Stage III non-small cell lung cancer: Prognostic value of FDG PET quantitative imaging features combined with clinical prognostic factors

David V. Fried, Osama Mawlawi, Lifei Zhang, Xenia Fave, Shouhao Zhou, Geoffrey Ibbott, Zhongxing Liao, Laurence E. Court

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Purpose: To determine whether quantitative imaging features from pretreatment positron emission tomography (PET) can enhance patient overall survival risk stratification beyond what can be achieved with conventional prognostic factors in patients with stage III non-small cell lung cancer (NSCLC). Materials and Methods: The institutional review board approved this retrospective chart review study and waived the requirement to obtain informed consent. The authors retrospectively identified 195 patients with stage III NSCLC treated definitively with radiation therapy between January 2008 and January 2013. All patients underwent pretreatment PET/computed tomography before treatment. Conventional PET metrics, along with histogram, shape and volume, and co-occurrence matrix features, were extracted. Linear predictors of overall survival were developed from leaveone-out cross-validation. Predictive Kaplan-Meier curves were used to compare the linear predictors with both quantitative imaging features and conventional prognostic factors to those generated with conventional prognostic factors alone. The Harrell concordance index was used to quantify the discriminatory power of the linear predictors for survival differences of at least 0, 6, 12, 18, and 24 months. Models were generated with features present in more than 50% of the cross-validation folds. Results: Linear predictors of overall survival generated with both quantitative imaging features and conventional prognostic factors demonstrated improved risk stratification compared with those generated with conventional prognostic factors alone in terms of log-rank statistic (P = .18 vs P = .0001, respectively) and concordance index (0.62 vs 0.58, respectively). The use of quantitative imaging features selected during cross-validation improved the model using conventional prognostic factors alone (P = .007). Disease solidity and primary tumor energy from the co-occurrence matrix were found to be selected in all folds of cross-validation. Conclusion: Pretreatment PET features were associated with overall survival when adjusting for conventional prognostic factors in patients with stage III NSCLC.

Original languageEnglish (US)
Pages (from-to)214-222
Number of pages9
JournalRadiology
Volume278
Issue number1
DOIs
StatePublished - Jan 2016

Fingerprint

Non-Small Cell Lung Carcinoma
Positron-Emission Tomography
Survival
Research Ethics Committees
Informed Consent
Radiotherapy
Neoplasms

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

Fried, David V. ; Mawlawi, Osama ; Zhang, Lifei ; Fave, Xenia ; Zhou, Shouhao ; Ibbott, Geoffrey ; Liao, Zhongxing ; Court, Laurence E. / Stage III non-small cell lung cancer : Prognostic value of FDG PET quantitative imaging features combined with clinical prognostic factors. In: Radiology. 2016 ; Vol. 278, No. 1. pp. 214-222.
@article{814d1f74f11a490a90ab25ef56e1999b,
title = "Stage III non-small cell lung cancer: Prognostic value of FDG PET quantitative imaging features combined with clinical prognostic factors",
abstract = "Purpose: To determine whether quantitative imaging features from pretreatment positron emission tomography (PET) can enhance patient overall survival risk stratification beyond what can be achieved with conventional prognostic factors in patients with stage III non-small cell lung cancer (NSCLC). Materials and Methods: The institutional review board approved this retrospective chart review study and waived the requirement to obtain informed consent. The authors retrospectively identified 195 patients with stage III NSCLC treated definitively with radiation therapy between January 2008 and January 2013. All patients underwent pretreatment PET/computed tomography before treatment. Conventional PET metrics, along with histogram, shape and volume, and co-occurrence matrix features, were extracted. Linear predictors of overall survival were developed from leaveone-out cross-validation. Predictive Kaplan-Meier curves were used to compare the linear predictors with both quantitative imaging features and conventional prognostic factors to those generated with conventional prognostic factors alone. The Harrell concordance index was used to quantify the discriminatory power of the linear predictors for survival differences of at least 0, 6, 12, 18, and 24 months. Models were generated with features present in more than 50{\%} of the cross-validation folds. Results: Linear predictors of overall survival generated with both quantitative imaging features and conventional prognostic factors demonstrated improved risk stratification compared with those generated with conventional prognostic factors alone in terms of log-rank statistic (P = .18 vs P = .0001, respectively) and concordance index (0.62 vs 0.58, respectively). The use of quantitative imaging features selected during cross-validation improved the model using conventional prognostic factors alone (P = .007). Disease solidity and primary tumor energy from the co-occurrence matrix were found to be selected in all folds of cross-validation. Conclusion: Pretreatment PET features were associated with overall survival when adjusting for conventional prognostic factors in patients with stage III NSCLC.",
author = "Fried, {David V.} and Osama Mawlawi and Lifei Zhang and Xenia Fave and Shouhao Zhou and Geoffrey Ibbott and Zhongxing Liao and Court, {Laurence E.}",
year = "2016",
month = "1",
doi = "10.1148/radiol.2015142920",
language = "English (US)",
volume = "278",
pages = "214--222",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "1",

}

Stage III non-small cell lung cancer : Prognostic value of FDG PET quantitative imaging features combined with clinical prognostic factors. / Fried, David V.; Mawlawi, Osama; Zhang, Lifei; Fave, Xenia; Zhou, Shouhao; Ibbott, Geoffrey; Liao, Zhongxing; Court, Laurence E.

In: Radiology, Vol. 278, No. 1, 01.2016, p. 214-222.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Stage III non-small cell lung cancer

T2 - Prognostic value of FDG PET quantitative imaging features combined with clinical prognostic factors

AU - Fried, David V.

AU - Mawlawi, Osama

AU - Zhang, Lifei

AU - Fave, Xenia

AU - Zhou, Shouhao

AU - Ibbott, Geoffrey

AU - Liao, Zhongxing

AU - Court, Laurence E.

PY - 2016/1

Y1 - 2016/1

N2 - Purpose: To determine whether quantitative imaging features from pretreatment positron emission tomography (PET) can enhance patient overall survival risk stratification beyond what can be achieved with conventional prognostic factors in patients with stage III non-small cell lung cancer (NSCLC). Materials and Methods: The institutional review board approved this retrospective chart review study and waived the requirement to obtain informed consent. The authors retrospectively identified 195 patients with stage III NSCLC treated definitively with radiation therapy between January 2008 and January 2013. All patients underwent pretreatment PET/computed tomography before treatment. Conventional PET metrics, along with histogram, shape and volume, and co-occurrence matrix features, were extracted. Linear predictors of overall survival were developed from leaveone-out cross-validation. Predictive Kaplan-Meier curves were used to compare the linear predictors with both quantitative imaging features and conventional prognostic factors to those generated with conventional prognostic factors alone. The Harrell concordance index was used to quantify the discriminatory power of the linear predictors for survival differences of at least 0, 6, 12, 18, and 24 months. Models were generated with features present in more than 50% of the cross-validation folds. Results: Linear predictors of overall survival generated with both quantitative imaging features and conventional prognostic factors demonstrated improved risk stratification compared with those generated with conventional prognostic factors alone in terms of log-rank statistic (P = .18 vs P = .0001, respectively) and concordance index (0.62 vs 0.58, respectively). The use of quantitative imaging features selected during cross-validation improved the model using conventional prognostic factors alone (P = .007). Disease solidity and primary tumor energy from the co-occurrence matrix were found to be selected in all folds of cross-validation. Conclusion: Pretreatment PET features were associated with overall survival when adjusting for conventional prognostic factors in patients with stage III NSCLC.

AB - Purpose: To determine whether quantitative imaging features from pretreatment positron emission tomography (PET) can enhance patient overall survival risk stratification beyond what can be achieved with conventional prognostic factors in patients with stage III non-small cell lung cancer (NSCLC). Materials and Methods: The institutional review board approved this retrospective chart review study and waived the requirement to obtain informed consent. The authors retrospectively identified 195 patients with stage III NSCLC treated definitively with radiation therapy between January 2008 and January 2013. All patients underwent pretreatment PET/computed tomography before treatment. Conventional PET metrics, along with histogram, shape and volume, and co-occurrence matrix features, were extracted. Linear predictors of overall survival were developed from leaveone-out cross-validation. Predictive Kaplan-Meier curves were used to compare the linear predictors with both quantitative imaging features and conventional prognostic factors to those generated with conventional prognostic factors alone. The Harrell concordance index was used to quantify the discriminatory power of the linear predictors for survival differences of at least 0, 6, 12, 18, and 24 months. Models were generated with features present in more than 50% of the cross-validation folds. Results: Linear predictors of overall survival generated with both quantitative imaging features and conventional prognostic factors demonstrated improved risk stratification compared with those generated with conventional prognostic factors alone in terms of log-rank statistic (P = .18 vs P = .0001, respectively) and concordance index (0.62 vs 0.58, respectively). The use of quantitative imaging features selected during cross-validation improved the model using conventional prognostic factors alone (P = .007). Disease solidity and primary tumor energy from the co-occurrence matrix were found to be selected in all folds of cross-validation. Conclusion: Pretreatment PET features were associated with overall survival when adjusting for conventional prognostic factors in patients with stage III NSCLC.

UR - http://www.scopus.com/inward/record.url?scp=84952898501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952898501&partnerID=8YFLogxK

U2 - 10.1148/radiol.2015142920

DO - 10.1148/radiol.2015142920

M3 - Article

C2 - 26176655

AN - SCOPUS:84952898501

VL - 278

SP - 214

EP - 222

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 1

ER -