Automated Machine Learning Approach for COVID-19 Diagnosis Based on Deep Efficient Features from Chest CT Images

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{Singh:2025:procs,

• author = "Vipul Kumar Singh and Jyotismita Barman and Maheshkumar H. Kolekar",
• title = "Automated Machine Learning Approach for {COVID-19} Diagnosis Based on Deep Efficient Features from Chest {CT} Images",
• journal = "Procedia Computer Science",
• year = "2025",
• volume = "258",
• pages = "1414--1424",
• note = "International Conference on Machine Learning and Data Engineering",
• keywords = "genetic algorithms, genetic programming, AI diagnostics, automated machine learning, computerized tomography, COVID-19, deep learning, EfficientNet, TPOT, ANN",
• ISSN = "1877-0509",
• URL = "https://www.sciencedirect.com/science/article/pii/S1877050925014772",
• DOI = "doi:10.1016/j.procs.2025.04.374",
• abstract = "Computer-aided diagnostic systems using artificial intelligence tools are viable resources aiding clinicians in decision-making. However, with a surfeit of Machine Learning (ML) algorithms, selecting the most promising model with the right set of hyperpa-rameters is often quite challenging. This challenge might be restricting many crucial developments in COVID-19 research. This paper presents an experimental demonstration of the applicability of Automated Machine Learning (autoML) in the screening of COVID-19 infection using deep features extracted from routine chest Computerized Tomography (CT) scan images. For this purpose, we have proposed an EfficientTPOTNet framework, which is a combination of EfficientNet B7 Convolutional Neural Network as a feature extractor paired with a robust ML pipeline generated using Tree-Based Pipeline Optimisation Tool (TPOT), an autoML library. The developed framework is validated and compared with other state-of-the-art feature extraction methods and manually created machine learning pipelines using 2482 (1252 COVID and 1230 Non-COVID) chest CT scan images from the SARS-CoV-2 CT dataset. Moreover, we have used 746 (349 COVID and 397 (Non-COVID) independent chest CT scan images from the COVID-CT dataset to study the generalisation ability of the ML pipeline on the unseen statistical distribution of data. The EfficientTPOTNet framework achieved a 10times10 fold cross-validation accuracy of 98.45percent and an F1-score of 98.64percent on the SARS-CoV-2 CT dataset",

}

Genetic Programming entries for Vipul Kumar Singh Jyotismita Barman Maheshkumar H Kolekar

Citations