{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:51:33Z","timestamp":1769190693409,"version":"3.49.0"},"reference-count":45,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This paper introduces a model that automates the diagnosis of a patient\u2019s condition, reducing reliance on highly trained professionals, particularly in resource-constrained settings. To ensure data consistency, the dataset was preprocessed for uniformity in size, format, and color channels. Image quality was further enhanced using histogram equalization to improve the dynamic range. Lung regions were isolated using segmentation techniques, which also eliminated extraneous areas from the images. A modified segmentation-based cropping technique was employed to define an optimal cropping rectangle. Feature extraction was performed using persistent homology, deep learning, and hybrid methodologies. Persistent homology captured topological features across multiple scales, while the deep learning model leveraged convolutional transition equivariance, input-adaptive weighting, and the global receptive field provided by Vision Transformers. By integrating features from both methods, the classification model effectively predicted severity levels (mild, moderate, severe). The segmentation-based cropping method showed a modest improvement, achieving 80% accuracy, while stand-alone persistent homology features reached 66% accuracy. Notably, the hybrid model outperformed existing approaches, including SVM, ResNet50, and VGG16, achieving an accuracy of 82%.<\/jats:p>","DOI":"10.3390\/bdcc9040083","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T08:48:00Z","timestamp":1743410880000},"page":"83","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["COVID-19 Severity Classification Using Hybrid Feature Extraction: Integrating Persistent Homology, Convolutional Neural Networks and Vision Transformers"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8966-7511","authenticated-orcid":false,"given":"Redet","family":"Assefa","sequence":"first","affiliation":[{"name":"Computer Science Department, College of Informatics, Tewodros Campus University of Gondar, Gondar 6200, Ethiopia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0749-3031","authenticated-orcid":false,"given":"Adane","family":"Mamuye","sequence":"additional","affiliation":[{"name":"School of IT and Engineering, College of Technology and Built Environment, Addis Ababa University, 5 Killo Campus, Addis Ababa 18869, Ethiopia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8545-3740","authenticated-orcid":false,"given":"Marco","family":"Piangerelli","sequence":"additional","affiliation":[{"name":"School of IT and Engineering, College of Technology and Built Environment, Addis Ababa University, 5 Killo Campus, Addis Ababa 18869, Ethiopia"},{"name":"Computer Science Division, School of Science and Technology, University of Camerino, 62017 Camerino, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,31]]},"reference":[{"key":"ref_1","unstructured":"(2024, August 06). Worldometer. COVID-19 Coronavirus Pandemic. Available online: https:\/\/www.worldometers.info\/coronavirus\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"E115","DOI":"10.1148\/radiol.2020200432","article-title":"Sensitivity of chest CT for COVID-19: Comparison to RT-PCR","volume":"296","author":"Fang","year":"2020","journal-title":"Radiology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.clinimag.2020.04.001","article-title":"Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review","volume":"64","author":"Jacobi","year":"2020","journal-title":"Clin. Imaging"},{"key":"ref_4","first-page":"100013","article-title":"Deep learning and its role in COVID-19 medical imaging","volume":"3","author":"Desai","year":"2020","journal-title":"Intell.-Based Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1007\/s10489-020-01826-w","article-title":"Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices","volume":"51","author":"Ahuja","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104054","DOI":"10.1016\/j.chemolab.2020.104054","article-title":"An automated Residual Exemplar Local Binary Pattern and iterative ReliefF based COVID-19 detection method using chest X-ray image","volume":"203","author":"Tuncer","year":"2020","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11548-020-02305-w","article-title":"Chest X-ray image phase features for improved diagnosis of COVID-19 using convolutional neural network","volume":"16","author":"Qi","year":"2021","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104284","DOI":"10.1016\/j.ijmedinf.2020.104284","article-title":"Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms","volume":"144","author":"Heidari","year":"2020","journal-title":"Int. J. Med. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3595","DOI":"10.1109\/JBHI.2020.3037127","article-title":"COVIDGR dataset and COVID-SDNet methodology for predicting COVID-19 based on chest X-ray images","volume":"24","author":"Tabik","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"114054","DOI":"10.1016\/j.eswa.2020.114054","article-title":"Deep learning approaches for COVID-19 detection based on chest X-ray images","volume":"164","author":"Ismael","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_11","first-page":"11","article-title":"COVID-19 detection in chest X-ray images using a deep learning approach","volume":"6","author":"Saiz","year":"2020","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"key":"ref_12","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 25."},{"key":"ref_13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_14","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Edelsbrunner, H., and Harer, J. (2010). Computational Topology: An Introduction, American Mathematical Society.","DOI":"10.1090\/mbk\/069"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5169","DOI":"10.1007\/s10462-022-10146-z","article-title":"Persistent-homology-based machine learning: A survey and a comparative study","volume":"55","author":"Pun","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: A review","volume":"42","author":"Anwar","year":"2018","journal-title":"J. Med. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102829","DOI":"10.1016\/j.media.2023.102829","article-title":"Deepsti: Towards tensor reconstruction using fewer orientations in susceptibility tensor imaging","volume":"87","author":"Fang","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"102046","DOI":"10.1016\/j.media.2021.102046","article-title":"BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset","volume":"71","author":"Signoroni","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1049\/ipr2.12153","article-title":"COVID-19 disease severity assessment using CNN model","volume":"15","author":"Irmak","year":"2021","journal-title":"IET Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20","DOI":"10.5152\/dir.2020.20205","article-title":"Determination of disease severity in COVID-19 patients using deep learning in chest X-ray images","volume":"27","author":"Blain","year":"2021","journal-title":"Diagn. Interv. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","article-title":"Adaptive document image binarization","volume":"33","author":"Sauvola","year":"2000","journal-title":"Pattern Recognit."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","article-title":"U-net and its variants for medical image segmentation: A review of theory and applications","volume":"9","author":"Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13032-015-0030-5","article-title":"\u201cAnterior convergent\u201d chest probing in rapid ultrasound transducer positioning versus formal chest ultrasonography to detect pneumothorax during the primary survey of hospital trauma patients: A diagnostic accuracy study","volume":"9","author":"Ziapour","year":"2015","journal-title":"J. Trauma Manag. Outcomes"},{"key":"ref_26","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on Bayesian optimization","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"373","DOI":"10.5662\/wjm.v13.i5.373","article-title":"Challenges and limitations of synthetic minority oversampling techniques in machine learning","volume":"13","author":"Alkhawaldeh","year":"2023","journal-title":"World J. Methodol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"ooad033","DOI":"10.1093\/jamiaopen\/ooad033","article-title":"Implications of resampling data to address the class imbalance problem (IRCIP): An evaluation of impact on performance between classification algorithms in medical data","volume":"6","author":"Welvaars","year":"2023","journal-title":"JAMIA Open"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4641","DOI":"10.1109\/ACCESS.2018.2789428","article-title":"Class weights random forest algorithm for processing class imbalanced medical data","volume":"6","author":"Zhu","year":"2018","journal-title":"IEEE Access"},{"key":"ref_30","unstructured":"Frid-Adar, M., Ben-Cohen, A., Amer, R., and Greenspan, H. (2018, January 16\u201320). Improving the segmentation of anatomical structures in chest radiographs using u-net with an imagenet pre-trained encoder. Proceedings of the Image Analysis for Moving Organ, Breast, and Thoracic Images: Third International Workshop, RAMBO 2018, Fourth International Workshop, BIA 2018, and First International Workshop, TIA 2018, Conjunction with MICCAI 2018, Granada, Spain. Proceedings 3."},{"key":"ref_31","first-page":"894","article-title":"An automatic approach to lung region segmentation in chest X-ray images using adapted U-Net architecture","volume":"11595","author":"Rahman","year":"2021","journal-title":"Proc. SPIE"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.24996\/ijs.2022.63.5.37","article-title":"Using Persistence Barcode to Show the Impact of Data Complexity on the Neural Network Architecture","volume":"63","author":"Alhelfi","year":"2022","journal-title":"Iraqi J. Sci."},{"key":"ref_33","unstructured":"Johnson, M., and Jung, J.H. (2021). Instability of the betti sequence for persistent homology and a stabilized version of the betti sequence. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"91916","DOI":"10.1109\/ACCESS.2020.2994762","article-title":"Covidgan: Data augmentation using auxiliary classifier gan for improved covid-19 detection","volume":"8","author":"Waheed","year":"2020","journal-title":"IEEE Access"},{"key":"ref_35","unstructured":"He, K., Girshick, R., and Doll\u00e1r, P. (November, January 27). Rethinking imagenet pre-training. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_36","unstructured":"Hendrycks, D., Lee, K., and Mazeika, M. (2019, January 9\u201315). Using pre-training can improve model robustness and uncertainty. Proceedings of the International Conference on Machine Learning. PMLR, Long Beach, CA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_38","unstructured":"Huang, W., Song, G., Li, M., Hu, W., and Xie, K. (August, January 31). Adaptive weight optimization for classification of imbalanced data. Proceedings of the International Conference on Intelligent Science and Big Data Engineering, Beijing, China."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.patrec.2015.12.012","article-title":"The classification of endoscopy images with persistent homology","volume":"83","author":"Dunaeva","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","article-title":"Attention gated networks: Learning to leverage salient regions in medical images","volume":"53","author":"Schlemper","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv. CSUR"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Castiglioni, I., Ippolito, D., Interlenghi, M., Monti, C.B., Salvatore, C., Schiaffino, S., Polidori, A., Gandola, D., Messa, C., and Sardanelli, F. (2020). Artificial intelligence applied on chest X-ray can aid in the diagnosis of COVID-19 infection: A first experience from Lombardy, Italy. medRxiv.","DOI":"10.1101\/2020.04.08.20040907"},{"key":"ref_43","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_45","unstructured":"Weights & Biases (2025, March 13). What Is Bayesian Hyperparameter Optimization?. Available online: https:\/\/wandb.ai\/wandb_fc\/articles\/reports\/What-Is-Bayesian-Hyperparameter-Optimization-With-Tutorial---Vmlldzo1NDQyNzcw."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/4\/83\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:06:36Z","timestamp":1760029596000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/4\/83"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["bdcc9040083"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9040083","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,31]]}}}