Advertisement

Combining Heterogeneously Labeled Datasets For Training Segmentation Networks

  • Jana Kemnitz
  • Christian F. Baumgartner
  • Wolfgang Wirth
  • Felix Eckstein
  • Sebastian K. Eder
  • Ender Konukoglu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11046)

Abstract

Accurate segmentation of medical images is an important step towards analyzing and tracking disease related morphological alterations in the anatomy. Convolutional neural networks (CNNs) have recently emerged as a powerful tool for many segmentation tasks in medical imaging. The performance of CNNs strongly depends on the size of the training data and combining data from different sources is an effective strategy for obtaining larger training datasets. However, this is often challenged by heterogeneous labeling of the datasets. For instance, one of the dataset may be missing labels or a number of labels may have been combined into a super label. In this work we propose a cost function which allows integration of multiple datasets with heterogeneous label subsets into a joint training. We evaluated the performance of this strategy on thigh MR and a cardiac MR datasets in which we artificially merged labels for half of the data. We found the proposed cost function substantially outperforms a naive masking approach, obtaining results very close to using the full annotations.

References

  1. 1.
    Shen, D., Wu, G., Suk, H.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19(1), 221–48 (2017)CrossRefGoogle Scholar
  2. 2.
    Prescott, J.W.: Quantitative imaging biomarkers: the application of advanced image processing and analysis to clinical and preclinical decision making. J. Digit. Imaging 26(1), 97–108 (2013)CrossRefGoogle Scholar
  3. 3.
    Litjens, G., Kooi, T., Bejnordi, B.E., Setio, A.A.A., Ciompi, F., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  4. 4.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI, pp. 234–41 (2015)Google Scholar
  5. 5.
    Iglesias, J.E., Sabuncu, M.R., Aganj, I., Bhatt, P., Casillas, C., et al.: An algorithm for optimal fusion of atlases with different labeling protocols. NeuroImage 106, 451–63 (2014)CrossRefGoogle Scholar
  6. 6.
    Peterfy, C.G., Schneider, E., Nevitt, M.: The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarthr. Cartil. 16(12), 1433–41 (2008)CrossRefGoogle Scholar
  7. 7.
    Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X. et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging (2018)Google Scholar
  8. 8.
    Ruhdorfer, A., Dannhauer, T., Wirth, W., Hitzl, W., Kwoh, C.K.: Cross-sectional and longitudinal side differences in thigh muscles. Arthr. Care Res. 65(7), 1034–42 (2013)CrossRefGoogle Scholar
  9. 9.
    Ruhdorfer, A., Wirth, W., Dannhauer, T., Eckstein, F.: Longitudinal (4 year) change of thigh muscle and adipose tissue distribution in chronically painful vs painless knees - data from the osteoarthritis initiative. Osteo. Cartil. 23(8) 1348–56 (2015)CrossRefGoogle Scholar
  10. 10.
    Cicek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: MICCAI, pp. 424–32 (2016)Google Scholar
  11. 11.
    Baumgartner, C.F., Koch, L.M., Pollefeys, M., Konukoglu, E.: An exploration of 2D and 3D deep learning techniques for cardiac MR image segmentation. In: Proceedings of the Statistical Atlases and Computational Models of the Heart (STACOM), ACDC Challenge, MICCAI17 Workshop (2017)Google Scholar
  12. 12.
    Kemnitz, J., Wirth, W., Eckstein, F., Culvenor, A.G.: The Role of Thigh Muscle and Adipose Tissue in Knee Osteoarthritis Progression in Women: Data from the Osteoarthritis Initiative. Osteo. Cartil. (2018) Epub ahead of printGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jana Kemnitz
    • 1
    • 2
    • 3
  • Christian F. Baumgartner
    • 3
  • Wolfgang Wirth
    • 1
    • 2
  • Felix Eckstein
    • 1
    • 2
  • Sebastian K. Eder
    • 1
  • Ender Konukoglu
    • 3
  1. 1.Paracelsus Medical University SalzburgSalzburgAustria
  2. 2.Chondrometrics GmbH AinringAinringGermany
  3. 3.Computer Vision Lab, ETH ZurichZurichSwitzerland

Personalised recommendations