Análise de Redes Neurais Convolucionais e Técnicas de Pré-processamento para Identificação de Dentes Serotinos com Cistos
Resumo
A extração dos terceiros molares está sempre em debate entre dentistas, isto porque podem surgir patologias com a sua permanência. Visando auxiliar no diagnóstico o presente trabalho procura automatizar a detecção de terceiros molares com cistos em imagens de radiografias. Para isso, são analisadas duas arquiteturas de Redes Neurais Convolucionais (CNN) para a classificação e experimentadas com técnicas de pré-processamento de imagem. Uma destas propostas, com uso de contraste morfológico, obteve melhor performance, com destaque à precisão de 0,93 e F1-score de 0,84. Os resultados demonstram que a proposta permite automatização no diagnóstico de cistos.
Referências
Zanetti, L. S. S., Marano, R. R., Bianchi, P. R., Garcia Junior, I. R. and de Barros, A. P. (2009). Transformação Cística como Consequência de Terceiro Molar Inferior Incluso. Revista Portuguesa de Estomatologia, Medicina Dentária e Cirurgia Maxilofacial, 50(1): 19 – 23, doi: 10.1016/S1646-2890(09)70012-3.
Slootweg, P. J. (1987). Carcinoma arising from reduced enamel epithelium. Journal of Oral Pathology, 16(10): 479 – 482, doi: 10.1111/j.1600-0714.1987.tb00676.x.
Ulaganathan, G., Banumathi, A., Amutha, J. J. and Jeevani Selvabala, A. (2012). Dental Cyst Delineation Using Live Wire Algorithm. In 2012 International Conference on Machine Vision and Image Processing (MVIP), pages 129 – 132, doi: 10.1109/MVIP.2012.6428777.
Salehinejad, J., Saghafi, S. and Ghazi, N. (2013). Glandular odontogenic cyst associated with an impacted tooth. Journal of Dental Materials and Techniques, 2: 99 – 103, doi: 10.22038/JDMT.2013.1053.
Patil, S. (2013). Prevalence and type of pathological conditions associated with unerupted and retained third molars in the western Indian population. Journal of Cranio-Maxillofacial Surgery, 2(1): 3 – 4.
Birdal, R. G., Gumus, E., Sertbas, A. and Birdal, I. S. (2016). Automated lesion detection in panoramic dental radiographs. Oral Radiology, 32(1): 111 – 118, doi: 10.1007/s11282-015-0222-8.
Banar, N., Bertels, J., Laurent, F., Boedi, R. M., Tobel, J. D., Thevissen, P. and Vandermeulen, P. (2020). Towards fully automated third molar development staging in panoramic radiographs. International Journal of Legal Medicine, 134(1): 1831–1841, doi: 10.1007%2Fs00414-020-02283-3.
Divya, K. V., Jatti, A., Joshi, R. and Krishna, S. D. (2017). Characterization of dental pathologies using digital panoramic X-ray images based on texture analysis. In 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 11 – 15, doi: 10.1109/EMBC.2017.8036894.
Lee, J. H., Kim, D. H. and Jeong, S. N. (2020). Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network. Oral diseases, 26(1): 152 – 158, doi: 10.1111/odi.13223.
Devi, R. K., Banumathi, A., Sangavi, G. and Dawood, M. S. (2020). A Novel Region Based Thresholding for Dental Cyst Extraction in Digital Dental X-Ray Images. New Trends in Computational Vision and Bio-inspired Computing, pages 1633 – 1640, doi: 10.1007/978-3-030-41862-5_167.
Kwon, O., Yong, T. H., Kang, S. R., Kim, J. E., Huh, K. H., Heo, M. S., Lee, S. S., Choi, S. C. and Yi, W. J. (2020). Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network. Dentomaxillofacial Radiology, 49(8): 20200185, doi: 10.1259/dmfr.20200185.
Birdal, R. G., Gumus, E., Sertbas, A. and Birdal, I. S. (2015). Automated lesion detection in panoramic dental radiographs. Oral Radiology, 32(2): 111 – 118, doi: 10.1007/s11282-015-0222-8.
Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep learning. [S.l.]: MIT press.
LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998). Gradient-based learning applied to document recognition. In Proceedings of the IEEE, 86(11): 2278 – 2324.
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X. Wang, G., Cai, J. and Chen, T. (2017). Recent advances in convolutional neural networks. Pattern Recognition, 77(1): 354 – 377, doi: https://doi.org/10.1016/j.patcog.2017.10.013
Slootweg, P. J. (1987). Carcinoma arising from reduced enamel epithelium. Journal of Oral Pathology, 16(10): 479 – 482, doi: 10.1111/j.1600-0714.1987.tb00676.x.
Ulaganathan, G., Banumathi, A., Amutha, J. J. and Jeevani Selvabala, A. (2012). Dental Cyst Delineation Using Live Wire Algorithm. In 2012 International Conference on Machine Vision and Image Processing (MVIP), pages 129 – 132, doi: 10.1109/MVIP.2012.6428777.
Salehinejad, J., Saghafi, S. and Ghazi, N. (2013). Glandular odontogenic cyst associated with an impacted tooth. Journal of Dental Materials and Techniques, 2: 99 – 103, doi: 10.22038/JDMT.2013.1053.
Patil, S. (2013). Prevalence and type of pathological conditions associated with unerupted and retained third molars in the western Indian population. Journal of Cranio-Maxillofacial Surgery, 2(1): 3 – 4.
Birdal, R. G., Gumus, E., Sertbas, A. and Birdal, I. S. (2016). Automated lesion detection in panoramic dental radiographs. Oral Radiology, 32(1): 111 – 118, doi: 10.1007/s11282-015-0222-8.
Banar, N., Bertels, J., Laurent, F., Boedi, R. M., Tobel, J. D., Thevissen, P. and Vandermeulen, P. (2020). Towards fully automated third molar development staging in panoramic radiographs. International Journal of Legal Medicine, 134(1): 1831–1841, doi: 10.1007%2Fs00414-020-02283-3.
Divya, K. V., Jatti, A., Joshi, R. and Krishna, S. D. (2017). Characterization of dental pathologies using digital panoramic X-ray images based on texture analysis. In 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 11 – 15, doi: 10.1109/EMBC.2017.8036894.
Lee, J. H., Kim, D. H. and Jeong, S. N. (2020). Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network. Oral diseases, 26(1): 152 – 158, doi: 10.1111/odi.13223.
Devi, R. K., Banumathi, A., Sangavi, G. and Dawood, M. S. (2020). A Novel Region Based Thresholding for Dental Cyst Extraction in Digital Dental X-Ray Images. New Trends in Computational Vision and Bio-inspired Computing, pages 1633 – 1640, doi: 10.1007/978-3-030-41862-5_167.
Kwon, O., Yong, T. H., Kang, S. R., Kim, J. E., Huh, K. H., Heo, M. S., Lee, S. S., Choi, S. C. and Yi, W. J. (2020). Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network. Dentomaxillofacial Radiology, 49(8): 20200185, doi: 10.1259/dmfr.20200185.
Birdal, R. G., Gumus, E., Sertbas, A. and Birdal, I. S. (2015). Automated lesion detection in panoramic dental radiographs. Oral Radiology, 32(2): 111 – 118, doi: 10.1007/s11282-015-0222-8.
Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep learning. [S.l.]: MIT press.
LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998). Gradient-based learning applied to document recognition. In Proceedings of the IEEE, 86(11): 2278 – 2324.
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X. Wang, G., Cai, J. and Chen, T. (2017). Recent advances in convolutional neural networks. Pattern Recognition, 77(1): 354 – 377, doi: https://doi.org/10.1016/j.patcog.2017.10.013
Publicado
15/06/2021
Como Citar
OLIVEIRA, Danilo Alves; BARRETO, Joniel Bastos; MESQUITA, Iago Magalhães de; PAULA JÚNIOR, Iális Cavalcante de; CHAVES, Filipe Nobre; SAMPIERI, Marcelo Bonifácio da Silva.
Análise de Redes Neurais Convolucionais e Técnicas de Pré-processamento para Identificação de Dentes Serotinos com Cistos. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 21. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 107-118.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2021.16057.
