Cover Image

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

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 th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ritter, Christian (Author) , Wollmann, Thomas (Author) , Gunkel, Manuel (Author) , Braun, Delia (Author) , Lee, Ji Young (Author) , Erfle, Holger (Author) , Rippe, Karsten (Author) , Bartenschlager, Ralf (Author) , Rohr, Karl (Author)
Format: Article (Journal)
Language:English
Published: 8 June 2019
In: International journal of computer assisted radiology and surgery
Year: 2019, Volume: 14, Issue: 11, Pages: 1847-1857
ISSN:1861-6429
DOI:10.1007/s11548-019-02010-3
Online Access:Verlag, Volltext: https://doi.org/10.1007/s11548-019-02010-3
Get full text
Author Notes:Christian Ritter, Thomas Wollmann, Patrick Bernhard, Manuel Gunkel, Delia M. Braun, Ji-Young Lee, Jan Meiners, Ronald Simon, Guido Sauter, Holger Erfle, Karsten Rippe, Ralf Bartenschlager, Karl Rohr
Description
Summary: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.
Item Description:Gesehen am 07.02.2020
Physical Description:Online Resource
ISSN:1861-6429
DOI:10.1007/s11548-019-02010-3

Similar Items