ANC: Attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block Attention Module

被引：43

作者：

Zhang, Yudong ^{[1
,3
]}

Zhang, Xin ^{[2
]}

Zhu, Weiguo ^{[1
]}

机构：

[1] Huaiyin Inst Technol, Jiangsu Key Lab Adv Mfg Technol, Huaian 223003, Peoples R China

[2] Fourth Peoples Hosp Huaian, Dept Med Imaging, Huaian 223002, Peoples R China

[3] Univ Leicester, Sch Informat, Leicester LE1 7RH, Leics, England

来源：

CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES | 2021年 / 127卷 / 03期

基金：

英国医学研究理事会;

关键词：

Deep learning; convolutional block attention module; attention mechanism; COVID-19; explainable diagnosis; CLASSIFICATION;

D O I：

10.32604/cmes.2021.015807

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

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.

引用

页码：1037 / 1058

页数：22

共 50 条

[41] Attention Based Residual Network for Effective Detection of COVID-19 and Viral Pneumonia
Nawshad, Muhammad Aasharib
Shami, Usama Aleem
Sajid, Sana
Fraz, Muhammad Moazam
2021 INTERNATIONAL CONFERENCE ON DIGITAL FUTURES AND TRANSFORMATIVE TECHNOLOGIES (ICODT2), 2021,
[42] Fault Diagnosis for Power Batteries Based on a Stacked Sparse Autoencoder and a Convolutional Block Attention Capsule Network
Zhou, Juan
Zhang, Shun
Wang, Peng
PROCESSES, 2024, 12 (04)
[43] Tea bud detection based on multi-scale convolutional block attention module
Gui, Jiangsheng
Wu, Dongwei
Xu, Huirong
Chen, Jianneng
Tong, Junhua
JOURNAL OF FOOD PROCESS ENGINEERING, 2024, 47 (02)
[44] Improved skeleton-based activity recognition using convolutional block attention module
Qin, Jing
Zhang, Shugang
Wang, Yiguo
Yang, Fei
Zhong, Xin
Lu, Weigang
COMPUTERS & ELECTRICAL ENGINEERING, 2024, 116
[45] A lightweight method for maize seed defects identification based on Convolutional Block Attention Module
Li, Chao
Chen, Zhenyu
Jing, Weipeng
Wu, Xiaoqiang
Zhao, Yonghui
FRONTIERS IN PLANT SCIENCE, 2023, 14
[46] Automatic Severity Classification of Diabetic Retinopathy Based on DenseNet and Convolutional Block Attention Module
Farag, Mohamed M.
Fouad, Mariam
Abdel-Hamid, Amr T.
IEEE ACCESS, 2022, 10 : 38299 - 38308
[47] Detection of solar panel defects based on separable convolution and convolutional block attention module
Yang, Xiyun
Zhang, Qiao
Wang, Shuyan
Zhao, Ya
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2023, 45 (03) : 7136 - 7149
[48] Convolutional block attention module based on visual mechanism for robot image edge detection
Ju, Aiyun
Wang, Zhongli
EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS, 2022, 9 (36)
[49] Non-intrusive Load Disaggregate Algorithm Based on Convolutional Block Attention Module
Xu X.
Zhao S.
Cui K.
Dianwang Jishu/Power System Technology, 2021, 45 (09): : 3700 - 3705
[50] CHANGE DETECTION IN SYNTHETIC APERTURE RADAR IMAGES BASED ON CONVOLUTIONAL BLOCK ATTENTION MODULE
Wang, Dong
Gao, Feng
Dong, Junyu
Wang, Shengke
2019 10TH INTERNATIONAL WORKSHOP ON THE ANALYSIS OF MULTITEMPORAL REMOTE SENSING IMAGES (MULTITEMP), 2019,

← 1 2 3 4 5 →