DARNet: Dual-Attention Residual Network for Automatic Diagnosis of COVID-19 via CT Images
2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021
; : 1528-1533, 2021.
Article
in English
| Scopus | ID: covidwho-1722894
ABSTRACT
The ongoing global pandemic of Coronavirus Disease 2019 (COVID-19) poses a serious threat to public health and the economy. Rapid and accurate diagnosis of COVID-19 is essential to prevent the further spread of the disease and reduce its mortality. Chest Computed tomography (CT) is an effective tool for the early diagnosis of lung diseases including pneumonia. However, detecting COVID-19 from CT is demanding and prone to human errors as some early-stage patients may have negative findings on images. Recently, many deep learning methods have achieved impressive performance in this regard. Despite their effectiveness, most of these methods underestimate the rich spatial information preserved in the 3D structure or suffer from the propagation of errors. To address this problem, we propose a Dual-Attention Residual Network (DARNet) to automatically identify COVID-19 from other common pneumonia (CP) and healthy people using 3D chest CT images. Specifically, we design a dual-attention module consisting of channel-wise attention and depth-wise attention mechanisms. The former is utilized to enhance channel independence, while the latter is developed to recalibrate the depth-level features. Then, we integrate them in a unified manner to extract and refine the features at different levels to further improve the diagnostic performance. We evaluate DARNet on a large public CT dataset and obtain superior performance. Besides, the ablation study and visualization analysis prove the effectiveness and interpretability of the proposed method. © 2021 IEEE.
attention module; chest CT; COVID-19 diagnosis; deep learning; residual network; Computerized tomography; Diagnosis; Health risks; Large dataset; Automatic diagnosis; Chest computed tomography; Computed tomography images; Coronavirus disease 2019 diagnose; Coronaviruses; Effective tool; Performance; Coronavirus
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS