Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
, 14 (11), 1847-1857

Hyperparameter Optimization for Image Analysis: Application to Prostate Tissue Images and Live Cell Data of Virus-Infected Cells

Affiliations
Comparative Study

Hyperparameter Optimization for Image Analysis: Application to Prostate Tissue Images and Live Cell Data of Virus-Infected Cells

Christian Ritter et al. Int J Comput Assist Radiol Surg.

Abstract

Purpose: Automated analysis of microscopy image data typically requires complex pipelines that involve multiple methods for different image analysis tasks. To achieve best results of the analysis pipelines, method-dependent hyperparameters need to be optimized. However, complex pipelines often suffer from the fact that calculation of the gradient of the loss function is analytically or computationally infeasible. Therefore, first- or higher-order optimization methods cannot be applied.

Methods: We developed a new framework for zero-order black-box hyperparameter optimization called HyperHyper, which has a modular architecture that separates hyperparameter sampling and optimization. We also developed a visualization of the loss function based on infimum projection to obtain further insights into the optimization problem.

Results: We applied HyperHyper in three different experiments with different imaging modalities, and evaluated in total more than 400.000 hyperparameter combinations. HyperHyper was used for optimizing two pipelines for cell nuclei segmentation in prostate tissue microscopy images and two pipelines for detection of hepatitis C virus proteins in live cell microscopy data. We evaluated the impact of separating the sampling and optimization strategy using different optimizers and employed an infimum projection for visualizing the hyperparameter space.

Conclusions: The separation of sampling and optimization strategy of the proposed HyperHyper optimization framework improves the result of the investigated image analysis pipelines. Visualization of the loss function based on infimum projection enables gaining further insights on the optimization process.

Keywords: Hyperparameter optimization; Microscopy image analysis; Optimization framework; Visualization.

Similar articles

See all similar articles

References

    1. IEEE Trans Med Imaging. 2012 Sep;31(9):1786-808 - PubMed

References

    1. Nat Methods. 2014 Mar;11(3):281-9 - PubMed

References

    1. Nucleic Acids Res. 2018 Jul 2;46(W1):W537-W544 - PubMed

References

    1. J Biotechnol. 2017 Nov 10;261:70-75 - PubMed

References

    1. IEEE Trans Image Process. 2005 Sep;14(9):1372-83 - PubMed

References

    1. Cytometry A. 2018 Mar;93(3):357-370 - PubMed

References

    1. IEEE Trans Med Imaging. 2015 Feb;34(2):415-32 - PubMed

References

    1. Nat Methods. 2017 Dec;14(12):1141-1152 - PubMed

References

    1. IEEE Trans Image Process. 2017 Mar;26(3):1405-1417 - PubMed

References

    1. Nat Biotechnol. 2017 Apr 11;35(4):316-319 - PubMed

References

    1. J Virol. 2014 Jul;88(14):7904-14 - PubMed

References

    1. Annu Rev Biomed Eng. 2010 Aug 15;12:119-42 - PubMed

References

    1. Int J Comput Assist Radiol Surg. 2017 Nov;12(11):1959-1970 - PubMed

Publication types

LinkOut - more resources

Feedback