Lesion Image Synthesis Using DCGANs for Metastatic Liver Cancer Detection

  • Keisuke DomanEmail author
  • Takaaki Konishi
  • Yoshito Mekada
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 1213)


This chapter proposes a method to detect metastatic liver cancer from X-ray CT images using a convolutional neural network (CNN). The proposed method generates various lesion images by the combination of three kinds of generation methods: (1) synthesis using Poisson Blending, (2) generation based on CT value distributions, and (3) generation using deep convolutional generative adversarial networks (DCGANs). The proposed method constructs two kinds of detectors by using synthetic (fake) lesion images generated by the methods as well as real ones. One of the detectors is a 2D CNN for detecting candidate regions in a CT image, and the other is a 3D CNN for validating the candidate regions. Experimental results showed that the proposed method gave 0.30 improvement from 0.65 to 0.95 in terms of the detection rate, and 0.70 improvement from 0.90 to 0.20 in terms of the number of false detections per case. From the results, we confirmed the effectiveness of the proposed method.


Cancer diagnosis Metastatic liver cancer Cancer detection CT image Lesion image synthesis CNN DCGAN Poisson Blending 


  1. 1.
    Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representationsGoogle Scholar
  2. 2.
    Szegedy C, Vanhoucke V, Ioffe S, Shlens J (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the international conference on learning representationsCrossRefGoogle Scholar
  3. 3.
    Targ S, Almeida D, Lyman K (2016) Resnet in resnet: generalizing residual architectures. In: Proceedings of the international conference on learning representationsGoogle Scholar
  4. 4.
    Prez P, Gangnet M, Blake A (2003) Poisson image editing. In: ACM special interest group on computer, vol 22, no 3, pp 313–318Google Scholar
  5. 5.
    Konishi T, Doman K, Nawano S, Mekada Y (2017) Metastatic liver cancer detection by 3D-CNN using artificial lesion images. In: IEICE technical committee on medical imaging technical research report, vol 116, no 393, pp 21–22 (in Japanese)Google Scholar
  6. 6.
    Konishi T, Doman K, Nawano S, Mekada Y (2017) A study on lesion image synthesis for metastatic liver cancer detection using artificial training images. In: The Japanese society of medical imaging technology, OP3-1 (in Japanese)Google Scholar
  7. 7.
    Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Neural information processing systems, vol 27, pp 2672–2680Google Scholar
  8. 8.
    Mekada Y, Doman K (2018) Learning sample generation for detecting liver cancer using 3D-CNN. In: Proceedings of 40th international engineering in medicine and biology conference, no 370, CThBT19.7Google Scholar
  9. 9.
    Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of the international conference on learning representationsGoogle Scholar
  10. 10.
    Christ PF et al (2016) Automatic liver and lesion segmentation in CT using cascaded fully convolutionalneural networks and 3D conditional random fields. In: International conference on medical image computing and computer-assisted intervention. LNCS, vol 9901. Springer, Heidelberg, pp 415–423CrossRefGoogle Scholar
  11. 11.
    About CAD contest, (in Japanese)
  12. 12.
  13. 13.
    Wu W, Wu S, Zhou Z, Zhang R, Zhang Y (2017) 3D liver tumor segmentation in CT images using improved fuzzy C-means and graph cuts. In: BioMed research international, vol 2017, pp 1–11Google Scholar
  14. 14.
    Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: Proceedings of medical image computing and computer assisted intervention society, pp 130–137Google Scholar
  15. 15.
    Cheng Y (1995) Mean shift, mode seeking, and clustering. IEEE Trans Pattern Anal Mach Intell 17(8):790–799CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Keisuke Doman
    • 1
    Email author
  • Takaaki Konishi
    • 2
    • 3
  • Yoshito Mekada
    • 1
  1. 1.Graduate School of EngineeringChukyo UniversityToyotaJapan
  2. 2.Graduate School of Computer and Cognitive SciencesChukyo UniversityToyotaJapan
  3. 3.Persol Research & Development Co., Ltd.TokyoJapan

Personalised recommendations