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

. 2023 Feb 4;50(6):1607–1620. doi: 10.1007/s00259-023-06127-1

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

© The Author(s) 2023

Open AccessThis 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 licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence 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 licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 1 — The CONSORT diagram of preparing and analyzing the cohorts of this study. Already delineated glioma, lung and prostate lesions (Ref-B) were collected from databases that were analyzed and published in prior studies [27–29]. Glioma and lung cohorts had one lesion per patient, while the prostate cohort contained multiple lesions per patient. Reference labels for glioma, lung and prostate lesions were 3-years survival, 2-years survival and low-vs-high risk, respectively. Three additional delineations were generated form Ref-B delineations: a fuzzy mask (Ref-F), an extended binary mask (Ext-B) and an extended fuzzy (Ext-F) mask. Fuzzy masks were generated by a three-dimensional Gaussian filtering, relying on the physical resolution of each cohort's PET imaging system. Samples having no variations or invalid radiomic values (e.g., by low-uptake lesions) were excluded from all delineation-specific databases to ensure a harmonized comparison among them. The resulted four databases per cohort underwent the comparative analysis (see the “Methods” section)