Automatic Prostate Segmentation in Magnetic Resonance Images Using Convolutional Neural Networks and a Probabilistic Map

• Jonnison L. Ferreira UFMA
• Giovanni L. F. da Silva UFMA
• Artur B. S. Reis UFMA
• André B. Cavalcante UFMA
• Aristófanes C. Silva UFMA
• Anselmo C. de Paiva UFMA

DOI: https://doi.org/10.5753/sbcas.2018.3683

Abstract

Prostate cancer is the second most common type of cancer among men, and prostate cancer screening has been increasing for prevention, diagnosis and treatment. Manual segmentation of the prostate is extremely timeconsuming and prone to variability among different specialists, suggesting the development of automatic techniques for prostate segmentation. In this work, we propose a fully automatic method for the prostate segmentation from magnetic resonance imaging using a deep learning technique and probabilistic map. The experimental results obtained here indicate a satisfactory segmentation, considering that we obtain an average Dice similarity coefficient of 85.17%.

References

Al-Qunaieer, F. S., Tizhoosh, H. R., and Rahnamayan, S. (2014). Multi-resolution level sets with shape priors: a validation report for 2d segmentation of prostate gland in t2w mr images. Journal of digital imaging, 27(6):833–847.

Bloch, N., Madabhushi, A., Huisman, H., et al. (2015). Nci-isbi 2013 challenge: automated segmentation of prostate structures.

Duda, R. (1973). Pattern classification and scene analysis. New-York, London, Sydny, Tronto A Wiley-Interscience Publication.

Gonzalez, R. and Woods, R. (2008). Digital image processing. Pearson, Prentice Hall.

INCA (2018). Instituto nacional do câncer - câncer -tipo - prostata. [link]. Acessado: 23 março 2018.

Karimi, D., Samei, G., Shao, Y., and Salcudean, T. (2017). A novel deep learning-based method for prostate segmentation in t2-weighted magnetic resonance imaging.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105.

LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324.

Li, A., Li, C., Wang, X., Eberl, S., Feng, D. D., and Fulham, M. (2013). Automated segmentation of prostate mr images using prior knowledge enhanced random walker. In Digital Image Computing: Techniques and Applications (DICTA), 2013 International Conference on, pages 1–7. IEEE.

Maan, B. and van der Heijden, F. (2012). Prostate mr image segmentation using 3d active appearance models. MICCAI Grand Challenge: Prostate MR Image Segmentation, 2012.

Mahapatra, D. and Buhmann, J. M. (2014). Prostate mri segmentation using learned semantic knowledge and graph cuts. IEEE Transactions on Biomedical Engineering, 61(3):756–764.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.

Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Smith, K., Clark, K., Bennett, W., Nolan, T., Kirby, J., Wolfsberger, M., Moulton, J., Vendt, B., and Freymann, J. (2015). Data from prostate-3t. DOI: 10.7937/K9/TCIA.2015.QJTV5IL5. Acessado: 01 agosto 2017.

Society, A. C. (2018). About prostate cancer. [link]. Acessado: 23 março 2018.

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., and Anguelov, D. (2015). & rabinovich, a.(2015). going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9.

Tian, Z., Liu, L., Zhang, Z., and Fei, B. (2018). Psnet: prostate segmentation on mri based on a convolutional neural network. Journal of Medical Imaging, 5(2):021208.

Yang, X., Rossi, P., Ogunleye, T., Marcus, D. M., Jani, A. B., Mao, H., Curran, W. J., and Liu, T. (2014). Prostate ct segmentation method based on nonrigid registration in ultrasound-guided ct-based hdr prostate brachytherapy. Medical physics, 41(11).

Yang, X., Zhan, S., and Xie, D. (2016). Landmark based prostate mri segmentation via improved level set method. In 2016 IEEE 13th International Conference on Signal Processing (ICSP), pages 29–34.

Zeiler, M. D. A. (2012). An adaptive learning rate method. arxiv preprint. arXiv preprint arXiv:1212.5701.

Zhu, Q., Du, B., Turkbey, B., Choyke, P. L., and Yan, P. (2017). Deeply-supervised cnn for prostate segmentation. In Neural Networks (IJCNN), 2017 International Joint Conference on, pages 178–184. IEEE.