Unsupervised Pathology Detection in Medical Images using Learning-based Methods

  • Hristina UzunovaEmail author
  • Heinz Handels
  • Jan Ehrhardt
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


Detecting pathologies automatically is challenging because of their big variability. As the usual supervised machine learning approaches would only be able to detect one type of pathologies, in this work we pursue an unsupervised approach: learn the entire variability of healthy data and detect pathologies by their differences to the learned norm. Two methods have been developed based on this principle: A modified PatchMatch algorithm shows plausible results on contrasting brain tumors, but bad generalization ability for other types of data. A CVAE-based method on the other hand performs significantly better and ca. 17 times faster on the brain data and can be generalized to other pathologies, e.g. lung tumors. Not only is the achieved Dice coefficient of 0.55 comparable to other supervised methods on this data, moreover this method reliably detects different pathology types and needs no groundtruth.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kamnitsas K, Ferrante E, Parisot S, et al. DeepMedic for brain tumor segmentation. Proc MICCAI. 2016; p. 138–149.Google Scholar
  2. 2.
    Krüger J, Ehrhardt J, Handels H. Probabilistic appearance models for segmentation and classification. Proc ICCV. 2015; p. 1698–1706.Google Scholar
  3. 3.
    Schlegl T, Seeböck P, Waldstein SM, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. Inf Process Med Imaging. 2017; p. 146–157.Google Scholar
  4. 4.
    Barnes C, Shechtman E, Finkelstein A, et al. PatchMatch: A randomized correspondence algorithm for structural image editing. Proc ACM SIGGRAPH. 2009;28(3).Google Scholar
  5. 5.
    Faktor A, Irani M. Clustering by composition: unsupervised discovery of image categories. Proc ECCV. 2012; p. 474–487.Google Scholar
  6. 6.
    Dalal N, Triggs B. Histograms of oriented gradients for human detection. Proc IEEE CVPR. 2005; p. 886–893.Google Scholar
  7. 7.
    Heinrich MP, Jenkinson M, Papie z BW, et al. Towards realtime multimodal fusion for image-guided interventions using self-similarities. Proc MICCAI. 2013; p. 187–194.Google Scholar
  8. 8.
    Lotan O, Irani M. Needle-Match: reliable patch matching under high uncertainty. Proc IEEE CVPR. 2016 June; p. 439–448.Google Scholar
  9. 9.
    Kingma DP, Mohamed S, Jimenez Rezende D, et al. Semi-supervised learning with deep generative models. Adv Neural Inf Process Syst. 2014;27:3581–3589.Google Scholar
  10. 10.
    Menze BH, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging. 2015;34(10):1993–2024.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  1. 1.Institut für Medizinische InformatikUniversität zu LübeckLübeckDeutschland

Personalised recommendations