Advertisement

A two-stage approach for automatic liver segmentation with Faster R-CNN and DeepLab

  • Wei Tang
  • Dongsheng ZouEmail author
  • Su Yang
  • Jing Shi
  • Jingpei Dan
  • Guowu Song
S.I. : Brain inspired Computing &Machine Learning Applied Research-BISMLARE
  • 8 Downloads

Abstract

Proper liver segmentation is a key step in many clinical applications, including computer-assisted diagnosis, radiation therapy and volume measurement. However, liver segmentation is still challenging due to fuzzy boundary, complex liver anatomy, present of pathologies, and diversified shape. This paper presents a novel two-stage liver detection and segmentation model DSL. The first stage uses improved Faster Regions with CNN features (Faster R-CNN) to detect approximate position of liver. The obtained images are processed and input into DeepLab to obtain the contour of liver. The proposed approach is validated on two datasets MICCAI-Sliver07 and 3Dircadb. Experimental results reveal that the proposed method outperforms the state-of-the-art solutions in terms of volume overlap error, average surface distance, relative volume difference, and total score.

Keywords

Liver segmentation DeepLab Faster R-CNN 

Notes

Acknowledgements

This work was partly supported by the National Nature Science Foundation of China (No. 61309013 and No. 51608070) and Chongqing Basic and frontier research projects (No. CSTC2014JCYJA40042 and No. CSTC2016JCYJA0022).

References

  1. 1.
    Alshaikhli SDS, Yang MY, Rosenhahn B (2015) Automatic 3D liver segmentation using sparse representation of global and local image information via level set formulation. arXiv:1508.01521
  2. 2.
    Boykov Y, Funka-Lea G (2006) Graph cuts and efficient N-D image segmentation. Int J Comput Vis 70(2):109–131CrossRefGoogle Scholar
  3. 3.
    Burkhardt H (2010) Integration of morphology and graph-based techniques for fully automatic liver segmentation. Majlesi J Electr Eng 4(3):59–66Google Scholar
  4. 4.
    Campadelli P, Casiraghi E (2009) Liver segmentation from CT scans: a survey. Artif Intell Med 45(2):185–196CrossRefGoogle Scholar
  5. 5.
    Chen LC, Papandreou G, Kokkinos I et al (2014) Semantic image segmentation with deep convolutional nets and fully connected CRFs. Comput Sci 4:357–361Google Scholar
  6. 6.
    Chen LC, Papandreou G, Kokkinos I et al (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848CrossRefGoogle Scholar
  7. 7.
    Chung F, Delingette H (2013) Regional appearance modeling based on the clustering of intensity profiles. Comput Vis Image Underst 117(6):705–717CrossRefGoogle Scholar
  8. 8.
    Dawant BM, Li R, Lennon B et al (2007) Semi-automatic segmentation of the liver and its evaluation on the MICCAI 2007 grand challenge data set. In: Proceedings of MICCAI workshop 3D segmentation clinic: a grand challenge, pp 215–221Google Scholar
  9. 9.
    Dong C, Chen YW, Tateyama T et al (2016) A knowledge-based interactive liver segmentation using random walks. In: International conference on fuzzy systems and knowledge discovery. IEEE, pp 1731–1736Google Scholar
  10. 10.
    Dou Q, Chen H, Jin Y et al (2016) 3D Deeply supervised network for automatic liver segmentation from CT volumes, pp 149–157Google Scholar
  11. 11.
    Erdt M, Steger S, Kirschner M et al (2010) Fast automatic liver segmentation combining learned shape priors with observed shape deviation. In: IEEE, international symposium on computer-based medical systems. IEEE, pp 249–254Google Scholar
  12. 12.
    Gambino O, Vitabile S, Re GL et al (2010) Automatic volumetric liver segmentation using texture based region growing. In: International conference on complex, intelligent and software intensive systems. IEEE Computer Society, pp 146–152Google Scholar
  13. 13.
    Ginneken BV, Heimann T, Styner M (2007) 3D Segmentation in the clinic: a grand challenge. In: Proceedings of 3D segmentation in the clinic: a grand challenge. Springer, Brisbane, pp 7–15Google Scholar
  14. 14.
    Girshick R (2015) Fast R-CNN. In: IEEE international conference on computer vision. IEEE, pp 1440–1448Google Scholar
  15. 15.
    Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE international conference on computer vision and pattern recognition, pp 580–587Google Scholar
  16. 16.
    He B, Huang C, Sharp G et al (2016) Fast automatic 3D liver segmentation based on a three-level AdaBoost-guided active shape model. Med Phys 43(5):2421CrossRefGoogle Scholar
  17. 17.
    Heimann T, Meinzer HP, Wolf I (2010) A statistical deformable model for the segmentation of liver CT volumes. In: MICCAI workshop on 3D Segmentation in the ClinicGoogle Scholar
  18. 18.
    Heimann T, Van GB, Styner MA et al (2009) Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Trans Med Imaging 28(8):1251–1265CrossRefGoogle Scholar
  19. 19.
    Jansen J, Schreurs R, Dubois L et al (2015) Orbital volume analysis: validation of a semi-automatic software segmentation method. Int J Comput Assist Radiol Surg 11(1):11–18CrossRefGoogle Scholar
  20. 20.
    Kainmüller D, Lange T, Lamecker H (2007) Shape constrained automatic segmentation of the liver based on a heuristic intensity model. In: MICCAI workshop on 3D Segmentation in the Clinic, pp 109–116Google Scholar
  21. 21.
    Saddi KA, Rousson M et al (2007) Global-to-local shape matching for liver segmentation in CT imagingGoogle Scholar
  22. 22.
    Kirschner M (2013) The probabilistic active shape model: from model construction to flexible medical image segmentation. PhD dissertationGoogle Scholar
  23. 23.
    Krähenbühl P, Koltun V (2011) Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Proceedings of advances in neural information processing systems, vol 24, pp 109–117Google Scholar
  24. 24.
    Liao M, Zhao YQ, Wang W et al (2016) Efficient liver segmentation in CT images based on graph cuts and bottleneck detection. Phys Med 32(11):1383CrossRefGoogle Scholar
  25. 25.
    Li G, Chen X, Shi F et al (2015) Automatic liver segmentation based on shape constraints and deformable graph cut in CT Images. IEEE Trans Image Process 24(12):5315MathSciNetCrossRefGoogle Scholar
  26. 26.
    Linguraru MG, Richbourg WJ, Watt JM et al (2011) Liver and tumor segmentation and analysis from CT of diseased patients via a generic affine invariant shape parameterization and graph cuts. In: International conference on abdominal imaging: computational and clinical applications. Springer, Berlin, pp 198–206Google Scholar
  27. 27.
    Lu F, Wu F, Hu P et al (2017) Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int J Comput Assist Radiol Surg 12(2):171–182CrossRefGoogle Scholar
  28. 28.
    Lu J, Shi L, Deng M et al (2011) An interactive approach to liver segmentation in CT based on deformable model integrated with attractor force. In: International conference on machine learning and cybernetics. IEEE, pp 1660–1665Google Scholar
  29. 29.
    Njg W (2017) Alternative RNA splicing in the pathogenesis of liver disease. Front Endocrinol 8:133CrossRefGoogle Scholar
  30. 30.
    Ren S, He K, Girshick R et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137CrossRefGoogle Scholar
  31. 31.
    Schmidt G, Athelogou MA, Schönmeyer R et al (2007) Cognition network technology for a fully automated 3-D segmentation of liver. In: MICCAI workshop on 3D Segmentation in the clinic: a grand challengeGoogle Scholar
  32. 32.
    Wang N, Huang L L, Zhang B (2010) A fast hybrid method for interactive liver segmentation. In: Chinese conference on pattern recognition, pp 1–5Google Scholar
  33. 33.
    Wimmer A, Soza G, Hornegger J (2009) A generic probabilistic active shape model for organ segmentation. In: Medical image computing and computer-assisted intervention–MICCAI 2009. Springer, Berlin, pp 26–33CrossRefGoogle Scholar
  34. 34.
    Yan J, Schwartz LH, Zhao B (2015) Semiautomatic segmentation of liver metastases on volumetric CT images. Med Phys 42(11):6283–6293CrossRefGoogle Scholar
  35. 35.
    Yang D, Xu D, Zhou S K et al (2017) Automatic liver segmentation using an adversarial image-to-image networkGoogle Scholar
  36. 36.
    Yang X, Yu HC, Choi Y et al (2014) A hybrid semi-automatic method for liver segmentation based on level-set methods using multiple seed points. Comput Methods Programs Biomed 113(1):69–79CrossRefGoogle Scholar
  37. 37.
    Shelhamer E, Long J, Darrell T (2014) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651CrossRefGoogle Scholar
  38. 38.
    Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 761–769Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2020

Authors and Affiliations

  1. 1.College of Computer Science, Chongqing UniversityChongqingChina
  2. 2.Sichuan Changhong Elextronics Co. Ltd.MianyangChina

Personalised recommendations