3D FCN Feature Driven Regression Forest-Based Pancreas Localization and Segmentation

  • Masahiro OdaEmail author
  • Natsuki Shimizu
  • Holger R. Roth
  • Ken’ichi Karasawa
  • Takayuki Kitasaka
  • Kazunari Misawa
  • Michitaka Fujiwara
  • Daniel Rueckert
  • Kensaku Mori
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)


This paper presents a fully automated atlas-based pancreas segmentation method from CT volumes utilizing 3D fully convolutional network (FCN) feature-based pancreas localization. Segmentation of the pancreas is difficult because it has larger inter-patient spatial variations than other organs. Previous pancreas segmentation methods failed to deal with such variations. We propose a fully automated pancreas segmentation method that contains novel localization and segmentation. Since the pancreas neighbors many other organs, its position and size are strongly related to the positions of the surrounding organs. We estimate the position and the size of the pancreas (localization) from global features by regression forests. As global features, we use intensity differences and 3D FCN deep learned features, which include automatically extracted essential features for segmentation. We chose 3D FCN features from a trained 3D U-Net, which is trained to perform multi-organ segmentation. The global features include both the pancreas and surrounding organ information. After localization, a patient-specific probabilistic atlas-based pancreas segmentation is performed. In evaluation results with 146 CT volumes, we achieved 60.6% of the Jaccard index and 73.9% of the Dice overlap.


Segmentation Pancreas Fully convolutional network Regression forest 



Parts of this research were supported by the MEXT/JSPS KAKENHI Grant Numbers 25242047, 26108006, 17H00867, the JSPS Bilateral International Collaboration Grants, and the JST ACT-I (JPMJPR16U9).


  1. 1.
    Okada, T., et al.: Automated segmentation of the liver from 3D CT images using probabilistic atlas and multi-level statistical shape model. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4791, pp. 86–93. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-75757-3_11 CrossRefGoogle Scholar
  2. 2.
    Chu, C., et al.: Multi-organ segmentation based on spatially-divided probabilistic atlas from 3D abdominal CT images. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 165–172. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40763-5_21 CrossRefGoogle Scholar
  3. 3.
    Wolz, R., Chu, C., Misawa, K., et al.: Automated abdominal multi-organ segmentation with subject-specific atlas generation. IEEE TMI 32(9), 1723–1730 (2013)Google Scholar
  4. 4.
    Karasawa, K., et al.: Structure specific atlas generation and its application to pancreas segmentation from contrasted abdominal CT volumes. In: Menze, B., Langs, G., Montillo, A., Kelm, M., Müller, H., Zhang, S., Cai, W., Metaxas, D. (eds.) MCV 2015. LNCS, vol. 9601, pp. 47–56. Springer, Cham (2016). doi: 10.1007/978-3-319-42016-5_5 CrossRefGoogle Scholar
  5. 5.
    Tong, T., Wolz, R., Wang, Z., et al.: Discriminative dictionary learning for abdominal multi-organ segmentation. Med. Image Anal. 23(1), 92–104 (2015)CrossRefGoogle Scholar
  6. 6.
    Saito, A., Nawano, S., Shimizu, A.: Joint optimization of segmentation and shape prior from level set-based statistical shape model, and its application to the automated segmentation of abdominal organs. Med. Image Anal. 28, 46–65 (2016)CrossRefGoogle Scholar
  7. 7.
    Roth, H.R., Lu, L., Farag, A., Sohn, A., Summers, R.M.: Spatial aggregation of holistically-nested networks for automated pancreas segmentation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 451–459. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_52 CrossRefGoogle Scholar
  8. 8.
    Oda, M., et al.: Regression forest-based atlas localization and direction specific atlas generation for pancreas segmentation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 556–563. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_64 CrossRefGoogle Scholar
  9. 9.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_49 CrossRefGoogle Scholar
  10. 10.
    Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: convolutional architecture for fast feature embedding. In: 22nd ACM International Conference On Multimedia, pp. 675–678. ACM (2014)Google Scholar
  11. 11.
    Criminisi, A., Robertson, D., Konukoglu, E., et al.: Regression forests for efficient anatomy detection and localization in computed tomography scans. Med. Image Anal. 17, 1293–1303 (2013)CrossRefGoogle Scholar
  12. 12.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE PAMI 23(11), 1222–1239 (2001)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Masahiro Oda
    • 1
    Email author
  • Natsuki Shimizu
    • 2
  • Holger R. Roth
    • 1
  • Ken’ichi Karasawa
    • 2
  • Takayuki Kitasaka
    • 3
  • Kazunari Misawa
    • 4
  • Michitaka Fujiwara
    • 5
  • Daniel Rueckert
    • 6
  • Kensaku Mori
    • 1
    • 7
  1. 1.Graduate School of InformaticsNagoya UniversityNagoyaJapan
  2. 2.Graduate School of Information ScienceNagoya UniversityNagoyaJapan
  3. 3.School of Information ScienceAichi Institute of TechnologyToyotaJapan
  4. 4.Aichi Cancer CenterNagoyaJapan
  5. 5.Nagoya University Graduate School of MedicineNagoyaJapan
  6. 6.Department of ComputingImperial College LondonLondonUK
  7. 7.Strategy Office, Information and CommunicationsNagoya UniversityNagoyaJapan

Personalised recommendations