Abstract
Brain tumor segmentation remains an open and popular challenge, for which countless medical image segmentation models have been proposed. Based on the platform that BraTS challenge 2021 provided for researchers, we implemented a battery of cutting-edge deep neural networks, such as nnU-Net, UNet++, CoTr, HRNet, and Swin-Unet to directly compare performances amongst distinct models. To improve segmentation accuracy, we first tried several modification techniques (e.g., data augmentation, region-based training, batch-dice loss function, etc.). Next, the outputs from the five best models were averaged using a final ensemble model, of which four models in the committee were organized in different architectures. As a result, the strengths of every single model were amplified by the aggregation. Our model took one of the best performing places in the Brain Tumor Segmentation (BraTS) 2021 competition amongst over 1200 excellent researchers from all over the world, which achieved Dice score of 0.9256, 0.8774, 0.8576 and Hausdor Distances (95%) of 4.36, 14.80, 14.49 for whole tumor, tumor core, and enhancing tumor respectively.
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
Baid, U., et al.: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv:2107.02314 (2021)
Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015). https://doi.org/10.1109/TMI.2014.2377694
Bakas, S., et al.: A dvancing the Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Nat. Sci.ntific Data 4, 170117 (2017). https://doi.org/10.1038/sdata.2017.117
Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. The Cancer Imaging Archive (2017). https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q
Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. The Cancer Imaging Archive (2017). https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2015)
Isensee, F., Jäger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: Automated design of deep learning methods for biomedical image segmentation. arXiv preprint arXiv:1904.08128 (2019)
Isensee, F., Jäger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18, 203–211 (2021). https://doi.org/10.1038/s41592-020-01008-z
Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: UNet++: redesigning skip connections to exploit multiscale features in image segmentation. arXiv:1912.05074v2 (2020)
Wang, J. et al.: Deep high-resolution representation learning for visual recognition. arXiv:1908.07919v2 (2020)
Cao, H., et al.: Swin-Unet: Unet-like pure transformer for medical image segmentation. arXiv:2015.05537v1 (2021)
Xie, Y., Zhang, J., Shen, C., Xia, Y.: CoTr: efficiently bridging CNN and transformer for 3D medical image segmentation. arXiv:2013.03024v1 (2021)
BraTS Challenge Data. https://www.synapse.org/#!Synapse:syn25829067/wiki/610865. Accessed 2 Aug 2021
BraTS Challenge Overview. https://www.synapse.org/#!Synapse:syn25829067/wiki/610863. Accessed 19 Aug 2021
Center for Biomedical Image Computing & Analytics. http://braintumorsegmentation.org/. Accessed 23 Dec 2021
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167v3 (2015)
Chang, Y., Lin, J., Wu, M., Chen, T., Hsu, W.H.: Batch-wise dice loss: rethinking the data imbalance for medical image segmentation. In: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada (2019)
Isensee, F., Jäger, P.F., Full, P.M., Vollmuth, P., Maier-Hein, K.H.: nnU-Net for Brain Tumor Segmentation. arXiv:2011.00848v1 (2020)
Salehil, S.S.M., Erdogmus, D., Gholipour, A.: Tversky loss function for image segmentation using 3D fully convolutional deep networks. arXiv:1706.05721v1 (2017)
Arbeláez, P., Hariharan, B., Gu, C., Gupta, S., Bourdev, L., Malik, J.: Semantic segmentation using regions and parts (2012). https://doi.org/10.1109/CVPR.2012.6248077
Kamnitsas, K., et al.: Ensembles of multiple models and architectures for robust brain tumour segmentation (2017). ISBN: 978-3-319-75237-2
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
Ren, J., Zhang, W., An, N., Hu, Q., Zhang, Y., Zhou, Y. (2022). Ensemble Outperforms Single Models in Brain Tumor Segmentation. In: Crimi, A., Bakas, S. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. Lecture Notes in Computer Science, vol 12962. Springer, Cham. https://doi.org/10.1007/978-3-031-08999-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-08999-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08998-5
Online ISBN: 978-3-031-08999-2
eBook Packages: Computer ScienceComputer Science (R0)
