Segmentação do ventrículo esquerdo em exames de Ressonância Magnética Cardíaca com aprendizado profundo e modelos deformáveis contendo restrições de forma

Resumo


Sistemas de Informação estão evoluindo para processar dados multimídia. A segmentação automática do ventrículo esquerdo em exames médicos para auxílio ao diagnóstico é um desafio multidisciplinar da área de Cardiologia. Diversas abordagens têm sido propostas, com destaque para redes de aprendizado profundo, que têm obtido excelente desempenho, mas ainda produzem segmentações com erros anatômicos. Considerando essa limitação, esse trabalho apresenta um método de segmentação híbrido que combina aprendizado profundo e modelos deformáveis com restrições de forma. A combinação favorece a produção de segmentações anatomicamente mais consistentes. Resultados indicam que o método é competitivo e oferece boa generalização.

Palavras-chave: Segmentação, Ventrículo esquerdo, Ressonância Magnética Cardíaca, Aprendizado profundo, Modelos deformáveis

Referências

Araujo, R. M., Maciel, R. S., and Boscarioli, C. (2017). I GranDSI-BR: Grandes Desafios de Pesquisa em Sistemas de Informação no Brasil (2016-2026). Comissão Especial de Sistemas de Informação (CE-SI) da Sociedade Brasileira de Computação (SBC).

Arrieta, C., Uribe, S., Sing-Long, C., Hurtado, D., Andia, M., Irarrazaval, P., and Tejos, C. (2017). Simultaneous left and right ventricle segmentation using topology preserving level sets. Biomedical Signal Processing and Control, 33:88 – 95.

Avendi, M. R., Kheradvar, A., and Jafarkhani, H. (2016). A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Medical Image Analysis, 30:108 – 119.

Bai, W., Shi, W., O’Regan, D. P., Tong, T., Wang, H., Jamil-Copley, S., Peters, N. S., and Rueckert, D. (2013). A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: Application to cardiac MR images. IEEE Transactions on Medical Imaging, 32(7):1302–1315.

Bergamasco, L. C. C. (2018). Recuperação de objetos médicos 3D utilizando harmônicos esféricos e redes de fluxo. PhD thesis, Universidade de São Paulo.

Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P.-A., Cetin, I., Lekadir, K., Camara, O., Ballester, M. A. G., Sanroma, G., Napel, S., Petersen, S., Tziritas, G., Grinias, E., Khened, M., Kollerathu, V. A., Krishnamurthi, G., Rohe, M.-M., Pennec, X., Sermesant, M., Isensee, F., Jager, P., Maier-Hein, K. H., Full, P. M., Wolf, I., Engelhardt, S., Baumgartner, C. F., Koch, L. M., Wolterink, J. M., Isgum, I., Jang, Y., Hong, Y., Patravali, J., Jain, S., Humbert, O., and Jodoin, P.-M. (2018). Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Transactions on Medical Imaging, 37(11):2514–2525.

Curiale, A. H., Colavecchia, F. D., Kaluza, P., Isoardi, R. A., and Mato, G. (2017). Automatic myocardial segmentation by using a deep learning network in cardiac MRI. In 2017 XLIII Latin American Computer Conference (CLEI), pages 1–6, Cordoba, Argentina. IEEE.

Hajiaghayi, M., Groves, E. M., Jafarkhani, H., and Kheradvar, A. (2017). A 3D active contour method for automated segmentation of the left ventricle from magnetic resonance images. IEEE Transactions on Biomedical Engineering, 64(1):134–144.

Hockings, P., Saeed, N., Simms, R., Smith, N., Hall, M. G., Waterton, J. C., and Sourbron, S. (2020). MRI biomarkers. In Advances in Magnetic Resonance Technology and Applications, pages liii–lxxxvi. Elsevier.

Hu, H., Gao, Z., Liu, L., Liu, H., Gao, J., Xu, S., Li, W., and Huang, L. (2014). Automatic segmentation of the left ventricle in cardiac MRI using local binary fitting model and dynamic programming techniques. PLoS ONE, 9(12):1–17.

Hu, H., Liu, H., Gao, Z., and Huang, L. (2013). Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming. Magnetic Resonance Imaging, 31(4):575 – 584.

Hu, H., Pan, N., Wang, J., Yin, T., and Ye, R. (2019). Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming. Neurocomputing, 347:139 – 148.

Karimi, D. and Salcudean, S. E. (2020). Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Transactions on Medical Imaging, 39(2):499–513.

Khened, M., Kollerathu, V. A., and Krishnamurthi, G. (2019). Fully convolutional multi-scale residual densenets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers. Medical Image Analysis, 51:21 – 45.

Li, C., Xu, C., Gui, C., and Fox, M. D. (2010). Distance regularized level set evolution and its application to image segmentation. IEEE Transactions on Image Processing, 19(12):3243–3254.

Liu, H., Hu, H., Xu, X., and Song, E. (2012). Automatic left ventricle segmentation in cardiac MRI using topological stable-state thresholding and region restricted dynamic programming. Academic Radiology, 19(6):723 – 731.

Liu, Y., Captur, G., Moon, J. C., Guo, S., Yang, X., Zhang, S., and Li, C. (2016). Distance regularized two level sets for segmentation of left and right ventricles from cine-MRI. Magnetic Resonance Imaging, 34(5):699 – 706.

Ma, Y., Wang, L., Ma, Y., Dong, M., Du, S., and Sun, X. (2016). An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images. International Journal of Computer Assisted Radiology and Surgery, 11(11):1951– 1964.

Ngo, T. A., Lu, Z., and Carneiro, G. (2017). Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance. Medical Image Analysis, 35:159 – 171.

ORGANIZACÃO MUNDIAL DA SAÚDE (2021). The top 10 causes of death. Disponível em: https://www.who.int/en/news-room/fact-sheets/detail/the-top-10-causes-of-death. Acesso em: 15 fev. 2022.

Petitjean, C. and Dacher, J. (2011). A review of segmentation methods in short axis cardiac MR images. Medical Image Analysis, 15(2):169 – 184.

Pluempitiwiriyawej, C., Moura, J. M. F., Wu, Y. L., and Ho, C. (2005). STACS: new active contour scheme for cardiac MR image segmentation. IEEE Transactions on Medical Imaging, 24(5):593–603.

Radau, P., Lu, Y., Connelly, K., Paul, G., Dick, A. J., and Wright, G. A. (2009). Evaluation framework for algorithms segmenting short axis cardiac MRI.

Ribeiro, M. A. O. and Nunes, F. L. S. (2021). Evaluating the pre-processing impact on the generalization of deep learning networks for left ventricle segmentation. In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, USA. IEEE.

Ribeiro, M. A. O. and Nunes, F. L. S. (2022). Left ventricle segmentation in cardiac MR: a systematic mapping of the last decade. ACM Computing Surveys.

Romaguera, L. V., Romero, F. P., Filho, C. F. F. C., and Costa, M. G. F. (2018). Myocardial segmentation in cardiac magnetic resonance images using fully convolutional neural networks. Biomedical Signal Processing and Control, 44:48 – 57.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Munich, Germany. Springer International Publishing.

Soomro, S., Akram, F., Munir, A., Lee, C. H., and Choi, K. N. (2017). Segmentation of left and right ventricles in cardiac MRI using active contours. Computational and Mathematical Methods in Medicine, 2017:1–16.

Tong, Q., Yuan, Z., Liao, X., Zheng, M., Zhu, W., Zhang, G., and Ning, M. (2017). A joint multi-scale convolutional network for fully automatic segmentation of the left ventricle. In IEEE International Conference on Image Processing (ICIP), pages 3110– 3114, Beijing, China. IEEE.

Tufvesson, J., Hedstrom, E., Steding-Ehrenborg, K., Carlsson, M., Arheden, H., and Heiberg, E. (2015). Validation and development of a new automatic algorithm for time-resolved segmentation of the left ventricle in magnetic resonance imaging. BioMed Research International, 2015:1–12.

Waite, S., Kolla, S., Jeudy, J., Legasto, A., Macknik, S. L., Martinez-Conde, S., Krupinski, E. A., and Reede, D. L. (2017). Tired in the reading room: The influence of fatigue in radiology. Journal of the American College of Radiology, 14(2):191–197.

Yang, C., Wu, W., Su, Y., and Zhang, S. (2017a). Left ventricle segmentation via two-layer level sets with circular shape constraint. Magnetic Resonance Imaging, 38:202 – 213.

Yang, D., Huang, Q., Axel, L., and Metaxas, D. (2018). Multi-component deformable models coupled with 2D-3D U-net for automated probabilistic segmentation of cardiac walls and blood. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 479–483, Washington, USA. IEEE.

Yang, X., Su, Y., Duan, R., Fan, H., Yeo, S. Y., Lim, C., Zhong, L., and Tan, R. S. (2016). Cardiac image segmentation by random walks with dynamic shape constraint. IET Computer Vision, 10(1):79–86.

Yang, X., Zeng, Z., and Yi, S. (2017b). Deep convolutional neural networks for automatic segmentation of left ventricle cavity from cardiac magnetic resonance images. IET Computer Vision, 11(8):643–649.

Yuan, T., Tong, Q., Liao, X., Du, X., and Zhao, J. (2018). Fully automatic segmentation of the left ventricle using multi-scale fusion learning. In 2018 24th International Conference on Pattern Recognition (ICPR), pages 3838–3843, Beijing, China. IEEE.

Zotti, C., Luo, Z., Lalande, A., and Jodoin, P. M. (2019). Convolutional neural network with shape prior applied to cardiac MRI segmentation. IEEE Journal of Biomedical and Health Informatics, 23(3):1119–1128.
Publicado
16/05/2022
RIBEIRO, Matheus A. O.; NUNES, Fatima L. S.. Segmentação do ventrículo esquerdo em exames de Ressonância Magnética Cardíaca com aprendizado profundo e modelos deformáveis contendo restrições de forma. In: CONCURSO DE TESES E DISSERTAÇÕES EM SISTEMAS DE INFORMAÇÃO - SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 18. , 2022, Curitiba/PR. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 113-126. DOI: https://doi.org/10.5753/sbsi_estendido.2022.222257.