像的转换）对数据集进行了分类。此外，众所周知，与使用原始数据集相比，使用 DWT 预处理方法可以提高架构的性能。使用 DWT 处理的 COVID-19 CT 扫描的 CNN 算法的结果非常有希望，其每个计算指标的分类性能均超过 98.8%。
