Computed Tomography Image-Based Deep Survival Regression for Metastatic Colorectal Cancer Using a Non-proportional Hazards Model

  • Alexander KatzmannEmail author
  • Alexander Mühlberg
  • Michael Sühling
  • Dominik Nörenberg
  • Stefan Maurus
  • Julian Walter Holch
  • Volker Heinemann
  • Horst-Michael Groß
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11843)


With more than 1,800,000 cases and over 862,000 deaths per year, metastatic colorectal cancer is the second leading cause of cancer related deaths in modern societies. The estimated patient survival is one of the main factors for therapy adjustment. While proportional hazard models are a key instrument for survival analysis within the last centuries, the assumption of hazard proportionality might be overly restrictive and their applicability to complex data remains difficult. Especially the integration of image data comes at the cost of a careful pre-selection of hand-crafted features only. With the rise of deep learning, directly differentiable models for survival analysis have been developed. While some inherit the difficulties of the proportionality assumption, others are restricted to scalar data input. Computed-tomography-based survival analysis remains a hardly researched topic at all. We propose a deep model for computed-tomography-based survival analysis providing a hazard probability output representation comparable to Cox regression without relying on the hazard proportionality assumption. The model is evaluated on multiple datasets, including metastatic colorectal cancer computed tomography imaging data, and significantly reduces the average prediction error compared to the Cox proportional hazards model.


Survival analysis Deep learning Computed tomography Colorectal cancer 


  1. 1.
    Surveillance, Epidemiology, and End Results (SEER) program ( research data (1973–2015), National Cancer Institute, DCCPS, Surveillance Research Program, released April 2018, based on the November 2017 submission (2017)
  2. 2.
    American Cancer Society: Cancer Facts and Figures. American Cancer Society, Atlanta (2019)Google Scholar
  3. 3.
    National Cancer Institute overall survival (2019). Accessed 01 Apr 2019
  4. 4.
    Aerts, H.J., et al.: Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 4006 (2014)CrossRefGoogle Scholar
  5. 5.
    Brierley, J.D., Gospodarowicz, M.K., Wittekind, C.: TNM Classification of Malignant Tumours. Wiley, Hoboken (2016)Google Scholar
  6. 6.
    Cohen, S.J., et al.: Relationship of circulating tumor cells to tumor response, progression-free survival, and overall survival in patients with metastatic colorectal cancer. Clin. Oncol. 26, 3213–3221 (2008)CrossRefGoogle Scholar
  7. 7.
    Efron, B.: Bootstrap methods: another look at the Jackknife. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics. SSS, pp. 569–593. Springer, New York (1992). Scholar
  8. 8.
    Ferlay, J., et al.: Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. Int. J. Cancer 136(5), E359–E386 (2015)CrossRefGoogle Scholar
  9. 9.
    Greenspan, H., Van Ginneken, B., Summers, R.M.: Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans. Med. Imaging 35(5), 1153–1159 (2016)CrossRefGoogle Scholar
  10. 10.
    Haarburger, C., Weitz, P., Rippel, O., Merhof, D.: Image-based survival analysis for lung cancer patients using CNNs. arXiv preprint arXiv:1808.09679 (2018)
  11. 11.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  12. 12.
    Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S., et al.: Random survival forests. Ann. Appl. Stat. 2(3), 841–860 (2008)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Katzman, J.L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., Kluger, Y.: Deep survival: a deep cox proportional hazards network. Stat 1050, 2 (2016)Google Scholar
  14. 14.
    Katzmann, A., et al.: Predicting lesion growth and patient survival in colorectal cancer patients using deep neural networks (2018)Google Scholar
  15. 15.
    Lao, J., et al.: A deep learning-based radiomics model for prediction of survival in Glioblastoma Multiforme. Sci. Rep. 7(1), 10353 (2017)CrossRefGoogle Scholar
  16. 16.
    Lee, C., Zame, W.R., Yoon, J., van der Schaar, M.: DeepHit: a deep learning approach to survival analysis with competing risks. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  17. 17.
    Miller Jr., R.G.: Survival Analysis, vol. 66. Wiley, Hoboken (2011)Google Scholar
  18. 18.
    Ries, L.A.G., et al.: Cancer incidence and survival among children and adolescents: United States SEER Program 1975–1995. Cancer incidence and survival among children and adolescents: United States SEER Program 1975–1995 (1999)Google Scholar
  19. 19.
    Rossi, P.H., Berk, R.A., Lenihan, K.J.: Money, work and crime: some experimental results (1980)Google Scholar
  20. 20.
    Schemper, M.: Cox analysis of survival data with non-proportional hazard functions. J. R. Stat. Soc.: Ser. D (Stat.) 41(4), 455–465 (1992)Google Scholar
  21. 21.
    Zauber, A.G., et al.: Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. New Engl. J. Med. 366(8), 687–696 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Alexander Katzmann
    • 1
    • 4
    Email author
  • Alexander Mühlberg
    • 1
  • Michael Sühling
    • 1
  • Dominik Nörenberg
    • 2
  • Stefan Maurus
    • 2
  • Julian Walter Holch
    • 3
  • Volker Heinemann
    • 3
  • Horst-Michael Groß
    • 4
  1. 1.Siemens Healthcare GmbH, Computed TomographyForchheimGermany
  2. 2.Department of RadiologyUniversity Hospital Großhadern, Ludwig-Maximilians-University MunichMunichGermany
  3. 3.Department of Internal Medicine III, Comprehensive Cancer CenterUniversity Hospital Großhadern, Ludwig-Maximilians-University MunichMunichGermany
  4. 4.Neuroinformatics and Cognitive Robotics LabIlmenau, University of TechnologyIlmenauGermany

Personalised recommendations