Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2018 Jul 27;8:11359. doi: 10.1038/s41598-018-29653-7

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2018

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Workflow of feature selection process. Two datasets were used to determine the feature stability by performing a Test/Retest measurement, and ranking all extracted features with respect to their stability in between the two measurements. The dynamic range in relation to the variability of the measurement was assessed and ranked from high to low. To identify features, which are user independent, the two datasets of each user were combined, and tested for their stability in between the different users. Furthermore, the Kruskal-Wallis test was performed on each dataset to generate a discriminative power ranking. The Test/Retest, dynamic range, multiple delineation and discriminative power rankings were applied to compute a final ranking of all extracted imaging features. The most stable features of each imaging biomarker class were selected to compose the radiomic signature. A correlation analysis was performed to exclude correlating features. The final radiomic signature consisted of four features which were not correlating, one from each imaging biomarker class.