Format

Send to

Choose Destination
Int J Comput Assist Radiol Surg. 2019 Nov;14(11):1847-1857. doi: 10.1007/s11548-019-02010-3. Epub 2019 Jun 8.

Hyperparameter optimization for image analysis: application to prostate tissue images and live cell data of virus-infected cells.

Author information

1
Biomedical Computer Vision Group, BioQuant, IPMB, University of Heidelberg and DKFZ, Im Neuenheimer Feld 267, Heidelberg, Germany. christian.ritter@bioquant.uni-heidelberg.de.
2
Biomedical Computer Vision Group, BioQuant, IPMB, University of Heidelberg and DKFZ, Im Neuenheimer Feld 267, Heidelberg, Germany.
3
High-Content Analysis of the Cell (HiCell) and Advanced Biological Screening Facility, BioQuant, University of Heidelberg, Im Neuenheimer Feld 267, Heidelberg, Germany.
4
Division of Chromatin Networks, DKFZ and BioQuant, Im Neuenheimer Feld 267, Heidelberg, Germany.
5
Department of Infectious Diseases, Molecular Virology, University Hospital Heidelberg, Im Neuenheimer Feld 344, Heidelberg, Germany.
6
German Center of Infection Research, Heidelberg Partner Site, Heidelberg, Germany.
7
Department of Pathology, University Medical Center Hamburg-Eppendorf, Martinistraße 52, Hamburg, Germany.

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

PMID:
31177423
DOI:
10.1007/s11548-019-02010-3

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center