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

[21] An effective deep residual network based class attention layer with bidirectional LSTM for diagnosis and classification of COVID-19
Pustokhin, Denis A.
Pustokhina, Irina V.
Dinh, Phuoc Nguyen
Phan, Son Van
Nguyen, Gia Nhu
Joshi, Gyanendra Prasad
Shankar, K.
JOURNAL OF APPLIED STATISTICS, 2023, 50 (03) : 477 - 494
[22] Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing
Liu, Xiong
Finelli, Luca A.
Hersch, Greg L.
Khalil, Iya
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 3761 - 3766
[23] Densely connected attention network for diagnosing COVID-19 based on chest CT
Fu, Yu
Xue, Peng
Dong, Enqing
COMPUTERS IN BIOLOGY AND MEDICINE, 2021, 137
[24] Fault diagnosis of industrial robot based on dual-module attention convolutional neural network
Lu K.
Chen C.
Wang T.
Cheng L.
Qin J.
Autonomous Intelligent Systems, 2022, 2 (01):
[25] Attention-RefNet: Interactive Attention Refinement Network for Infected Area Segmentation of COVID-19
Kitrungrotsakul, Titinunt
Chen, Qingqing
Wu, Huitao
Iwamoto, Yutaro
Hu, Hongjie
Zhu, Wenchao
Chen, Chao
Xu, Fangyi
Zhou, Yong
Lin, Lanfen
Tong, Ruofeng
Li, Jingsong
Chen, Yen-Wei
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (07) : 2363 - 2373
[26] Nonlocal convolutional block attention module VNet for gliomas automatic segmentation
Fang, Ying
Huang, He
Yang, Weiji
Xu, Xiaomei
Jiang, Weiwei
Lai, Xiaobo
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2022, 32 (02) : 528 - 543
[27] Generative Adversarial Network Based on LSTM and Convolutional Block Attention Module for Industrial Smoke Image Recognition
Li, Dahai
Yang, Rui
Chen, Su
COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2023, 20 (04) : 1707 - 1728
[28] Structural Attention Graph Neural Network for Diagnosis and Prediction of COVID-19 Severity
Liu, Yanbei
Li, Henan
Luo, Tao
Zhang, Changqing
Xiao, Zhitao
Wei, Ying
Gao, Yaozong
Shi, Feng
Shan, Fei
Shen, Dinggang
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (02) : 557 - 567
[29] Tomato Leaf Disease Diagnosis Based on Improved Convolution Neural Network by Attention Module
Zhao, Shengyi
Peng, Yun
Liu, Jizhan
Wu, Shuo
AGRICULTURE-BASEL, 2021, 11 (07):
[30] FAM: focal attention module for lesion segmentation of COVID-19 CT images
Wu, Xiaoxin
Zhang, Zhihao
Guo, Lingling
Chen, Hui
Luo, Qiaojie
Jin, Bei
Gu, Weiyan
Lu, Fangfang
Chen, Jingjing
JOURNAL OF REAL-TIME IMAGE PROCESSING, 2022, 19 (06) : 1091 - 1104

← 1 2 3 4 5 →