SAM: Self-augmentation mechanism for COVID-19 detection using chest X-ray images

作者：

Highlights：

• Feature augmentation is introduced to mitigate the current lack of sufficient annotated data.

• A combined CNN-BiLSTM is employed for the diagnosis of COVID-19 in a robust manner.

• Experimental results demonstrate state-of-the-art performance on three COVID-19 databases.

• PCA and t-SNE feature visualization has been utilized for the explainability of the proposed learning model.

摘要

•Feature augmentation is introduced to mitigate the current lack of sufficient annotated data.•A combined CNN-BiLSTM is employed for the diagnosis of COVID-19 in a robust manner.•Experimental results demonstrate state-of-the-art performance on three COVID-19 databases.•PCA and t-SNE feature visualization has been utilized for the explainability of the proposed learning model.

论文关键词：COVID-19 detection,Feature augmentation,Transfer learning,BiLSTM,RICA

论文评审过程：Received 12 August 2021, Revised 7 January 2022, Accepted 8 January 2022, Available online 17 January 2022, Version of Record 2 February 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108207