Exploratory radiomic features from integrated 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer

Serena Baiocco; Bert-Ram Sah; Andrew Mallia; Christian Kelly-Morland; Radhouene Neji; Alessandro Bevilacqua; Gary J. R. Cook; Vicky Goh

doi:10.1007/s00259-019-04306-7

Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer

Serena Baiocco, Bert-Ram Sah, Andrew Mallia, Christian Kelly-Morland, Radhouene Neji, Alessandro Bevilacqua, Gary J. R. Cook, Vicky Goh

Research output: Contribution to journal › Article › peer-review

15 Citations (Scopus)

163 Downloads (Pure)

Abstract

Purpose: To determine if 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18F-FDG PET/MRI) features are associated with contemporaneous metastases in patients with oesophageal/gastroesophageal cancer. Methods: Following IRB approval and informed consent, patients underwent a staging PET/MRI following 18F-FDG injection (326±28 MBq) and 156 ± 23 minutes uptake time. First- order histogram and second-order grey level co-occurrence matrix features were computed for PET standardized uptake value (SUV) and MRI T1-W, T2-W, diffusion weighted (DWI) and apparent diffusion coefficient (ADC) images for the whole tumour volume. K-means clustering assessed the correlation of feature-pairs with metastases. Multivariate analysis of variance (MANOVA) was performed to assess the statistical separability of the groups identified by feature-pairs. Sensitivity (SN), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) were calculated for these features and compared with SUVmax, ADCmean and maximum diameter alone for predicting contemporaneous metastases. Results: 20 patients (18 males, 2 female; median 67 years, range: 52-86) comprised the final study cohort; 10 patients had metastases. Lower second-order SUV entropy combined with higher second-order ADC entropy were the best feature-pair for discriminating metastatic patients, MANOVA p-value <0.001 (SN=80%, SP=80%, PPV=80%, NPV=80%, ACC=80%). SUVmax (SN=30%, SP=80%, PPV=60%, NPV=53%, ACC=55%), ADCmean (SN = 20%, SP = 70%, PPV = 40%, NPV = 47%, ACC = 45%) and tumour maximum diameter (SN=10%, SP=90%, PPV=50%, NPV=50%, ACC=50%) had poorer sensitivity and accuracy. Conclusion: High ADC entropy combined with low SUV entropy is associated with a higher prevalence of metastases and a promising initial signature for future study.

Original language	English
Pages (from-to)	1478–1484
Journal	European journal of nuclear medicine and molecular imaging
Early online date	27 Mar 2019
DOIs	https://doi.org/10.1007/s00259-019-04306-7
Publication status	E-pub ahead of print - 27 Mar 2019

Keywords

F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging
Oesophageal cancer
Radiomic analysis

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s00259-019-04306-7Licence: CC BY

Exploratory radiomic features from_BAIOCCO_Accepted1March2019_GOLD VoRFinal published version, 1.46 MBLicence: CC BY

Fingerprint

Dive into the research topics of 'Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer'. Together they form a unique fingerprint.

Cite this

Baiocco, S., Sah, B.-R., Mallia, A., Kelly-Morland, C., Neji, R., Bevilacqua, A., Cook, G. J. R., & Goh, V. (2019). Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer. European journal of nuclear medicine and molecular imaging, 1478–1484. Advance online publication. https://doi.org/10.1007/s00259-019-04306-7

@article{25ffb85e0097459ab8e8535e0938ca2d,

title = "Exploratory radiomic features from integrated 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer",

abstract = "Purpose: To determine if 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18F-FDG PET/MRI) features are associated with contemporaneous metastases in patients with oesophageal/gastroesophageal cancer. Methods: Following IRB approval and informed consent, patients underwent a staging PET/MRI following 18F-FDG injection (326±28 MBq) and 156 ± 23 minutes uptake time. First- order histogram and second-order grey level co-occurrence matrix features were computed for PET standardized uptake value (SUV) and MRI T1-W, T2-W, diffusion weighted (DWI) and apparent diffusion coefficient (ADC) images for the whole tumour volume. K-means clustering assessed the correlation of feature-pairs with metastases. Multivariate analysis of variance (MANOVA) was performed to assess the statistical separability of the groups identified by feature-pairs. Sensitivity (SN), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) were calculated for these features and compared with SUVmax, ADCmean and maximum diameter alone for predicting contemporaneous metastases. Results: 20 patients (18 males, 2 female; median 67 years, range: 52-86) comprised the final study cohort; 10 patients had metastases. Lower second-order SUV entropy combined with higher second-order ADC entropy were the best feature-pair for discriminating metastatic patients, MANOVA p-value <0.001 (SN=80%, SP=80%, PPV=80%, NPV=80%, ACC=80%). SUVmax (SN=30%, SP=80%, PPV=60%, NPV=53%, ACC=55%), ADCmean (SN = 20%, SP = 70%, PPV = 40%, NPV = 47%, ACC = 45%) and tumour maximum diameter (SN=10%, SP=90%, PPV=50%, NPV=50%, ACC=50%) had poorer sensitivity and accuracy. Conclusion: High ADC entropy combined with low SUV entropy is associated with a higher prevalence of metastases and a promising initial signature for future study. ",

keywords = "F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging, Oesophageal cancer, Radiomic analysis",

author = "Serena Baiocco and Bert-Ram Sah and Andrew Mallia and Christian Kelly-Morland and Radhouene Neji and Alessandro Bevilacqua and Cook, {Gary J. R.} and Vicky Goh",

year = "2019",

month = mar,

day = "27",

doi = "10.1007/s00259-019-04306-7",

language = "English",

pages = "1478–1484",

journal = "European journal of nuclear medicine and molecular imaging",

issn = "1619-7089",

publisher = "Springer",

}

Baiocco, S, Sah, B-R, Mallia, A, Kelly-Morland, C, Neji, R, Bevilacqua, A, Cook, GJR & Goh, V 2019, 'Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer', European journal of nuclear medicine and molecular imaging, pp. 1478–1484. https://doi.org/10.1007/s00259-019-04306-7

Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer. / Baiocco, Serena; Sah, Bert-Ram; Mallia, Andrew et al.
In: European journal of nuclear medicine and molecular imaging, 27.03.2019, p. 1478–1484.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Exploratory radiomic features from integrated 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer

AU - Baiocco, Serena

AU - Sah, Bert-Ram

AU - Mallia, Andrew

AU - Kelly-Morland, Christian

AU - Neji, Radhouene

AU - Bevilacqua, Alessandro

AU - Cook, Gary J. R.

AU - Goh, Vicky

PY - 2019/3/27

Y1 - 2019/3/27

N2 - Purpose: To determine if 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18F-FDG PET/MRI) features are associated with contemporaneous metastases in patients with oesophageal/gastroesophageal cancer. Methods: Following IRB approval and informed consent, patients underwent a staging PET/MRI following 18F-FDG injection (326±28 MBq) and 156 ± 23 minutes uptake time. First- order histogram and second-order grey level co-occurrence matrix features were computed for PET standardized uptake value (SUV) and MRI T1-W, T2-W, diffusion weighted (DWI) and apparent diffusion coefficient (ADC) images for the whole tumour volume. K-means clustering assessed the correlation of feature-pairs with metastases. Multivariate analysis of variance (MANOVA) was performed to assess the statistical separability of the groups identified by feature-pairs. Sensitivity (SN), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) were calculated for these features and compared with SUVmax, ADCmean and maximum diameter alone for predicting contemporaneous metastases. Results: 20 patients (18 males, 2 female; median 67 years, range: 52-86) comprised the final study cohort; 10 patients had metastases. Lower second-order SUV entropy combined with higher second-order ADC entropy were the best feature-pair for discriminating metastatic patients, MANOVA p-value <0.001 (SN=80%, SP=80%, PPV=80%, NPV=80%, ACC=80%). SUVmax (SN=30%, SP=80%, PPV=60%, NPV=53%, ACC=55%), ADCmean (SN = 20%, SP = 70%, PPV = 40%, NPV = 47%, ACC = 45%) and tumour maximum diameter (SN=10%, SP=90%, PPV=50%, NPV=50%, ACC=50%) had poorer sensitivity and accuracy. Conclusion: High ADC entropy combined with low SUV entropy is associated with a higher prevalence of metastases and a promising initial signature for future study.

AB - Purpose: To determine if 18F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18F-FDG PET/MRI) features are associated with contemporaneous metastases in patients with oesophageal/gastroesophageal cancer. Methods: Following IRB approval and informed consent, patients underwent a staging PET/MRI following 18F-FDG injection (326±28 MBq) and 156 ± 23 minutes uptake time. First- order histogram and second-order grey level co-occurrence matrix features were computed for PET standardized uptake value (SUV) and MRI T1-W, T2-W, diffusion weighted (DWI) and apparent diffusion coefficient (ADC) images for the whole tumour volume. K-means clustering assessed the correlation of feature-pairs with metastases. Multivariate analysis of variance (MANOVA) was performed to assess the statistical separability of the groups identified by feature-pairs. Sensitivity (SN), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) were calculated for these features and compared with SUVmax, ADCmean and maximum diameter alone for predicting contemporaneous metastases. Results: 20 patients (18 males, 2 female; median 67 years, range: 52-86) comprised the final study cohort; 10 patients had metastases. Lower second-order SUV entropy combined with higher second-order ADC entropy were the best feature-pair for discriminating metastatic patients, MANOVA p-value <0.001 (SN=80%, SP=80%, PPV=80%, NPV=80%, ACC=80%). SUVmax (SN=30%, SP=80%, PPV=60%, NPV=53%, ACC=55%), ADCmean (SN = 20%, SP = 70%, PPV = 40%, NPV = 47%, ACC = 45%) and tumour maximum diameter (SN=10%, SP=90%, PPV=50%, NPV=50%, ACC=50%) had poorer sensitivity and accuracy. Conclusion: High ADC entropy combined with low SUV entropy is associated with a higher prevalence of metastases and a promising initial signature for future study.

KW - F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging

KW - Oesophageal cancer

KW - Radiomic analysis

UR - http://www.scopus.com/inward/record.url?scp=85064073895&partnerID=8YFLogxK

U2 - 10.1007/s00259-019-04306-7

DO - 10.1007/s00259-019-04306-7

M3 - Article

SN - 1619-7089

SP - 1478

EP - 1484

JO - European journal of nuclear medicine and molecular imaging

JF - European journal of nuclear medicine and molecular imaging

ER -

Baiocco S, Sah BR, Mallia A, Kelly-Morland C, Neji R, Bevilacqua A et al. Exploratory radiomic features from integrated ¹⁸F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging are associated with contemporaneous metastases in oesophageal/gastroesophageal cancer. European journal of nuclear medicine and molecular imaging. 2019 Mar 27;1478–1484. Epub 2019 Mar 27. doi: 10.1007/s00259-019-04306-7