Abstract
Quantitative measurement of hepatocellular carcinoma (HCC) on multi-phase contrast-enhanced magnetic resonance imaging (CEMRI) is one of the key processes for HCC treatment and prognosis. However, direct automated quantitative measurement using the CNN-based network a still challenging task due to: (1) The lack of ability for capturing long-range dependencies of multi-anatomy in the whole medical image; (2) The lack of mechanism for fusing and selecting multi-phase CEMRI information. In this study, we propose a multi-function Transformer regression network (mfTrans-Net) for HCC quantitative measurement. Specifically, we first design three parallel CNN-based encoders for multi-phase CEMRI feature extraction and dimension reducing. Next, the non-local Transformer makes our mfTrans-Net self-attention for capturing the long-range dependencies of multi-anatomy. At the same time, a phase-aware Transformer captures the relevance between multi-phase CEMRI for multi-phase CEMRI information fusion and selection. Lastly, we proposed a multi-level training strategy, which enables an enhanced loss function to improve the quantification task. The mfTrans-Net is validated on multi-phase CEMRI of 138 HCC subjects. Our mfTrans-Net achieves high performance of multi-index quantification that the mean absolute error of center point, max-diameter, circumference, and area is down to 2.35 mm, 2.38 mm, 8.28 mm, and 116.15 mm\(^2\), respectively. The results show that mfTrans-Net has great potential for small lesions quantification in medical images and clinical application value.
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
References
Cereser, L., et al.: Comparison of portal venous and delayed phases of gadolinium-enhanced magnetic resonance imaging study of cirrhotic liver for the detection of contrast washout of hypervascular hepatocellular carcinoma. J. Comput. Assist. Tomog 34(5), 706–711 (2010)
Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Ge, R., et al.: K-net: integrate left ventricle segmentation and direct quantification of paired echo sequence. IEEE Trans. Med. Imaging 39(5), 1690–1702 (2019)
Ge, R., et al.: Pv-lvnet: direct left ventricle multitype indices estimation from 2d echocardiograms of paired apical views with deep neural networks. Med. Image Anal. 58, 101554 (2019)
Goh, B.K.: Importance of tumor size as a prognostic factor after partial liver resection for solitary hepatocellular carcinoma: Implications on the current ajcc staging system. J. Surg. Oncol 113(1), 89–93 (2016)
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)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Hwang, S., et al.: The impact of tumor size on long-term survival outcomes after resection of solitary hepatocellular carcinoma: single-institution experience with 2558 patients. J. Gastrointest. Surg. 19(7), 1281–1290 (2015)
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. arXiv preprint arXiv:1506.02025 (2015)
Kim, Y.S., et al.: Strahlentherapie und Onkologie 192(10), 714–721 (2016). https://doi.org/10.1007/s00066-016-1028-2
Lin, L., et al.: Multiple axial spine indices estimation via dense enhancing network with cross-space distance-preserving regularization. IEEE J. Biomed. Health Inf. 24(11), 3248–3257 (2020)
Liu, H., et al.: Reclassification of tumor size for solitary hbv-related hepatocellular carcinoma by minimum p value method: a large retrospective study. World J. Surg. Oncol. 18(1), 1–10 (2020)
Liver, E.A.F.T.S.O.T., et al.: Easl clinical practice guidelines: management of hepatocellular carcinoma. J. Hepatol. 69(1), 182–236 (2018)
Pang, Shumao, Leung, Stephanie, Ben Nachum, Ilanit, Feng, Qianjin, Li, Shuo: Direct automated quantitative measurement of spine via cascade amplifier regression network. In: Frangi, Alejandro F.., Schnabel, Julia A.., Davatzikos, Christos, Alberola-López, Carlos, Fichtinger, Gabor (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 940–948. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_104
Ruan, Y., et al.: Mb-fsgan: joint segmentation and quantification of kidney tumor on ct by the multi-branch feature sharing generative adversarial network. Med. Image Anal. 64, 101721 (2020)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Wu, G., Wu, J., Wang, B., Zhu, X., Shi, X., Ding, Y.: Importance of tumor size at diagnosis as a prognostic factor for hepatocellular carcinoma survival: a population-based study. Cancer Manag. Res. 10, 4401 (2018)
Xu, C., Howey, J., Ohorodnyk, P., Roth, M., Zhang, H., Li, S.: Segmentation and quantification of infarction without contrast agents via spatiotemporal generative adversarial learning. Med. Image Anal. 59, 101568 (2020)
Zhao, J., et al.: Tripartite-gan: synthesizing liver contrast-enhanced mri to improve tumor detection. Med. Image Anal. 63, 101667 (2020)
Zhao, J., Li, D., Xiao, X., Chong, J., Chen, B., Li, S.: United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast mri. Med. Image Anal., 102154 (2021)
Acknowledgements
This work is partly supported by the China Scholarship Council (No.202008370191).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, J. et al. (2021). mfTrans-Net: Quantitative Measurement of Hepatocellular Carcinoma via Multi-Function Transformer Regression Network. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12905. Springer, Cham. https://doi.org/10.1007/978-3-030-87240-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-87240-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87239-7
Online ISBN: 978-3-030-87240-3
eBook Packages: Computer ScienceComputer Science (R0)
