en
Scientific article
Open access
English

Assessing radiomics feature stability with simulated CT acquisitions

Published inScientific reports, vol. 12, no. 1, 4732
Publication date2022-03-18
First online date2022-03-18
Abstract

Medical imaging quantitative features had once disputable usefulness in clinical studies. Nowadays, advancements in analysis techniques, for instance through machine learning, have enabled quantitative features to be progressively useful in diagnosis and research. Tissue characterisation is improved via the “radiomics” features, whose extraction can be automated. Despite the advances, stability of quantitative features remains an important open problem. As features can be highly sensitive to variations of acquisition details, it is not trivial to quantify stability and efficiently select stable features. In this work, we develop and validate a Computed Tomography (CT) simulator environment based on the publicly available ASTRA toolbox ( www.astra-toolbox.com ). We show that the variability, stability and discriminative power of the radiomics features extracted from the virtual phantom images generated by the simulator are similar to those observed in a tandem phantom study. Additionally, we show that the variability is matched between a multi-center phantom study and simulated results. Consequently, we demonstrate that the simulator can be utilised to assess radiomics features’ stability and discriminative power.

eng
Keywords
  • Machine Learning
  • Phantoms, Imaging
  • Retrospective Studies
  • Tomography, X-Ray Computed / methods
Funding
  • ETH Domain - Strategic Focal Area "Personalized Health and Related Technologies (PHRT)" [2018-531]
  • Swiss Personalised Health Network - QA4IQI Quality assessment for interoperable quantitative computed tomography imaging [DMS2445]
Citation (ISO format)
FLOURIS, Kyriakos et al. Assessing radiomics feature stability with simulated CT acquisitions. In: Scientific reports, 2022, vol. 12, n° 1, p. 4732. doi: 10.1038/s41598-022-08301-1
Main files (1)
Article (Published version)
Identifiers
ISSN of the journal2045-2322
105views
253downloads

Technical informations

Creation09/20/2022 9:55:00 AM
First validation09/20/2022 9:55:00 AM
Update time03/16/2023 10:14:15 AM
Status update03/16/2023 10:14:14 AM
Last indexation02/01/2024 9:19:03 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack