Abstract
Over the past years, Convolutional Neural Networks (CNNs) have dominated the field of medical image segmentation. But they have difficulty representing long-range dependencies. Recently, the Transformer has been applied to medical image segmentation. Transformer-based architectures that utilize the self-attention (core of the Transformer) mechanism can encode long-range dependencies on images with highly expressive learning capabilities. In this paper, we introduce an adaptive multi-modality 3D medical image segmentation network based on Transformer (called msFormer), which is also a powerful 3D fusion network, and extend the application of Transformer to multi-modality medical image segmentation. This fusion network is modeled in the U-shaped structure to exploit complementary features of different modalities at multiple scales, which increases the cubical representations. We conducted a comprehensive experimental analysis on the Prostate and BraTS2021 datasets. The results show that our method achieves an average DSC of 0.905 and 0.851 on these two datasets, respectively, outperforming existing state-of-the-art methods and providing significant improvements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hastreiter, P., Bischoff, B., Fahlbusch, R., Doerfler, A., et al.: Data fusion and 3D visualization for optimized representation of neurovascular relationships in the posterior fossa. Acta Neurochirurgica 164(8), 1–11 (2022)
Pereira, H.R., Barzegar, M., Hamadelseed, O., Esteve, A.V., et al.: 3D surgical planning of pediatric tumors: a review. Int. J. Comput. Assist. Radiol. Surg. 17, 1–12 (2022). https://doi.org/10.1007/s11548-022-02557-8
Moussallem, M., Valette, P.-J., Traverse-Glehen, A., Houzard, C., et al.: New strategy for automatic tumor segmentation by adaptive thresholding on PET/CT images. J. Appl. Clin. Med. Phys. 13(5), 236–251 (2012)
Liu, Z., Song, Y., Maere, C., Liu, Q., et al.: A method for PET-CT lung cancer segmentation based on improved random walk. In: 24th International Conference on Pattern Recognition (ICPR), PP. 1187–1192 (2018)
Song, Q., Bai, J., Han, D., Bhatia, S., et al.: Optimal co-segmentation of tumor in PET-CT images with context information. IEEE Trans. Med. Imaging 32(9), 1685–1697 (2013)
Zhao, X., Li, L., Lu, W., Tan, S.: Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network. Phys. Med. Biol. 64(1), 015011 (2018)
Kumar, A., Fulham, M., Feng, D., Kim, J.: Co-learning feature fusion maps from PET-CT images of lung cancer. IEEE Trans. Med. Imaging 39(1), 204–217 (2019)
Xue, Z., Li, P., Zhang, L., Lu, X., et al.: Multi-modal co-learning for liver lesion segmentation on PET-CT images. IEEE Trans. Med. Imaging 40(12), 3531–3542 (2021)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit J., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Shamshad, F., Khan, S., Zamir S.W., et al.: Transformers in medical imaging: a survey. arXiv preprint arXiv:2201.09873 (2022)
Chen, J., Lu, Y., Yu, Q., Luo X., et al.: TransuNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 574–584 (2022)
Cao, H., Wang, Y., Chen, J., Jiang, D.,et al.: Swin-unet: unet-like pure transformer for medical image segmentation. arXiv preprint arXiv:2105.05537 (2021)
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
Dong, X., Bao, J., Chen, D., Zhang, W., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652 (2021)
Liu, Z., Lin, Y., Cao, Y., Hu, H., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)
Simpson, A.L., Antonelli, M., Bakas, S., Bilello, M., et al.: A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063 (2019)
Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. The cancer imaging archive 286, (2017)
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. Nat. Sci. Data 4, 170117 (2017)
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4(1), 1–13 (2017)
Baid, U., Ghodasara, S., Mohan, S., Bilello, M., et al.: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)
Xu, L., Tetteh, G., Lipkova, J., Zhao, Y., et al.: Automated whole-body bone lesion detection for multiple myeloma on 68GA-Pentixafor PET/CT imaging using deep learning methods. Contrast Media Mol. Imaging 2018, 2391925 (2018)
Zhang, Y., et al.: Modality-aware mutual learning for multi-modal medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 589–599. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_56
Zhou, T., Ruan, S., Guo, Y., Canu, S.: A multi-modality fusion network based on attention mechanism for brain tumor segmentation. In: 2020 IEEE 17th international symposium on biomedical imaging (ISBI), pp. 377–380 (2020)
Zhou, H.-Y., Guo, J., Zhang, Y., Yu, L., et al.: nnFormer: interleaved transformer for volumetric segmentation. arXiv preprint arXiv:2109.03201 (2021)
Acknowledgment
This work was supported in part by the National Natural Science Foundation of China (Grant Nos. 61901074 and 61902046) and the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant Nos. KJQN201900636 and KJQN201900631) and China Postdoctoral Science Foundation (Grant No. 2021M693771) and Chongqing postgraduates innovation project (CYS21310).
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
Tan, J., Jiang, C., Li, L., Li, H., Li, W., Zheng, S. (2022). msFormer: Adaptive Multi-Modality 3D Transformer for Medical Image Segmentation. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13535. Springer, Cham. https://doi.org/10.1007/978-3-031-18910-4_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-18910-4_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18909-8
Online ISBN: 978-3-031-18910-4
eBook Packages: Computer ScienceComputer Science (R0)