Tuberculosis and COVID-19 severity assessment in computed tomography images: a multi-model deep learning approach

Tuberculosis and COVID-19 diseases are both lung-infected diseases. While tuberculosis is a bacterial infection, COVID-19 is a virus infection. Both diseases are deadly but can be treated if detected early. Several researchers have employed the analysis of lung CT scans in the diagnosis and detection of both diseases. In this paper, we address the segmentation of tuberculosis and COVID-19-infected lung areas and the severity assessment of the diseases. DAvoU-Net, a 3D-Unet segmentation network, was first used to segment the affected areas of the lung CT scans. Afterwards, a 3D CNN model was employed to extract the spatial image features from tuberculosis and COVID-19 datasets. The extracted spatial features from the 3D CNN were fused with sequential features extracted by a Bi-LSTM model. An improved weighted average fusion method merged the spatial and sequential features from the 3D-CNN and Bi-LSTM models. The comparative performance of the novel improved weighted average fusion method with previously used fusion methods shows that it outperformed the previously used fusion methods. It generated an overall classification accuracy of 94.5% and 97.2% on tuberculosis and COVID-19 datasets, respectively.