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 language | English |
|---|---|
| Pages (from-to) | 199-206 |
| Number of pages | 8 |
| Journal | Journal of nuclear medicine |
| Volume | 60 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 1 Feb 2019 |
Fingerprint
Keywords
- 18F-FDG PET/CT
- Principal component analysis
- Radiomics
- Vulvar cancer
Cite this
}
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 journal › Article › Academic › peer-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
AN - SCOPUS:85060946645
VL - 60
SP - 199
EP - 206
JO - Journal of nuclear medicine
JF - Journal of nuclear medicine
SN - 0161-5505
IS - 2
ER -