Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer: Secondary analysis of ACRIN 6668/RTOG 0235

Nitin Ohri, Fenghai Duan, Bradley S. Snyder, Bo Wei, Mitchell Machtay, Abass Alavi, Barry A. Siegel, Douglas W. Johnson, Jeffrey D. Bradley, Albert DeNittis, Maria Werner-Wasik, Issam El Naqa

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on 18F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information. Methods: Patients with locally advanced NSCLC underwent 18F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups. Results: Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm3, and the optimal Sum- Mean cutpoint for tumors above 93.3 cm3 was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P <0.001). Conclusion: We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.

Original languageEnglish (US)
Pages (from-to)843-848
Number of pages6
JournalJournal of Nuclear Medicine
Volume57
Issue number6
DOIs
StatePublished - Jun 1 2016

Fingerprint

Fluorodeoxyglucose F18
Tumor Burden
Radiology
Non-Small Cell Lung Carcinoma
Survival
Neoplasms
Chemoradiotherapy
Validation Studies

Keywords

  • FDG-PET
  • Chemoradiotherapy
  • Non-small cell lung cancer
  • Textural features

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer : Secondary analysis of ACRIN 6668/RTOG 0235. / Ohri, Nitin; Duan, Fenghai; Snyder, Bradley S.; Wei, Bo; Machtay, Mitchell; Alavi, Abass; Siegel, Barry A.; Johnson, Douglas W.; Bradley, Jeffrey D.; DeNittis, Albert; Werner-Wasik, Maria; El Naqa, Issam.

In: Journal of Nuclear Medicine, Vol. 57, No. 6, 01.06.2016, p. 843-848.

Research output: Contribution to journalArticle

Ohri, N, Duan, F, Snyder, BS, Wei, B, Machtay, M, Alavi, A, Siegel, BA, Johnson, DW, Bradley, JD, DeNittis, A, Werner-Wasik, M & El Naqa, I 2016, 'Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer: Secondary analysis of ACRIN 6668/RTOG 0235', Journal of Nuclear Medicine, vol. 57, no. 6, pp. 843-848. https://doi.org/10.2967/jnumed.115.166934
Ohri, Nitin ; Duan, Fenghai ; Snyder, Bradley S. ; Wei, Bo ; Machtay, Mitchell ; Alavi, Abass ; Siegel, Barry A. ; Johnson, Douglas W. ; Bradley, Jeffrey D. ; DeNittis, Albert ; Werner-Wasik, Maria ; El Naqa, Issam. / Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer : Secondary analysis of ACRIN 6668/RTOG 0235. In: Journal of Nuclear Medicine. 2016 ; Vol. 57, No. 6. pp. 843-848.
@article{498ffdd585d94de7a6be5f04483a2e9d,
title = "Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer: Secondary analysis of ACRIN 6668/RTOG 0235",
abstract = "In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on 18F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information. Methods: Patients with locally advanced NSCLC underwent 18F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups. Results: Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm3, and the optimal Sum- Mean cutpoint for tumors above 93.3 cm3 was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P <0.001). Conclusion: We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.",
keywords = "FDG-PET, Chemoradiotherapy, Non-small cell lung cancer, Textural features",
author = "Nitin Ohri and Fenghai Duan and Snyder, {Bradley S.} and Bo Wei and Mitchell Machtay and Abass Alavi and Siegel, {Barry A.} and Johnson, {Douglas W.} and Bradley, {Jeffrey D.} and Albert DeNittis and Maria Werner-Wasik and {El Naqa}, Issam",
year = "2016",
month = "6",
day = "1",
doi = "10.2967/jnumed.115.166934",
language = "English (US)",
volume = "57",
pages = "843--848",
journal = "Journal of Nuclear Medicine",
issn = "0161-5505",
publisher = "Society of Nuclear Medicine Inc.",
number = "6",

}

TY - JOUR

T1 - Pretreatment 18F-FDG PET textural features in locally advanced non-small cell lung cancer

T2 - Secondary analysis of ACRIN 6668/RTOG 0235

AU - Ohri, Nitin

AU - Duan, Fenghai

AU - Snyder, Bradley S.

AU - Wei, Bo

AU - Machtay, Mitchell

AU - Alavi, Abass

AU - Siegel, Barry A.

AU - Johnson, Douglas W.

AU - Bradley, Jeffrey D.

AU - DeNittis, Albert

AU - Werner-Wasik, Maria

AU - El Naqa, Issam

PY - 2016/6/1

Y1 - 2016/6/1

N2 - In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on 18F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information. Methods: Patients with locally advanced NSCLC underwent 18F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups. Results: Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm3, and the optimal Sum- Mean cutpoint for tumors above 93.3 cm3 was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P <0.001). Conclusion: We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.

AB - In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on 18F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information. Methods: Patients with locally advanced NSCLC underwent 18F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups. Results: Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm3, and the optimal Sum- Mean cutpoint for tumors above 93.3 cm3 was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P <0.001). Conclusion: We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.

KW - FDG-PET

KW - Chemoradiotherapy

KW - Non-small cell lung cancer

KW - Textural features

UR - http://www.scopus.com/inward/record.url?scp=84973667683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973667683&partnerID=8YFLogxK

U2 - 10.2967/jnumed.115.166934

DO - 10.2967/jnumed.115.166934

M3 - Article

C2 - 26912429

AN - SCOPUS:84973667683

VL - 57

SP - 843

EP - 848

JO - Journal of Nuclear Medicine

JF - Journal of Nuclear Medicine

SN - 0161-5505

IS - 6

ER -