Department of Electronics and Communication Engineering, Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India.
Anna University, Chennai, Tamil Nadu, India.
J Xray Sci Technol. 2022;30(3):491-512. doi: 10.3233/XST-211113.
Although detection of COVID-19 from chest X-ray radiography (CXR) images is faster than PCR sputum testing, the accuracy of detecting COVID-19 from CXR images is lacking in the existing deep learning models.
This study aims to classify COVID-19 and normal patients from CXR images using semantic segmentation networks for detecting and labeling COVID-19 infected lung lobes in CXR images.
For semantically segmenting infected lung lobes in CXR images for COVID-19 early detection, three structurally different deep learning (DL) networks such as SegNet, U-Net and hybrid CNN with SegNet plus U-Net, are proposed and investigated. Further, the optimized CXR image semantic segmentation networks such as GWO SegNet, GWO U-Net, and GWO hybrid CNN are developed with the grey wolf optimization (GWO) algorithm. The proposed DL networks are trained, tested, and validated without and with optimization on the openly available dataset that contains 2,572 COVID-19 CXR images including 2,174 training images and 398 testing images. The DL networks and their GWO optimized networks are also compared with other state-of-the-art models used to detect COVID-19 CXR images.
All optimized CXR image semantic segmentation networks for COVID-19 image detection developed in this study achieved detection accuracy higher than 92%. The result shows the superiority of optimized SegNet in segmenting COVID-19 infected lung lobes and classifying with an accuracy of 98.08% compared to optimized U-Net and hybrid CNN.
The optimized DL networks has potential to be utilised to more objectively and accurately identify COVID-19 disease using semantic segmentation of COVID-19 CXR images of the lungs.
虽然从胸部 X 射线摄影（CXR）图像中检测 COVID-19 比 PCR 痰检测更快，但现有的深度学习模型在从 CXR 图像中检测 COVID-19 的准确性方面存在不足。
本研究旨在使用语义分割网络从 CXR 图像中对 COVID-19 和正常患者进行分类，以检测和标记 CXR 图像中 COVID-19 感染的肺叶。
为了从 CXR 图像中早期检测 COVID-19，提出并研究了三种结构不同的深度学习（DL）网络，即 SegNet、U-Net 和混合 CNN 与 SegNet 加 U-Net。此外，还使用灰狼优化（GWO）算法开发了优化的 CXR 图像语义分割网络，如 GWO SegNet、GWO U-Net 和 GWO 混合 CNN。在所提供的包含 2572 张 COVID-19 CXR 图像的公开数据集上，对所提出的 DL 网络及其 GWO 优化网络进行了训练、测试和验证，其中包括 2174 张训练图像和 398 张测试图像。还将这些 DL 网络及其 GWO 优化网络与其他用于检测 COVID-19 CXR 图像的最先进模型进行了比较。
本研究中开发的所有用于 COVID-19 图像检测的优化 CXR 图像语义分割网络的检测准确率均高于 92%。结果表明，优化后的 SegNet 在分割 COVID-19 感染的肺叶和分类方面具有优势，准确率为 98.08%，优于优化后的 U-Net 和混合 CNN。
优化后的 DL 网络具有潜力，可通过对 COVID-19 肺部 CXR 图像进行语义分割，更客观、更准确地识别 COVID-19 疾病。
