Radiomics in vulvar cancer: First clinical experience using18F-FDG PET/CT images

Angela Collarino (Corresponding Author), Giorgia Garganese, Simona M. Fragomeni, Lenka M. Pereira Arias-Bouda, Francesco P. Ieria, Ronald Boellaard, Vittoria Rufini, Lioe Fee De Geus-Oei, Giovanni Scambia, Renato A. Valdés Olmos, Alessandro Giordano, Willem Grootjans, Floris H.P. Van Velden

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

This study investigated whether radiomic features derived from preoperative PET images could predict both tumor biology and prognosis in women with invasive squamous cell carcinoma of the vulva. Methods: Patients were retrospectively included if they had a unifocal primary cancer at least 2.6 cm in diameter, received a preoperative18F-FDG PET/CT scan followed by surgery, and had at least 6 mo of follow-up data.18F-FDG PET images were analyzed by semiautomatically drawing a volume of interest on the primary tumor in each PET image, followed by extraction of 83 radiomic features. Unique radiomic features were identified by principal-component analysis (PCA), after which they were compared with histopathology using nonpairwise group comparison and linear regression. Univariate and multivariate Cox regression analyses were used to correlate the identified features with progression-free survival (PFS) and overall survival (OS). Survival curves were estimated using the Kaplan–Meier method. Results: Forty women were included. PCA revealed 4 unique radiomic features, which were not associated with histopathologic characteristics such as grade, depth of invasion, lymph-vascular space invasion, and metastatic lymph nodes. No statistically significant correlation was found between the identified features and PFS. However, Moran’s I, a feature that identifies global spatial autocorrelation, correlated with OS (P 5 0.03). Multivariate Cox regression analysis showed that extracapsular invasion of the metastatic lymph nodes and Moran’s I were independent prognostic factors for PFS and OS. Conclusion: Our data show that PCA is usable to identify specific radiomic features. Although the identified features did not correlate strongly with tumor biology, Moran’s I was found to predict patient prognosis. Larger studies are required to establish the clinical relevance of the observed findings.

Original languageEnglish
Pages (from-to)199-206
Number of pages8
JournalJournal of nuclear medicine
Volume60
Issue number2
DOIs
Publication statusPublished - 1 Feb 2019

Fingerprint

Vulvar Neoplasms
Principal Component Analysis
Disease-Free Survival
Survival
Neoplasms
Lymph Nodes
Regression Analysis
Spatial Analysis
Vulva
Lymph
Blood Vessels
Squamous Cell Carcinoma
Linear Models

Keywords

  • 18F-FDG PET/CT
  • Principal component analysis
  • Radiomics
  • Vulvar cancer

Cite this

Collarino, A., Garganese, G., Fragomeni, S. M., Pereira Arias-Bouda, L. M., Ieria, F. P., Boellaard, R., ... Van Velden, F. H. P. (2019). Radiomics in vulvar cancer: First clinical experience using18F-FDG PET/CT images. Journal of nuclear medicine, 60(2), 199-206. https://doi.org/10.2967/jnumed.118.215889
Collarino, Angela ; Garganese, Giorgia ; Fragomeni, Simona M. ; Pereira Arias-Bouda, Lenka M. ; Ieria, Francesco P. ; Boellaard, Ronald ; Rufini, Vittoria ; De Geus-Oei, Lioe Fee ; Scambia, Giovanni ; Valdés Olmos, Renato A. ; Giordano, Alessandro ; Grootjans, Willem ; Van Velden, Floris H.P. / Radiomics in vulvar cancer : First clinical experience using18F-FDG PET/CT images. In: Journal of nuclear medicine. 2019 ; Vol. 60, No. 2. pp. 199-206.
@article{3d9c151d8330416098639516fab5d363,
title = "Radiomics in vulvar cancer: First clinical experience using18F-FDG PET/CT images",
abstract = "This study investigated whether radiomic features derived from preoperative PET images could predict both tumor biology and prognosis in women with invasive squamous cell carcinoma of the vulva. Methods: Patients were retrospectively included if they had a unifocal primary cancer at least 2.6 cm in diameter, received a preoperative18F-FDG PET/CT scan followed by surgery, and had at least 6 mo of follow-up data.18F-FDG PET images were analyzed by semiautomatically drawing a volume of interest on the primary tumor in each PET image, followed by extraction of 83 radiomic features. Unique radiomic features were identified by principal-component analysis (PCA), after which they were compared with histopathology using nonpairwise group comparison and linear regression. Univariate and multivariate Cox regression analyses were used to correlate the identified features with progression-free survival (PFS) and overall survival (OS). Survival curves were estimated using the Kaplan–Meier method. Results: Forty women were included. PCA revealed 4 unique radiomic features, which were not associated with histopathologic characteristics such as grade, depth of invasion, lymph-vascular space invasion, and metastatic lymph nodes. No statistically significant correlation was found between the identified features and PFS. However, Moran’s I, a feature that identifies global spatial autocorrelation, correlated with OS (P 5 0.03). Multivariate Cox regression analysis showed that extracapsular invasion of the metastatic lymph nodes and Moran’s I were independent prognostic factors for PFS and OS. Conclusion: Our data show that PCA is usable to identify specific radiomic features. Although the identified features did not correlate strongly with tumor biology, Moran’s I was found to predict patient prognosis. Larger studies are required to establish the clinical relevance of the observed findings.",
keywords = "18F-FDG PET/CT, Principal component analysis, Radiomics, Vulvar cancer",
author = "Angela Collarino and Giorgia Garganese and Fragomeni, {Simona M.} and {Pereira Arias-Bouda}, {Lenka M.} and Ieria, {Francesco P.} and Ronald Boellaard and Vittoria Rufini and {De Geus-Oei}, {Lioe Fee} and Giovanni Scambia and {Vald{\'e}s Olmos}, {Renato A.} and Alessandro Giordano and Willem Grootjans and {Van Velden}, {Floris H.P.}",
year = "2019",
month = "2",
day = "1",
doi = "10.2967/jnumed.118.215889",
language = "English",
volume = "60",
pages = "199--206",
journal = "Journal of nuclear medicine",
issn = "0161-5505",
publisher = "Society of Nuclear Medicine Inc.",
number = "2",

}

Collarino, A, Garganese, G, Fragomeni, SM, Pereira Arias-Bouda, LM, Ieria, FP, Boellaard, R, Rufini, V, De Geus-Oei, LF, Scambia, G, Valdés Olmos, RA, Giordano, A, Grootjans, W & Van Velden, FHP 2019, 'Radiomics in vulvar cancer: First clinical experience using18F-FDG PET/CT images' Journal of nuclear medicine, vol. 60, no. 2, pp. 199-206. https://doi.org/10.2967/jnumed.118.215889

Radiomics in vulvar cancer : First clinical experience using18F-FDG PET/CT images. / Collarino, Angela (Corresponding Author); Garganese, Giorgia; Fragomeni, Simona M.; Pereira Arias-Bouda, Lenka M.; Ieria, Francesco P.; Boellaard, Ronald; Rufini, Vittoria; De Geus-Oei, Lioe Fee; Scambia, Giovanni; Valdés Olmos, Renato A.; Giordano, Alessandro; Grootjans, Willem; Van Velden, Floris H.P.

In: Journal of nuclear medicine, Vol. 60, No. 2, 01.02.2019, p. 199-206.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Radiomics in vulvar cancer

T2 - First clinical experience using18F-FDG PET/CT images

AU - Collarino, Angela

AU - Garganese, Giorgia

AU - Fragomeni, Simona M.

AU - Pereira Arias-Bouda, Lenka M.

AU - Ieria, Francesco P.

AU - Boellaard, Ronald

AU - Rufini, Vittoria

AU - De Geus-Oei, Lioe Fee

AU - Scambia, Giovanni

AU - Valdés Olmos, Renato A.

AU - Giordano, Alessandro

AU - Grootjans, Willem

AU - Van Velden, Floris H.P.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - This study investigated whether radiomic features derived from preoperative PET images could predict both tumor biology and prognosis in women with invasive squamous cell carcinoma of the vulva. Methods: Patients were retrospectively included if they had a unifocal primary cancer at least 2.6 cm in diameter, received a preoperative18F-FDG PET/CT scan followed by surgery, and had at least 6 mo of follow-up data.18F-FDG PET images were analyzed by semiautomatically drawing a volume of interest on the primary tumor in each PET image, followed by extraction of 83 radiomic features. Unique radiomic features were identified by principal-component analysis (PCA), after which they were compared with histopathology using nonpairwise group comparison and linear regression. Univariate and multivariate Cox regression analyses were used to correlate the identified features with progression-free survival (PFS) and overall survival (OS). Survival curves were estimated using the Kaplan–Meier method. Results: Forty women were included. PCA revealed 4 unique radiomic features, which were not associated with histopathologic characteristics such as grade, depth of invasion, lymph-vascular space invasion, and metastatic lymph nodes. No statistically significant correlation was found between the identified features and PFS. However, Moran’s I, a feature that identifies global spatial autocorrelation, correlated with OS (P 5 0.03). Multivariate Cox regression analysis showed that extracapsular invasion of the metastatic lymph nodes and Moran’s I were independent prognostic factors for PFS and OS. Conclusion: Our data show that PCA is usable to identify specific radiomic features. Although the identified features did not correlate strongly with tumor biology, Moran’s I was found to predict patient prognosis. Larger studies are required to establish the clinical relevance of the observed findings.

AB - This study investigated whether radiomic features derived from preoperative PET images could predict both tumor biology and prognosis in women with invasive squamous cell carcinoma of the vulva. Methods: Patients were retrospectively included if they had a unifocal primary cancer at least 2.6 cm in diameter, received a preoperative18F-FDG PET/CT scan followed by surgery, and had at least 6 mo of follow-up data.18F-FDG PET images were analyzed by semiautomatically drawing a volume of interest on the primary tumor in each PET image, followed by extraction of 83 radiomic features. Unique radiomic features were identified by principal-component analysis (PCA), after which they were compared with histopathology using nonpairwise group comparison and linear regression. Univariate and multivariate Cox regression analyses were used to correlate the identified features with progression-free survival (PFS) and overall survival (OS). Survival curves were estimated using the Kaplan–Meier method. Results: Forty women were included. PCA revealed 4 unique radiomic features, which were not associated with histopathologic characteristics such as grade, depth of invasion, lymph-vascular space invasion, and metastatic lymph nodes. No statistically significant correlation was found between the identified features and PFS. However, Moran’s I, a feature that identifies global spatial autocorrelation, correlated with OS (P 5 0.03). Multivariate Cox regression analysis showed that extracapsular invasion of the metastatic lymph nodes and Moran’s I were independent prognostic factors for PFS and OS. Conclusion: Our data show that PCA is usable to identify specific radiomic features. Although the identified features did not correlate strongly with tumor biology, Moran’s I was found to predict patient prognosis. Larger studies are required to establish the clinical relevance of the observed findings.

KW - 18F-FDG PET/CT

KW - Principal component analysis

KW - Radiomics

KW - Vulvar cancer

UR - http://www.scopus.com/inward/record.url?scp=85060946645&partnerID=8YFLogxK

U2 - 10.2967/jnumed.118.215889

DO - 10.2967/jnumed.118.215889

M3 - Article

VL - 60

SP - 199

EP - 206

JO - Journal of nuclear medicine

JF - Journal of nuclear medicine

SN - 0161-5505

IS - 2

ER -

Collarino A, Garganese G, Fragomeni SM, Pereira Arias-Bouda LM, Ieria FP, Boellaard R et al. Radiomics in vulvar cancer: First clinical experience using18F-FDG PET/CT images. Journal of nuclear medicine. 2019 Feb 1;60(2):199-206. https://doi.org/10.2967/jnumed.118.215889