Advertisement

Black-Box Hyperparameter Optimization for Nuclei Segmentation in Prostate Tissue Images

  • Thomas WollmannEmail author
  • Patrick Bernhard
  • Manuel Gunkel
  • Delia M. Braun
  • Jan Meiners
  • Ronald Simon
  • Guido Sauter
  • Holger Erfle
  • Karsten Rippe
  • Karl Rohr
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Segmentation of cell nuclei is essential for analyzing highcontent histological screens. Often, parameters of automatic approaches need to be optimized, which is tedious and difficult to perform manually. We propose a novel hyperparameter optimization framework, which formulates optimization as a combination of candidate sampling and an optimization strategy. We present a clustering based and a deep neural network based pipeline for nuclei segmentation, for which the parameters are optimized using state of the art optimizers as well as a novel optimizer. The pipelines were applied to challenging prostate cancer tissue images. We performed a quantitative evaluation using 28,388 parameter settings. It turned out that the deep neural network outperforms the clustering based pipeline, while the results for different optimizers vary slightly.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Wang Y, Du S, Balakrishnan S, et al. Stochastic Zeroth-order Optimization in High Dimensions. arXiv:1710.10551; 2017.
  2. 2.
    Ramani S, Blu T, Unser M. Monte-carlo SURE: a black-box optimization of regularization parameters for general denoising algorithms. IEEE Trans Image Process. 2008;17(9):1540-1554.MathSciNetCrossRefGoogle Scholar
  3. 3.
    Hansen N, Auger A, Ros R, et al.; ACM. Comparing results of 31 algorithms from the black-box optimization benchmarking BBOB-2009. Proc GECCO. 2010; p. 1689-1696.Google Scholar
  4. 4.
    Teodoro G, Kurҫ TM, Taveira LF, et al. Algorithm sensitivity analysis and parameter tuning for tissue image segmentation pipelines. Bioinformatics. 2016;33(7):1064-1072.Google Scholar
  5. 5.
    Snoek J, Larochelle H, Adams RP. Practical bayesian optimization of machine learning algorithms. Proc Adv Neural Inf Process Syst. 2012; p. 2951-2959.Google Scholar
  6. 6.
    Bergstra J, Yamins D, Cox DD; Citeseer. Hyperopt: a python library for optimizing the hyperparameters of machine learning algorithms. Proc SciPy. 2013; p. 13-20.Google Scholar
  7. 7.
    Komer B, Bergstra J, Eliasmith C. Hyperopt-sklearn: automatic hyperparameter configuration for scikit-learn. Proc ICML Workshop AutoML. 2014; p. 2825-2830.Google Scholar
  8. 8.
    Golovin D, Solnik B, Moitra S, et al.; ACM. Google vizier: a service for black-box optimization. Proc SIGKDD. 2017; p. 1487-1495.Google Scholar
  9. 9.
    Ronneberger O, Fischer P, Brox T; Springer. U-net: convolutional networks for biomedical image segmentation. Proc MICCAI. 2015; p. 234-241.Google Scholar
  10. 10.
    Hutter F, Hoos HH, Leyton-Brown K; Springer. Sequential model-based optimization for general algorithm configuration. Proc LION. 2011; p. 507-523.Google Scholar
  11. 11.
    Chen T, Guestrin C; ACM. Xgboost: a scalable tree boosting system. Proc SIGKDD. 2016; p. 785-794.Google Scholar
  12. 12.
    Goldberg DE. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley; 1989.Google Scholar
  13. 13.
    Parzen E. On estimation of a probability density function and mode. Ann Math Stat. 1962;33(3):1065-1076.MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Thomas Wollmann
    • 1
    Email author
  • Patrick Bernhard
    • 1
  • Manuel Gunkel
    • 2
  • Delia M. Braun
    • 3
  • Jan Meiners
    • 4
  • Ronald Simon
    • 4
  • Guido Sauter
    • 4
  • Holger Erfle
    • 2
  • Karsten Rippe
    • 3
  • Karl Rohr
    • 1
  1. 1.University of Heidelberg, BioQuant, IPMB, and DKFZ Heidelberg, Biomedical Computer Vision GroupHeidelbergDeutschland
  2. 2.High-Content Analysis of the Cell (HiCell) and Advanced Biological Screening Facility, BioQuantUniversity of HeidelbergHeidelbergDeutschland
  3. 3.Division of Chromatin NetworksDKFZ and BioQuantHeidelbergDeutschland
  4. 4.Department of PathologyUniversity Medical Center Hamburg-EppendorfHamburgDeutschland

Personalised recommendations