Algorithm sensitivity analysis and parameter tuning for tissue image segmentation pipelines.

• Type of Material: Article
• Authors: George Teodoro, University of Brasília; Tahsin M. Kurç, Stony Brook University; Luis F. R. Taveira, University of Brasília; Alba C. M. A. Melo, University of Brasília; Yi Gao, Stony Brook University; Jun Kong, Emory University; Joel H. Saltz, Stony Brook University
• Language: English
• Date: 2017-04-01
• Publisher: Oxford University Press
• Publication Version: Final Published Version
• Copyright Statement: © The Author 2016. Published by Oxford University Press. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1093/bioinformatics/btw749
• Title of Journal or Parent Work: Bioinformatics
• Volume: 33
• Issue: 7
• Start Page: 1064
• End Page: 1072
• Grant/Funding Information: This research used resources of the XSEDE Science Gateways program under grant TG-ASC130023.; This work was supported in part by 1U24CA180924-01A1 from the NCI, R01LM011119-01 and R01LM009239 from the NLM, CNPq and NIH K25CA181503.
• Research Categories: Computer Science; Biology, Bioinformatics

Abstract

Motivation: Sensitivity analysis and parameter tuning are important processes in large-scale image analysis. They are very costly because the image analysis workflows are required to be executed several times to systematically correlate output variations with parameter changes or to tune parameters. An integrated solution with minimum user interaction that uses effective methodologies and high performance computing is required to scale these studies to large imaging datasets and expensive analysis workflows. Results: The experiments with two segmentation workflows show that the proposed approach can (i) quickly identify and prune parameters that are non-influential; (ii) search a small fraction (about 100 points) of the parameter search space with billions to trillions of points and improve the quality of segmentation results (Dice and Jaccard metrics) by as much as 1.42× compared to the results from the default parameters; (iii) attain good scalability on a high performance cluster with several effective optimizations. Conclusions: Our work demonstrates the feasibility of performing sensitivity analyses, parameter studies and auto-tuning with large datasets. The proposed framework can enable the quantification of error estimations and output variations in image segmentation pipelines.