ANC: Attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block Attention Module
Yudong Zhang, Xin Zhang, Wei‐Guo Zhu
Abstract
Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network for COVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed to avoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structure of which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracy of our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: This proposed ANC method is superior to 9 state-of-the-art approaches.
Topics & Concepts
OverfittingCoronavirus disease 2019 (COVID-19)Block (permutation group theory)Computer scienceConvolutional neural networkAttention networkArtificial intelligenceMachine learningAlgorithmPattern recognition (psychology)Artificial neural networkMathematicsMedicineGeometryPathologyInfectious disease (medical specialty)DiseaseCOVID-19 diagnosis using AIAnomaly Detection Techniques and ApplicationsMachine Learning in Healthcare