Swin-textural: A novel textural features-based image classification model for COVID-19 detection on chest computed tomography
Article
Article Title | Swin-textural: A novel textural features-based image classification model for COVID-19 detection on chest computed tomography |
---|---|
ERA Journal ID | 212809 |
Article Category | Article |
Authors | Tuncer, Ilknur, Barua, Prabal Datta, Dogan, Sengul, Baygin, Mehmet, Tuncer, Turker, Tan, Ru-San, Yeong, Chai Hong and Acharya, U. Rajendra |
Journal Title | Informatics in Medicine Unlocked |
Journal Citation | 36 |
Article Number | 101158 |
Number of Pages | 11 |
Year | 2023 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 2352-9148 |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.imu.2022.101158 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S2352914822002957 |
Abstract | Background: Chest computed tomography (CT) has a high sensitivity for detecting COVID-19 lung involvement and is widely used for diagnosis and disease monitoring. We proposed a new image classification model, swin-textural, that combined swin-based patch division with textual feature extraction for automated diagnosis of COVID-19 on chest CT images. The main objective of this work is to evaluate the performance of the swin architecture in feature engineering. Material and method: We used a public dataset comprising 2167, 1247, and 757 (total 4171) transverse chest CT images belonging to 80, 80, and 50 (total 210) subjects with COVID-19, other non-COVID lung conditions, and normal lung findings. In our model, resized 420 × 420 input images were divided using uniform square patches of incremental dimensions, which yielded ten feature extraction layers. At each layer, local binary pattern and local phase quantization operations extracted textural features from individual patches as well as the undivided input image. Iterative neighborhood component analysis was used to select the most informative set of features to form ten selected feature vectors and also used to select the 11th vector from among the top selected feature vectors with accuracy >97.5%. The downstream kNN classifier calculated 11 prediction vectors. From these, iterative hard majority voting generated another nine voted prediction vectors. Finally, the best result among the twenty was determined using a greedy algorithm. Results: Swin-textural attained 98.71% three-class classification accuracy, outperforming published deep learning models trained on the same dataset. The model has linear time complexity. Conclusions: Our handcrafted computationally lightweight swin-textural model can detect COVID-19 accurately on chest CT images with low misclassification rates. The model can be implemented in hospitals for efficient automated screening of COVID-19 on chest CT images. Moreover, findings demonstrate that our presented swin-textural is a self-organized, highly accurate, and lightweight image classification model and is better than the compared deep learning models for this dataset. |
Keywords | Computed tomography images; COVID-19 classification; Swin; Swin-textural; Textural feature extraction |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 400306. Computational physiology |
Byline Affiliations | Ngee Ann Polytechnic, Singapore |
Singapore University of Social Sciences (SUSS), Singapore | |
Asia University, Taiwan | |
Government office in Elazig, Turkiye | |
School of Business | |
University of Technology Sydney | |
Firat University, Turkey | |
Ardahan University, Turkiye | |
National Heart Centre, Singapore | |
Duke-NUS Medical School, Singapore | |
Taylor's University, Malaysia |
https://research.usq.edu.au/item/yyw5v/swin-textural-a-novel-textural-features-based-image-classification-model-for-covid-19-detection-on-chest-computed-tomography
Download files
87
total views51
total downloads5
views this month4
downloads this month
Export as
Related outputs
Fibromyalgia Detection and Diagnosis: A Systematic Review of Data-Driven Approaches and Clinical Implications
Atmakuru, Anirudh, Chakraborty, Subrata, Salvi, Massimo, Faust, Oliver, Barua, Prabal Datta, Kobayashi, Makiko, Tan, Ru San, Molinari, Filippo, Hafeez-Baig, Abdul and Acharya, U. Rajendra. 2025. "Fibromyalgia Detection and Diagnosis: A Systematic Review of Data-Driven Approaches and Clinical Implications." IEEE Access. 13, pp. 25026-25044. https://doi.org/10.1109/ACCESS.2025.3539196Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images
Key, Sefa, Kurum, Huseyin, Esmez, Omer, Hafeez-Baig, Abdul, Hajiyeva, Rena, Dogan, Sengul and Tuncer, Turker. 2025. "Automated hip dysplasia detection using novel FlexiLBPHOG model with ultrasound images." Ain Shams Engineering Journal. 16 (1). https://doi.org/10.1016/j.asej.2024.103235Artificial Intelligence-Based Suicide Prevention and Prediction: A Systematic Review (2019-2023)
Atmakuru, Anirudh, Shahini, Alen, Chakraborty, Subrata, Seoni, Silvia, Salvi, Massimo, Hafeez-Baig, Abdul, Rashid, Sadaf, Tan, Ru San, Barua, Prabal Datta, Molinari, Filippo and Acharya, U Rajendra. 2025. "Artificial Intelligence-Based Suicide Prevention and Prediction: A Systematic Review (2019-2023)." Information Fusion. 114. https://doi.org/10.1016/j.inffus.2024.102673Explainable deeply-fused nets electricity demand prediction model: Factoring climate predictors for accuracy and deeper insights with probabilistic confidence interval and point-based forecasts
Ghimire, Sujan, AL-Musaylh, Mohanad S., Nguyen-Huy, Thong, Deo, Ravinesh C., Acharya, Rajendra, Casillas-Perez, David, Yaseen, Zaher Mundher and Salcedo-sanz, Sancho. 2025. "Explainable deeply-fused nets electricity demand prediction model: Factoring climate predictors for accuracy and deeper insights with probabilistic confidence interval and point-based forecasts." Applied Energy. 378 (Part A). https://doi.org/10.1016/j.apenergy.2024.124763AttentionPoolMobileNeXt: An automated construction damage detection model based on a new convolutional neural network and deep feature engineering models
Aydin, Mehmet, Barua, Prabal Datta, Chadalavada, Sreenivasulu, Dogan, Sengul, Tuncer, Turker, Chakraborty, Subrata and Acharya, Rajendra U.. 2025. "AttentionPoolMobileNeXt: An automated construction damage detection model based on a new convolutional neural network and deep feature engineering models." Multimedia Tools and Applications. 84 (4), pp. 1821-1843. https://doi.org/10.1007/s11042-024-19163-2Directed Lobish-based explainable feature engineering model with TTPat and CWINCA for EEG artifact classification
Tuncer, Turker, Dogan, Sengul, Baygin, Mehmet, Tasci, Irem, Mungen, Bulent, Tasci, Burak, Barua, Prabal Datta and Acharya, U.R.. 2024. "Directed Lobish-based explainable feature engineering model with TTPat and CWINCA for EEG artifact classification." Knowledge-Based Systems. 305. https://doi.org/10.1016/j.knosys.2024.112555Retinal Health Screening Using Artificial Intelligence with Digital Fundus Images: A Review of the Last Decade (2012-2023)
Islam, Saad, Deo, Ravinesh C., Barua, Prabal Datta, Soar, Jeffrey, Yu, Ping and Acharya, U. Rajendra. 2024. "Retinal Health Screening Using Artificial Intelligence with Digital Fundus Images: A Review of the Last Decade (2012-2023)." IEEE Access. 12, pp. 176630-176685. https://doi.org/10.1109/ACCESS.2024.3477420Automated EEG-based language detection using directed quantum pattern technique
Dogan, Sengul, Tuncer, Turker, Barua, Prabal Datta and Acharya, U.R.. 2024. "Automated EEG-based language detection using directed quantum pattern technique." Applied Soft Computing. 167 (Part A). https://doi.org/10.1016/j.asoc.2024.112301A Novel Hybrid Model for Automatic Non-Small Cell Lung Cancer Classification Using Histopathological Images
Katar, Oguzhan, Yildirim, Ozal, Tan, Ru-San and Acharya, U Rajendra. 2024. "A Novel Hybrid Model for Automatic Non-Small Cell Lung Cancer Classification Using Histopathological Images." Diagnostics. 14 (22). https://doi.org/10.3390/diagnostics14222497Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies
Akpinar, Muhammed Halil, Sengur, Abdulkadir, Salvi, Massimo, Seoni, Silvia, Faust, Oliver, Mir, Hasan, Molinari,Filippo and Acharya, U. Rajendra. 2024. "Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies." IEEE Open Journal of Engineering in Medicine and Biology. 6, pp. 183-192. https://doi.org/10.1109/OJEMB.2024.3508472RECOMED: A comprehensive pharmaceutical recommendation system
Zomorodi, Mariam, Ghodsollahee, Ismail, Martin, Jennifer H, Talley, Nicholas J, Salari, Vahid, Pławiak, Paweł, Rahimi, Kazem and Acharya, U.R.. 2024. "RECOMED: A comprehensive pharmaceutical recommendation system." Artificial Intelligence in Medicine. 157. https://doi.org/10.1016/j.artmed.2024.102981Artificial intelligence in assessing cardiovascular diseases and risk factors via retinal fundus images: A review of the last decade
Abdollahi, Mirsaeed, Jafarizadeh, Ali, Ghafouri-Asbagh, Amirhosein, Sobhi, Navid, Pourmoghtader, Keysan, Pedrammehr, Siamak, Asadi, Houshyar, Tan, Ru-San, Alizadehsani, Roohallah and Acharya, U. Rajendra. 2024. "Artificial intelligence in assessing cardiovascular diseases and risk factors via retinal fundus images: A review of the last decade." WIREs Data Mining and Knowledge Discovery. 14 (6). https://doi.org/10.1002/widm.1560Early prediction of sudden cardiac death using multimodal fusion of ECG Features extracted from Hilbert–Huang and wavelet transforms with explainable vision transformer and CNN models
Telangore, Hardik, Azad, Victor, Sharma, Manish, Bhurane, Ankit, Tan, Ru San and Acharya, U. Rajendra. 2024. "Early prediction of sudden cardiac death using multimodal fusion of ECG Features extracted from Hilbert–Huang and wavelet transforms with explainable vision transformer and CNN models." Computer Methods and Programs in Biomedicine. 257. https://doi.org/10.1016/j.cmpb.2024.108455A Pragmatic Approach to Fetal Monitoring via Cardiotocography Using Feature Elimination and Hyperparameter Optimization
Hardalac, Firat, Akmal, Haad, Ayturan, Kubilay, Acharya, U. Rajendra and Tan, Ru-San. 2024. "A Pragmatic Approach to Fetal Monitoring via Cardiotocography Using Feature Elimination and Hyperparameter Optimization." Interdisciplinary Sciences: Computational Life Sciences. 16 (4), pp. 882-906. https://doi.org/10.1007/s12539-024-00647-6Automated System for the Detection of Heart Anomalies Using Phonocardiograms: A Systematic Review
Gudigar, Anjan, Raghavendra, U., Maithri, M., Samanth, Jyothi, Inamdar, Mahesh Anil, Vidhya, V., Vicnesh, Jahmunah, Prabhu, Mukund A., Tan, Ru-San, Yeong, Chai Hong, Molinari, Filippo and Acharya, U. R.. 2024. "Automated System for the Detection of Heart Anomalies Using Phonocardiograms: A Systematic Review." IEEE Access. 12, pp. 138399-138428. https://doi.org/10.1109/ACCESS.2024.3465511