Abstract
Multi-model data can enhance brain tumor segmentation for the rich information it provides. However, it also introduces some redundant information that interferes with the segmentation estimation, as some modalities may catch features irrelevant to the tissue of interest. Besides, the ambiguous boundaries and irregulate shapes of different grade tumors lead to a non-confidence estimate of segmentation quality. Given these concerns, we exploit an uncertainty-guided U-shaped transformer with multiple heads to construct drop-out format masks for robust training. Specifically, our drop-out masks are composed of boundary mask, prior probability mask, and conditional probability mask, which can help our approach focus more on uncertainty regions. Extensive experimental results show that our method achieves comparable or higher results than previous state-of-the-art brain tumor segmentation methods, achieving average dice coefficients of \(91.37\%\) and Hausdorff distance of 4.91 on the BraTS2021 dataset. Our code is freely available at https://github.com/chaineypung/BTS-UGT
Graphical abstract
Similar content being viewed by others
Data availibility
The data that support the findings of this study are openly available at https://www.kaggle.com/datasets/dschettler8845/brats-2021-task1
References
Deo S, Sharma J, Kumar S (2022) Globocan 2020 report on global cancer burden: challenges and opportunities for surgical oncologists. Ann Surg Oncol 29(11):6497–6500
Farmanfarma K. K., M, Mohammadian Shahabinia Z, et al. (2019) “Brain cancer in the world: an epidemiological review,” World Cancer Research Journal 6(5),
Hoover J.M, Morris J.M, and Meyer F.B, (2011) “Use of preoperative magnetic resonance imaging t1 and t2 sequences to determine intraoperative meningioma consistency,” Surg Neurol Int 2
Zhang D, Huang G, Zhang Q et al (2021) Cross-modality deep feature learning for brain tumor segmentation. Pattern Recognition 110 107562
Zhang Y, Yang J, Tian J, et al. (2021) “Modality-aware mutual learning for multi-modal medical image segmentation,” International Conference on Medical Image Computing and Computer-Assisted Intervention, 589–599
Jin B, Cruz L, Gonçalves N (2020) Deep facial diagnosis: deep transfer learning from face recognition to facial diagnosis. IEEE Access 8:123649–123661
Zheng Q, Zhao P, Li Y et al (2021) Spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification. Neural Comput Appl 33(13):7723-7745
Zheng Q, Zhao P, Zhang D et al (2021) Mr-dcae: manifold regularization-based deep convolutional autoencoder for unauthorized broadcasting identification. Int J Intell Syst 36(12):7204–7238
Xiao Z, Xu X, Xing H et al (2021) Rtfn: a robust temporal feature network for time series classification. Information sciences 571:65–86
Zheng Q, Tian X, Yang M et al (2020) Pac-bayesian framework based drop-path method for 2d discriminative convolutional network pruning. Multidimens Syst Signal 31(3):793–827
Jiang Z, Ding C, Liu M et al (2019) Two-stage cascaded u-net: 1st place solution to brats challenge 2019 segmentation task in International MICCAI brainlesion workshop, 231–241. Springer
Isensee F, Jäger P.F., Full P.M., et al. (2020) “nnu-net for brain tumor segmentation,” International MICCAI Brainlesion Workshop, 118–132
Isensee F, Jaeger PF, Kohl SA et al (2021) nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18(2):203–211
Wang W, Chen C, Ding M, et al. (2021) “Transbts: multimodal brain tumor segmentation using transformer,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 109–119
Hatamizadeh A, Tang Y, Nath V, et al. (2022) “Unetr: transformers for 3d medical image segmentation,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 574–584
Zheng Q, Zhao P, Wang H et al (2022) Fine-grained modulation classification using multi-scale radio transformer with dual-channel representation. IEEE Communications Letters 26(6):1298–1302
Touvron H, Cord M, Douze M, et al. (2021) “Training data-efficient image transformers & distillation through attention,” in International Conference on Machine Learning, 10347–10357
Zheng S, Lu J, Zhao H, et al. (2021) “Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6881–6890
Chen J, Lu Y, Yu Q, et al. (2021) “Transunet: transformers make strong encoders for medical image segmentation,” arXiv:2102.04306
Liu Z, Lin Y, Cao Y, et al. (2021) “Swin transformer: hierarchical vision transformer using shifted windows,” in Proceedings of the IEEE/CVF International Conference o Computer Vision, 10012–10022
Goetz M, Weber C, Binczyk F et al (2015) Dalsa: domain adaptation for supervised learning from sparsely annotated mr images. IEEE transactions on medical imaging 35(1):184–196
McKinley R, Meier R, Wiest R (2018) Ensembles of densely-connected cnns with label-uncertainty for brain tumor segmentation, in International MICCAI Brainlesion Workshop, 456–465. Springer
Jungo A, McKinley R, Meier R et al (2017) Towards uncertainty-assisted brain tumor segmentation and survival prediction, in International MICCAI Brainlesion Workshop, 474–485. Springer
Lakshminarayanan B, Pritzel A, and Blundell C, (2017) “Simple and scalable predictive uncertainty estimation using deep ensembles,” Advances in neural information processing systems 30
Gal Y, and Ghahramani Z, (2016) “Dropout as a bayesian approximation: Representing model uncertainty in deep learning,” in international conference on machine learning, 1050–1059, PMLR
Amersfoort J. Van, Smith L, Teh Y. W, et al. (2020) “Uncertainty estimation using a single deep deterministic neural network,” in International conference on machine learning, 9690–9700, PMLR
Sensoy M, Kaplan L, and Kandemir M, (2018) “Evidential deep learning to quantify classification uncertainty,” Advances in neural information processing systems 31
McKinley R, Rebsamen M, Meier R et al (2020) Triplanar ensemble of 3d-to-2d cnns with label-uncertainty for brain tumor segmentation, in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 5th International Workshop, BrainLes 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 17, 2019, Revised Selected Papers, Part I 5, 379–387. Springer
Mehrtash A, Wells WM, Tempany CM et al (2020) Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE transactions on medical imaging 39(12):3868–3878
Jungo A, Meier R, Ermis E et al (2018) On the effect of inter-observer variability for a reliable estimation of uncertainty of medical image segmentation, in Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference, Granada, Spain, September 16–20, 2018, Proceedings, Part I, 682–690. Springer
Nair T, Precup D, Arnold DL et al (2020) Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation. Medical image analysis 59 101557
Kohl S, Romera-Paredes B, Meyer C, et al. (2018) “A probabilistic u-net for segmentation of ambiguous images,” Adv Neural Inf Process 31
Mukhoti J, Amersfoort J, van Torr P.H., et al. (2021) “Deep deterministic uncertainty for semantic segmentation,” arXiv:2111.00079
Peiris H, Hayat M, Chen Z, et al. (2021) “A volumetric transformer for accurate 3d tumor segmentation,” arXiv:2111.13300
Dosovitskiy A, Beyer L, Kolesnikov A, et al. (2020) “An image is worth 16x16 words: transformers for image recognition at scale,” arXiv:2010.11929
Yang F, Zhai Q, Li X, et al. (2021) “Uncertainty-guided transformer reasoning for camouflaged object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 4146–4155
Myronenko A (2018) “3d mri brain tumor segmentation using autoencoder regularization,” in International MICCAI Brainlesion Workshop, 311–320
Taha AA, Hanbury A (2015) Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC medical imaging 15(1):1–28
Menze BH, Jakab A, Bauer S et al (2014) The multimodal brain tumor image segmentation benchmark (brats). IEEE transactions on medical imaging 34(10):1993–2024
Chang J, Zhang X, Ye M, et al. (2018) “Brain tumor segmentation based on 3d unet with multi-class focal loss,” in 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, 1–5
Chen Z, Xie L, Chen Y et al. (2021) “Generative adversarial network based cerebrovascular segmentation for time-of-flight magnetic resonance angiography image,” Neurocomputing
Chen C, Liu X, Ding M, et al. (2019) “3d dilated multi-fiber network for real-time brain tumor segmentation in mri,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 184–192
Shen H, Wang R, Zhang J, et al. (2017) “Boundary-aware fully convolutional network for brain tumor segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 433–441, Springer
Xiao Z, Zhang H, Tong H, et al. (2022) “An efficient temporal network with dual self-distillation for electroencephalography signal classification,” in 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 1759–1762, IEEE
Xing H, Xiao Z, Zhan D et al (2022) Selfmatch: robust semisupervised time-series classification with self-distillation. Int J Intell Syst 37(11):8583–8610
Cheng J, Liu J, Kuang H et al (2022) A fully automated multimodal mri-based multi-task learning for glioma segmentation and idh genotyping. IEEE Transactions on Medical Imaging 41(6):1520–1532
Tanno R, Saeedi A, Sankaranarayanan S et al. (2019) “Learning from noisy labels by regularized estimation of annotator confusion,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11244–11253
Acknowledgements
This research was sponsored in part by the National Natural Science Foundation of China (Grant No. 62002327, 61976190, 62073294, U22A2040); Natural Science Foundation of Zhejiang Province (Grant No. LQ21F020017, LZ21F030003); The Key Technology Research and Development Program of Zhejiang Province (Grant No. 2020C03070)
Author information
Authors and Affiliations
Contributions
Zan Chen: writing—original draft, methodology, investigation, validation, formal analysis, funding acquisition. Chenxu Peng: writing—original draft, methodology, software, validation, visualization. Wenlong Guo: software, validation, visualization. Lei Xie: investigation, validation, data curation. Qichuan Zhuge: resources, supervision, data curation. Caiyun Wen: investigation, resources, project administration. Yuanjing Feng: writing—review and editing, conceptualization, methodology, supervision, project administration, formal analysis, funding acquisition.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, Z., Peng, C., Guo, W. et al. Uncertainty-guided transformer for brain tumor segmentation. Med Biol Eng Comput 61, 3289–3301 (2023). https://doi.org/10.1007/s11517-023-02899-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-023-02899-8