Machine Learning Model Based on Radiomic Features for Differentiation between COVID-19 and Pneumonia on Chest X-rayopen access
- Authors
- Kim, Young Jae
- Issue Date
- Sep-2022
- Publisher
- MDPI
- Keywords
- COVID-19; pneumonia; radiomic feature; machine learning; chest X-ray
- Citation
- SENSORS, v.22, no.17
- Journal Title
- SENSORS
- Volume
- 22
- Number
- 17
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85655
- DOI
- 10.3390/s22176709
- ISSN
- 1424-8220
- Abstract
- Machine learning approaches are employed to analyze differences in real-time reverse transcription polymerase chain reaction scans to differentiate between COVID-19 and pneumonia. However, these methods suffer from large training data requirements, unreliable images, and uncertain clinical diagnosis. Thus, in this paper, we used a machine learning model to differentiate between COVID-19 and pneumonia via radiomic features using a bias-minimized dataset of chest X-ray scans. We used logistic regression (LR), naive Bayes (NB), support vector machine (SVM), k-nearest neighbor (KNN), bagging, random forest (RF), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) to differentiate between COVID-19 and pneumonia based on training data. Further, we used a grid search to determine optimal hyperparameters for each machine learning model and 5-fold cross-validation to prevent overfitting. The identification performances of COVID-19 and pneumonia were compared with separately constructed test data for four machine learning models trained using the maximum probability, contrast, and difference variance of the gray level co-occurrence matrix (GLCM), and the skewness as input variables. The LGBM and bagging model showed the highest and lowest performances; the GLCM difference variance showed a high overall effect in all models. Thus, we confirmed that the radiomic features in chest X-rays can be used as indicators to differentiate between COVID-19 and pneumonia using machine learning.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 보건과학대학 > 의용생체공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85655)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.