Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays

• Published in: Pattern recognition Vol. 110; p. 107613
• Main Authors: Wang, Zheng, Xiao, Ying, Li, Yong, Zhang, Jie, Lu, Fanggen, Hou, Muzhou, Liu, Xiaowei
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.02.2021
• Subjects: Chest X-ray (CXR); Community-acquired pneumonia (CAP); Computer-aided detection (CAD); COVID-19; Deep learning (DL); COVID-19; Computer-aided detection (CAD); Community-acquired pneumonia (CAP); Deep learning (DL); Chest X-ray (CXR)
• DOI: 10.1016/j.patcog.2020.107613
• ISSN: 0031-3203

•We proposed a novel framework, CHP-Net, to differentiate and localize COVID-19 from community acquired pneumonia.•We used excessive data augmentation to extend the available dataset and optimize the CHP-Net generalization capability.•Comparing to other ConvNet, CHP-Net works much more efficiently to extract feature information on chest X-Ray.•All metrics, including categorical loss, accuracy, precision, recall and F1-score, proved CHP-Net fits good for the task.•CHP-Net are better than the previous methods tested in detecting COVID-19 and exceeding to radiologist. The COVID-19 outbreak continues to threaten the health and life of people worldwide. It is an immediate priority to develop and test a computer-aided detection (CAD) scheme based on deep learning (DL) to automatically localize and differentiate COVID-19 from community-acquired pneumonia (CAP) on chest X-rays. Therefore, this study aims to develop and test an efficient and accurate deep learning scheme that assists radiologists in automatically recognizing and localizing COVID-19. A retrospective chest X-ray image dataset was collected from open image data and the Xiangya Hospital, which was divided into a training group and a testing group. The proposed CAD framework is composed of two steps with DLs: the Discrimination-DL and the Localization-DL. The first DL was developed to extract lung features from chest X-ray radiographs for COVID-19 discrimination and trained using 3548 chest X-ray radiographs. The second DL was trained with 406-pixel patches and applied to the recognized X-ray radiographs to localize and assign them into the left lung, right lung or bipulmonary. X-ray radiographs of CAP and healthy controls were enrolled to evaluate the robustness of the model. Compared to the radiologists’ discrimination and localization results, the accuracy of COVID-19 discrimination using the Discrimination-DL yielded 98.71%, while the accuracy of localization using the Localization-DL was 93.03%. This work represents the feasibility of using a novel deep learning-based CAD scheme to efficiently and accurately distinguish COVID-19 from CAP and detect localization with high accuracy and agreement with radiologists.