Imaging-Genomic Study of Head and Neck Squamous Cell Carcinoma: Associations Between Radiomic Phenotypes and Genomic Mechanisms via Integration of The Cancer Genome Atlas and The Cancer Imaging Archive

Yitan Zhu, Abdallah S.R. Mohamed, Stephen Yenzen Lai, Shengjie Yang, Aasheesh Kanwar, Lin Wei, Mona Kamal, Subhajit Sengupta, Hesham Elhalawani, Heath Skinner, Dennis Stephen Mackin, Jay Shiao, Jay Messer, Andrew Wong, Yao Ding, Lifei Zhang, Laurence Edward Court, Yuan Ji, Clifton Fuller

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

PURPOSE: Recent data suggest that imaging radiomic features of a tumor could be indicative of important genomic biomarkers. Understanding the relationship between radiomic and genomic features is important for basic cancer research and future patient care. We performed a comprehensive study to discover the imaginggenomic associations in head and neck squamous cell carcinoma (HNSCC) and explore the potential of predicting tumor genomic alternations using radiomic features. METHODS: Our retrospective study integrated whole-genome multiomics data from The Cancer Genome Atlas with matched computed tomography imaging data from The Cancer Imaging Archive for the same set of 126 patients with HNSCC. Linear regression and gene set enrichment analysis were used to identify statistically significant associations between radiomic imaging and genomic features. Random forest classifier was used to predict the status of two key HNSCC molecular biomarkers, human papillomavirus and disruptive TP53 mutation, on the basis of radiomic features. RESULTS: Widespread and statistically significant associations were discovered between genomic features (including microRNA expression, somatic mutations, and transcriptional activity, copy number variations, and promoter region DNA methylation changes of pathways) and radiomic features characterizing the size, shape, and texture of tumor. Prediction of human papillomavirus and TP53 mutation status using radiomic features achieved areas under the receiver operating characteristic curve of 0.71 and 0.641, respectively. CONCLUSION: Our exploratory study suggests that radiomic features are associated with genomic characteristics at multiple molecular layers in HNSCC and provides justification for continued development of radiomics as biomarkers for relevant genomic alterations in HNSCC.

Original languageEnglish (US)
Pages (from-to)1-9
Number of pages9
JournalJCO clinical cancer informatics
Issue number3
DOIs
StatePublished - Feb 1 2019

Fingerprint

Atlases
Genome
Phenotype
Neoplasms
Biomarkers
Mutation
DNA Methylation
MicroRNAs
Genetic Promoter Regions
ROC Curve
Carcinoma, squamous cell of head and neck
Linear Models
Patient Care
Retrospective Studies
Tomography
Research
Genes

Cite this

Imaging-Genomic Study of Head and Neck Squamous Cell Carcinoma : Associations Between Radiomic Phenotypes and Genomic Mechanisms via Integration of The Cancer Genome Atlas and The Cancer Imaging Archive. / Zhu, Yitan; Mohamed, Abdallah S.R.; Lai, Stephen Yenzen; Yang, Shengjie; Kanwar, Aasheesh; Wei, Lin; Kamal, Mona; Sengupta, Subhajit; Elhalawani, Hesham; Skinner, Heath; Mackin, Dennis Stephen; Shiao, Jay; Messer, Jay; Wong, Andrew; Ding, Yao; Zhang, Lifei; Court, Laurence Edward; Ji, Yuan; Fuller, Clifton.

In: JCO clinical cancer informatics, No. 3, 01.02.2019, p. 1-9.

Research output: Contribution to journalArticle

@article{f3ee4434a379451dac6312cca756052e,
title = "Imaging-Genomic Study of Head and Neck Squamous Cell Carcinoma: Associations Between Radiomic Phenotypes and Genomic Mechanisms via Integration of The Cancer Genome Atlas and The Cancer Imaging Archive",
abstract = "PURPOSE: Recent data suggest that imaging radiomic features of a tumor could be indicative of important genomic biomarkers. Understanding the relationship between radiomic and genomic features is important for basic cancer research and future patient care. We performed a comprehensive study to discover the imaginggenomic associations in head and neck squamous cell carcinoma (HNSCC) and explore the potential of predicting tumor genomic alternations using radiomic features. METHODS: Our retrospective study integrated whole-genome multiomics data from The Cancer Genome Atlas with matched computed tomography imaging data from The Cancer Imaging Archive for the same set of 126 patients with HNSCC. Linear regression and gene set enrichment analysis were used to identify statistically significant associations between radiomic imaging and genomic features. Random forest classifier was used to predict the status of two key HNSCC molecular biomarkers, human papillomavirus and disruptive TP53 mutation, on the basis of radiomic features. RESULTS: Widespread and statistically significant associations were discovered between genomic features (including microRNA expression, somatic mutations, and transcriptional activity, copy number variations, and promoter region DNA methylation changes of pathways) and radiomic features characterizing the size, shape, and texture of tumor. Prediction of human papillomavirus and TP53 mutation status using radiomic features achieved areas under the receiver operating characteristic curve of 0.71 and 0.641, respectively. CONCLUSION: Our exploratory study suggests that radiomic features are associated with genomic characteristics at multiple molecular layers in HNSCC and provides justification for continued development of radiomics as biomarkers for relevant genomic alterations in HNSCC.",
author = "Yitan Zhu and Mohamed, {Abdallah S.R.} and Lai, {Stephen Yenzen} and Shengjie Yang and Aasheesh Kanwar and Lin Wei and Mona Kamal and Subhajit Sengupta and Hesham Elhalawani and Heath Skinner and Mackin, {Dennis Stephen} and Jay Shiao and Jay Messer and Andrew Wong and Yao Ding and Lifei Zhang and Court, {Laurence Edward} and Yuan Ji and Clifton Fuller",
year = "2019",
month = "2",
day = "1",
doi = "10.1200/CCI.18.00073",
language = "English (US)",
pages = "1--9",
journal = "JCO clinical cancer informatics",
issn = "2473-4276",
publisher = "American Society of Clinical Oncology",
number = "3",

}

TY - JOUR

T1 - Imaging-Genomic Study of Head and Neck Squamous Cell Carcinoma

T2 - Associations Between Radiomic Phenotypes and Genomic Mechanisms via Integration of The Cancer Genome Atlas and The Cancer Imaging Archive

AU - Zhu, Yitan

AU - Mohamed, Abdallah S.R.

AU - Lai, Stephen Yenzen

AU - Yang, Shengjie

AU - Kanwar, Aasheesh

AU - Wei, Lin

AU - Kamal, Mona

AU - Sengupta, Subhajit

AU - Elhalawani, Hesham

AU - Skinner, Heath

AU - Mackin, Dennis Stephen

AU - Shiao, Jay

AU - Messer, Jay

AU - Wong, Andrew

AU - Ding, Yao

AU - Zhang, Lifei

AU - Court, Laurence Edward

AU - Ji, Yuan

AU - Fuller, Clifton

PY - 2019/2/1

Y1 - 2019/2/1

N2 - PURPOSE: Recent data suggest that imaging radiomic features of a tumor could be indicative of important genomic biomarkers. Understanding the relationship between radiomic and genomic features is important for basic cancer research and future patient care. We performed a comprehensive study to discover the imaginggenomic associations in head and neck squamous cell carcinoma (HNSCC) and explore the potential of predicting tumor genomic alternations using radiomic features. METHODS: Our retrospective study integrated whole-genome multiomics data from The Cancer Genome Atlas with matched computed tomography imaging data from The Cancer Imaging Archive for the same set of 126 patients with HNSCC. Linear regression and gene set enrichment analysis were used to identify statistically significant associations between radiomic imaging and genomic features. Random forest classifier was used to predict the status of two key HNSCC molecular biomarkers, human papillomavirus and disruptive TP53 mutation, on the basis of radiomic features. RESULTS: Widespread and statistically significant associations were discovered between genomic features (including microRNA expression, somatic mutations, and transcriptional activity, copy number variations, and promoter region DNA methylation changes of pathways) and radiomic features characterizing the size, shape, and texture of tumor. Prediction of human papillomavirus and TP53 mutation status using radiomic features achieved areas under the receiver operating characteristic curve of 0.71 and 0.641, respectively. CONCLUSION: Our exploratory study suggests that radiomic features are associated with genomic characteristics at multiple molecular layers in HNSCC and provides justification for continued development of radiomics as biomarkers for relevant genomic alterations in HNSCC.

AB - PURPOSE: Recent data suggest that imaging radiomic features of a tumor could be indicative of important genomic biomarkers. Understanding the relationship between radiomic and genomic features is important for basic cancer research and future patient care. We performed a comprehensive study to discover the imaginggenomic associations in head and neck squamous cell carcinoma (HNSCC) and explore the potential of predicting tumor genomic alternations using radiomic features. METHODS: Our retrospective study integrated whole-genome multiomics data from The Cancer Genome Atlas with matched computed tomography imaging data from The Cancer Imaging Archive for the same set of 126 patients with HNSCC. Linear regression and gene set enrichment analysis were used to identify statistically significant associations between radiomic imaging and genomic features. Random forest classifier was used to predict the status of two key HNSCC molecular biomarkers, human papillomavirus and disruptive TP53 mutation, on the basis of radiomic features. RESULTS: Widespread and statistically significant associations were discovered between genomic features (including microRNA expression, somatic mutations, and transcriptional activity, copy number variations, and promoter region DNA methylation changes of pathways) and radiomic features characterizing the size, shape, and texture of tumor. Prediction of human papillomavirus and TP53 mutation status using radiomic features achieved areas under the receiver operating characteristic curve of 0.71 and 0.641, respectively. CONCLUSION: Our exploratory study suggests that radiomic features are associated with genomic characteristics at multiple molecular layers in HNSCC and provides justification for continued development of radiomics as biomarkers for relevant genomic alterations in HNSCC.

UR - http://www.scopus.com/inward/record.url?scp=85061265618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061265618&partnerID=8YFLogxK

U2 - 10.1200/CCI.18.00073

DO - 10.1200/CCI.18.00073

M3 - Article

C2 - 30730765

AN - SCOPUS:85061265618

SP - 1

EP - 9

JO - JCO clinical cancer informatics

JF - JCO clinical cancer informatics

SN - 2473-4276

IS - 3

ER -