Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning
Radiomics, an emerging discipline in medical imaging, focuses on extracting detailed quantitative features from images to unveil subtle patterns imperceptible to the naked eye. This study specifically employs radiomics and machine learning techniques to discern cases of viral pneumonia and COVID-19....
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10486890/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540570460880896 |
|---|---|
| author | A. Beena Godbin S. Graceline Jasmine |
| author_facet | A. Beena Godbin S. Graceline Jasmine |
| author_sort | A. Beena Godbin |
| collection | DOAJ |
| description | Radiomics, an emerging discipline in medical imaging, focuses on extracting detailed quantitative features from images to unveil subtle patterns imperceptible to the naked eye. This study specifically employs radiomics and machine learning techniques to discern cases of viral pneumonia and COVID-19. By harnessing intricate radiomic features derived from medical images, the objective is to train a machine learning model capable of accurately distinguishing between patients with viral pneumonia, COVID-19, and those unaffected. To optimize the performance of machine learning models, the paper incorporates genetic algorithms for hyperparameter optimization. A comparative analysis is conducted among the genetic algorithm-based TPOT (Tree-based Pipeline Optimization Tool) settings, namely TPOT-Default, TPOT-Light, and TPOT-Sparse, to select the most effective hyperparameters. Custom modifications are introduced to the TPOT model to align it with the specific requirements of the current model, resulting in a noteworthy achievement. The proposed model attains a remarkable 94% AUC (Area Under the Curve) when employing the Random Forest algorithm. Furthermore, the study systematically evaluates the execution time taken by each TPOT model. The model’s performance is comprehensively assessed through key metrics, including accuracy, precision, sensitivity, specificity, and F1-score. The techniques suggested in this article could aid radiologists in identifying anomalies in chest X-ray (CXR) images, offering a more accurate and efficient interpretation to improve medical decision-making. |
| format | Article |
| id | doaj-art-f3d308a611ce4ddc8b1011bb53c134f2 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-f3d308a611ce4ddc8b1011bb53c134f22025-02-05T00:00:45ZengIEEEIEEE Access2169-35362024-01-0112476564767110.1109/ACCESS.2024.338378110486890Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine LearningA. Beena Godbin0S. Graceline Jasmine1https://orcid.org/0000-0001-6267-2433School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaRadiomics, an emerging discipline in medical imaging, focuses on extracting detailed quantitative features from images to unveil subtle patterns imperceptible to the naked eye. This study specifically employs radiomics and machine learning techniques to discern cases of viral pneumonia and COVID-19. By harnessing intricate radiomic features derived from medical images, the objective is to train a machine learning model capable of accurately distinguishing between patients with viral pneumonia, COVID-19, and those unaffected. To optimize the performance of machine learning models, the paper incorporates genetic algorithms for hyperparameter optimization. A comparative analysis is conducted among the genetic algorithm-based TPOT (Tree-based Pipeline Optimization Tool) settings, namely TPOT-Default, TPOT-Light, and TPOT-Sparse, to select the most effective hyperparameters. Custom modifications are introduced to the TPOT model to align it with the specific requirements of the current model, resulting in a noteworthy achievement. The proposed model attains a remarkable 94% AUC (Area Under the Curve) when employing the Random Forest algorithm. Furthermore, the study systematically evaluates the execution time taken by each TPOT model. The model’s performance is comprehensively assessed through key metrics, including accuracy, precision, sensitivity, specificity, and F1-score. The techniques suggested in this article could aid radiologists in identifying anomalies in chest X-ray (CXR) images, offering a more accurate and efficient interpretation to improve medical decision-making.https://ieeexplore.ieee.org/document/10486890/Radiomic featurechest X-rayviral pneumoniaCOVID-19machine learning |
| spellingShingle | A. Beena Godbin S. Graceline Jasmine Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning IEEE Access Radiomic feature chest X-ray viral pneumonia COVID-19 machine learning |
| title | Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning |
| title_full | Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning |
| title_fullStr | Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning |
| title_full_unstemmed | Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning |
| title_short | Leveraging Radiomics and Genetic Algorithms to Improve Lung Infection Diagnosis in X-Ray Images Using Machine Learning |
| title_sort | leveraging radiomics and genetic algorithms to improve lung infection diagnosis in x ray images using machine learning |
| topic | Radiomic feature chest X-ray viral pneumonia COVID-19 machine learning |
| url | https://ieeexplore.ieee.org/document/10486890/ |
| work_keys_str_mv | AT abeenagodbin leveragingradiomicsandgeneticalgorithmstoimprovelunginfectiondiagnosisinxrayimagesusingmachinelearning AT sgracelinejasmine leveragingradiomicsandgeneticalgorithmstoimprovelunginfectiondiagnosisinxrayimagesusingmachinelearning |