Advertisement

Liver Tissue Classification Using an Auto-context-based Deep Neural Network with a Multi-phase Training Framework

  • Fan Zhang
  • Junlin Yang
  • Nariman Nezami
  • Fabian Laage-gaupp
  • Julius Chapiro
  • Ming De Lin
  • James Duncan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11075)

Abstract

In this project, our goal is to classify different types of liver tissue on 3D multi-parameter magnetic resonance images in patients with hepatocellular carcinoma. In these cases, 3D fully annotated segmentation masks from experts are expensive to acquire, thus the dataset available for training a predictive model is usually small. To achieve the goal, we designed a novel deep convolutional neural network that incorporates auto-context elements directly into a U-net-like architecture. We used a patch-based strategy with a weighted sampling procedure in order to train on a sufficient number of samples. Furthermore, we designed a multi-resolution and multi-phase training framework to reduce the learning space and to increase the regularization of the model. Our method was tested on images from 20 patients and yielded promising results, outperforming standard neural network approaches as well as a benchmark method for liver tissue classification.

Keywords

Tissue classification Convolutional neural network Auto-context Multi-phase training Hepatocellular carcinoma Magnetic resonance imaging 

References

  1. 1.
    Christ, P.F., et al.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 415–423. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_48CrossRefGoogle Scholar
  2. 2.
    Li, W., Jia, F., Hu, Q.: Automatic segmentation of liver tumor in CT images with deep convolutional neural networks. J. Comput. Commun. 3(11), 146 (2015)CrossRefGoogle Scholar
  3. 3.
    Raoul, J.L., et al.: Evolving strategies for the management of intermediate-stage hepatocellular carcinoma: available evidence and expert opinion on the use of transarterial chemoembolization. Cancer Treat. Rev. 37(3), 212–220 (2011)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Raza, A., Sood, G.K.: Hepatocellular carcinoma review: current treatment, and evidence-based medicine. World J. Gastroenterol. WJG 20(15), 4115 (2014)CrossRefGoogle Scholar
  5. 5.
    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_28CrossRefGoogle Scholar
  6. 6.
    Salehi, S.S.M., Erdogmus, D., Gholipour, A.: Auto-context convolutional neural network (auto-net) for brain extraction in magnetic resonance imaging. IEEE Trans. Med. Imaging 36(11), 2319–2330 (2017)CrossRefGoogle Scholar
  7. 7.
    Treilhard, J., et al.: Liver tissue classification in patients with hepatocellular carcinoma by fusing structured and rotationally invariant context representation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 81–88. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_10CrossRefGoogle Scholar
  8. 8.
    Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 32(10), 1744–1757 (2010)CrossRefGoogle Scholar
  9. 9.
    Vodopivec, T., Lepetit, V., Peer, P.: Fine hand segmentation using convolutional neural networks. CoRR abs/1608.07454 (2016). http://arxiv.org/abs/1608.07454
  10. 10.
    Zeng, G., Yang, X., Li, J., Yu, L., Heng, P.-A., Zheng, G.: 3D U-net with multi-level deep supervision: fully automatic segmentation of proximal femur in 3D MR images. In: Wang, Q., Shi, Y., Suk, H.-I., Suzuki, K. (eds.) MLMI 2017. LNCS, vol. 10541, pp. 274–282. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67389-9_32CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Fan Zhang
    • 1
  • Junlin Yang
    • 1
  • Nariman Nezami
    • 3
  • Fabian Laage-gaupp
    • 3
  • Julius Chapiro
    • 3
  • Ming De Lin
    • 3
    • 4
  • James Duncan
    • 1
    • 2
  1. 1.Department of Biomedical EngineeringYale UniversityNew HavenUSA
  2. 2.Department of Electrical EngineeringYale UniversityNew HavenUSA
  3. 3.Department of Radiology and Biomedical ImagingYale UniversityNew HavenUSA
  4. 4.Philips Research North AmericaCambridgeUSA

Personalised recommendations