Radiomics for the Classification of Radiological Patterns in Computed Tomography

Heloísa Dias Viotto; Felipe Duarte Silva; Guilherme Eduardo Gonçalves da Silva; Heloisa de Oliveira Pinho; Ricardo Quer do Nascimento Filho; Lucas Ferrari de Oliveira

doi:10.22456/2175-2745.150929

Authors

Heloísa Dias Viotto Universidade Federal do Paraná (UFPR) https://orcid.org/0009-0008-6523-2933
Felipe Duarte Silva Universidade Federal do Paraná (UFPR) https://orcid.org/0009-0006-3651-1103
Guilherme Eduardo Gonçalves da Silva Universidade Federal do Paraná (UFPR) https://orcid.org/0009-0000-8850-5078
Heloisa de Oliveira Pinho Universidade Federal do Paraná (UFPR) https://orcid.org/0009-0000-7252-6907
Ricardo Quer do Nascimento Filho Universidade Federal do Paraná (UFPR) https://orcid.org/0009-0007-1842-1101
Lucas Ferrari de Oliveira Universidade Federal do Paraná (UFPR) https://orcid.org/0000-0002-8198-0877

DOI:

https://doi.org/10.22456/2175-2745.150929

Keywords:

radiomic, radiological patterns, machine learning

Abstract

Pulmonary diseases are a major issue today, being one of the leading causes of death worldwide. Because of this, it is essential to develop methods to improve their diagnosis. This study arises from this problem, with the aim of identifying radiomic features in Computed Tomography (CT) and to evaluate the performance of different machine learning algorithms, including KNN, SVM, RF, and MLP. The results obtained show satisfactory values, with specificity standing out. SVM had the best performance with, with a mean specificity of 96.25% and a mean sensitivity of 85.05% both with a small standard deviation.

Downloads

Download data is not yet available.

References

[1] KEERTHI, P.; Y, S. S. S.; S, I. Lung cancer classification using deep neural networks. In: 2025 AI-Driven Smart Healthcare for Society 5.0. [S.l.: s.n.], 2025. p. 1–6.

[2] HAQUE, K. N. et al. EfficientYoNet: An attention based lung cancer detection through hybrid CNN approach. In: 2024 27th International Conference on Computer and Information Technology (ICCIT). [S.l.: s.n.], 2024. p. 717–722.

[3] World Health Organization. The top 10 causes of death. Genebra, Suíça, 2024. Fact sheet. Acesso em: 19 jun. 2025. Disponível em: ⟨https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death⟩.

[4] Instituto Nacional de Câncer (INCA). Estatísticas de câncer: números. Rio de Janeiro, Brasil, 2022. Portal Gov.br. Acesso em: 19 jun. 2025. Disponível em: ⟨https://www.gov.br/inca/pt-br/assuntos/cancer/numeros⟩.

[5] NARVEKAR, S. et al. A survey on detection of lung cancer using different image processing techniques. In: 2022 3rd International Conference on Intelligent Engineering and Management (ICIEM). [S.l.: s.n.], 2022. p. 13–18.

[6] SU, H. et al. Tgmt: A terminology-guided multi-task approach for lung cancer CT report generation. In: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). [S.l.: s.n.], 2024. p. 1–5.

[7] G, S. V.; PONRAJ, N.; L, D. P. Study on public chest x-ray data sets for lung disease classification. In: 2021 3rd International Conference on Signal Processing and Communication (ICPSC). [S.l.: s.n.], 2021. p. 54–58.

[8] AZEVEDO–MARQUES, P. M. d. Diagnóstico auxiliado por computador na radiologia. Radiologia Brasileira, v. 34, p. 285–293, 2001.

[9] PEREIRA, F. R.; OLIVEIRA, L. F. de. Desenvolvimento de um sistema CAD para detecção de nódulo pulmonar em exames de tomografia computadorizada de tórax. In: SBC. Anais do Congresso Brasileiro de Informática em Saúde (CBIS). Brasil, 2021.

[10] DULF, E.-H. et al. Computer-aided diagnosis system for colorectal cancer. In: 2021 25th International Conference on System Theory, Control and Computing (ICSTCC). [S.l.: s.n.], 2021. p. 178–181.

[11] AERTS, H. J. W. L. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications, v. 5, n. 1, p. 4006, 2014. ISSN 2041-1723. Disponível em: ⟨https://doi.org/10.1038/ncomms5006⟩.

[12] LIU, Z. et al. The applications of radiomics in precision diagnosis and treatment of oncology: Opportunities and challenges. Theranostics, v. 9, n. 5, p. 1303–1322, 2019. Disponível em: ⟨https://doi.org/10.7150/thno.30309⟩.

[13] SCHALL, B.; ANTY, R.; FILLATRE, L. Non-linear logistic regression applied to radiomics. In: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). [S.l.: s.n.], 2024. p. 1–4.

[14] I, G. et al. Enhanced robustness in lung cancer classification from CT images using noise-resistant dynamic integral neural networks. In: 2025 International Conference on Emerging Technologies in Engineering Applications (ICETEA). [S.l.: s.n.], 2025. p. 1–6.

[15] METAGAR, S. M.; SAYYED, F. R. Lung cancer detection and classification using machine learning algorithm(cnn). In: 2024 Second International Conference on Advances in Information Technology (ICAIT). [S.l.: s.n.], 2024. v. 1, p. 1–5.

[16] de Margerie-Mellon, C.; CHASSAGNON, G. Artificial intelligence: A critical review of applications for lung nodule and lung cancer. Diagnostic and Interventional Imaging, v. 104, n. 1, p. 11–17, 2023. ISSN 2211-5684. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S221156842200225X⟩.

[17] MIDDHA, S.; KUMAR, A. Advancements in early lung cancer detection using convolutional neural networks. In: 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI). [S.l.: s.n.], 2023. v. 1, p. 1–6.

[18] TIMMEREN, J. E. van et al. Radiomics in medical imaging - “how-to” guide and critical reflection. Insights into Imaging, 2020.

[19] MAYERHOEFER, M. E. et al. Introduction to radiomics. J Nucl Med., 2020.

[20] POTGHAN, S.; RAJAMENAKSHI, R.; BHISE, A. Multi-layer perceptron based lung tumor classification. In: 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA). [S.l.: s.n.], 2018. p. 499–502.

[21] YU, H. et al. Advancing precision in lung cancer subtyping: Integration of machine learning feature selection with MLP. In: 2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE). [S.l.: s.n.], 2024. p. 514–518.

[22] ROHMAH, A. et al. Comparison of machine learning model for lung cancer detection using classification techniques. In: 2024 International Conference of Adisutjipto on Aerospace Electrical Engineering and Informatics (ICAAEEI). [S.l.: s.n.], 2024. p. 1–6.

[23] AL-OFARY, S.; ILHAN, H. O. Classification of pca based reduced deep features by svm for diagnosing lung and colon cancer. In: 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA). [S.l.: s.n.], 2023. p. 1–5.

[24] GUAN, P. et al. Lung cancer gene expression database analysis incorporating prior knowledge with support vector machine-based classification method. v. 28, n. 1, p. 103, 2009. ISSN 1756-9966. Disponível em: ⟨https://doi.org/10.1186/1756-9966-28-103⟩.

[25] IRION, K. L. et al. Radiograma de tórax e tomografia computadorizada na avaliação do enfisema pulmonar. Jornal Brasileiro de Pneumologia, Sociedade Brasileira de Pneumologia e Tisiologia, v. 33, n. 6, p. 720–732, Nov 2007. ISSN 1806-3713. Disponível em: ⟨https://doi.org/10.1590/S1806-37132007000600017⟩.

[26] SANTOS, M. L. d. O. et al. Opacidades em vidro fosco nas doenças pulmonares difusas: correlação da tomografia computadorizada de alta resolução com a anatomopatologia. Radiologia Brasileira, Publicação do Colégio Brasileiro de Radiologia e Diagnóstico por Imagem, v. 36, n. 6, p. 329–338, Nov 2003. ISSN 0100-3984. Disponível em: ⟨https://doi.org/10.1590/S0100-39842003000600003⟩.

[27] BACELAR, V. K. S. S. et al. Fibrose pulmonar pós-covid-19: uma revisão integrativa. Observatório de la Economía Latinoamericana, v. 21, n. 9, p. 13280–13294, set. 2023. Disponível em: ⟨https://ojs.observatoriolatinoamericano.com/ojs/index.php/olel/article/view/1325⟩.

[28] BANKIER, A. A. et al. Fleischner society: Glossary of terms for thoracic imaging. Radiology, v. 310, n. 2, p. e232558, 2024. PMID: 38411514. Disponível em: ⟨https://doi.org/10.1148/radiol.232558⟩.

[29] HE, Y. et al. Rpild-score: A quantitative CT radiomics-based model for predicting rapidly progressive interstitial lung disease in dermatomyositis with anti-mda5 antibody. Respiratory Research, v. 25, n. 1, p. 112, 2024.

[30] HAGA, H. et al. CT-based radiomics approach to evaluate lymphocytic infiltration in the lung of patients with idiopathic interstitial pneumonias. Japanese Journal of Radiology, v. 42, n. 4, p. 356–364, 2024.

[31] BERNARDI, F. et al. Radiomic features for the differentiation of usual interstitial pneumonia and non-UIP fibrosing interstitial lung diseases. Journal of Imaging, v. 8, n. 11, p. 317, 2022.

[32] YOON, H. et al. Deep learning-based subtype classification of interstitial lung disease using high-resolution CT images. IEEE Transactions on Medical Imaging, 2023. A ser completado com dados reais caso existam.

[33] LIU, F. et al. A multimodal approach combining radiomics and clinical features for predicting post-COVID interstitial lung disease. Medical Image Analysis, 2023. A ser completado com dados reais caso existam.

[34] ROHMAH, S. N. et al. Lung cancer classification using radiomics and machine learning techniques. In: 2024 International Conference on Advanced and Applied Engineering (ICAAE). [S.l.: s.n.], 2024. p. 1–6.

[35] BAGESTEIRO, L. D.; OLIVEIRA, L. F.; WEINGAERTNER, D. Blockwise classification of lung patterns in unsegmented CT images. In: 28th IEEE International Symposium on Computer-Based Medical Systems (CBMS). [S.l.: s.n.], 2015. p. 177–182.

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

[37] OTSU, N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, v. 9, n. 1, p. 62–66, 1979.

[38] GRIETHUYSEN, J. J. M. van et al. Computational radiomics system to decode the radiographic phenotype. Cancer Research, v. 77, n. 21, p. e104–e107, 2017.

[39] POWERS, D. M. W. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, v. 2, n. 1, p. 37–63, 2011.

[40] KABIR, M.; TAHITI, T. J.; PROME, T. A. A comparative study of certain convolutional neural network architectures for X-ray image analysis in bone fracture detection and identification. In: 2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA). [S.l.: s.n.], 2024. p. 1–8.

[41] KHAN, S. A.; RANA, Z. A. Evaluating performance of software defect prediction models using area under precision-recall curve (AUC-PR). In: 2019 2nd International Conference on Advancements in Computational Sciences (ICACS). [S.l.: s.n.], 2019. p. 1–6.