Abstract
Accurate and reliable brain tumor segmentation is a critical component in cancer diagnosis. According to deep learning model, a novel brain tumor segmentation method is developed by integrating fully convolutional neural networks (FCNN) and dense micro-block difference feature (DMDF) into a unified framework so as to obtain segmentation results with appearance and spatial consistency. Firstly, we propose a local feature to describe the rotation invariant property of the texture. In order to deal with the change of rotation and scale in texture image, Fisher vector encoding method is used to analyze the texture feature, which can combine with the scale information without increasing the dimension of the local feature. The obtained local features have strong robustness to rotation and gray intensity variation. Then, the non-quantifiable local feature is fused to the FCNN to perform fine boundary segmentation. Since brain tumors occupy a small portion of the image, deconvolutional layers are designed with skip connections to obtain a high quality feature map. Compared with the traditional MRI brain tumor segmentation methods, the experimental results show that the segmentation accuracy and stability has been greatly improved. Average Dice index can be up to 90.98%. And the proposed method has very high real-time performance, where brain tumor image can segment within 1 s.
Similar content being viewed by others
References
Pereira, S. et al., Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans. Med. Imaging:1–1, 2016.
Zhao, Xiaomei, et al. "Brain tumor segmentation using a fully convolutional neural network with conditional random fields." (2016).
Meier, R. et al., Clinical evaluation of a fully-automatic segmentation method for longitudinal brain tumor Volumetry. Sci. Rep. 6(1):23376, 2016.
Rakesh, Z., and Kebin, J., Multiscale CNNs for brain tumor segmentation and diagnosis. Comput. Math. Methods Med. 2016:1–7, 2016.
Kamnitsas, K., et al. "DeepMedic for Brain Tumor Segmentation." 2016.
Szilagyi, Guotai, et al. "Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks." (2017).
Ali, N., et al. Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods. Elsevier Science Publishers B. V.2016.
Dong, H., et al. "Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks." 2017.
Havaei, M., Davy, A., Wardefarley, D. et al., Brain tumor segmentation with deep neural networks.[J]. Med. Image Anal. 35:18–31, 2015.
Zhao, X. et al., A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med. Image Anal. 43:98–111, 2017.
Chang, P. D., Fully convolutional deep residual neural networks for brain tumor segmentation. In: International workshop on Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Cham: Springer, 2016.
Sehgal, A., et al. "Automatic brain tumor segmentation and extraction in MR images." 2016 Conference on Advances in Signal Processing (CASP) IEEE, 2016.
Kaur, A.."An Automatic Brain Tumor Extraction System Using Different Segmentation Methods." Second International Conference on Computational Intelligence & Communication Technology IEEE, 2016.
Lang, L. Zhao, and K. Jia."Brain tumor image segmentation based on convolution neural network." International Congress on Image & Signal Processing IEEE, 2017.
Cabria, I., and Gondra, I., MRI segmentation fusion for brain tumor detection. Inform. Fus. 36:1–9, 2017.
Hussain, S., Anwar, S. M., Majid, M. "Brain tumor segmentation using cascaded deep convolutional neural network." Engineering in Medicine & Biology Society IEEE, 2017.
Qian, P., Zhou, J., Jiang, Y., Liang, F., Zhao, K., Wang, S., Su, K.-H., and Muzic, Jr., R. F., Multi-view maximum entropy clustering by jointly leveraging inter-view collaborations and intra-view-weighted attributes. IEEE Acc. 6:28594–28610, 2018.
Li, Y., Jia, F., and Qin, J., Brain tumor segmentation from multimodal magnetic resonance images via sparse representation. Artif. Intell. Med. 73:1–13, 2016.
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., and Vedaldi, A., Describing textures in the wild. Proc. IEEE Conf. Comput. Vis. Pattern Recog.:3606–3613, 2014.
Chang, P.D..."Fully Convolutional Deep Residual Neural Networks for Brain Tumor Segmentation."2016.
Calonder, M., Lepetit, V., Strecha, C., and Fua, P., Brief: Binary robust independent elementary features. Proc. Eur. Conf. Comput. Vis. (ECCV):778–792, 2010.
Rublee, E., Rabaud, V., Konolige, K., and Bradski, G., ORB: An efficient alternative to sift or surf. Proc. IEEE Int. Conf. Comput. Vis.:2564–2571, 2011.
Sharma, G., ul Hussain, S., and Jurie, F., Local higher-order statistics (LHS) for texture categorization and facial analysis. Proc. Eur. Conf. Comput. Vis.:1–12, 2012.
Sauwen, N. et al., Comparison of unsupervised classification methods for brain tumor segmentation using multi-parametric MRI. Neuroimage Clin. 12.C:753–764, 2016.
KJ Xia, JQ Wang, Y Wu. Robust Alzheimer Disease classification based on Feature Integration Fusion Model for Magnetic[J]. Journal of med. imaging and health infor. vol.7,1-6, 2017.
Chen, J. et al., WLD: A robust local image descriptor. IEEE Trans. Pattern Anal. Mach. Intell. 32(9):1705–1720, Sep, 2010.
Tang, Z., Wang, S., Huo, J., Guo, H., Zhao, H., & Mei, Y.. Bayesian Framework with Non-local and Low-rank Constraint for Image Reconstruction. Journal of Physics Conference Series. 2017.
Perronnin, F., Sánchez, J., and Mensink, T., Improving the fisher kernel for large-scale image classification. Proc. Eur. Conf. Comput. Vis.:143–156, 2010.
Varma, M., and Zisserman, A., A statistical approach to material classifi-cation using image patch exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 31(11):2032–2047, Nov. 2009.
Quan, Y., Xu, Y., Sun, Y., and Luo, Y., Lacunarity analysis on image pat-terns for texture classification. Proc. IEEE Conf. Comput. Vis. Pattern Recog.:160–167, 2014.
Qian, P., Sun, S., Jiang, Y., Kuan-Hao, S., Ni, T., Wang, S., and Jr, R. F. M., Cross-domain, soft-partition clustering with diversity measure and knowledge reference. Pattern Recogn. 50:155–177, 2016.
Agn, M., et al. "Brain Tumor Segmentation Using a Generative Model with an RBM Prior on Tumor Shape. " 2016.
Qian, P., Chung, F., Wang, S., and Deng, Z., Fast graph-based relaxed clustering for large data sets using minimal enclosing ball. IEEE Trans. Syst. Man Cybern. B 42(3):672–687, 2012.
Hussain, S., and Triggs, B., Visual recognition using local quantized patterns. Proc. Eur. Conf. Comput. Vis.:716–729, 2012.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
We declare that we have no conflict of interest. The paper does not contain any studies with human participants or animals performed by any of the authors. Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the Topical Collection on Image & Signal Processing
Rights and permissions
About this article
Cite this article
Deng, W., Shi, Q., Luo, K. et al. Brain Tumor Segmentation Based on Improved Convolutional Neural Network in Combination with Non-quantifiable Local Texture Feature. J Med Syst 43, 152 (2019). https://doi.org/10.1007/s10916-019-1289-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-019-1289-2