An end-to-end framework for diagnosing COVID-19 pneumonia via Parallel Recursive MLP module and Bi-LTSM correlation

Yiwen Liu, Wenyu Xing, Mingbo Zhao, MINGQUAN LIN
Medical Imaging with Deep Learning, PMLR 227:416-425, 2024.

Abstract

To fully extract the feature information of lung parenchyma in Chest X-ray images and realize the auxiliary diagnosis of COVID-19 pneumonia, this paper proposed an end-to-end deep learning model, which is mainly composed of object detection, depth feature generation, and multi-channel fusion classification. Firstly, the convolutional neural network (CNN) and region proposal network (RPN)-based object detection module was adopted to detect chest cavity region of interest (ROI). Then, according to the obtained coordinate information of ROI and the convolution feature map of original image, the new convolution feature maps of ROI were obtained with number of 13. By screening 4 representative feature maps form 4 convolution layers with different receptive fields and combining with original ROI image, the 5-dimensional (5D) feature maps were generated as the multi-channel input of classification module. Moreover, in each channel of classification module, three pyramidal recursive MLPs were employed to achieve cross-scale and cross-channel feature analysis. Finally, the correlation analysis of multi-channel output was realized by bi-directional long short memory (Bi-LSTM) module, and the auxiliary diagnosis of pneumonia disease was realized through fully connected layer and SoftMax function. Experimental results show that the proposed model has better classification performance and diagnosis effect than previous methods, with great clinical application potential.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-liu24a, title = {An end-to-end framework for diagnosing COVID-19 pneumonia via Parallel Recursive MLP module and Bi-LTSM correlation}, author = {Liu, Yiwen and Xing, Wenyu and Zhao, Mingbo and LIN, MINGQUAN}, booktitle = {Medical Imaging with Deep Learning}, pages = {416--425}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/liu24a/liu24a.pdf}, url = {https://proceedings.mlr.press/v227/liu24a.html}, abstract = {To fully extract the feature information of lung parenchyma in Chest X-ray images and realize the auxiliary diagnosis of COVID-19 pneumonia, this paper proposed an end-to-end deep learning model, which is mainly composed of object detection, depth feature generation, and multi-channel fusion classification. Firstly, the convolutional neural network (CNN) and region proposal network (RPN)-based object detection module was adopted to detect chest cavity region of interest (ROI). Then, according to the obtained coordinate information of ROI and the convolution feature map of original image, the new convolution feature maps of ROI were obtained with number of 13. By screening 4 representative feature maps form 4 convolution layers with different receptive fields and combining with original ROI image, the 5-dimensional (5D) feature maps were generated as the multi-channel input of classification module. Moreover, in each channel of classification module, three pyramidal recursive MLPs were employed to achieve cross-scale and cross-channel feature analysis. Finally, the correlation analysis of multi-channel output was realized by bi-directional long short memory (Bi-LSTM) module, and the auxiliary diagnosis of pneumonia disease was realized through fully connected layer and SoftMax function. Experimental results show that the proposed model has better classification performance and diagnosis effect than previous methods, with great clinical application potential.} }
Endnote
%0 Conference Paper %T An end-to-end framework for diagnosing COVID-19 pneumonia via Parallel Recursive MLP module and Bi-LTSM correlation %A Yiwen Liu %A Wenyu Xing %A Mingbo Zhao %A MINGQUAN LIN %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-liu24a %I PMLR %P 416--425 %U https://proceedings.mlr.press/v227/liu24a.html %V 227 %X To fully extract the feature information of lung parenchyma in Chest X-ray images and realize the auxiliary diagnosis of COVID-19 pneumonia, this paper proposed an end-to-end deep learning model, which is mainly composed of object detection, depth feature generation, and multi-channel fusion classification. Firstly, the convolutional neural network (CNN) and region proposal network (RPN)-based object detection module was adopted to detect chest cavity region of interest (ROI). Then, according to the obtained coordinate information of ROI and the convolution feature map of original image, the new convolution feature maps of ROI were obtained with number of 13. By screening 4 representative feature maps form 4 convolution layers with different receptive fields and combining with original ROI image, the 5-dimensional (5D) feature maps were generated as the multi-channel input of classification module. Moreover, in each channel of classification module, three pyramidal recursive MLPs were employed to achieve cross-scale and cross-channel feature analysis. Finally, the correlation analysis of multi-channel output was realized by bi-directional long short memory (Bi-LSTM) module, and the auxiliary diagnosis of pneumonia disease was realized through fully connected layer and SoftMax function. Experimental results show that the proposed model has better classification performance and diagnosis effect than previous methods, with great clinical application potential.
APA
Liu, Y., Xing, W., Zhao, M. & LIN, M.. (2024). An end-to-end framework for diagnosing COVID-19 pneumonia via Parallel Recursive MLP module and Bi-LTSM correlation. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:416-425 Available from https://proceedings.mlr.press/v227/liu24a.html.

Related Material