Prognostic value of pre-treatment CT texture analysis in combination with change in size of the primary tumor in response to induction chemotherapy for HPV-positive oropharyngeal squamous cell carcinoma

Tamari A. Miller, Kayla R. Robinson, Hui Li, Tanguy Lim Seiwert, Daniel J. Haraf, Li Lan, Maryellen L. Giger, Daniel T. Ginat

Research output: Contribution to journalArticle

Abstract

Background: To determine the additive value of quantitative radiomic texture features in predicting progression in human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) based on pre-treatment CT. Methods: Retrospective analysis of a single-center cohort of adult patients enrolled in a response-adapted radiation volume de-escalation trial treated with induction chemotherapy. Texture analysis of HPV-positive OPSCC was performed via primary tumor site contouring on pre-treatment contrast-enhanced CT scans. Percent change in size of the tumor in response to induction chemotherapy based on RECIST 1.1 criteria and progression free survival were clinically determined for this cohort. Receiver operating characteristic (ROC) analysis was performed to compare the accuracy of percent change in tumor size after induction chemotherapy with a combination of change in tumor size and radiomic texture features for predicting tumor progression. Results: Radiomic texture analysis of the primary tumors in 38 patients with OPSCC depicted on pretreatment neck CT scans using skewness and entropy in combination with percent change in tumor size after induction chemotherapy yielded a statistically significant increase in accuracy for predicting tumor progression over change in tumor size alone, with an area under the curve of 0.80 versus 0.56 (one-tailed P=0.0087). Conclusions: This pilot study suggests that disease progression in patients with HPV-positive OPSCC is more accurately predicted using a combination of texture features on pre-treatment CT scans, along with change in tumor size compared to change in tumor size alone and could therefore serve as a radiomic texture signature.

Original languageEnglish (US)
Pages (from-to)399-408
Number of pages10
JournalQuantitative Imaging in Medicine and Surgery
Volume9
Issue number3
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Induction Chemotherapy
Squamous Cell Carcinoma
Neoplasms
Therapeutics
Entropy
ROC Curve
Disease-Free Survival
Area Under Curve
Disease Progression
Neck
Radiation

Keywords

  • Cancer
  • Computerized tomography (CT)
  • Oropharyngeal
  • Size
  • Texture analysis

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Prognostic value of pre-treatment CT texture analysis in combination with change in size of the primary tumor in response to induction chemotherapy for HPV-positive oropharyngeal squamous cell carcinoma. / Miller, Tamari A.; Robinson, Kayla R.; Li, Hui; Lim Seiwert, Tanguy; Haraf, Daniel J.; Lan, Li; Giger, Maryellen L.; Ginat, Daniel T.

In: Quantitative Imaging in Medicine and Surgery, Vol. 9, No. 3, 01.01.2019, p. 399-408.

Research output: Contribution to journalArticle

@article{4151c86fba5140c3bfe0240d74e6da57,
title = "Prognostic value of pre-treatment CT texture analysis in combination with change in size of the primary tumor in response to induction chemotherapy for HPV-positive oropharyngeal squamous cell carcinoma",
abstract = "Background: To determine the additive value of quantitative radiomic texture features in predicting progression in human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) based on pre-treatment CT. Methods: Retrospective analysis of a single-center cohort of adult patients enrolled in a response-adapted radiation volume de-escalation trial treated with induction chemotherapy. Texture analysis of HPV-positive OPSCC was performed via primary tumor site contouring on pre-treatment contrast-enhanced CT scans. Percent change in size of the tumor in response to induction chemotherapy based on RECIST 1.1 criteria and progression free survival were clinically determined for this cohort. Receiver operating characteristic (ROC) analysis was performed to compare the accuracy of percent change in tumor size after induction chemotherapy with a combination of change in tumor size and radiomic texture features for predicting tumor progression. Results: Radiomic texture analysis of the primary tumors in 38 patients with OPSCC depicted on pretreatment neck CT scans using skewness and entropy in combination with percent change in tumor size after induction chemotherapy yielded a statistically significant increase in accuracy for predicting tumor progression over change in tumor size alone, with an area under the curve of 0.80 versus 0.56 (one-tailed P=0.0087). Conclusions: This pilot study suggests that disease progression in patients with HPV-positive OPSCC is more accurately predicted using a combination of texture features on pre-treatment CT scans, along with change in tumor size compared to change in tumor size alone and could therefore serve as a radiomic texture signature.",
keywords = "Cancer, Computerized tomography (CT), Oropharyngeal, Size, Texture analysis",
author = "Miller, {Tamari A.} and Robinson, {Kayla R.} and Hui Li and {Lim Seiwert}, Tanguy and Haraf, {Daniel J.} and Li Lan and Giger, {Maryellen L.} and Ginat, {Daniel T.}",
year = "2019",
month = "1",
day = "1",
doi = "10.21037/qims.2019.03.08",
language = "English (US)",
volume = "9",
pages = "399--408",
journal = "Quantitative Imaging in Medicine and Surgery",
issn = "2223-4292",
publisher = "AME Publishing Company",
number = "3",

}

TY - JOUR

T1 - Prognostic value of pre-treatment CT texture analysis in combination with change in size of the primary tumor in response to induction chemotherapy for HPV-positive oropharyngeal squamous cell carcinoma

AU - Miller, Tamari A.

AU - Robinson, Kayla R.

AU - Li, Hui

AU - Lim Seiwert, Tanguy

AU - Haraf, Daniel J.

AU - Lan, Li

AU - Giger, Maryellen L.

AU - Ginat, Daniel T.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: To determine the additive value of quantitative radiomic texture features in predicting progression in human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) based on pre-treatment CT. Methods: Retrospective analysis of a single-center cohort of adult patients enrolled in a response-adapted radiation volume de-escalation trial treated with induction chemotherapy. Texture analysis of HPV-positive OPSCC was performed via primary tumor site contouring on pre-treatment contrast-enhanced CT scans. Percent change in size of the tumor in response to induction chemotherapy based on RECIST 1.1 criteria and progression free survival were clinically determined for this cohort. Receiver operating characteristic (ROC) analysis was performed to compare the accuracy of percent change in tumor size after induction chemotherapy with a combination of change in tumor size and radiomic texture features for predicting tumor progression. Results: Radiomic texture analysis of the primary tumors in 38 patients with OPSCC depicted on pretreatment neck CT scans using skewness and entropy in combination with percent change in tumor size after induction chemotherapy yielded a statistically significant increase in accuracy for predicting tumor progression over change in tumor size alone, with an area under the curve of 0.80 versus 0.56 (one-tailed P=0.0087). Conclusions: This pilot study suggests that disease progression in patients with HPV-positive OPSCC is more accurately predicted using a combination of texture features on pre-treatment CT scans, along with change in tumor size compared to change in tumor size alone and could therefore serve as a radiomic texture signature.

AB - Background: To determine the additive value of quantitative radiomic texture features in predicting progression in human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) based on pre-treatment CT. Methods: Retrospective analysis of a single-center cohort of adult patients enrolled in a response-adapted radiation volume de-escalation trial treated with induction chemotherapy. Texture analysis of HPV-positive OPSCC was performed via primary tumor site contouring on pre-treatment contrast-enhanced CT scans. Percent change in size of the tumor in response to induction chemotherapy based on RECIST 1.1 criteria and progression free survival were clinically determined for this cohort. Receiver operating characteristic (ROC) analysis was performed to compare the accuracy of percent change in tumor size after induction chemotherapy with a combination of change in tumor size and radiomic texture features for predicting tumor progression. Results: Radiomic texture analysis of the primary tumors in 38 patients with OPSCC depicted on pretreatment neck CT scans using skewness and entropy in combination with percent change in tumor size after induction chemotherapy yielded a statistically significant increase in accuracy for predicting tumor progression over change in tumor size alone, with an area under the curve of 0.80 versus 0.56 (one-tailed P=0.0087). Conclusions: This pilot study suggests that disease progression in patients with HPV-positive OPSCC is more accurately predicted using a combination of texture features on pre-treatment CT scans, along with change in tumor size compared to change in tumor size alone and could therefore serve as a radiomic texture signature.

KW - Cancer

KW - Computerized tomography (CT)

KW - Oropharyngeal

KW - Size

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=85064398807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064398807&partnerID=8YFLogxK

U2 - 10.21037/qims.2019.03.08

DO - 10.21037/qims.2019.03.08

M3 - Article

VL - 9

SP - 399

EP - 408

JO - Quantitative Imaging in Medicine and Surgery

JF - Quantitative Imaging in Medicine and Surgery

SN - 2223-4292

IS - 3

ER -