Application of ensemble method for classification of cardiac medical images
DOI:
https://doi.org/10.59681/2175-4411.v17.2025.1207Keywords:
machine learning, cardiomyopathies, magnetic resonance imaging, cineAbstract
Heart diseases are responsible for approximately 17 million deaths worldwide, according to the World Health Organization. This scenario has led to an increased demand for preventive medical care, resulting in a higher number of cardiac magnetic resonance imaging (MRI) exams. Identifying cardiomyopathies within this growing volume of exams poses a significant challenge for medical teams. To support this process, this study proposes a supervised machine learning methodology for the recognition of cardiomyopathies. The method takes into account different slices of the heart and the specific characteristics of the cardiac cycle, addressing limitations found in previous approaches. During the experiments, an accuracy of 80.00% and a precision of 82.26% were achieved in the best test case, which considers the structures of the epicardium and endocardium during the diastolic phase of the cardiac cycle. The results highlight the potential of the proposed approach in supporting medical diagnosis, especially in contexts of high exam demand.
Downloads
References
World Health Organization (WOS). Cardiovascular diseases. [Internet]. 2021. [citado 2025 ago 13] Disponível em: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
Hanna TN, Zygmont ME, Peterson R, Theriot D, Shekhani H, Johnson JO, et al. The Effects of Fatigue From Overnight Shifts on Radiology Search Patterns and Diagnostic Performance. J Am Coll Radiol. 2018 Dec;15(12):1709-1716. doi: 10.1016/j.jacr.2017.12.019. Epub 2018 Feb 1. PMID: 29366599; PMCID: PMC6054573. DOI: https://doi.org/10.1016/j.jacr.2017.12.019
Simran V, Gupta A. Effective prediction of heart disease using data mining and machine learning: A review. In International Conference on Artificial Intelligence and Smart Systems (ICAIS); 2021. p. 249-253. DOI: https://doi.org/10.1109/ICAIS50930.2021.9395963
Bergamasco L. Recuperação de objetos médicos 3D utilizando harmônicos esféricos e redes de fluxo. Tese de Doutorado. São Paulo: Universidade de São Paulo (USP); 2018.
Ghosh P, Azam S, Jonkman M, Karim A, Shamrat F, Ignatious E, et al. Efficient Prediction of Cardiovascular Disease Using Machine Learning Algorithms With Relief and LASSO Feature Selection Techniques. 2021. IEEE Access, 9, 19304-19326. DOI: https://doi.org/10.1109/ACCESS.2021.3053759
Salvatore C, Cerasa A, Castiglioni I, Gallivanone F, Augimeri A, Lopez M, et al. Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy. Journal of Neuroscience Methods. 2014; 222:230-237. DOI: https://doi.org/10.1016/j.jneumeth.2013.11.016
Moreno A, Rodriguez J, Martínez F. Regional Multiscale Motion Representation for Cardiac Disease Prediction. XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA) 2019 (pp. 1-5). DOI: https://doi.org/10.1109/STSIVA.2019.8730231
Zhuang J, Cai J, Wang R, Zhang J, Zheng WS. Deep kNN for Medical Image Classification. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. 2020;127–36. DOI: https://doi.org/10.1007/978-3-030-59710-8_13
Norvig, Russel P, Artificial S. Intelligence. A modern approach. Vol. 90. Prentice Hall, 2020.
Raza K. Improving the prediction accuracy of heart disease with ensemble learning and majority voting rule [Internet]. ScienceDirect. Academic Press; 2019. p. 179–96. [citado 2025 ago 13] Disponível em: https://www.sciencedirect.com/science/article/abs/pii/B9780128153703000086 DOI: https://doi.org/10.1016/B978-0-12-815370-3.00008-6
Miao K, Miao J, Miao G. Diagnosing Coronary Heart Disease using Ensemble Machine Learning. International Journal of Advanced Computer Science and Applications. 2016;7(10). DOI: https://doi.org/10.14569/IJACSA.2016.071004
Fries JA, Varma P, Chin-Hung Chen V, Xiao K, Tejeda H, Saha P, et al. Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences. Nature Communications. 2019 Jul 15;10(1). DOI: https://doi.org/10.1038/s41467-019-11012-3
Qayyum A, Anwar SM, Awais M, Majid M. Medical image retrieval using deep convolutional neural network. Neurocomputing. 2017 Nov;266:8–20. DOI: https://doi.org/10.1016/j.neucom.2017.05.025
Nasimov R, Nasimova N, Botirjon K; ABDULLAYEV, Munis. Deep Learning Algorithm for Classifying Dilated Cardiomyopathy and Hypertrophic Cardiomyopathy in Transport Workers. Lecture Notes In Computer Science, [S.L.], p. 218-230, 2023. Springer Nature Switzerland. [citado 2025 ago 13] Disponível em: http://dx.doi.org/10.1007/978-3-031-30258-9_19. DOI: https://doi.org/10.1007/978-3-031-30258-9_19
Balaji GN, Subashini TS, Chidambaram N. Detection and diagnosis of dilated cardiomyopathy and hypertrophic cardiomyopathy using image processing techniques. Engineering Science And Technology, An International Journal, [S.L.], v. 19, n. 4, p. 1871-1880, dez. 2016. Elsevier BV. [citado 2025 ago 13] Disponível em: http://dx.doi.org/10.1016/j.jestch.2016.10.001. DOI: https://doi.org/10.1016/j.jestch.2016.10.001
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Guilherme Ormond Sampaio, Leon Ferreira Bellini, Leila Cristina Carneiro Bergamasco
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
