Diagnóstico do câncer oral através da classificação de alto nível

• Ricardo B. Lima Filho UFU
• Murillo G. Carneiro UFU

DOI: https://doi.org/10.5753/sbcas_estendido.2023.229937

Abstract

This work investigates high-level classification techniques derived from properties and measures of complex networks for the salivary detection of oral cancer using Total Attenuated Reflectance by Fourier Transform Infrared Spectroscopy (ATR-FTIR). ATR-FTIR is a sustainable, fast and non-invasive platform capable of contributing to the detection of several diseases. Among the several network measures evaluated in this study, our results indicate clustering coefficient as the most satisfactory one with 71% and 81% of accuracy and sensitivity, respectively. Moreover, the high-level technique outperformed several other classifiers used for spectral analysis, including state-of-the-art ones like support vector machine and convolutional neural networks.

References

Baek, S.-J., Park, A., Ahn, Y.-J., and Choo, J. (2015). Baseline correction using asymmetrically reweighted penalized least squares smoothing. Analyst, 140(1):250–257.

Barauna, V. G., Singh, M. N., Barbosa, L. L., Marcarini, W. D., Vassallo, P. F., Mill, J. G., Ribeiro-Rodrigues, R., Campos, L. C., Warnke, P. H., and Martin, F. L. (2021). Ultrarapid on-site detection of sars-cov-2 infection using simple atr-ftir spectroscopy and an analysis algorithm: high sensitivity and specificity. Analytical Chemistry, 93(5):2950–2958.

Boelens, H. F., Dijkstra, R. J., Eilers, P. H., Fitzpatrick, F., and Westerhuis, J. A. (2004). New background correction method for liquid chromatography with diode array detection, infrared spectroscopic detection and raman spectroscopic detection. Journal of chromatography A, 1057(1-2):21–30.

Caixeta, D. C., Carneiro, M. G., Rodrigues, R., Alves, D. C. T., Goulart, L. R., Cunha, T. M., Espindola, F. S., Vitorino, R., and Sabino-Silva, R. (2023). Salivary atr-ftir spectroscopy coupled with support vector machine classification for screening of type 2 diabetes mellitus. Diagnostics, 13(8):1396.

Carneiro, M. G. (2017). Redes complexas para classificação de dados via conformidade de padrão, caracterização de importância e otimização estrutural. PhD thesis, Universidade de São Paulo.

Carneiro, M. G., Gama, B. C., and Ribeiro, O. S. (2021). Complex network measures for data classification. In 2021 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.

Carneiro, M. G. and Zhao, L. (2018). Organizational data classification based on the importance concept of complex networks. IEEE Transactions on Neural Networks and Learning Systems, 29(8):3361–3373.

Fernandes, J. M., Oliveira, G. M. B., and Carneiro, M. G. (2023). Network optimization based on genetic algorithm for high-level data classification. IEEE Latin America Transactions, 21(2):295–301.

Ferreira, I. C., Aguiar, E. M., Silva, A. T., Santos, L. L., Cardoso-Sousa, L., Araujo, T. G., Santos, D. W., Goulart, L. R., Sabino-Silva, R., and Maia, Y. C. (2020). Attenuated total reflection-fourier transform infrared (atr-ftir) spectroscopy analysis of saliva for breast cancer diagnosis. Journal of oncology, 2020.

Freitas, R. M., Rodrigues, A. M. X., Matos Júnior, A., and Oliveira, G. (2016). Fatores de risco e principais alterações citopatológicas do câncer bucal: uma revisão de literatura. Rbac, 48(1):13–8.