Efficient Methods and Parallel Execution for Algorithm Sensitivity Analysis with Parameter Tuning on Microscopy Imaging Datasets

TL;DR

This paper presents a high-performance computing framework for efficient parameter sensitivity analysis and auto-tuning in microscopy image analysis, significantly reducing computational costs and enabling large dataset processing.

Contribution

The authors introduce a scalable, efficient framework utilizing HPC resources for sensitivity analysis and auto-tuning in image segmentation and classification algorithms.

Findings

Achieved over 85% execution efficiency on HPC clusters.

Auto-tuning converges by exploring only 0.0009% of the parameter space.

Framework enables large-scale sensitivity analysis with limited impact on output.

Abstract

Background: We describe an informatics framework for researchers and clinical investigators to efficiently perform parameter sensitivity analysis and auto-tuning for algorithms that segment and classify image features in a large dataset of high-resolution images. The computational cost of the sensitivity analysis process can be very high, because the process requires processing the input dataset several times to systematically evaluate how output varies when input parameters are varied. Thus, high performance computing techniques are required to quickly execute the sensitivity analysis process. Results: We carried out an empirical evaluation of the proposed method on high performance computing clusters with multi-core CPUs and co-processors (GPUs and Intel Xeon Phis). Our results show that (1) the framework achieves excellent scalability and efficiency on a high performance computing cluster -- execution efficiency remained above 85% in all experiments; (2) the parameter auto-tuning methods are able to converge by visiting only a small fraction (0.0009%) of the search space with limited impact to the algorithm output (0.56% on average). Conclusions: The sensitivity analysis framework provides a range of strategies for the efficient exploration of the parameter space, as well as multiple indexes to evaluate the effect of parameter modification to outputs or even correlation between parameters. Our work demonstrates the feasibility of performing sensitivity analyses, parameter studies, and auto-tuning with large datasets with the use of high-performance systems and techniques. The proposed technologies will enable the quantification of error estimations and output variations in these pipelines, which may be used in application specific ways to assess uncertainty of conclusions extracted from data generated by these image analysis pipelines.