Hyperparameter optimization for image analysis: application to prostate tissue images and live cell data of virus-infected cells
Standard
Hyperparameter optimization for image analysis: application to prostate tissue images and live cell data of virus-infected cells. / Ritter, Christian; Wollmann, Thomas; Bernhard, Patrick; Gunkel, Manuel; Braun, Delia M; Lee, Ji-Young; Meiners, Jan; Simon, Ronald; Sauter, Guido; Erfle, Holger; Rippe, Karsten; Bartenschlager, Ralf; Rohr, Karl.
In: INT J COMPUT ASS RAD, Vol. 14, No. 11, 11.2019, p. 1847-1857.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Hyperparameter optimization for image analysis: application to prostate tissue images and live cell data of virus-infected cells
AU - Ritter, Christian
AU - Wollmann, Thomas
AU - Bernhard, Patrick
AU - Gunkel, Manuel
AU - Braun, Delia M
AU - Lee, Ji-Young
AU - Meiners, Jan
AU - Simon, Ronald
AU - Sauter, Guido
AU - Erfle, Holger
AU - Rippe, Karsten
AU - Bartenschlager, Ralf
AU - Rohr, Karl
PY - 2019/11
Y1 - 2019/11
N2 - 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.
AB - 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.
U2 - 10.1007/s11548-019-02010-3
DO - 10.1007/s11548-019-02010-3
M3 - SCORING: Journal article
C2 - 31177423
VL - 14
SP - 1847
EP - 1857
JO - INT J COMPUT ASS RAD
JF - INT J COMPUT ASS RAD
SN - 1861-6410
IS - 11
ER -