English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background: We describe an informatics framework for researchers and clinicalinvestigators to efficiently perform parameter sensitivity analysis andauto-tuning for algorithms that segment and classify image features in a largedataset of high-resolution images. The computational cost of the sensitivityanalysis process can be very high, because the process requires processing theinput dataset several times to systematically evaluate how output varies wheninput parameters are varied. Thus, high performance computing techniques arerequired to quickly execute the sensitivity analysis process.  Results: We carried out an empirical evaluation of the proposed method onhigh performance computing clusters with multi-core CPUs and co-processors(GPUs and Intel Xeon Phis). Our results show that (1) the framework achievesexcellent scalability and efficiency on a high performance computing cluster --execution efficiency remained above 85% in all experiments; (2) the parameterauto-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 ofstrategies for the efficient exploration of the parameter space, as well asmultiple indexes to evaluate the effect of parameter modification to outputs oreven correlation between parameters. Our work demonstrates the feasibility ofperforming sensitivity analyses, parameter studies, and auto-tuning with largedatasets with the use of high-performance systems and techniques. The proposedtechnologies will enable the quantification of error estimations and outputvariations in these pipelines, which may be used in application specific waysto assess uncertainty of conclusions extracted from data generated by theseimage analysis pipelines.

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