Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening
Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administe...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/9/1364 |
| _version_ | 1797505216821592064 |
|---|---|
| author | Chia-Hung Lin Feng-Zhou Zhang Jian-Xing Wu Ning-Sheng Pai Pi-Yun Chen Ching-Chou Pai Chung-Dann Kan |
| author_facet | Chia-Hung Lin Feng-Zhou Zhang Jian-Xing Wu Ning-Sheng Pai Pi-Yun Chen Ching-Chou Pai Chung-Dann Kan |
| author_sort | Chia-Hung Lin |
| collection | DOAJ |
| description | Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administering drugs and surgical treatments. In this study, we will establish a multilayer one-dimensional (1D) convolutional neural network (CNN)-based classifier for automatic cardiomegaly level screening based on chest X-ray (CXR) image classification in frontal posteroanterior view. Using two-round 1D convolutional processes in the convolutional pooling layer, two-dimensional (2D) feature maps can be converted into feature signals, which can enhance their characteristics for identifying normal condition and cardiomegaly levels. In the classification layer, a classifier based on gray relational analysis, which has a straightforward mathematical operation, is used to screen the cardiomegaly levels. Based on the collected datasets from the National Institutes of Health CXR image database, the proposed multilayer 1D CNN-based classifier with K-fold cross-validation has promising results for the intended medical purpose, with precision of 97.80%, recall of 98.20%, accuracy of 98.00%, and F1 score of 0.9799. |
| first_indexed | 2024-03-10T04:15:27Z |
| format | Article |
| id | doaj.art-d5ed035a77f949caada822cb1cfef84e |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T04:15:27Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-d5ed035a77f949caada822cb1cfef84e2023-11-23T08:02:32ZengMDPI AGElectronics2079-92922022-04-01119136410.3390/electronics11091364Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level ScreeningChia-Hung Lin0Feng-Zhou Zhang1Jian-Xing Wu2Ning-Sheng Pai3Pi-Yun Chen4Ching-Chou Pai5Chung-Dann Kan6Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung City 41170, TaiwanDivision of Cardiovascular Surgery, Show-Chwan Memorial Hospital, Changhua 500, TaiwanDivision of Cardiovascular Surgery, Department of Surgery, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan City 70101, TaiwanPalpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administering drugs and surgical treatments. In this study, we will establish a multilayer one-dimensional (1D) convolutional neural network (CNN)-based classifier for automatic cardiomegaly level screening based on chest X-ray (CXR) image classification in frontal posteroanterior view. Using two-round 1D convolutional processes in the convolutional pooling layer, two-dimensional (2D) feature maps can be converted into feature signals, which can enhance their characteristics for identifying normal condition and cardiomegaly levels. In the classification layer, a classifier based on gray relational analysis, which has a straightforward mathematical operation, is used to screen the cardiomegaly levels. Based on the collected datasets from the National Institutes of Health CXR image database, the proposed multilayer 1D CNN-based classifier with K-fold cross-validation has promising results for the intended medical purpose, with precision of 97.80%, recall of 98.20%, accuracy of 98.00%, and F1 score of 0.9799.https://www.mdpi.com/2079-9292/11/9/1364cardiomegalychest X-rayposteroanterior viewone-dimension convolutional neural networkgrey relational analysis |
| spellingShingle | Chia-Hung Lin Feng-Zhou Zhang Jian-Xing Wu Ning-Sheng Pai Pi-Yun Chen Ching-Chou Pai Chung-Dann Kan Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening Electronics cardiomegaly chest X-ray posteroanterior view one-dimension convolutional neural network grey relational analysis |
| title | Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening |
| title_full | Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening |
| title_fullStr | Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening |
| title_full_unstemmed | Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening |
| title_short | Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening |
| title_sort | posteroanterior chest x ray image classification with a multilayer 1d convolutional neural network based classifier for cardiomegaly level screening |
| topic | cardiomegaly chest X-ray posteroanterior view one-dimension convolutional neural network grey relational analysis |
| url | https://www.mdpi.com/2079-9292/11/9/1364 |
| work_keys_str_mv | AT chiahunglin posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT fengzhouzhang posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT jianxingwu posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT ningshengpai posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT piyunchen posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT chingchoupai posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening AT chungdannkan posteroanteriorchestxrayimageclassificationwithamultilayer1dconvolutionalneuralnetworkbasedclassifierforcardiomegalylevelscreening |