Research on pneumonia classification based on improved ResNet50
Pages 288 - 296
Abstract
Applying deep learning to medical image recognition for identification and recognition can greatly alleviate the limited medical resources, avoid human error and human error, and greatly improve the efficiency of diagnosis. This study used a dataset of chest X-ray images identified by COVID-19, including normal, COVID-19 and other pneumonia categories, and performed a simple pre-processing operation on the sample data. Secondly, by improving ResNet50 model and integrating attention mechanism, SE module, ECA module and CBAM module are embedded respectively on the basis of ResNet50 network. The ECA-ResNet50 model with high recognition rate was obtained, and its recognition accuracy was 99.23%, accuracy 98.36%, recall rate 99.17%, F1 value 98.76. Compared with other original models, the accuracy and efficiency of ECA-ResNet50 model in the novel coronavirus pneumonia lung ct image dataset have been improved. Based on the limited COVID-19 image samples, this paper overcomes the shortcomings of traditional deep learning models that require a large amount of training data, and establishes an efficient, accurate multi-classification model with strong feature transfer ability.
References
[1]
Miao Yanru. Deep learning-based CT image repair of spinal tumors [D]. University of Chinese Academy of Sciences, China (shenzhen institutes of advanced technology, Chinese Academy of Sciences), 2020. The /, dc nki. GSZXJ. 2020.000062.
[2]
JU Weixin, Zhao Ximei, Wei Bin Recognition of liver cirrhosis by GoogleNet-PNN model [J]. Computer Engineering and Applications, 2019, 55(05): 112-117.
[3]
Sun Jai. Study on intelligent analysis of pathological characteristics of pulmonary nodules CT images and key techniques of information retrieval based on image features [D]. Shanghai Institute of Technical Physics, University of Chinese Academy of Sciences, 2017.
[4]
Li Q, Cai W, Wang X, Medical image classification with convolutional neural network[C]//International Conference on Control Automation Robotics & Vision. IEEE, 2014. The / ICARCV. 2014.7064414.
[5]
Chen L Y. Diagnosis of oral and maxillofacial surgery diseases based on deep learning [D]. Nanjing University, 2019. (in Chinese)
[6]
Tara N. Sainath, Brian Kingsbury, George Saon, Hagen Soltau, Abdel-rahman Mohamed, George Dahl, Bhuvana Ramabhadran, Deep Convolutional Neural Networks for Large-scale Speech Tasks, Neural Networks, Volume 64, 2015.
[7]
Journal of Central South University (Medical Science Edition), 2020, 45(03): 262-268.
[8]
Ding Yi, Huang Zengfa, ZHAO Shengchao Analysis of clinical and imaging characteristics of novel coronavirus pneumonia (COVID-19) [J]. Practice of radiology, 2020, 35 (3) : 281-285. The / j.carol carroll nki. 1000-0313.2020.03.008.
[9]
Wang JC, Liu JP, Wang YUanyuan, Dynamic changes of chest CT imaging in patients with COVID-19 [J]. Journal of Zhejiang University (Medical Science Edition), 2019, 49(02):191-197.
[10]
Cao Jia, Zhou Jun, Liao Xingnan Clinical features and CT signs of elderly patients with novel coronavirus pneumonia [J]. Journal of Wuhan University (Medical Edition), 2019, 41(04): 551-554. J.1671-8852.2020.0087.
[11]
Song Y, Zheng S, Li L,et al. Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19)with CT images [J].Cold Spring Harbor Laboratory Press, 2020.
[12]
Gozes O, Frid-Adar M, Greenspan H,et al.Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for Automated Detection & Patient Monitoring using Deep Learning CT Image Analysis [J].arXiv e-prints, 2020.
[13]
Xu X, Jiang X, Ma C,et al. Deep Learning System to Screen Coronavirus Disease 2019 Pneumonia[J].arXiv, 2020.
[14]
Saeedi A, Saeedi M, Maghsoudi A. A Novel and Reliable Deep Learning Web-Based Tool to Detect COVID-19 Infection from Chest CT-Scan [J]. 2020.
[15]
Chen X, Yao L, Zhou T,et al. Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images [J].Pattern recognition, 2021, 113:107826.
[16]
Saeedi A, Saeedi M, Maghsoudi A .A Novel and Reliable Deep Learning Web-Based Tool to Detect COVID-19 Infection from Chest CT-Scan [J]. 2020.
[17]
Narin A, Kaya C, Pamuk Z .Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks [J]. 2020.
Index Terms
- Research on pneumonia classification based on improved ResNet50
Recommendations
CT2CXR: CT-based CXR Synthesis for Covid-19 Pneumonia Classification
Machine Learning in Medical ImagingAbstractChest X-ray (CXR) is a common imaging modality for examination of pneumonia. However, some pneumonia signs which are visible in CT may not be clearly identifiable in CXR. It is challenging to create a good ground truth for positive pneumonia cases ...
Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans
Abstract BackgroundThe coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically ...
Highlights- MIP can identify changes in vascular morphology and COVID-19 lesions in CT images.
An improved approach of lung image segmentation based on watershed algorithm
ICIMCS '15: Proceedings of the 7th International Conference on Internet Multimedia Computing and ServiceAs a preprocessing step of chest Computed Tomography (CT) images, lung segmentation is significant for the diagnosis of lung disease. The traditional watershed algorithm is sensitive to the noise and has the drawback of over-segmentation problem. This ...
Comments
Information & Contributors
Information
Published In
October 2023
1809 pages
ISBN:9798400708305
DOI:10.1145/3650400
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 17 April 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
EITCE 2023
EITCE 2023: 2023 7th International Conference on Electronic Information Technology and Computer Engineering
October 20 - 22, 2023
Xiamen, China
Acceptance Rates
Overall Acceptance Rate 508 of 972 submissions, 52%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 16Total Downloads
- Downloads (Last 12 months)16
- Downloads (Last 6 weeks)3
Reflects downloads up to 20 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format