Advertisement

Four-dimensional fully convolutional residual network-based liver segmentation in Gd-EOB-DTPA-enhanced MRI

  • Tomomi TakenagaEmail author
  • Shouhei Hanaoka
  • Yukihiro Nomura
  • Mitsutaka Nemoto
  • Masaki Murata
  • Takahiro Nakao
  • Soichiro Miki
  • Takeharu Yoshikawa
  • Naoto Hayashi
  • Osamu Abe
Original Article
  • 33 Downloads

Abstract

Purpose

Gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) tends to show higher diagnostic accuracy than other modalities. There is a demand for computer-assisted detection (CAD) software for Gd-EOB-DTPA-enhanced MRI. Segmentation with high accuracy is important for CAD software. We propose a liver segmentation method for Gd-EOB-DTPA-enhanced MRI that is based on a four-dimensional (4D) fully convolutional residual network (FC-ResNet). The aims of this study are to determine the best combination of an input image and output image in our proposed method and to compare our proposed method with the previous rule-based segmentation method.

Methods

We prepared a five-phase image set and a hepatobiliary phase image set as the input image sets to determine the best input image set. We also prepared a labeled liver image and labeled liver and labeled body trunk images as the output image sets to determine the best output image set. In addition, we optimized the hyperparameters of our proposed model. We used 30 cases to train our model, 10 cases to determine the hyperparameters of our model, and 20 cases to evaluate our model.

Results

Our network with the five-phase image set and the output image set of labeled liver and labeled body trunk images showed the highest accuracy. Our proposed method showed higher accuracy than the previous rule-based segmentation method. The Dice coefficient of the liver region was 0.944 ± 0.018.

Conclusion

Our proposed 4D FC-ResNet showed satisfactory performance for liver segmentation as preprocessing in CAD software.

Keywords

Segmentation Gd-EOB-DTPA CAD Liver Convolutional neural network 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare no conflicts of interest with regard to the present study.

References

  1. 1.
    Akai H, Kiryu S, Matsuda I et al (2012) Detection of hepatocellular carcinoma by Gd-EOB-DTPA-enhanced liver MRI: comparison with triple phase 64 detector row helical CT. Eur J Radiol 80(2):310–315CrossRefGoogle Scholar
  2. 2.
    Berger-Kulemann V, Schima W, Baroud S et al (2012) Gadoxetic acid-enhanced 30 T MR imaging versus multidetector-row CT in the detection of colorectal metastases in fatty liver using intraoperative ultrasound and histopathology as a standard of reference. Eur J Surg Radiol 38(2):670–676Google Scholar
  3. 3.
    Takenaga T, Hanaoka S, Nemoto M et al. (2017) Segmentation of liver region in Gd-EOB enhanced magnetic resonance images. In: Proceedings of IFMIA 2017 the international forum medical imaging in Asia, Okinawa, pp 19–20Google Scholar
  4. 4.
    Huynh HT, Le-Trong N, Oto A, Suzuki K (2017) Fully automated MR liver volumetry using watershed segmentation coupled with active contouring. Int J Comput Assist Radiol Surg 12(2):235–243CrossRefGoogle Scholar
  5. 5.
    Oh J, Martin DR, Hu X (2014) Partitioned edge-function-scaled region-based active contour (p-ESRAC): automated liver segmentation in multiphase contrast-enhanced MRI. Med Phys 41(4):219–244CrossRefGoogle Scholar
  6. 6.
    Christ PF, Ettlinger F, Grun F et al (2017) Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks. arXiv:1702.05970v2
  7. 7.
    Lee J, Kim KW, Kim S et al (2014) Feasibility of semiautomated MR volumetry using gadoxetic acid–enhanced MRI at hepatobiliary phase for living liver donors. Magn Reson Med 72(3):640–645CrossRefGoogle Scholar
  8. 8.
    Drozdzal M, Chartrand G, Vorontsov E et al (2018) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13CrossRefGoogle Scholar
  9. 9.
    Glocker B, Sotiras A, Komodakis N, Paragios N (2011) Deformable medical image registration: setting the state of the art with discrete methods. Annu Rev Biomed Eng 13:219–244CrossRefGoogle Scholar
  10. 10.
    Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. arXiv:1412.6980
  11. 11.
    Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305Google Scholar
  12. 12.
    Chainer. http://chainer.org/. Accessed 6 September 2018
  13. 13.
    Wan SY, Higgins WE (2003) Symmetric region growing. IEEE Trans Image Process 12:1007–1015CrossRefGoogle Scholar
  14. 14.
    Isensee F, Jaeger PF, Full PM, et al (2017) Automatic cardiac disease assessment on cine-mri via time-series segmentation and domain specific features. In: International workshop on statistical atlases and computational models of the heart, pp 120–129Google Scholar

Copyright information

© CARS 2019

Authors and Affiliations

  • Tomomi Takenaga
    • 1
    • 2
    Email author
  • Shouhei Hanaoka
    • 3
  • Yukihiro Nomura
    • 1
  • Mitsutaka Nemoto
    • 4
  • Masaki Murata
    • 1
  • Takahiro Nakao
    • 5
  • Soichiro Miki
    • 1
  • Takeharu Yoshikawa
    • 1
  • Naoto Hayashi
    • 1
  • Osamu Abe
    • 3
    • 5
  1. 1.Department of Computational Diagnostic Radiology and Preventive Medicinethe University of Tokyo HospitalTokyoJapan
  2. 2.Department of Radiological SciencesIbaraki Prefectural University of Health SciencesInashiki-gunJapan
  3. 3.Department of Radiologythe University of Tokyo HospitalTokyoJapan
  4. 4.Faculty of Biology-Oriented Science and TechnologyKindai UniversityKinokawaJapan
  5. 5.Radiology and Biomedical Engineering, Graduate School of Medicinethe University of TokyoTokyoJapan

Personalised recommendations