Segmentación de tejido cerebral mediante redes neuronales convolucionales basadas en U-Net

• David Jiménez-Murillo ^[1] ; Stiven Alexander Henao-Garcés ^[1] ; Andrés Eduardo Castro-Ospina ^[1] ; Leonardo Duque-Muñoz ^[1] ; Daniel Nieto-Mora ^[1]
  1. [1] Instituto Tecnológico Metropolitano,Medellín, Colombia
• Localización: RISTI: Revista Ibérica de Sistemas e Tecnologias de Informação, ISSN-e 1646-9895, Nº. 52, 2023, págs. 5-24
• Idioma: español
• DOI: 10.17013/risti.52.5-24
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    La Resonancia Magnética (MRI, por sus siglas en inglés) es un método no invasivo que produce imágenes anatómicas volumétricas de alta resolución. Este método se utiliza comúnmente para diagnosticar diversas patologías cerebrales, como enfermedades desmielinizantes, demencia, enfermedades cerebrovasculares, epilepsia, entre otras. Sin embargo, la segmentación manual de tejidos en estas imágenes es una tarea compleja que requiere una cantidad significativa de tiempo y esfuerzo por parte de especialistas. Para abordar esto, se han propuesto diversas estrategias en la literatura que implican menos participación de expertos, tanto automáticas como semiautomáticas. En este estudio, se realiza una comparación entre una red neuronal convolucional basada en la arquitectura U-Net y otros dos métodos de segmentación de MRI, Dipy y FSL. La comparación utiliza tres conjuntos de datos disponibles públicamente, MRBrainS13, MRBrainS18 e IBSR, que contienen volúmenes de MRI con tejidos cerebrales segmentados manualmente. El rendimiento de cada método se evalúa usando el coeficiente de Dice, el índice de Jaccard, el área bajo la curva y la similitud estructural. Los resultados demuestran que los métodos basados en redes neuronales convolucionales logran mejorar la segmentación de tejido cerebral.

  • English

    Magnetic Resonance Imaging (MRI) is a non-invasive method that produces volumetric, high-resolution anatomy images. This method is commonly used for diagnosing various brain pathologies, such as demyelinating diseases, dementia, cerebrovascular diseases, and epilepsy, among others. However, manually segmenting tissues in these images is a complex task that requires a significant amount of time and effort from specialists. To address this, various strategies have been proposed in the literature that involve less expert involvement, both automatic and semi-automatic. In this study, a comparison is made between a convolutional neural network based on U-Net architecture and two other MRI segmentation methods, Dipy and FSL. The comparison uses three publicly available datasets, MRBrainS13, MRBrainS18, and IBSR, which contain MRI volumes with manually segmented brain tissues. The performance of each method is evaluated using four measures of similarity: The Dice coefficient, the Jaccard index, the area under the curve, and structural similarity. The results demonstrate that the methods based on convolutional neural networks achieve segmentations that are more

• Referencias bibliográficas
  • Akkus, Z., Galimzianova, A., Hoogi, A., Rubin, D. L., & Erickson, B. J. (2017). Deep learning for brain MRI segmentation: state of the...
  • Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan,...
  • Anwar, S. M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., & Khan, M. K. (2018). Medical Image Analysis using Convolutional Neural...
  • Aronica, E., Becker, A. J., & Spreafico, R. (2012). Malformations of cortical development. Brain Pathology, 22(3),380–401.
  • Avants, B. B., Tustison, N. J., Wu, J., Cook, P. A., & Gee, J. C. (2011). An open source multivariate framework for n-tissue segmentation...
  • Billot, B., Greve, D., Van Leemput, K., Fischl, B., Iglesias, J. E., & Dalca, A. V. (2020). A learning strategy for contrast-agnostic...
  • Castillo-Carranza, A. P., Bravo-Huivin, E. K., & Cieza-Mostacero, S. E. (2022). Revisión sistemática: La Aplicación del Deep Learning...
  • Chang, H.-H., & Hsieh, C.-C. (2017). Brain segmentation in MR images using a texturebased classifier associated with mathematical morphology....
  • Chen, L., & Merhof, D. (2018). MixNet: Multi-modality Mix Network for Brain Segmentation. International MICCAI Brainlesion Workshop, 367–377....
  • Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net: learning dense volumetric segmentation from...
  • Clèrigues, A., Valverde, S., Salvi, J., Oliver, A., & Lladó, X. (2023). Minimizing the effect of white matter lesions on deep learning...
  • de Brebisson, A., & Montana, G. (2015). Deep neural networks for anatomical brain segmentation. In Proceedings of the IEEE Conference...
  • Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297–302.
  • Hyman, S. E. (2003). Diagnosing disorders. Scientific American, 289(3), 96–103.
  • Ito, R., Nakae, K., Hata, J., Okano, H., & Ishii, S. (2019). Semi-supervised deep learning of brain tissue segmentation. Neural Networks,...
  • Jaccard, P. (1912). The distribution of the flora in the alpine zone. New Phytologist, 11(2), 37–50.
  • Jenkinson, M., Beckmann, C. F., Behrens, T. E. J., Woolrich, M. W., & Smith, S. M. (2012). FSL (FMRIB Software Library). Neuroimage, 62(2),...
  • Jiang, H., Diao, Z., Shi, T., Zhou, Y., Wang, F., Hu, W., Zhu, X., Luo, S., Tong, G., & Yao, Y. D. (2023). A review of deep learning-based...
  • Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980.
  • Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural...
  • Kuijf, H. J., & Bennink, E. (2019). MRBrainS18 Grand challenge on MR brain segmentation at MICCAI 2018.
  • Kumar, M., Rathore, R. K. S., Srivastava, A., Yadav, S. K., Behari, S., & Gupta, R. K. (2011). Correlation of diffusion tensor imaging...
  • LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE,...
  • Liu, Q., Zhang, N. (2017). A Review of Image Recognition with Deep Convolutional Neural Network. In: Intelligent Computing Theories and Application...
  • Mendrik, A. (2013). Evaluation framework for MR brain image segmentation. MICCAI Grand Challenge.
  • Mendrik, A. M., Vincken, K. L., Kuijf, H. J., Breeuwer, M., Bouvy, W. H., De Bresser, J., Alansary, A., De Bruijne, M., Carass, A., El-Baz,...
  • Ndajah, P., Kikuchi, H., Yukawa, M., Watanabe, H., & Muramatsu, S. (2010). SSIM image quality metric for denoised images. In: Proc. 3rd...
  • Peruzzo, D., Arrigoni, F., Triulzi, F., Righini, A., Parazzini, C., & Castellani, U. (2016). A framework for the automatic detection and...
  • Rashid, T., Liu, H., Ware, J. B., Li, K., Romero, J. R., Fadaee, E., Nasrallah, I. M., Hilal, S., Bryan, R. N., Hughes, T. M., Davatzikos,...
  • Rohlfing, T. (2012). Image Similarity and Tissue Overlaps as Surrogates for Image Registration Accuracy: Widely Used but Unreliable. IEEE...
  • Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International Conference...
  • Sánchez Fernández, I., Yang, E., Amengual-Gual, M., Barcia Aguilar, C., Calvachi Prieto, P., & Peters, J. M. (2021). Convolutional neural...
  • Sarma, A., & Pruthi, S. (2023). Congenital Brain Malformations- Update on Newer Classification and Genetic Basis. Seminars in Roentgenology,...
  • Shamir, R. R., Duchin, Y., Kim, J., Sapiro, G., & Harel, N. (2019). Continuous dice coefficient: a method for evaluating probabilistic...
  • Siddique, N., Paheding, S., Elkin, C. P., & Devabhaktuni, V. (2021). U-net and its variants for medical image segmentation: A review of...
  • Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. ArXiv Preprint ArXiv:1409.1556....
  • Smith, S. M. (2002). Fast robust automated brain extraction. Human Brain Mapping, 17(3), 143–155.
  • Somasundaram, K., & Kalaividya, P. A. (2016). Brain portion segmentation from Magnetic Resonance Images (MRI) of human head scan using...
  • Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with...
  • Toscano, I., Bravo, D. A. M., De-La-torre, M., Juárez, B. A., & Mireles, G. A. G. (2023). Automated analysis of SEM micrographs using...
  • Van Calster, B., Van Belle, V., Condous, G., Bourne, T., Timmerman, D., & Van Huffel, S. (2008). Multi-class AUC metrics and weighted...
  • Woolrich, M. W., Jbabdi, S., Patenaude, B., Chappell, M., Makni, S., Behrens, T., Beckmann, C., Jenkinson, M., & Smith, S. M. (2009)....
  • Zhang, Y., Brady, J. M., & Smith, S. (2000). Hidden Markov random field model for segmentation of brain MR image. Medical Imaging 2000...
  • Zhang, Y., Brady, M., & Smith, S. (2001). Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization...
  • Zubrikhina, M. O., Abramova, O. V, Yarkin, V. E., Ushakov, V. L., Ochneva, A. G., Bernstein, A. V, Burnaev, E. V, Andreyuk, D. S., Savilov,...