Research on Classification of ConvNeXt Chest X-ray Images Based on Attention Mechanism

Baoyu Peng; Yimin Miao; Changyou Fu; Yi Wang

doi:10.54097/ijbls.v4i3.12

Authors

Baoyu Peng
Yimin Miao
Changyou Fu
Yi Wang

DOI:

https://doi.org/10.54097/ijbls.v4i3.12

Keywords:

Attention Mechanism, Transfer Learning, Chest X-ray, Disease Classification, Data Enhancement

Abstract

The global novel coronavirus pandemic has become the norm, and lung disease is one of the most important diseases at presentation In order to improve the reading efficiency and the accuracy of disease classification, this paper proposes a transfer learning model based on attention mechanism: CS ConvNeXt In the data preprocessing stage, the generalization ability of the model is improved by data augmentation, and in the model learning stage, the ConvNeXt network with attention mechanism is used to study and migrate to the proposed dataset COVIDx, and the model is tested by the COVIDx dataset in the testing stage Experiments show that the CS ConvNeXt transfer learning method can improve the accuracy of CXR image classification, and the average accuracy of Chest X-ray images for three categories reaches 98.18%, of which the accuracy for COVID-19 reaches 99.52%.

Downloads

Download data is not yet available.

References

Y. Yizhou, S. Dejun, M. Jiechao, and Z. Zhen, "Advances in application of artificial intelligence in medical image analysis," Chinese Journal of Medical Imaging Technology, Vol. 35(2019) No. 12, p. 1808-1812.

X. Baohong, D. Chong, and X. Guizhi, " research on the application of convolution neural network in the diagnosis of alzheimer's," disease Journal of Biomedical Engineering, Vol. 38(2021) No. 01, p. 169-177.

Z. Xiong, V. V. Fedorov, X. Fu, E. Cheng, and R. Macleod et al., "Fully automatic left atrium segmentation from late gadolinium enhanced magnetic resonance imaging using a dual fully convolutional neural network," Ieee Transactions On Medical Imaging, Vol. 38(2019) No. 2, p. 515-524.

W. Ying, L. Liangping, X. Bo, J. Huang, and Z. Luyu, "Classification and diaanosis of ultrasound images with breast tumors based on transfer learning," Chinese Journal of Medical Imaging Technology, Vol. 35(2019) No. 03, p. 357-360.

K. Padmavathi, M. V. Karki, and M. Bhat, "Medical image fusion of different modalities using dual tree complex wavelet transform with pca," in 2016 International Conference on Circuits, Controls, Communications and Computing (I4C), IEEE, Bangalore, India2016, p. 1-5.

X. Wang, Y. Peng, Le Lu, Z. Lu, and M. Bagheri et al., "Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI, USA, 2017, p. 3462-3471.

L. Yao, J. Prosky, E. Poblenz, B. Covington, and K. Lyman, "Weakly supervised medical diagnosis and localization from multiple resolutions," arXiv e-prints,2018, p. 1803-7703.

Z. Zhirui, L. Qiang, and G. Xin, "Multilabel chest x-ray disease classification based on a dense squeeze-and-excitation network," Journal of lmage and Graphics, Vol. 25(2020) No. 10, p. 2238-2248.

T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, and O. Yildirim et al., "Automated detection of covid-19 cases using deep neural networks with x-ray images," Computers in Biology and Medicine, Vol. 121(2020), p. 103792.

C. Wenjuan and Y. Guoqing, "Lmproved cxr image classification algorithm based on xdense-rc-net," Application Research of Computers, Vol. 39(2022) No. 12, p. 3803-3807.

S. Lingyun, L. Qiang, G. Xin, and D. Xuewen, "Disease classification algorithm of chest -ray based on efficient channel attention," Laser & Optoelectronics Progress, Vol. 60(2023) No. 12, p. 360-369.

P. Yu, B. Rui, W. Huiqian, and H. Zhiwei, "Research progress of antiphage defense systems in bacteria," Life Science Instruments, Vol. 20(2022) No. 02, p. 44-50.

K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Las Vegas, NV, USA, 2016, p. 770-778.

T. D. Pham, "Classification of covid-19 chest x-rays with deep learning: new models or fine tuning?" Health Information Science and Systems, Vol. 9(2020) No. 1, p. 2.

J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, UT, USA, 2018, p. 7132-7141.

S. Woo, J. Park, J. Lee, and I. S. Kweon, "Cbam: convolutional block attention module," in Computer Vision – ECCV 2018, Springer International Publishing, Cham,2018, p. 3-19.