Abstract
Recently, brain tumor segmentation has achieved great success, partially because of deep learning-based relation exploration and multiscale analysis. However, the computational complexity hinders the real-time application. In this paper, we propose a revised multitask learning approach in which a lightweight network with only two scales is adopted to segment different kinds of tumor regions. Moreover, we design a hybrid hard sampling method that considers both sample sparsity and effectiveness. Extensive experiments on the BraTS19 segmentation challenge dataset have shown that our proposed method improves the Dice coefficient by a margin of 0.4–1.0 for different kinds of brain tumor regions and obtains results that are competitive with state-of-the-art brain tumor segmentation approaches.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R.T., Berger, C., Ha, S.M., Rozycki, M., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv preprint arXiv:1811.02629 (2018)
Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. In: Proceedings of the International Conference on Machine Learning, pp. 2285–2294 (2015)
Chen, W., Sun, T., Li, M., Jiang, H., Zhou, C.: A new image co-segmentation method using saliency detection for surveillance image of coal miners. Comput. Electr. Eng. 40(8), 227–235 (2014)
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Chen, H., Dou, Q., Yu, L., Qin, J., Heng, P.-A.: VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images. NeuroImage 170, 446–455 (2018)
Chong, Y., Chen, W., Li, Z., Lam, W.H.K., Zheng, C., Li, Q.: Integrated real-time vision-based preceding vehicle detection in urban roads. Neurocomputing 116, 144–149 (2013)
Dolz, J., Gopinath, K., Yuan, J., Lombaert, H., Desrosiers, C., Ayed, I.B.: HyperDense-Net: a hyper-densely connected CNN for multi-modal image segmentation. IEEE Trans. Med. Imaging 38(5), 1116–1126 (2018)
Hamghalam, M., Lei, B., Wang, T.: Brain Tumor Synthetic Segmentation in 3D Multimodal MRI Scans. arXiv preprint arXiv:1909.13640 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., Maier-Hein, K.H: No new-net. In: International MICCAI Brainlesion Workshop, pp. 234–244 (2018)
Li, X., Luo, G., Wang, K.: Multi-step Cascaded Networks for Brain Tumor Segmentation, International MICCAI Brainlesion Workshop (2019)
Liu, J., Zong, G.: New delay-dependent asymptotic stability conditions concerning BAM neural networks of neutral type. Neurocomputing 72(10–12), 2549–2555 (2009)
Liu, J.-X., Xu, Y., Zheng, C.-H., Kong, H., Lai, Z.-H.: RPCA-based tumor classification using gene expression data. IEEE/ACM Trans. Comput. Biol. Bioinform (TCBB) 12(4), 964–970 (2015)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)
McKinley, R., Meier, R., Wiest, R.: Ensembles of densely-connected CNNs with label-uncertainty for brain tumor segmentation. In: International MICCAI Brainlesion Workshop, pp. 456–465 (2018)
Myronenko, A.: 3D MRI brain tumor segmentation using autoencoder regularization. In: International MICCAI Brainlesion Workshop, pp. 311–320 (2018)
Ren, X., Zhang, L., Ahmad, S., Nie, D., Yang, F., Xiang, L., Wang, Q., Shen, D.: Task decomposition and synchronization for semantic biomedical image segmentation. IEEE Trans. Med. Imaging 39(5), 120–130 (2019)
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: Hints for thin deep nets. In: Proceedings of the International Conference on Learning Representations, pp. 520–530 (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shao, H.: Less conservative delay-dependent stability criteria for neural networks with time-varying delays. Neurocomputing 73(7–9), 1528–1532 (2010)
Vu, M.H., Nyholm, T., Löfstedt, T.: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networks. arXiv preprint arXiv:1910.05338 (2019)
Wang, F., Jiang, R., Zheng, L., Biswal, B., Meng, C.: Brain-wise Tumor Segmentation and Patient Overall Survival Prediction. arXiv preprint arXiv:1909.12901 (2019)
Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks. In: International MICCAI Brainlesion Workshop, pp. 178–190 (2017)
Wu, Y., Wu, Y., Chen, Y.: Mean square exponential stability of uncertain stochastic neural networks with time-varying delay. Neurocomputing 72(10–12), 2379–2384 (2009)
Zheng, C.-H., Huang, D.-S., Zhang, L., Kong, X.-Z.: Tumor clustering using nonnegative matrix factorization with gene selection. IEEE Trans. Inf. Technol. Biomed. 13(4), 599–607 (2009)
Zheng, C.-H., Zhang, L., Ng, T.-Y., Shiu, C.K., Huang, D.-S.: Metasample-based sparse representation for tumor classification. IEEE Trans. Inf. Technol. Biomed. 8(5), 1273–1282 (2011)
Zhou, C., Liu, C.: An efficient segmentation method using saliency object detection. Multimed. Tools Appl. 74(15), 5623–5634 (2015)
Zhou, C., Wu, D., Qin, W., Liu, C.: An efficient two-stage region merging method for interactive image segmentation. Comput. Electr. Eng. 54, 220–229 (2016)
Acknowledgements
This work was supported in part by the National Key R&D Program of China under Grant 2016YFB1000400, in part by the National Natural Science Foundation of China under Grant 61972351, in part by the Scientific Research Foundation of National Health and Family Planning Commission under Grant WKJ-ZJ-1814, in part by the Key R&D Plan of Zhejiang Province under Grant 2019C03002, in part by the Natural Science Foundation of Zhejiang Province under Grant LY19F030005 and Grant LY18F020008, and in part by the Hangzhou Major Science and Technology Innovation Project under Grant 20172011A038.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cheng, G., Cheng, J., Luo, M. et al. Effective and efficient multitask learning for brain tumor segmentation. J Real-Time Image Proc 17, 1951–1960 (2020). https://doi.org/10.1007/s11554-020-00961-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-020-00961-4