Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features

Arman Rahmim, Kirstine P. Bak-Fredslund, Saeed Ashrafinia, Lijun Lu, C. Ross Schmidtlein, Rathan Subramaniam, Anni Morsing, Susanne Keiding, Jacob Horsager, Ole L. Munk

Research output: Contribution to journalArticle

Abstract

Objective: We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures. Patients and methods: A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32–82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression. Results: Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively. Conclusions: PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.

Original languageEnglish (US)
Pages (from-to)101-109
Number of pages9
JournalEuropean Journal of Radiology
Volume113
DOIs
StatePublished - Apr 1 2019

Fingerprint

Disease-Free Survival
Neoplasm Metastasis
Liver
Survival
Tumor Burden
Kaplan-Meier Estimate
Glycolysis
Survival Analysis
Neoplasms

Keywords

  • Colorectal liver metastasis
  • Intra-tumoral heterogeneity
  • PET/CT
  • Prognosis
  • Radiomics
  • Volumetric features

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features. / Rahmim, Arman; Bak-Fredslund, Kirstine P.; Ashrafinia, Saeed; Lu, Lijun; Schmidtlein, C. Ross; Subramaniam, Rathan; Morsing, Anni; Keiding, Susanne; Horsager, Jacob; Munk, Ole L.

In: European Journal of Radiology, Vol. 113, 01.04.2019, p. 101-109.

Research output: Contribution to journalArticle

Rahmim, A, Bak-Fredslund, KP, Ashrafinia, S, Lu, L, Schmidtlein, CR, Subramaniam, R, Morsing, A, Keiding, S, Horsager, J & Munk, OL 2019, 'Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features', European Journal of Radiology, vol. 113, pp. 101-109. https://doi.org/10.1016/j.ejrad.2019.02.006
Rahmim, Arman ; Bak-Fredslund, Kirstine P. ; Ashrafinia, Saeed ; Lu, Lijun ; Schmidtlein, C. Ross ; Subramaniam, Rathan ; Morsing, Anni ; Keiding, Susanne ; Horsager, Jacob ; Munk, Ole L. / Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features. In: European Journal of Radiology. 2019 ; Vol. 113. pp. 101-109.
@article{6b734eef26a048ccb1e07cb792184bcc,
title = "Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features",
abstract = "Objective: We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures. Patients and methods: A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32–82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression. Results: Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively. Conclusions: PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.",
keywords = "Colorectal liver metastasis, Intra-tumoral heterogeneity, PET/CT, Prognosis, Radiomics, Volumetric features",
author = "Arman Rahmim and Bak-Fredslund, {Kirstine P.} and Saeed Ashrafinia and Lijun Lu and Schmidtlein, {C. Ross} and Rathan Subramaniam and Anni Morsing and Susanne Keiding and Jacob Horsager and Munk, {Ole L.}",
year = "2019",
month = "4",
day = "1",
doi = "10.1016/j.ejrad.2019.02.006",
language = "English (US)",
volume = "113",
pages = "101--109",
journal = "European Journal of Radiology",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features

AU - Rahmim, Arman

AU - Bak-Fredslund, Kirstine P.

AU - Ashrafinia, Saeed

AU - Lu, Lijun

AU - Schmidtlein, C. Ross

AU - Subramaniam, Rathan

AU - Morsing, Anni

AU - Keiding, Susanne

AU - Horsager, Jacob

AU - Munk, Ole L.

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Objective: We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures. Patients and methods: A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32–82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression. Results: Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively. Conclusions: PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.

AB - Objective: We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures. Patients and methods: A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32–82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression. Results: Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively. Conclusions: PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.

KW - Colorectal liver metastasis

KW - Intra-tumoral heterogeneity

KW - PET/CT

KW - Prognosis

KW - Radiomics

KW - Volumetric features

UR - http://www.scopus.com/inward/record.url?scp=85061554275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061554275&partnerID=8YFLogxK

U2 - 10.1016/j.ejrad.2019.02.006

DO - 10.1016/j.ejrad.2019.02.006

M3 - Article

C2 - 30927933

AN - SCOPUS:85061554275

VL - 113

SP - 101

EP - 109

JO - European Journal of Radiology

JF - European Journal of Radiology

SN - 0720-048X

ER -