External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients

Ralph T. H. Leijenaar; Sean Walsh; Akshayaa Vaidyanathan; Lorenzo Aliboni; Victoria Lopez Sanchez; Michelle Leech; Ronan Joyce; Charles Gillham; Frederic Kridelka; Roland Hustinx; Denis Danthine; Mariaelena Occhipinti; Wim Vos; Julien Guiot; Philippe Lambin; Pierre Lovinfosse

doi:10.1038/s41598-023-34162-3

External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients

Ralph T. H. Leijenaar, Sean Walsh, Akshayaa Vaidyanathan, Lorenzo Aliboni, Victoria Lopez Sanchez, Michelle Leech, Ronan Joyce, Charles Gillham, Frederic Kridelka, Roland Hustinx, Denis Danthine, Mariaelena Occhipinti, Wim Vos, Julien Guiot, Philippe Lambin, Pierre Lovinfosse^*

^*Corresponding author for this work

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

Abstract

The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

Original language	English
Article number	7198
Number of pages	7
Journal	Scientific Reports
Volume	13
Issue number	1
DOIs	https://doi.org/10.1038/s41598-023-34162-3
Publication status	Published - 3 May 2023

Keywords

HUMAN PAPILLOMA-VIRUS
FEATURES

Access to Document

10.1038/s41598-023-34162-3Licence: CC BY

Cite this

Leijenaar, R. T. H., Walsh, S., Vaidyanathan, A., Aliboni, L., Sanchez, V. L., Leech, M., Joyce, R., Gillham, C., Kridelka, F., Hustinx, R., Danthine, D., Occhipinti, M., Vos, W., Guiot, J., Lambin, P., & Lovinfosse, P. (2023). External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients. Scientific Reports, 13(1), Article 7198. https://doi.org/10.1038/s41598-023-34162-3

@article{9bd610c51fef474492e518c9d7a29efc,

title = "External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients",

abstract = "The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.",

keywords = "HUMAN PAPILLOMA-VIRUS, FEATURES",

author = "Leijenaar, {Ralph T. H.} and Sean Walsh and Akshayaa Vaidyanathan and Lorenzo Aliboni and Sanchez, {Victoria Lopez} and Michelle Leech and Ronan Joyce and Charles Gillham and Frederic Kridelka and Roland Hustinx and Denis Danthine and Mariaelena Occhipinti and Wim Vos and Julien Guiot and Philippe Lambin and Pierre Lovinfosse",

year = "2023",

month = may,

day = "3",

doi = "10.1038/s41598-023-34162-3",

language = "English",

volume = "13",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

Leijenaar, RTH, Walsh, S, Vaidyanathan, A, Aliboni, L, Sanchez, VL, Leech, M, Joyce, R, Gillham, C, Kridelka, F, Hustinx, R, Danthine, D, Occhipinti, M, Vos, W, Guiot, J, Lambin, P & Lovinfosse, P 2023, 'External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients', Scientific Reports, vol. 13, no. 1, 7198. https://doi.org/10.1038/s41598-023-34162-3

TY - JOUR

T1 - External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients

AU - Leijenaar, Ralph T. H.

AU - Walsh, Sean

AU - Vaidyanathan, Akshayaa

AU - Aliboni, Lorenzo

AU - Sanchez, Victoria Lopez

AU - Leech, Michelle

AU - Joyce, Ronan

AU - Gillham, Charles

AU - Kridelka, Frederic

AU - Hustinx, Roland

AU - Danthine, Denis

AU - Occhipinti, Mariaelena

AU - Vos, Wim

AU - Guiot, Julien

AU - Lambin, Philippe

AU - Lovinfosse, Pierre

PY - 2023/5/3

Y1 - 2023/5/3

N2 - The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

AB - The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

KW - HUMAN PAPILLOMA-VIRUS

KW - FEATURES

U2 - 10.1038/s41598-023-34162-3

DO - 10.1038/s41598-023-34162-3

M3 - Article

C2 - 37137947

SN - 2045-2322

VL - 13

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 7198

ER -