TY - GEN
T1 - Pulmonary X-Ray Image Classification Using Deep Learning with Coordinate Attention and Meta-ACON Activation Function
AU - Chen, Hongkang
AU - Lu, Huijuan
AU - Chai, Zhuijun
AU - Zhu, Wenjie
AU - Huo, Wanli
AU - Yao, Yudong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Pneumonia is a serious health risk that usually examined by lung X-rays. Traditional deep learning models neglect image location information, fail to establish long-range dependencies and the limited ability to handle pneumonia features. In this paper, we propose MCANet model based on ResNet50 architecture by combining coordinate attention module and introducing a new activation function (Meta-ACON). The coordinate attention module in this model is used to capture positional information and establish long-range dependencies on feature maps. Meta-ACON activation function can adaptively select whether each neuron is activated, which contributes to dynamically handling pneumonia features. This paper performs comparison experiments on the public dataset ChestXray2020. Accuracy, Precision, Recall, and F1-score are used as evaluation metrics. Experiment results show that the MCANet improves each metrics compared with the original ResNet50 by 4.14%, 3.63%,4.25% and 3.99% respectively.
AB - Pneumonia is a serious health risk that usually examined by lung X-rays. Traditional deep learning models neglect image location information, fail to establish long-range dependencies and the limited ability to handle pneumonia features. In this paper, we propose MCANet model based on ResNet50 architecture by combining coordinate attention module and introducing a new activation function (Meta-ACON). The coordinate attention module in this model is used to capture positional information and establish long-range dependencies on feature maps. Meta-ACON activation function can adaptively select whether each neuron is activated, which contributes to dynamically handling pneumonia features. This paper performs comparison experiments on the public dataset ChestXray2020. Accuracy, Precision, Recall, and F1-score are used as evaluation metrics. Experiment results show that the MCANet improves each metrics compared with the original ResNet50 by 4.14%, 3.63%,4.25% and 3.99% respectively.
KW - attention mechanism
KW - linear and nonlinear
KW - long-range dependencies
KW - Pneumonia X-ray
KW - ResNet50
UR - http://www.scopus.com/inward/record.url?scp=85192478995&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192478995&partnerID=8YFLogxK
U2 - 10.1109/ITME60234.2023.00059
DO - 10.1109/ITME60234.2023.00059
M3 - Conference contribution
AN - SCOPUS:85192478995
T3 - Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023
SP - 250
EP - 255
BT - Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023
T2 - 13th International Conference on Information Technology in Medicine and Education, ITME 2023
Y2 - 24 November 2023 through 26 November 2023
ER -