Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas

Ryan Clay, Benjamin R. Kipp, Sarah Jenkins, Ron A. Karwoski, Fabien Maldonado, Srinivasan Rajagopalan, Jesse S. Voss, Brian Jack Bartholmai, Marie Christine Aubry, Tobias D Peikert

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-relevant mutations in lung adenocarcinoma. Comprehensive analysis of targetable mutations (50-gene-panel) and CANARY analysis of the preoperative (≤3 months) high resolution CT (HRCT) was performed for 118 pulmonary nodules of the adenocarcinoma spectrum surgically resected between 2006-2010. Logistic regression with stepwise variable selection was used to determine predictors of mutations. We identified 140 mutations in 106 of 118 nodules. TP53 (n = 48), KRAS (n = 47) and EGFR (n = 15) were the most prevalent. The combination of Y (Yellow) and G (Green) exemplars, fibrosis within the surrounding lung and smoking status were the best discriminators for an EGFR mutation (AUC 0.77 and 0.87, respectively). None of the EGFR mutants expressing TP53 (n = 5) had a good prognosis based on CANARY features. No quantitative features were significantly associated with KRAS mutations. Our exploratory analysis indicates that quantitative CT analysis of a nodule and surrounding lung may noninvasively predict the presence of EGFR mutations in pulmonary nodules of the adenocarcinoma spectrum.

Original languageEnglish (US)
Article number17620
JournalScientific Reports
Volume7
Issue number1
DOIs
StatePublished - Dec 1 2017

Fingerprint

Mutation
Tomography
Lung
Adenocarcinoma of lung
Disease-Free Survival
Area Under Curve
Neoplasms
Fibrosis
Software
Color
Logistic Models
Smoking
Genes
Therapeutics

ASJC Scopus subject areas

  • General

Cite this

Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas. / Clay, Ryan; Kipp, Benjamin R.; Jenkins, Sarah; Karwoski, Ron A.; Maldonado, Fabien; Rajagopalan, Srinivasan; Voss, Jesse S.; Bartholmai, Brian Jack; Aubry, Marie Christine; Peikert, Tobias D.

In: Scientific Reports, Vol. 7, No. 1, 17620, 01.12.2017.

Research output: Contribution to journalArticle

Clay, Ryan ; Kipp, Benjamin R. ; Jenkins, Sarah ; Karwoski, Ron A. ; Maldonado, Fabien ; Rajagopalan, Srinivasan ; Voss, Jesse S. ; Bartholmai, Brian Jack ; Aubry, Marie Christine ; Peikert, Tobias D. / Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas. In: Scientific Reports. 2017 ; Vol. 7, No. 1.
@article{10d54835b41742ffae056a3bf0fa4e63,
title = "Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas",
abstract = "Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-relevant mutations in lung adenocarcinoma. Comprehensive analysis of targetable mutations (50-gene-panel) and CANARY analysis of the preoperative (≤3 months) high resolution CT (HRCT) was performed for 118 pulmonary nodules of the adenocarcinoma spectrum surgically resected between 2006-2010. Logistic regression with stepwise variable selection was used to determine predictors of mutations. We identified 140 mutations in 106 of 118 nodules. TP53 (n = 48), KRAS (n = 47) and EGFR (n = 15) were the most prevalent. The combination of Y (Yellow) and G (Green) exemplars, fibrosis within the surrounding lung and smoking status were the best discriminators for an EGFR mutation (AUC 0.77 and 0.87, respectively). None of the EGFR mutants expressing TP53 (n = 5) had a good prognosis based on CANARY features. No quantitative features were significantly associated with KRAS mutations. Our exploratory analysis indicates that quantitative CT analysis of a nodule and surrounding lung may noninvasively predict the presence of EGFR mutations in pulmonary nodules of the adenocarcinoma spectrum.",
author = "Ryan Clay and Kipp, {Benjamin R.} and Sarah Jenkins and Karwoski, {Ron A.} and Fabien Maldonado and Srinivasan Rajagopalan and Voss, {Jesse S.} and Bartholmai, {Brian Jack} and Aubry, {Marie Christine} and Peikert, {Tobias D}",
year = "2017",
month = "12",
day = "1",
doi = "10.1038/s41598-017-17659-6",
language = "English (US)",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas

AU - Clay, Ryan

AU - Kipp, Benjamin R.

AU - Jenkins, Sarah

AU - Karwoski, Ron A.

AU - Maldonado, Fabien

AU - Rajagopalan, Srinivasan

AU - Voss, Jesse S.

AU - Bartholmai, Brian Jack

AU - Aubry, Marie Christine

AU - Peikert, Tobias D

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-relevant mutations in lung adenocarcinoma. Comprehensive analysis of targetable mutations (50-gene-panel) and CANARY analysis of the preoperative (≤3 months) high resolution CT (HRCT) was performed for 118 pulmonary nodules of the adenocarcinoma spectrum surgically resected between 2006-2010. Logistic regression with stepwise variable selection was used to determine predictors of mutations. We identified 140 mutations in 106 of 118 nodules. TP53 (n = 48), KRAS (n = 47) and EGFR (n = 15) were the most prevalent. The combination of Y (Yellow) and G (Green) exemplars, fibrosis within the surrounding lung and smoking status were the best discriminators for an EGFR mutation (AUC 0.77 and 0.87, respectively). None of the EGFR mutants expressing TP53 (n = 5) had a good prognosis based on CANARY features. No quantitative features were significantly associated with KRAS mutations. Our exploratory analysis indicates that quantitative CT analysis of a nodule and surrounding lung may noninvasively predict the presence of EGFR mutations in pulmonary nodules of the adenocarcinoma spectrum.

AB - Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-relevant mutations in lung adenocarcinoma. Comprehensive analysis of targetable mutations (50-gene-panel) and CANARY analysis of the preoperative (≤3 months) high resolution CT (HRCT) was performed for 118 pulmonary nodules of the adenocarcinoma spectrum surgically resected between 2006-2010. Logistic regression with stepwise variable selection was used to determine predictors of mutations. We identified 140 mutations in 106 of 118 nodules. TP53 (n = 48), KRAS (n = 47) and EGFR (n = 15) were the most prevalent. The combination of Y (Yellow) and G (Green) exemplars, fibrosis within the surrounding lung and smoking status were the best discriminators for an EGFR mutation (AUC 0.77 and 0.87, respectively). None of the EGFR mutants expressing TP53 (n = 5) had a good prognosis based on CANARY features. No quantitative features were significantly associated with KRAS mutations. Our exploratory analysis indicates that quantitative CT analysis of a nodule and surrounding lung may noninvasively predict the presence of EGFR mutations in pulmonary nodules of the adenocarcinoma spectrum.

UR - http://www.scopus.com/inward/record.url?scp=85038236741&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038236741&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-17659-6

DO - 10.1038/s41598-017-17659-6

M3 - Article

C2 - 29247171

AN - SCOPUS:85038236741

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 17620

ER -