Department of Physics, Faculty of Mathematics and Natural Sciences, Brawijaya University, Malang, East Java, Indonesia.
Department of Radiology, Faculty of Medicine, Brawijaya University, East Java, Malang, Indonesia.
J Xray Sci Technol. 2022;30(1):57-71. doi: 10.3233/XST-211005.
Analysis of chest X-ray images is one of the primary standards in diagnosing patients with COVID-19 and pneumonia, which is faster than using PCR Swab method. However, accuracy of using X-ray images needs to be improved.
To develop a new deep learning system of chest X-ray images and evaluate whether it can quickly and accurately detect pneumonia and COVID-19 patients.
The developed deep learning system (UBNet v3) uses three architectural hierarchies, namely first, to build an architecture containing 7 convolution layers and 3 ANN layers (UBNet v1) to classify between normal images and pneumonia images. Second, using 4 layers of convolution and 3 layers of ANN (UBNet v2) to classify between bacterial and viral pneumonia images. Third, using UBNet v1 to classify between pneumonia virus images and COVID-19 virus infected images. An open-source database with 9,250 chest X-ray images including 3,592 COVID-19 images were used in this study to train and test the developed deep learning models.
CNN architecture with a hierarchical scheme developed in UBNet v3 using a simple architecture yielded following performance indices to detect chest X-ray images of COVID-19 patients namely, 99.6%accuracy, 99.7%precision, 99.7%sensitivity, 99.1%specificity, and F1 score of 99.74%. A desktop GUI-based monitoring and classification system supported by a simple CNN architecture can process each chest X-ray image to detect and classify COVID-19 image with an average time of 1.21 seconds.
Using three hierarchical architectures in UBNet v3 improves system performance in classifying chest X-ray images of pneumonia and COVID-19 patients. A simple architecture also speeds up image processing time.
分析胸部 X 光图像是诊断 COVID-19 和肺炎患者的主要标准之一，其速度快于使用 PCR 拭子方法。然而，X 光图像的准确性需要提高。
开发一种新的胸部 X 光图像深度学习系统，并评估其是否能快速准确地检测肺炎和 COVID-19 患者。
所开发的深度学习系统（UBNet v3）使用三个架构层次，首先，构建一个包含 7 个卷积层和 3 个 ANN 层的架构（UBNet v1），用于对正常图像和肺炎图像进行分类。其次，使用 4 个卷积层和 3 个 ANN 层（UBNet v2）对细菌性和病毒性肺炎图像进行分类。第三，使用 UBNet v1 对肺炎病毒图像和 COVID-19 病毒感染图像进行分类。本研究使用了一个包含 9250 张胸部 X 光图像的开源数据库，其中包括 3592 张 COVID-19 图像，用于训练和测试所开发的深度学习模型。
UBNet v3 中使用分层方案开发的 CNN 架构采用简单架构，其检测 COVID-19 患者胸部 X 光图像的性能指标如下：准确率 99.6%，精确率 99.7%，灵敏度 99.7%，特异性 99.1%，F1 得分为 99.74%。一个基于桌面 GUI 的监测和分类系统，支持简单的 CNN 架构，能够以平均 1.21 秒的速度处理每张胸部 X 光图像，以检测和分类 COVID-19 图像。
UBNet v3 中使用三个分层架构可提高肺炎和 COVID-19 患者胸部 X 光图像分类的系统性能。简单的架构还可加快图像处理时间。
