A fast right ventricle segmentation in cine-MRI from a dense hough representation

Fabio Martínez-Carrillo; Alejandra Moreno Tarazona; Luis Carlos  Guayacán Chaparro; Lola Xiomara Bautista Rozo; Jean Alejandro  Pico

doi:10.33571/rpolitec.v18n35a6

Autores

Fabio Martínez-Carrillo Doctor en Sistemas y Computación. Docente UIS. Bucaramanga, Colombia, Grupo de Investigación BIVL. Universidad Industrial de Santander (UIS)
Alejandra Moreno Universidad Industrial de Santander https://orcid.org/0000-0002-2066-6710
Luis Carlos Guayacán Universidad Industrial de Santander
Lola Bautista Universidad Industrial de Santander https://orcid.org/0000-0002-3853-007X
Jean Pico Universidad Industrial de Santander

DOI:

https://doi.org/10.33571/rpolitec.v18n35a6

Palavras-chave:

Dense Hough Transform, Heart Characterization, RV Segmentation, Heart Disease Classification, Cardiac MRI

Resumo

Segmentation of the right ventricle (RV) is essential for the diagnosis of multiple cardiac pathologies and conditions. However, its manual delineation is a tedious task and computational support is complex due to geometric and dynamic variability. This work introduces a dense Hough transform and representation (HT) that allows a nonparametric characterization of the shape, encoding each voxel by its curvature and orientation. This representation is integrated into a bayesian tracking approach, which efficiently segments the RV structure throughout the cardiac cycle. The proposed approach was evaluated on a public dataset, with 16 patients, achieving a Sørensen-Dice coefficient of 0.87 and 0.92, for complete volumes and basal structures, respectively. These results evidence an adequate fit of the proposed model with respect to RV shape throughout the entire cardiac cycle.

La segmentación del Ventrículo Derecho (VD) es esencial para el diagnóstico de múltiples patologías y condiciones cardiacas. Sin embargo, su delineación manual es una tarea tediosa y el soporte computacional resulta complejo debido a la variabilidad geométrica y dinámica. Este trabajo introduce una transformación y representación densa de Hough (TH) que permite una caracterización no paramétrica de la forma, codificando cada vóxel por su curvatura y orientación. Esta representación es integrada en un enfoque de seguimiento bayesiano, que logra de forma eficiente segmentar la estructura del VD, a lo largo del ciclo cardíaco. El enfoque propuesto fue evaluado en un conjunto de datos públicos, con 16 pacientes, logrando un coeficiente Sørensen-Dice de 0,87 y 0,92, para volúmenes completos y estructuras basales, respectivamente. Estos resultados evidencian una adecuada adaptación del modelo propuesto respecto a la forma del VD a lo largo de todo el ciclo cardíaco.

Métricas do artigo

Resumo: 350 PDF (Español (España)): 132 HTML (Español (España)): 47

Métricas PlumX

Biografia do Autor

Alejandra Moreno, Universidad Industrial de Santander

Referências

World Health Organization. (2019). World health statistics 2019: monitoring health for the SDGs, sustaina-ble development goals. World Health Organization.

Labrador, A. M. A., Martínez, F., & Castro, E. R. (2013, November). A novel right ventricle segmentation approach from local spatio-temporal MRI information. In Iberoamerican Congress on Pattern Recognition (pp. 206-213). Springer, Berlin, Heidelberg.

Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P. A., ... & 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.

Petitjean, C., Zuluaga, M. A., Bai, W., Dacher, J. N., Grosgeorge, D., Caudron, J., ... & Yuan, J. (2015). Right ventricle segmentation from cardiac MRI: a collation study. Medical image analysis, 19(1), 187-202.

Vanderpool, R. R., Pinsky, M. R., Naeije, R., Deible, C., Kosaraju, V., Bunner, C., ... & Simon, M. A. (2015). RV-pulmonary arterial coupling predicts outcome in patients referred for pulmonary hypertension. Heart, 101(1), 37-43.

Buchner, S., Eglseer, M., Debl, K., Hetzenecker, A., Luchner, A., Husser, O., ... & Arzt, M. (2015). Sleep disordered breathing and enlargement of the right heart after myocardial infarction. European Respiratory Journal, 45(3), 680-690.

Gilbert, K., Lam, H. I., Pontré, B., Cowan, B. R., Occleshaw, C. J., Liu, J. Y., & Young, A. A. (2017). An interactive tool for rapid biventricular analysis of congenital heart disease. Clinical physiology and functional imaging, 37(4), 413-420.

Petitjean, C., & Dacher, J. N. (2011). A review of segmentation methods in short axis cardiac MR imag-es. Medical image analysis, 15(2), 169-184.

Winter, M. M., Bernink, F. J., Groenink, M., Bouma, B. J., van Dijk, A. P., Helbing, W. A., ... & Mulder, B. J. (2008). Evaluating the systemic right ventricle by CMR: the importance of consistent and reproducible de-lineation of the cavity. Journal of Cardiovascular Magnetic Resonance, 10(1), 1-8.

Tran, P. V. (2016). A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv preprint arXiv:1604.00494.

El-Rewaidy, H., Ibrahim, E. S., & Fahmy, A. S. (2016). Segmentation of the right ventricle in MRI images using a dual active shape model. IET Image Processing, 10(10), 717-723.

Sedai, S., Garnavi, R., Roy, P., & Liang, X. (2015, August). Multi-atlas label fusion using hybrid of dis-criminative and generative classifiers for segmentation of cardiac MR images. In 2015 37th Annual Interna-tional Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2977-2980). IEEE.

Xie, L., Sedai, S., Liang, X., Compas, C. B., Wang, H., Yushkevich, P. A., & Syeda-Mahmood, T. (2015, April). Multi-atlas label fusion with augmented atlases for fast and accurate segmentation of cardiac MR images. In 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI) (pp. 376-379). IEEE.

Zhen, X., Wang, Z., Islam, A., Bhaduri, M., Chan, I., & Li, S. (2016). Multi-scale deep networks and re-gression forests for direct bi-ventricular volume estimation. Medical image analysis, 30, 120-129.

Avendi, M. R., Kheradvar, A., & Jafarkhani, H. (2016). Fully automatic segmentation of heart chambers in cardiac MRI using deep learning. Journal of Cardiovascular Magnetic Resonance, 18(1), 1-3.

Manzanera, A. (2012). Dense Hough transforms on gray level images using multi-scale derivatives. In SIXIEME WORKSHOP AMINA 2012" Applications Médicales de l'Informatique: Nouvelles Approches".

Duffner, S., & Garcia, C. (2013). Pixeltrack: a fast adaptive algorithm for tracking non-rigid objects. In Proceedings of the IEEE international conference on computer vision (pp. 2480-2487).

Luo, G., An, R., Wang, K., Dong, S., & Zhang, H. (2016, September). A deep learning network for right ventricle segmentation in short-axis MRI. In 2016 Computing in Cardiology Conference (CinC) (pp. 485-488). IEEE.

El-Rewaidy, H., Ibrahim, E. S., & Fahmy, A. S. (2016). Segmentation of the right ventricle in MRI images using a dual active shape model. IET Image Processing, 10(10), 717-723.

El-Rewaidy, H., & Fahmy, A. S. (2015, April). Segmentation of the Right Ventricle in MR images using dual active shape model in the Bookstein coordinates. In 2015 IEEE 12th International Symposium on Bio-medical Imaging (ISBI) (pp. 1320-1323). IEEE.

Maier, O. M., Jiménez, D., Santos, A., & Ledesma-Carbayo, M. J. (2012). Segmentation of RV in 4D cardiac MR volumes using region-merging graph cuts. In 2012 Computing in Cardiology (pp. 697-700). IEEE.

Zuluaga, M. A., Cardoso, M. J., Modat, M., & Ourselin, S. (2013). Multi-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion. In International Conference on Functional Imaging and Modeling of the Heart (pp. 174-181). Springer, Berlin, Heidelberg.

Bai, W., Shi, W., Wang, H., Peters, N. S., & Rueckert, D. (2012). Multiatlas based segmentation with lo-cal label fusion for right ventricle MR images. image, 6, 9.

Grosgeorge, D., Petitjean, C., Dacher, J. N., & Ruan, S. (2013). Graph cut segmentation with a sta-tistical shape model in cardiac MRI. Computer Vision and Image Understanding, 117(9), 1027-1035.