Next Article in Journal
Publisher’s Note: Continued Publication of Tomography by MDPI
Previous Article in Journal
A System-Agnostic, Adaptable and Extensible Animal Support Cradle System for Cardio-Respiratory-Synchronised, and Other, Multi-Modal Imaging of Small Animals
Open AccessArticle

Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions

Department of Radiology, New York Presbyterian Hospital, Columbia University Medical Center, New York, NY 10032, USA
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Current address: Department of Radiology, The University of Chicago, Chicago, IL 60637, USA.
Tomography 2021, 7(1), 55-64; https://doi.org/10.3390/tomography7010005
Received: 9 October 2020 / Accepted: 17 December 2020 / Published: 9 February 2021
We propose a novel framework for determining radiomics feature robustness by considering the effects of both biological and noise signals. This framework is preliminarily tested in a study predicting the epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients. Pairs of CT images (baseline, 3-week post therapy) of 46 NSCLC patients with known EGFR mutation status were collected and a FDA-customized anthropomorphic thoracic phantom was scanned on two vendors’ scanners at four different tube currents. Delta radiomics features were extracted from the NSCLC patient CTs and reproducible, non-redundant, and informative features were identified. The feature value differences between EGFR mutant and EGFR wildtype patients were quantitatively measured as the biological signal. Similarly, radiomics features were extracted from the phantom CTs. A pairwise comparison between settings resulted in a feature value difference that was quantitatively measured as the noise signal. Biological signals were compared to noise signals at each setting to determine if the distributions were significantly different by two-sample t-test, and thus robust. Four optimal features were selected to predict EGFR mutation status, Tumor-Mass, Sigmoid-Offset-Mean, Gabor-Energy and DWT-Energy, which quantified tumor mass, tumor-parenchyma density transition at boundary, line-like pattern inside tumor and intratumoral heterogeneity, respectively. The first three variables showed robustness across the majority of studied CT acquisition parameters. The textual feature DWT-Energy was less robust. The proposed framework was able to determine robustness of radiomics features at specific settings by comparing biological signal to noise signal. Identification of robust radiomics features may improve the generalizability of radiomics models in future studies. View Full-Text
Keywords: radiomics; reproducibility; robustness; NSCLC; phantom; EGFR radiomics; reproducibility; robustness; NSCLC; phantom; EGFR
Show Figures

Figure 1

MDPI and ACS Style

Lu, L.; Sun, S.H.; Afran, A.; Yang, H.; Lu, Z.F.; So, J.; Schwartz, L.H.; Zhao, B. Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions. Tomography 2021, 7, 55-64. https://doi.org/10.3390/tomography7010005

AMA Style

Lu L, Sun SH, Afran A, Yang H, Lu ZF, So J, Schwartz LH, Zhao B. Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions. Tomography. 2021; 7(1):55-64. https://doi.org/10.3390/tomography7010005

Chicago/Turabian Style

Lu, Lin; Sun, Shawn H.; Afran, Aaron; Yang, Hao; Lu, Zheng F.; So, James; Schwartz, Lawrence H.; Zhao, Binsheng. 2021. "Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions" Tomography 7, no. 1: 55-64. https://doi.org/10.3390/tomography7010005

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop