Next Article in Journal
Regional Ultrahigh-Resolution Rescan in a Clinical Whole-Body CT Scanner Using a Contact Detector Insert
Previous Article in Journal
A Web-Based Response-Assessment System for Development and Validation of Imaging Biomarkers in Oncology
 
 
Tomography is published by MDPI from Volume 7 Issue 1 (2021). Previous articles were published by another publisher in Open Access under a CC-BY (or CC-BY-NC-ND) licence, and they are hosted by MDPI on mdpi.com as a courtesy and upon agreement with Grapho, LLC.
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom

Department of Radiology, Columbia University Medical Center, 710 West 168th Street, B26, New York, NY 10032, USA
*
Author to whom correspondence should be addressed.
Submission received: 1 January 2019 / Revised: 24 January 2019 / Accepted: 21 February 2019 / Published: 1 March 2019

Abstract

We studied the reliability of radiomic features on abdominal computed tomography (CT) images reconstructed with multiple CT image acquisition settings using the ACR (American College of Radiology) CT Phantom. Twenty-four sets of CT images of the ACR CT phantom were attained from a GE Discovery 750HD scanner using 24 different image acquisition settings, combinations of 4 tube currents (25, 50, 100, 200 Effective mAs), 3 slice thicknesses (1.25, 2.5, 5 mm), and 2 convolution kernels (STANDARD and SOFT). Polyethylene (−95 HU) and acrylic (120 HU) of the phantom model were selected for calculating real feature value; a noise-free, computer-generated phantom image series that reproduced the 2 objects and the background was used for calculating reference feature value. Feature reliability was defined as the degree of predicting reference feature value from real feature value. Radiomic features mean, std, skewness, kurtosis, gray-level co-occurrence matrix (GLCM)-energy, GLCM-contrast, GLCM-correlation, GLCM-homogeneity were investigated. The value of R2 ≥ 0.85 was considered to be of high reliability. The reliability of mean and std were high across all image acquisition settings. At 200 Effective mAs, all features except GLCM-homogeneity showed high reliability, whereas at 25 Effective mAs, most features (except mean and std) showed low reliability. From high to low, reliability was ranked in the following order: mean, std, skewness, kurtosis, GLCM-energy, correlation, contrast and homogeneity. CT image acquisition settings affected the reliability of radiomic features. High reliable features were attained from images reconstructed at high tube current and thick slice thickness.
Keywords: quantitative imaging biomarkers; Radiomic Features; Reliability; Abdominal CT quantitative imaging biomarkers; Radiomic Features; Reliability; Abdominal CT

Share and Cite

MDPI and ACS Style

Lu, L.; Liang, Y.; Schwartz, L.H.; Zhao, B. Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom. Tomography 2019, 5, 226-231. https://0-doi-org.brum.beds.ac.uk/10.18383/j.tom.2019.00005

AMA Style

Lu L, Liang Y, Schwartz LH, Zhao B. Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom. Tomography. 2019; 5(1):226-231. https://0-doi-org.brum.beds.ac.uk/10.18383/j.tom.2019.00005

Chicago/Turabian Style

Lu, Lin, Yongguang Liang, Lawrence H. Schwartz, and Binsheng Zhao. 2019. "Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom" Tomography 5, no. 1: 226-231. https://0-doi-org.brum.beds.ac.uk/10.18383/j.tom.2019.00005

Article Metrics

Back to TopTop