Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

© 2017, Springer-Verlag GmbH Germany. Purpose: Radiomic features derived from the texture analysis of different imaging modalities e show promise in lesion characterisation, response prediction, and prognostication in lung cancer patients. The present study aimed to identify an images-based radiomic signature capable of predicting disease-free survival (DFS) in non-small cell lung cancer (NSCLC) patients undergoing surgery. Methods: A cohort of 295 patients was selected. Clinical parameters (age, sex, histological type, tumour grade, and stage) were recorded for all patients. The endpoint of this study was DFS. Both computed tomography (CT) and fluorodeoxyglucose positron emission tomography (PET) images generated from the PET/CT scanner were analysed. Textural features were calculated using the LifeX package. Statistical analysis was performed using the R platform. The datasets were separated into two cohorts by random selection to perform training and validation of the statistical models. Predictors were fed into a multivariate Cox proportional hazard regression model and the receiver operating characteristic (ROC) curve as well as the corresponding area under the curve (AUC) were computed for each model built. Results: The Cox models that included radiomic features for the CT, the PET, and the PET+CT images resulted in an AUC of 0.75 (95%CI: 0.65–0.85), 0.68 (95%CI: 0.57–0.80), and 0.68 (95%CI: 0.58–0.74), respectively. The addition of clinical predictors to the Cox models resulted in an AUC of 0.61 (95%CI: 0.51–0.69), 0.64 (95%CI: 0.53–0.75), and 0.65 (95%CI: 0.50–0.72) for the CT, the PET, and the PET+CT images, respectively. Conclusions: A radiomic signature, for either CT, PET, or PET/CT images, has been identified and validated for the prediction of disease-free survival in patients with non-small cell lung cancer treated by surgery.
Original languageEnglish
Pages (from-to)207-217
Number of pages11
JournalEuropean Journal of Nuclear Medicine and Molecular Imaging
Volume45
Issue number2
DOIs
Publication statusPublished - Feb 1 2018

Fingerprint

Non-Small Cell Lung Carcinoma
Disease-Free Survival
Proportional Hazards Models
Area Under Curve
X-Ray Computed Tomography Scanners
Positron Emission Tomography Computed Tomography
Statistical Models
ROC Curve
Germany
Lung Neoplasms
Neoplasms

Keywords

  • CT
  • Lung cancer
  • PET/CT
  • Prognosis
  • Radiomics
  • Texture analysis

Cite this

@article{eda18ee5eb3f4f5b94fa041b2edb9aed,
title = "Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery",
abstract = "{\circledC} 2017, Springer-Verlag GmbH Germany. Purpose: Radiomic features derived from the texture analysis of different imaging modalities e show promise in lesion characterisation, response prediction, and prognostication in lung cancer patients. The present study aimed to identify an images-based radiomic signature capable of predicting disease-free survival (DFS) in non-small cell lung cancer (NSCLC) patients undergoing surgery. Methods: A cohort of 295 patients was selected. Clinical parameters (age, sex, histological type, tumour grade, and stage) were recorded for all patients. The endpoint of this study was DFS. Both computed tomography (CT) and fluorodeoxyglucose positron emission tomography (PET) images generated from the PET/CT scanner were analysed. Textural features were calculated using the LifeX package. Statistical analysis was performed using the R platform. The datasets were separated into two cohorts by random selection to perform training and validation of the statistical models. Predictors were fed into a multivariate Cox proportional hazard regression model and the receiver operating characteristic (ROC) curve as well as the corresponding area under the curve (AUC) were computed for each model built. Results: The Cox models that included radiomic features for the CT, the PET, and the PET+CT images resulted in an AUC of 0.75 (95{\%}CI: 0.65–0.85), 0.68 (95{\%}CI: 0.57–0.80), and 0.68 (95{\%}CI: 0.58–0.74), respectively. The addition of clinical predictors to the Cox models resulted in an AUC of 0.61 (95{\%}CI: 0.51–0.69), 0.64 (95{\%}CI: 0.53–0.75), and 0.65 (95{\%}CI: 0.50–0.72) for the CT, the PET, and the PET+CT images, respectively. Conclusions: A radiomic signature, for either CT, PET, or PET/CT images, has been identified and validated for the prediction of disease-free survival in patients with non-small cell lung cancer treated by surgery.",
keywords = "CT, Lung cancer, PET/CT, Prognosis, Radiomics, Texture analysis",
author = "Margarita Kirienko and Luca Cozzi and Lidija Antunovic and Lisa Lozza and Antonella Fogliata and Emanuele Voulaz and Alexia Rossi and Alexia Rossi and Arturo Chiti and Arturo Chiti and Martina Sollini",
year = "2018",
month = "2",
day = "1",
doi = "10.1007/s00259-017-3837-7",
language = "English",
volume = "45",
pages = "207--217",
journal = "European Journal of Nuclear Medicine and Molecular Imaging",
issn = "1619-7070",
publisher = "Springer Verlag",
number = "2",

}

TY - JOUR

T1 - Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery

AU - Kirienko, Margarita

AU - Cozzi, Luca

AU - Antunovic, Lidija

AU - Lozza, Lisa

AU - Fogliata, Antonella

AU - Voulaz, Emanuele

AU - Rossi, Alexia

AU - Rossi, Alexia

AU - Chiti, Arturo

AU - Chiti, Arturo

AU - Sollini, Martina

PY - 2018/2/1

Y1 - 2018/2/1

N2 - © 2017, Springer-Verlag GmbH Germany. Purpose: Radiomic features derived from the texture analysis of different imaging modalities e show promise in lesion characterisation, response prediction, and prognostication in lung cancer patients. The present study aimed to identify an images-based radiomic signature capable of predicting disease-free survival (DFS) in non-small cell lung cancer (NSCLC) patients undergoing surgery. Methods: A cohort of 295 patients was selected. Clinical parameters (age, sex, histological type, tumour grade, and stage) were recorded for all patients. The endpoint of this study was DFS. Both computed tomography (CT) and fluorodeoxyglucose positron emission tomography (PET) images generated from the PET/CT scanner were analysed. Textural features were calculated using the LifeX package. Statistical analysis was performed using the R platform. The datasets were separated into two cohorts by random selection to perform training and validation of the statistical models. Predictors were fed into a multivariate Cox proportional hazard regression model and the receiver operating characteristic (ROC) curve as well as the corresponding area under the curve (AUC) were computed for each model built. Results: The Cox models that included radiomic features for the CT, the PET, and the PET+CT images resulted in an AUC of 0.75 (95%CI: 0.65–0.85), 0.68 (95%CI: 0.57–0.80), and 0.68 (95%CI: 0.58–0.74), respectively. The addition of clinical predictors to the Cox models resulted in an AUC of 0.61 (95%CI: 0.51–0.69), 0.64 (95%CI: 0.53–0.75), and 0.65 (95%CI: 0.50–0.72) for the CT, the PET, and the PET+CT images, respectively. Conclusions: A radiomic signature, for either CT, PET, or PET/CT images, has been identified and validated for the prediction of disease-free survival in patients with non-small cell lung cancer treated by surgery.

AB - © 2017, Springer-Verlag GmbH Germany. Purpose: Radiomic features derived from the texture analysis of different imaging modalities e show promise in lesion characterisation, response prediction, and prognostication in lung cancer patients. The present study aimed to identify an images-based radiomic signature capable of predicting disease-free survival (DFS) in non-small cell lung cancer (NSCLC) patients undergoing surgery. Methods: A cohort of 295 patients was selected. Clinical parameters (age, sex, histological type, tumour grade, and stage) were recorded for all patients. The endpoint of this study was DFS. Both computed tomography (CT) and fluorodeoxyglucose positron emission tomography (PET) images generated from the PET/CT scanner were analysed. Textural features were calculated using the LifeX package. Statistical analysis was performed using the R platform. The datasets were separated into two cohorts by random selection to perform training and validation of the statistical models. Predictors were fed into a multivariate Cox proportional hazard regression model and the receiver operating characteristic (ROC) curve as well as the corresponding area under the curve (AUC) were computed for each model built. Results: The Cox models that included radiomic features for the CT, the PET, and the PET+CT images resulted in an AUC of 0.75 (95%CI: 0.65–0.85), 0.68 (95%CI: 0.57–0.80), and 0.68 (95%CI: 0.58–0.74), respectively. The addition of clinical predictors to the Cox models resulted in an AUC of 0.61 (95%CI: 0.51–0.69), 0.64 (95%CI: 0.53–0.75), and 0.65 (95%CI: 0.50–0.72) for the CT, the PET, and the PET+CT images, respectively. Conclusions: A radiomic signature, for either CT, PET, or PET/CT images, has been identified and validated for the prediction of disease-free survival in patients with non-small cell lung cancer treated by surgery.

KW - CT

KW - Lung cancer

KW - PET/CT

KW - Prognosis

KW - Radiomics

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=85029909809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029909809&partnerID=8YFLogxK

U2 - 10.1007/s00259-017-3837-7

DO - 10.1007/s00259-017-3837-7

M3 - Article

AN - SCOPUS:85029909809

VL - 45

SP - 207

EP - 217

JO - European Journal of Nuclear Medicine and Molecular Imaging

JF - European Journal of Nuclear Medicine and Molecular Imaging

SN - 1619-7070

IS - 2

ER -