Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural networks
- 107 Downloads
We address the automatic segmentation of healthy and cancerous liver tissues (parenchyma, active and necrotic parts of hepatocellular carcinoma (HCC) tumor) on multiphase CT images using a deep learning approach.
We devise a cascaded convolutional neural network based on the U-Net architecture. Two strategies for dealing with multiphase information are compared: Single-phase images are concatenated in a multi-dimensional features map on the input layer, or output maps are computed independently for each phase before being merged to produce the final segmentation. Each network of the cascade is specialized in the segmentation of a specific tissue. The performances of these networks taken separately and of the cascaded architecture are assessed on both single-phase and on multiphase images.
In terms of Dice coefficients, the proposed method is on par with a state-of-the-art method designed for automatic MR image segmentation and outperforms previously used technique for interactive CT image segmentation. We validate the hypothesis that several cascaded specialized networks have a higher prediction accuracy than a single network addressing all tasks simultaneously. Although the portal venous phase alone seems to provide sufficient contrast for discriminating tumors from healthy parenchyma, the multiphase information brings significant improvement for the segmentation of cancerous tissues (active versus necrotic part).
The proposed cascaded multiphase architecture showed promising performances for the automatic segmentation of liver tissues, allowing to reliably estimate the necrosis rate, a valuable imaging biomarker of the clinical outcome.
KeywordsHepatocellular carcinoma Multiphase CT Semantic segmentation Fully convolutional networks (FCNs) Liver tissues
This study was funded by IHU Strasbourg through ANR grant 10-IAHU-0002.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- 2.Ben-Cohen A, Diamant I, Klang E, Amitai M, Greenspan H (2016) Fully convolutional network for liver segmentation and lesions detection. In: Carneiro G et al (eds) Deep learning and data labeling for medical applications, vol 10008. Springer, Cham, pp 77–85. https://doi.org/10.1007/978-3-319-46976-8
- 3.Christ PF, Ettlinger F, Grün F, Elshaera MEA, Lipkova J, Schlecht S, Ahmaddy F, Tatavarty S, Bickel M, Bilic P, Rempfler M, Hofmann F, Anastasi MD, Ahmadi SA, Kaissis G, Holch J, Sommer W, Braren R, Heinemann V, Menze B (2017) Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks, pp 1–20. arXiv:1702.05970
- 4.Conze PH, Noblet V, Rousseau F, Heitz F, de Blasi V, Memeo R, Pessaux P (2017) Scale-adaptive supervoxel-based random forests for liver tumor segmentation in dynamic contrast-enhanced CT scans. Int J Comput Assist Radiol Surg 12(2):223–233. https://doi.org/10.1007/s11548-016-1493-1 CrossRefGoogle Scholar
- 5.Erdt M, Steger S, Kirschner M, Wesarg S (2010) Fast automatic liver segmentation combining learned shape priors with observed shape deviation. In: Proceedings—IEEE symposium on computer-based medical systems, pp 249–254. https://doi.org/10.1109/CBMS.2010.6042650
- 6.Bray F, Ferlay Jacques, Soerjomataram Isabelle, Siegel RL, Torre LA, Jemal A (2018) Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians. https://doi.org/10.3322/caac.21492
- 15.Li CY, Wang X, Eberl S, Fulham M, Yin Y, Feng D (2010) Fully automated liver segmentation for low- and high-contrast ct volumes based on probabilistic atlases. In: Proceedings—international conference on image processing ICIP, pp 1733–1736. https://doi.org/10.1109/ICIP.2010.5654434
- 20.Oldhafer KJ, Chavan A, Frühauf NR, Flemming P, Schlitt HJ, Kubicka S, Nashan B, Weimann A, Raab R, Manns MP, Galanski M (1998) Arterial chemoembolization before liver transplantation in patients with hepatocellular carcinoma: Marked tumor necrosis, but no survival benefit? J Hepatol 29(6):953–959. https://doi.org/10.1016/S0168-8278(98)80123-2 CrossRefGoogle Scholar
- 21.Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation, pp 1–8. arXiv:1505.04597
- 23.Sadigh G, Applegate KE, Baumgarten DA (2014) Comparative accuracy of intravenous contrast-enhanced CT versus noncontrast CT plus intravenous contrast-enhanced CT in the detection and characterization of patients with hypervascular liver metastases. Critic Apprais Topic Acad Radiol 21(1):113–125. https://doi.org/10.1016/j.acra.2013.08.023 CrossRefGoogle Scholar
- 30.Zhang F, Yang J, Nezami N, Laage-gaupp F, Chapiro J, De Lin M, Duncan J (2018) Liver tissue classification using an auto-context-based deep neural network with a multi-phase training framework. In: Bai W, Sanroma G, Wu G, Munsell BC, Zhan Y, Coupé P (eds) Patch-based techniques in medical imaging. Springer, Cham, pp 59–66CrossRefGoogle Scholar
- 31.Zheng W, Thorne N, Mckew JC (2015) Deep learning in medical image analysis. Annu Rev Biomed Eng 18:1067–1073. https://doi.org/10.1016/j.drudis.2013.07.001.Phenotypic Google Scholar