AVNC: Attention-Based VGG-Style Network for COVID-19 Diagnosis by CBAM

• Published in: IEEE sensors journal Vol. 22; no. 18; pp. 17431 - 17438
• Main Authors: Wang, Shui-Hua, Fernandes, Steven Lawrence, Zhu, Ziquan, Zhang, Yu-Dong
• Format: Journal Article
• Language: English
• Published: United States IEEE 15.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Attention; Bacterial diseases; Computer networks; convolutional block attention module; convolutional neural network; COVID-19; diagnosis; Labeling; Lung; Modules; Testing; Three-dimensional displays; Ultrasonic imaging; VGG; covid-19; diagnosis; convolutional block attention module; convolutional neural network; Attention; VGG
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2021.3062442

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.