Abstract
We propose the first Self-Attention Capsule Network that was designed to deal with unique core challenges of medical imaging, specifically for tissue classification. These challenges are - significant data heterogeneity with statistics variability across imaging domains, insufficient spatial context and local fine-grained details, and limited training data. Moreover, our proposed method solves limitations of the baseline Capsule Networks (CapsNet) such as handling complicated challenging data and limited computational resources. To cope with these challenges, our method is composed of a self-attention module that simplifies the complexity of the input data such that the CapsNet routing mechanism can be efficiently used, while extracting much richer contextual information, compared with CNNs. To demonstrate the strengths of our method, it was extensively evaluated on three diverse medical datasets and three natural benchmarks. The proposed method outperformed other methods we compared with in classification accuracy but also in robustness, within and across different datasets and domains.
B. Wilcox and Y. Gupta—Equal Contributors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Aminian, M., Khotanlou, H.: Capsnet-based brain tumor segmentation in multimodal MRI images using inhomogeneous voxels in del vector domain. Multimedia Tools Appl. 81(13), 17793–17815 (2022)
Aziz, M.J., et al.: Accurate automatic glioma segmentation in brain MRI images based on capsnet. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3882–3885. IEEE (2021)
Bilic, P., et al.: The liver tumor segmentation benchmark (lits). CoRR abs/1901.04056 (2019). http://arxiv.org/abs/1901.04056
Choi, J., Seo, H., Im, S., Kang, M.: Attention routing between capsules. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)
Duarte, K., et al.: Routing with self-attention for multimodal capsule networks (2021)
Elmezain, M., Mahmoud, A., Mosa, D.T., Said, W.: Brain tumor segmentation using deep capsule network and latent-dynamic conditional random fields. J. Imaging 8(7), 190 (2022)
Fan, T., Wang, G., Li, Y., Wang, H.: Ma-net: a multi-scale attention network for liver and tumor segmentation. IEEE Access 8, 179656–179665 (2020)
Fu, H., Wang, H., Yang, J.: Video summarization with a dual attention capsule network. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 446–451 (2021). https://doi.org/10.1109/ICPR48806.2021.9412057
Hahn, T., Pyeon, M., Kim, G.: Self-routing capsule networks. In: NeurIPS (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016). http://arxiv.org/abs/1608.06993
Huang, W., Zhou, F.: Da-capsnet: dual attention mechanism capsule network. Sci. Rep. 10(1), 1–13 (2020)
Jetley, S., Lord, N.A., Lee, N., Torr, P.H.S.: Learn to pay attention. CoRR abs/1804.02391 (2018). http://arxiv.org/abs/1804.02391
Jiménez-Sánchez, A., Albarqouni, S., Mateus, D.: Capsule networks against medical imaging data challenges. In: CVII-STENT/LABELS@MICCAI (2018)
Jo, Y., et al.: Quantitative phase imaging and artificial intelligence: a review. IEEE J. Sel. Top. Quant. Electron. 25, 1–14 (2019)
Kaul, C., Manandhar, S., Pears, N.: Focusnet: an attention-based fully convolutional network for medical image segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 455–458 (2019). https://doi.org/10.1109/ISBI.2019.8759477
Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order Boltzmann machine. In: Advances in Neural Information Processing Systems, vol. 23. pp. 1243–1251 (2010)
Mazzia, V., Salvetti, F., Chiaberge, M.: Efficient-capsnet: capsule network with self-attention routing. Sci. Rep. 11(1), 1–13 (2021)
Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, vol. 3 (2014)
Mobiny, A., Van Nguyen, H.: Fast CapsNet for lung cancer screening. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 741–749. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_82
Oktay, O., et al.: Attention u-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)
Olshausen, B.A., Anderson, C.H., Essen, D.C.V.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. J. Neurosci. 13, 4700–4719 (1993)
Paik, I., Kwak, T., Kim, I.: Capsule networks need an improved routing algorithm. In: Lee, W.S., Suzuki, T. (eds.) Proceedings of the Eleventh Asian Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 101, pp. 489–502. PMLR, Nagoya, Japan, 17–19 November 2019
Phaye, S.S.R., Sikka, A., Dhall, A., Bathula, D.: Dense and diverse capsule networks: making the capsules learn better (2018)
Pino, C., Vecchio, G., Fronda, M., Calandri, M., Aldinucci, M., Spampinato, C.: Twinlivernet: predicting TACE treatment outcome from CT scans for hepatocellular carcinoma using deep capsule networks. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3039–3043. IEEE (2021)
Qian, W., Jiaxing, Z., Sen, S., Zheng, Z.: Attentional neural network: feature selection using cognitive feedback. In: Advances in Neural Information Processing Systems, vol. 27. pp. 2033–2041 (2014)
Ranjbarzadeh, R., Bagherian Kasgari, A., Jafarzadeh Ghoushchi, S., Anari, S., Naseri, M., Bendechache, M.: Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images. Sci. Rep. 11(1), 1–17 (2021)
Reichert, D.P., Seriès, P., Storkey, A.J.: A hierarchical generative model of recurrent object-based attention in the visual cortex. In: ICANN (2011)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. arXiv preprint arXiv:1710.09829 (2017)
Shang, Y., Xu, N., Jin, Z., Yao, X.: Capsule network based on self-attention mechanism. In: 2021 13th International Conference on Wireless Communications and Signal Processing (WCSP), pp. 1–4. IEEE (2021)
Sinha, A., Dolz, J.: Multi-scale self-guided attention for medical image segmentation. IEEE J. Biomed. Health Inform. 25(1), 121–130 (2021). https://doi.org/10.1109/JBHI.2020.2986926
Survarachakan, S., Johansen, J.S., Pedersen, M.A., Amani, M., Lindseth, F.: Capsule nets for complex medical image segmentation tasks. In: CVCS (2020)
Tang, H., et al.: Spatial context-aware self-attention model for multi-organ segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 939–949 (2021)
Tang, Y., Srivastava, N., Salakhutdinov, R.: Learning generative models with visual attention. arXiv preprint arXiv:1312.6110 (2013)
Tran, M., Ly, L., Hua, B.S., Le, N.: SS-3DCapsNet: self-supervised 3D capsule networks for medical segmentation on less labeled data. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE (2022)
Tsai, Y.H., Srivastava, N., Goh, H., Salakhutdinov, R.: Capsules with inverted dot-product attention routing. CoRR abs/2002.04764 (2020). https://arxiv.org/abs/2002.04764
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. arXiv preprint arXiv:1711.07971 (2017)
Xi, E., Bing, S., Jin, Y.: Capsule network performance on complex data. CoRR abs/1712.03480 (2017)
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)
Özbulak, G.: Image colorization by capsule networks (2019)
Acknowledgements
This work was supported in part by grants from the National Cancer Institute, National Institutes of Health, U01CA142555 and 1U01CA190214.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hoogi, A., Wilcox, B., Gupta, Y., Rubin, D. (2023). Self-attention Capsule Network for Tissue Classification in Case of Challenging Medical Image Statistics. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13803. Springer, Cham. https://doi.org/10.1007/978-3-031-25066-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-25066-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25065-1
Online ISBN: 978-3-031-25066-8
eBook Packages: Computer ScienceComputer Science (R0)