COVID-19 Screening in Chest X-Ray Images Using Lung Region Priors

• Main Authors: An, J. (Author), Cai, Q. (Author), Gao, Z. (Author), Qu, Z. (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2021
• Subjects: Article; Biological organs; chest X-ray image; Chest X-ray image; Classification networks; convolutional neural network; coronavirus disease 2019; COVID-19; Cross-domain; Deep learning; Deep Learning; Diagnosis; diagnostic imaging; Domain adaptation; Early diagnosis; Health-care system; human; Humans; image segmentation; learning; learning algorithm; lung; Lung; lung disease; lung segmentation; Lung segmentation; machine learning; mathematical model; multi-appearance; pneumonia; Prior knowledge; SARS-CoV-2; thorax radiography; training; tuberculosis; Unsupervised domain adaptation; X ray; X-Rays
• Online Access: View Fulltext in Publisher

 Early screening of COVID-19 is essential for pandemic control, and thus to relieve stress on the health care system. Lung segmentation from chest X-ray (CXR) is a promising method for early diagnoses of pulmonary diseases. Recently, deep learning has achieved great success in supervised lung segmentation. However, how to effectively utilize the lung region in screening COVID-19 still remains a challenge due to domain shift and lack of manual pixel-level annotations. We hereby propose a multi-appearance COVID-19 screening framework by using lung region priors derived from CXR images. Firstly, we propose a multi-scale adversarial domain adaptation network (MS-AdaNet) to boost the cross-domain lung segmentation task as the prior knowledge to the classification network. Then, we construct a multi-appearance network (MA-Net), which is composed of three sub-networks to realize multi-appearance feature extraction and fusion using lung region priors. At last, we can obtain prediction results from normal, viral pneumonia, and COVID-19 using the proposed MA-Net. We extend the proposed MS-AdaNet for lung segmentation task on three different public CXR datasets. The results suggest that the MS-AdaNet outperforms contrastive methods in cross-domain lung segmentation. Moreover, experiments reveal that the proposed MA-Net achieves accuracy of 98.83\% and F1-score of 98.71\% on COVID-19 screening. The results indicate that the proposed MA-Net can obtain significant performance on COVID-19 screening. © 2013 IEEE.