Cargando…
Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression
Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9313959/ https://www.ncbi.nlm.nih.gov/pubmed/35898478 http://dx.doi.org/10.1155/2022/8415187 |
_version_ | 1784754202626490368 |
---|---|
author | Yang, Chao-Peng Zhu, Jian-Qing Yan, Tan Su, Qiu-Ling Zheng, Li-Xin |
author_facet | Yang, Chao-Peng Zhu, Jian-Qing Yan, Tan Su, Qiu-Ling Zheng, Li-Xin |
author_sort | Yang, Chao-Peng |
collection | PubMed |
description | Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods can effectively eliminate similar problems. However, the complex network structure and redundant parameters of deep neural networks and the limited storage and computing resources of clinical medical hardware devices make it difficult for this method to use widely in clinical practice. Therefore, this paper studies a lightweight pneumonia classification network, CPGResNet50 (ResNet50 with custom channel pruning and ghost methods), based on ResNet50 pruning and compression to better meet the application requirements of clinical pneumonia auxiliary diagnosis with high precision and low memory. First, based on the hierarchical channel pruning method, the channel after the convolutional layer in the bottleneck part of the backbone network layer is used as the pruning object, and the pruning operation is performed after its normalization to obtain a network model with a high compression ratio. Second, the pruned convolutional layers are decomposed into original convolutions and cheap convolutions using the optimized convolution method. The feature maps generated by the two convolution parts are combined as the input to the next convolutional layer. Further, we conducted many experiments using pneumonia X-ray medical image data. The results show that the proposed method reduces the number of parameters of the ResNet50 network model from 23.7 M to 3.455 M when the pruning rate is 90%, a reduction is more than 85%, FIOPs dropped from 4.12G to 523.09 M, and the speed increased by more than 85%. The model training accuracy error remained within 1%. Therefore, the proposed method has a good performance in the auxiliary diagnosis of pneumonia and obtained good experimental results. |
format | Online Article Text |
id | pubmed-9313959 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-93139592022-07-26 Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression Yang, Chao-Peng Zhu, Jian-Qing Yan, Tan Su, Qiu-Ling Zheng, Li-Xin Comput Math Methods Med Research Article Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods can effectively eliminate similar problems. However, the complex network structure and redundant parameters of deep neural networks and the limited storage and computing resources of clinical medical hardware devices make it difficult for this method to use widely in clinical practice. Therefore, this paper studies a lightweight pneumonia classification network, CPGResNet50 (ResNet50 with custom channel pruning and ghost methods), based on ResNet50 pruning and compression to better meet the application requirements of clinical pneumonia auxiliary diagnosis with high precision and low memory. First, based on the hierarchical channel pruning method, the channel after the convolutional layer in the bottleneck part of the backbone network layer is used as the pruning object, and the pruning operation is performed after its normalization to obtain a network model with a high compression ratio. Second, the pruned convolutional layers are decomposed into original convolutions and cheap convolutions using the optimized convolution method. The feature maps generated by the two convolution parts are combined as the input to the next convolutional layer. Further, we conducted many experiments using pneumonia X-ray medical image data. The results show that the proposed method reduces the number of parameters of the ResNet50 network model from 23.7 M to 3.455 M when the pruning rate is 90%, a reduction is more than 85%, FIOPs dropped from 4.12G to 523.09 M, and the speed increased by more than 85%. The model training accuracy error remained within 1%. Therefore, the proposed method has a good performance in the auxiliary diagnosis of pneumonia and obtained good experimental results. Hindawi 2022-07-18 /pmc/articles/PMC9313959/ /pubmed/35898478 http://dx.doi.org/10.1155/2022/8415187 Text en Copyright © 2022 Chao-Peng Yang et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Yang, Chao-Peng Zhu, Jian-Qing Yan, Tan Su, Qiu-Ling Zheng, Li-Xin Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title | Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title_full | Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title_fullStr | Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title_full_unstemmed | Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title_short | Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression |
title_sort | auxiliary pneumonia classification algorithm based on pruning compression |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9313959/ https://www.ncbi.nlm.nih.gov/pubmed/35898478 http://dx.doi.org/10.1155/2022/8415187 |
work_keys_str_mv | AT yangchaopeng auxiliarypneumoniaclassificationalgorithmbasedonpruningcompression AT zhujianqing auxiliarypneumoniaclassificationalgorithmbasedonpruningcompression AT yantan auxiliarypneumoniaclassificationalgorithmbasedonpruningcompression AT suqiuling auxiliarypneumoniaclassificationalgorithmbasedonpruningcompression AT zhenglixin auxiliarypneumoniaclassificationalgorithmbasedonpruningcompression |