Agrupamento de Imagens Tumorais de MRI utilizando Extração de Descritores baseados em Séries Temporais
Resumo
Na categoria de tumores com localização primária no cérebro, os gliomas são os mais comuns e agressivos. A identificação desses tumores junto ao tratamento precoce é a chave para o bem estar do paciente. Neste artigo é proposto um método para a representação de imagens como séries temporais, descritores do formato do tumor, e a utilização de métodos de agrupamento utilizando as distancias euclidiana e DTW, obtendo um coeficiente de silhueta de 0,639 com a distancia DTW, agrupando 60% dos casos. Os experimentos realizados mostraram resultados preliminares que precisam ser avaliados por especialistas do domínio.Referências
Akkus, Z., Galimzianova, A., Hoogi, A., Rubin, D. L., e Erickson, B. J. (2017). Deep learning for brain mri segmentation: State of the art and future directions. JDI, 20:449–459.
Batista, G., Campana, B., e Keogh, E. (2010). Classification of live moths combining texture, color and shape primitives. In 2010 Ninth ICMLA, pages 903–906.
Batista, G. E., Keogh, E. J., Tataw, O. M., e de Souza, V. (2014). Cid: an efficient complexity-invariant distance for time series. Data Mining and Knowledge Discovery, 28(3):634–669.
Bauer, S., Wiest, R., Nolte, L.-P., e Reyes, M. (2013). A survey of mri-based medical image analysis for brain tumor studies. PMB, 58(13):R97–R129.
Berndt, D. J. e Clifford, J. (1994). Using Dynamic Time Warping to Find Patterns in Time Series. In Proceedigns of the Workshop on KDD, volume 10, pages 359–370.
Campello, R. J. G. B. et al. (2013). Density-based clustering based on hierarchical density estimates. In Adv. in Knowl. Discov. and Data Min., pages 160–172. Springer Berlin Heidelberg.
Canny, J. (1986). A computational approach to edge detection. IEEE PAMI, 8(6):679–698.
Delgado-Lopez, P. D. e Corrales-García, E. M. (2016). Survival in glioblastoma: a review on the impact of treatment modalities. Clinical and Translational Oncology, 18.
Gonzalez, R. C. e Woods, R. C. (2009). Processamento digital de imagens. Pearson Prentice Hall, 3 ed. edition.
Goodenberger, M. L. e Jenkins, R. B. (2012). Genetics of adult glioma. Cancer Genetics, 205:P613–621.
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., e Larochelle, H. (2016). Brain tumor segmentation with deep neural networks. MedIA, 35:18–31.
Iqbal, S., Ghani, M. U., Saba, T., e Rehman, A. (2018). Brain tumor segmentation in multi-spectral mri using convolutional neural networks (cnn). Microsc. Res. Tech., 81(4):419–427.
Kanani, P. e Padole, M. (2020). Ecg heartbeat arrhythmia classification using time-series augmented signals and deep learning approach. Procedia Comput. Sci., 171:524–531.
Keogh, E., Wei, L., Xi, X., Lee, S.-H., e Vlachos, M. (2006). Lb keogh supports exact indexing of shapes under rotation invariance with arbitrary representations and distance measures. In Proceedings of the 32nd VLDB, pages 882–893.
Naser, M. A. e Deen, M. J. (2020). Brain tumor segmentation and grading of lower-grade glioma using deep learning in mri images. Comput. Biol. Med., 121:103758.
Pereira, S., Pinto, A., Alves, V., e Silva, C. A. (2016). Brain tumor segmentation using convolutional neural networks in mri images. IEEE T-MI, 35(5):1240–1251.
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math., 20:53–65.
Silva, D. F. e Batista, G. E. (2016). Speeding up all-pairwise dynamic time warping matrix calculation. Proceedings of the 2016 SDM.
Tavenard, R. (2021). An introduction to dynamic time warping. https://rtavenar.github.io/blog/dtw.html. Acesso em: 03/02/2022.
Zhou, C., Ding, C., Wang, X., Lu, Z., e Tao, D. (2019). One-pass multi-task networks with cross-task guided attention for brain tumor segmentation. CoRR, abs/1906.01796.
Batista, G., Campana, B., e Keogh, E. (2010). Classification of live moths combining texture, color and shape primitives. In 2010 Ninth ICMLA, pages 903–906.
Batista, G. E., Keogh, E. J., Tataw, O. M., e de Souza, V. (2014). Cid: an efficient complexity-invariant distance for time series. Data Mining and Knowledge Discovery, 28(3):634–669.
Bauer, S., Wiest, R., Nolte, L.-P., e Reyes, M. (2013). A survey of mri-based medical image analysis for brain tumor studies. PMB, 58(13):R97–R129.
Berndt, D. J. e Clifford, J. (1994). Using Dynamic Time Warping to Find Patterns in Time Series. In Proceedigns of the Workshop on KDD, volume 10, pages 359–370.
Campello, R. J. G. B. et al. (2013). Density-based clustering based on hierarchical density estimates. In Adv. in Knowl. Discov. and Data Min., pages 160–172. Springer Berlin Heidelberg.
Canny, J. (1986). A computational approach to edge detection. IEEE PAMI, 8(6):679–698.
Delgado-Lopez, P. D. e Corrales-García, E. M. (2016). Survival in glioblastoma: a review on the impact of treatment modalities. Clinical and Translational Oncology, 18.
Gonzalez, R. C. e Woods, R. C. (2009). Processamento digital de imagens. Pearson Prentice Hall, 3 ed. edition.
Goodenberger, M. L. e Jenkins, R. B. (2012). Genetics of adult glioma. Cancer Genetics, 205:P613–621.
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., e Larochelle, H. (2016). Brain tumor segmentation with deep neural networks. MedIA, 35:18–31.
Iqbal, S., Ghani, M. U., Saba, T., e Rehman, A. (2018). Brain tumor segmentation in multi-spectral mri using convolutional neural networks (cnn). Microsc. Res. Tech., 81(4):419–427.
Kanani, P. e Padole, M. (2020). Ecg heartbeat arrhythmia classification using time-series augmented signals and deep learning approach. Procedia Comput. Sci., 171:524–531.
Keogh, E., Wei, L., Xi, X., Lee, S.-H., e Vlachos, M. (2006). Lb keogh supports exact indexing of shapes under rotation invariance with arbitrary representations and distance measures. In Proceedings of the 32nd VLDB, pages 882–893.
Naser, M. A. e Deen, M. J. (2020). Brain tumor segmentation and grading of lower-grade glioma using deep learning in mri images. Comput. Biol. Med., 121:103758.
Pereira, S., Pinto, A., Alves, V., e Silva, C. A. (2016). Brain tumor segmentation using convolutional neural networks in mri images. IEEE T-MI, 35(5):1240–1251.
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math., 20:53–65.
Silva, D. F. e Batista, G. E. (2016). Speeding up all-pairwise dynamic time warping matrix calculation. Proceedings of the 2016 SDM.
Tavenard, R. (2021). An introduction to dynamic time warping. https://rtavenar.github.io/blog/dtw.html. Acesso em: 03/02/2022.
Zhou, C., Ding, C., Wang, X., Lu, Z., e Tao, D. (2019). One-pass multi-task networks with cross-task guided attention for brain tumor segmentation. CoRR, abs/1906.01796.
Publicado
27/06/2022
Como Citar
MEDEIROS JÚNIOR, José Gilberto B. de; FERRERO, Carlos Andrés.
Agrupamento de Imagens Tumorais de MRI utilizando Extração de Descritores baseados em Séries Temporais. In: ESCOLA REGIONAL DE BANCO DE DADOS (ERBD), 17. , 2022, Lages/SC.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 109-118.
ISSN 2595-413X.
DOI: https://doi.org/10.5753/erbd.2022.223688.
