Advertisement

Fully-Automated Analysis of Body Composition from CT in Cancer Patients Using Convolutional Neural Networks

  • Christopher P. Bridge
  • Michael Rosenthal
  • Bradley Wright
  • Gopal Kotecha
  • Florian Fintelmann
  • Fabian Troschel
  • Nityanand Miskin
  • Khanant Desai
  • William Wrobel
  • Ana Babic
  • Natalia Khalaf
  • Lauren Brais
  • Marisa Welch
  • Caitlin Zellers
  • Neil Tenenholtz
  • Mark Michalski
  • Brian Wolpin
  • Katherine Andriole
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11041)

Abstract

The amounts of muscle and fat in a person’s body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate the analysis of CT body composition using a DenseNet to select the CT slice and U-Net to perform segmentation. We train and test our methods on independent cohorts. Our results show Dice scores (0.95−0.98) and correlation coefficients (R = 0.99) that are favorable compared to human readers. These results suggest that fully automated body composition analysis is feasible, which could enable both clinical use and large-scale population studies.

References

  1. 1.
    Belharbi, S.: Spotting L3 slice in CT scans using deep convolutional network and transfer learning. Comput. Biol. Med. 87, 95–103 (2017)CrossRefGoogle Scholar
  2. 2.
    Danai, L.V., et al.: Altered exocrine function can drive adipose wasting in early pancreatic cancer. Nature 558(7711), 600–604 (2018). https://www.ncbi.nlm.nih.gov/pubmed/29925948CrossRefGoogle Scholar
  3. 3.
    Foldyna, B., et al.: Computed tomography-based fat and muscle characteristics are associated with mortality after transcatheter aortic valve replacement. J. Cardiovasc. Comput. Tomogr. 12(3), 223–228 (2018). http://www.sciencedirect.com/science/article/pii/S1934592518300571CrossRefGoogle Scholar
  4. 4.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  5. 5.
    Kim, J.Y., et al.: Computerized automated quantification of subcutaneous and visceral adipose tissue from computed tomography scans: development and validation study. JMIR Med. Inform. 4(1), e2 (2016)CrossRefGoogle Scholar
  6. 6.
    Kullberg, J., et al.: Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies. Sci. Rep. 7(1), 10425 (2017)Google Scholar
  7. 7.
    Lee, H., et al.: Pixel-level deep segmentation: artificial intelligence quantifies muscle on computed tomography for body morphometric analysis. J. Digit. Imaging 30(4), 487–498 (2017)CrossRefGoogle Scholar
  8. 8.
    Martin, L., et al.: Cancer cachexia in the age of obesity: skeletal muscle depletion is a powerful prognostic factor, independent of body mass index. J. Clin. Oncol. 31(12), 1539–47 (2013)CrossRefGoogle Scholar
  9. 9.
    Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565–571, October 2016Google Scholar
  10. 10.
    Parikh, A.M., et al.: Development and validation of a rapid and robust method to determine visceral adipose tissue volume using computed tomography images. PLoS ONE 12(8), e0183515 (2017)CrossRefGoogle Scholar
  11. 11.
    Popuri, K., Cobzas, D., Esfandiari, N., Baracos, V., Jägersand, M.: Body composition assessment in axial CT images using FEM-based automatic segmentation of skeletal muscle. IEEE Trans. Med. Imaging 35(2), 512–520 (2016)CrossRefGoogle Scholar
  12. 12.
    Prado, C.M., et al.: Prevalence and clinical implications of sarcopenic obesity in patients with solid tumours of the respiratory and gastrointestinal tracts: a population-based study. Lancet Oncol. 9(7), 629–35 (2008)CrossRefGoogle Scholar
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  14. 14.
    Shen, W., et al.: Total body skeletal muscle and adipose tissue volumes: estimation from a single abdominal cross-sectional image. J. Appl. Physiol. 97(6), 2333–2338 (2004)CrossRefGoogle Scholar
  15. 15.
    Shen, W., et al.: Visceral adipose tissue: relations between single-slice areas and total volume. Am. J. Clin. Nutr. 80(2), 271–278 (2004)CrossRefGoogle Scholar
  16. 16.
    Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Christopher P. Bridge
    • 1
  • Michael Rosenthal
    • 2
  • Bradley Wright
    • 1
  • Gopal Kotecha
    • 1
  • Florian Fintelmann
    • 3
  • Fabian Troschel
    • 3
  • Nityanand Miskin
    • 2
  • Khanant Desai
    • 2
  • William Wrobel
    • 2
  • Ana Babic
    • 4
  • Natalia Khalaf
    • 2
  • Lauren Brais
    • 4
  • Marisa Welch
    • 4
  • Caitlin Zellers
    • 4
  • Neil Tenenholtz
    • 1
  • Mark Michalski
    • 1
  • Brian Wolpin
    • 4
  • Katherine Andriole
    • 1
  1. 1.MGH and BWH Center for Clinical Data ScienceBostonUSA
  2. 2.Brigham and Women’s HospitalBostonUSA
  3. 3.Massachusetts General HospitalBostonUSA
  4. 4.Dana-Farber Cancer InstituteBostonUSA

Personalised recommendations