Abstract
The Brain tumor image segmentation process is a delicate and a challenging task in medical image analysis. Gliomas are the dominant type of brain tumor, the reason behind which brain image segmentation research has been focusing on. Manual segmentation of Glioma for this type of cancer diagnosis is a difficult and time-consuming task. In this work, we develop an automatic segmentation method to segment 3D MRI brain tumor images. Graph-based Neural Networks (GNNs) is used to exploit the structural information present in graph data by aggregating information over connected nodes, allowing them to effectively capture information relation between data elements. By considering GNN to model the content information of the image, the medical image segmentation problem is transformed into a graph-based energy minimization problem. Aiming at segmenting 3D MRI images, we develop a Deep Learning segmentation method called SCGNN-3DBUNet for 3D brain tumor task segmentation. For that, we have adopted a variation of GNNs for the automatic segmentation of brain tumors from MRI scans by combining an extension of U-Net with GNNs. We evaluated this hybrid approach performance using the online BraTS 2020 dataset. The obtained results are promising compared with the state-of-the-art approaches with a Dice score of 0.89 for the whole tumor.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ravi, D., et al.: Deep learning for health informatics. IEEE J. Biomed. Health Inform. 21, 4–21 (2017)
Kwon, J.M., Lee, Y., Lee, Y., Lee, S., Park, J.: An algorithm based on deep learning for predicting in-hospital cardiac arrest. J. Am. Heart Assoc. 7(13), e008678 (2018)
Shin, H.C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE TMI 35, 1285–1298 (2016)
Zhang, L., Ren, Z.: Comparison of CT and MRI images for the prediction of soft-tissue sarcoma grading and lung metastasis via a convolutional neural networks model. J. Clin. Radiol. 75, 64–69 (2020)
Liu, X., Song, L., Liu, S., Zhang, Y.: A review of deep-learning-based medical image segmentation methods. J. Sustain. 2021(13), 1–21 (2021)
Defferrard, M., Bresson, X., Vandergheynst, P. Convolutional neural networks on graphs with fast localized spectral filtering. In: 30th Conference on Neural Information Processing Systems (NIPS 2016), Spain (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. Int. Conf. MICCA I, 234–241 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp. 448–456 (2015)
Kekre, H.B., Gharge, S.M.: Image segmevntation using extended edge operator for mammography images. IJCSE 2, 1086–1091 (2010)
Falcao, A.X., Udupa, J.K.: A 3D generalization of user-steered live-wire segmentation. J. Med. Image Anal. 4, 389–402 (2000)
Jianbo, S., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)
Moftah, H., Azar, A., Al-Shammari, E., Ghali, N., Hassanien, A., Shoman, M.: Adaptive k-means clustering algorithm for MR breast image segmentation. Neural Comput. Appl. 24(7–8), 1917–1928 (2013)
Gammoudi, I., Mahjoub, M.A.: Brain tumor segmentation using community detection algorithm. In: International Conference on Cyberworlds (CW), pp. 1–7 (2021)
Kamnitsas, K., et al.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. J. Med. Image Anal. 36, 61–78 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., Asari, V.K.: Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. J. Med. Imaging 1–12 (2018)
Tremeau, A., Colantoni, P.: Regions adjacency graph applied to color image segmentation. IEEE Trans. Image Process. 9, 1–10 (2000)
Stutz, D., Hermans, A., Leibe, B.: Superpixels: an evaluation of the state-of-the-art. J. Comput. Vision Image Underst. 166, 1–27 (2018)
Radhakrishna, A., Appu, S., Kevin, S., Aurelien, L., Pascal, F., Sabine, S.: SLIC superpixels compared to stateof-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry, pp. 1–14 (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. Int. Conf. Learn. Represent. 1–14 (2017)
Kurt, H.: Approximation capabilities of multilayer feedforward networks. J. Neural Networks 2, 251–257 (1991)
Bakas, S., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR, pp. 1–15 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gammoudi, I., Ghozi, R., Mahjoub, M.A. (2022). Hybrid Architecture for 3D Brain Tumor Image Segmentation Based on Graph Neural Network Pooling. In: Bădică, C., Treur, J., Benslimane, D., Hnatkowska, B., Krótkiewicz, M. (eds) Advances in Computational Collective Intelligence. ICCCI 2022. Communications in Computer and Information Science, vol 1653. Springer, Cham. https://doi.org/10.1007/978-3-031-16210-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-16210-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16209-1
Online ISBN: 978-3-031-16210-7
eBook Packages: Computer ScienceComputer Science (R0)