AUTHOR=Sun Weiwei , Pang Yu , Zhang Guo 

TITLE=CCT: Lightweight compact convolutional transformer for lung disease CT image classification

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.1066999

DOI=10.3389/fphys.2022.1066999

ISSN=1664-042X

ABSTRACT=The computed tomography (CT) imaging results are an important criterion for diagnosing Covid-19 cases. In patients with Covid-19, CT images clearly reveal the characteristics of lung lesions. Therefore, this study offers a Covid-19 chest CT detection model using a lightweight compact convolutional transformer (CCT) that uses chest CT images to build a new coronary pneumonia detection model. We added a position offset term and changed the attention mechanism of the transformer encoder to an axial attention mechanism module. Thus, the classification performance of the model was improved in terms of height and width. We show that the model efficiently classified COVID-19, community pneumonia, and normal conditions on the CC-CCII dataset. The proposed model outperforms other comparable models in the test set, achieving 98.5% accuracy and 98.6% sensitivity. The results show that our method achieves a larger receptive field on CT images, which positively impacts the CT image classification. Thus, this method can provide adequate assistance to clinicians.