Rough Sets and Multilayer Perceptron in Tandem for Processing the Aleatory Uncertainty in COVID-19 Cases

Kalyl Henings; Vinícius Hansen; Gilmário Barbosa Santos

doi:10.22456/2175-2745.139289

Authors

Kalyl Henings Universidade do Estado de Santa Catarina
Vinícius Hansen Universidade do Estado de Santa Catarina https://orcid.org/0009-0006-1720-0879
Gilmário Barbosa Santos Universidade do Estado de Santa Catarina https://orcid.org/0000-0002-0759-2526

DOI:

https://doi.org/10.22456/2175-2745.139289

Keywords:

Unceartainty Treatment, Rough Sets, Multilayer Perceptron, COVID-19, pulmonary RX

Abstract

It is common sense that challenging clinical cases can occur in the practice of medicine. These clinical cases can lead to undesirable situations of diagnostic uncertainty, making it important to identify these difficult cases and lead them to a discussion by experts for appropriate characterization. In remote/isolated regions, it is crucial to have a computational system that can support the health personnel in identifying these challenging cases. Events such as the COVID-19 pandemic have demonstrated the need for this type of system to assist in screening medical exams. Although the chest X-ray examination is a valuable diagnostic tool for COVID-19 cases, some conditions can be so challenging that doctors can be faced with uncertainty in diagnosis. This article proposes a system that combines machine learning via Multilayer Perceptron neural network in conjunction with the detection of uncertainty via Rough Sets in modeling a system that incorporates uncertainty to produce a classification of cases as positive for the disease, negative for the disease, or diagnostically uncertain. This system would serve as support for the rapid and efficient triage of cases, particularly those classified as “uncertain,” for a medical committee of specialists in a video conference, for example. Experiments were carried out and the trained model achieved 87.61% overall accuracy and a hit rate consistent across all classes.

Downloads

Download data is not yet available.

References

WHO Coronavirus (COVID-19) Dashboard. 2023. Disponível em: ⟨https://covid19.who.int⟩.

BARATELLA, E. et al. Severity of lung involvement on chest x-rays in sars-coronavirus-2 infected patients as a possible tool to predict clinical progression: an observational retrospective analysis of the relationship between radiological, clinical, and laboratory data. J. bras. pneumol., v. 46, 2020.

ARSHAD, A. et al. Association of Chest Xray (CXR) findings with outcomes in COVID-19 Patients. Journal of the Pakistan Medical Association, v. 72, n. 9, p. 1746–1749, 2022. ISSN 0030-9982. Publisher: Knowledge Bylanes.

BRUNO, M. A. 256 Shades of gray: uncertainty and diagnostic error in radiology. Diagnosis, v. 4, n. 3, p. 149–157, set. 2017. ISSN 2194-802X. Publisher: De Gruyter. Disponível em: ⟨https://www.degruyter.com/document/doi/10.1515/dx-2017-0006/html⟩.

KURZ, A. et al. Uncertainty estimation in medical image classification: Systematic review. JMIR Med Inform., v. 10, p. e36427, august 2022.

ABDAR, M. et al. A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information Fusion, v. 76, p. 243–297, 2021. ISSN 1566-2535. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1566253521001081⟩.

ZOU, K. et al. A review of uncertainty estimation and its application in medical imaging. Meta-Radiology, v. 1, n. 1, p. 100003, 2023. ISSN 2950-1628. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S2950162823000036⟩.

HANSEN, V.; HENINGS, K.; SANTOS, G. B. d. Applying FOSS Support Vector Machine and Rough Sets on COVID-19 Cases Triage. In: Anais do Latin Science 2023. SBC, 2023. p. 22–27. ISSN: 2160-1348. Disponível em: ⟨https://sol.sbc.org.br/index.php/latinoware/article/view/26077⟩.

HUANG, L. et al. A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods. 2023.

ALIZADEHSANI, R. et al. Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991-2020). Ann Oper Res, v. 21, p. 1–42, 2021.

PAWLAK, Z. Rough set theory and its applications. Journal of Telecommunications and Information Technology, nr 3, p. 7–10, 2002. ISSN 1509-4553. Disponível em: ⟨http://yadda.icm.edu.pl/baztech/element/bwmeta1.element.baztech-article-BPS2-0018-0017⟩.

ROUGH Set Theory | An Introduction. 2019. Section: Machine Learning. Disponível em: ⟨https://www.geeksforgeeks.org/rough-set-theory-an-introduction/⟩.

CHEN, Y. et al. Measures of uncertainty for neighborhood rough sets. Knowledge-Based Systems, v. 120, p. 226–235, 2017. ISSN 0950-7051. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0950705117300096⟩.

ANACONDA Software Distribution. Anaconda Inc., 2020. Publication Title: Anaconda Documentation Version Number: Vers. 2-2.4.0. Disponível em: ⟨https://docs.anaconda.com/⟩.

RAHMAN, T. et al. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine, v. 132, p. 104319, maio 2021. ISSN 0010-4825. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S001048252100113X⟩.

CHOWDHURY, M. E. H. et al. Can AI Help in Screening Viral and COVID-19 Pneumonia? IEEE Access, v. 8, p. 132665–132676, 2020. ISSN 2169-3536. Conference Name: IEEE Access.

VAYA, M. I. et al. BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients. arXiv, 2020. ArXiv:2006.01174 [cs, eess]. Disponível em: ⟨http://arxiv.org/abs/2006.01174⟩.

WANG, Z. et al. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, v. 13, n. 4, p. 600–612, abr. 2004. ISSN 1941-0042. Conference Name: IEEE Transactions on Image Processing.

ALHASHIM, I.; WONKA, P. High Quality Monocular Depth Estimation via Transfer Learning. arXiv, 2019. ArXiv:1812.11941 [cs]. Disponível em: ⟨http://arxiv.org/abs/1812.11941⟩.

WALT, S. et al. scikit-image: image processing in Python. PeerJ, v. 2, p. e453, jun. 2014. ISSN 2167-8359. Disponível em: ⟨https://doi.org/10.7717/peerj.453⟩.

JT XU S, W. B. K. Efficient data mining for local binary pattern in texture image analysis. Expert Syst Appl., v. 42, n. 9, p. 4529–4539, 2015.

SABRI, N. et al. COVID-19 detection for chest X-ray images using local binary pattern. International Journal of Emerging Trends in Engineering Research, p. 78–81, 2020. Disponível em: ⟨https://doi.org/10.30534/ijeter/2020/1281.12020⟩.

THEPADE, S. D.; JADHAV, K. Covid19 Identification from Chest X-Ray Images using Local Binary Patterns with assorted Machine Learning Classifiers. In: 2020 IEEE Bombay Section Signature Conference (IBSSC). [S.l.: s.n.], 2020. p. 46–51.

RIBEIRO, S. S.; YAO, J. Toward a Three-Way Image Classification Model: A Case Study on Corn Grain Images. In: 2019 IEEE International Symposium on Multimedia (ISM). San Diego, CA, USA: IEEE, 2019. p. 177–1776. ISBN 978-1-72815-606-4. Disponível em: ⟨https://ieeexplore.ieee.org/document/8959001/⟩.

RIBEIRO, S. S. TWD. 2023. Original-date: 2021-06-23T17:31:12Z. Disponível em: ⟨https://github.com/profssribeiro/twd⟩.

JANKOWSKI, D. Roughsets-base: Python library for base Roughsets methods. Zenodo, 2022. Disponível em: ⟨https://zenodo.org/record/5957474⟩.

JANKOWSKI, D. darekjk/roughsets-base. 2023. Original-date: 2022-02-03T08:30:14Z. Disponível em: ⟨https://github.com/darekjk/roughsets-base⟩.

PEDREGOSA, F. et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, v. 12, p. 2825–2830, 2011.

ZANATY, E. A. Support Vector Machines (SVMs) versus Multilayer Perception (MLP) in data classification. Egyptian Informatics Journal, v. 13, n. 3, p. 177–183, nov. 2012. ISSN 1110-8665. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1110866512000345⟩.

GHOSH, S.; MONDAL, S.; GHOSH, B. A comparative study of breast cancer detection based on svm and mlp bpn classifier. In: 2014 First International Conference on Automation, Control, Energy and Systems (ACES). [S.l.: s.n.], 2014. p. 1–4.