Noninvasive characterization of the histopathologic features of pulmonary nodules of the lung adenocarcinoma spectrum using computer-aided nodule assessment and risk yield (CANARY) - A pilot study

Fabien Maldonado, Jennifer M. Boland, Sushravya Raghunath, Marie Christine Aubry, Brian Jack Bartholmai, Mariza De Andrade, Thomas E. Hartman, Ronald A. Karwoski, Srinivasan Rajagopalan, Anne-Marie Gisele Sykes, Ping Yang, Eunhee S. Yi, Richard A. Robb, Tobias D Peikert

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

INTRODUCTION: Pulmonary nodules of the adenocarcinoma spectrum are characterized by distinctive morphological and radiologic features and variable prognosis. Noninvasive high-resolution computed tomography-based risk stratification tools are needed to individualize their management. METHODS: Radiologic measurements of histopathologic tissue invasion were developed in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum and validated in 86 consecutively resected nodules. Nodules were isolated and characterized by computer-aided analysis, and data were analyzed by Spearman correlation, sensitivity, and specificity and the positive and negative predictive values. RESULTS: Computer-aided nodule assessment and risk yield (CANARY) can noninvasively characterize pulmonary nodules of the adenocarcinoma spectrum. Unsupervised clustering analysis of high-resolution computed tomography data identified nine unique exemplars representing the basic radiologic building blocks of these lesions. The exemplar distribution within each nodule correlated well with the proportion of histologic tissue invasion, Spearman R = 0.87, p < 0.0001 and 0.89 and p < 0.0001 for the training and the validation set, respectively. Clustering of the exemplars in three-dimensional space corresponding to tissue invasion and lepidic growth was used to develop a CANARY decision algorithm that successfully categorized these pulmonary nodules as "aggressive" (invasive adenocarcinoma) or "indolent" (adenocarcinoma in situ and minimally invasive adenocarcinoma). Sensitivity, specificity, positive predictive value, and negative predictive value of this approach for the detection of aggressive lesions were 95.4, 96.8, 95.4, and 96.8%, respectively, in the training set and 98.7, 63.6, 94.9, and 87.5%, respectively, in the validation set. CONCLUSION: CANARY represents a promising tool to noninvasively risk stratify pulmonary nodules of the adenocarcinoma spectrum.

Original languageEnglish (US)
Pages (from-to)452-460
Number of pages9
JournalJournal of Thoracic Oncology
Volume8
Issue number4
DOIs
StatePublished - Apr 2013

Fingerprint

Lung
Cluster Analysis
Adenocarcinoma
Tomography
Sensitivity and Specificity
Adenocarcinoma of lung
Growth
Adenocarcinoma in Situ

Keywords

  • Computer-aided image analysis
  • Lung adenocarcinoma
  • Pulmonary nodules
  • Risk stratification

ASJC Scopus subject areas

  • Oncology
  • Pulmonary and Respiratory Medicine

Cite this

Noninvasive characterization of the histopathologic features of pulmonary nodules of the lung adenocarcinoma spectrum using computer-aided nodule assessment and risk yield (CANARY) - A pilot study. / Maldonado, Fabien; Boland, Jennifer M.; Raghunath, Sushravya; Aubry, Marie Christine; Bartholmai, Brian Jack; De Andrade, Mariza; Hartman, Thomas E.; Karwoski, Ronald A.; Rajagopalan, Srinivasan; Sykes, Anne-Marie Gisele; Yang, Ping; Yi, Eunhee S.; Robb, Richard A.; Peikert, Tobias D.

In: Journal of Thoracic Oncology, Vol. 8, No. 4, 04.2013, p. 452-460.

Research output: Contribution to journalArticle

Maldonado, Fabien ; Boland, Jennifer M. ; Raghunath, Sushravya ; Aubry, Marie Christine ; Bartholmai, Brian Jack ; De Andrade, Mariza ; Hartman, Thomas E. ; Karwoski, Ronald A. ; Rajagopalan, Srinivasan ; Sykes, Anne-Marie Gisele ; Yang, Ping ; Yi, Eunhee S. ; Robb, Richard A. ; Peikert, Tobias D. / Noninvasive characterization of the histopathologic features of pulmonary nodules of the lung adenocarcinoma spectrum using computer-aided nodule assessment and risk yield (CANARY) - A pilot study. In: Journal of Thoracic Oncology. 2013 ; Vol. 8, No. 4. pp. 452-460.
@article{059c968a2fe14f57a8233c62d5bbdebd,
title = "Noninvasive characterization of the histopathologic features of pulmonary nodules of the lung adenocarcinoma spectrum using computer-aided nodule assessment and risk yield (CANARY) - A pilot study",
abstract = "INTRODUCTION: Pulmonary nodules of the adenocarcinoma spectrum are characterized by distinctive morphological and radiologic features and variable prognosis. Noninvasive high-resolution computed tomography-based risk stratification tools are needed to individualize their management. METHODS: Radiologic measurements of histopathologic tissue invasion were developed in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum and validated in 86 consecutively resected nodules. Nodules were isolated and characterized by computer-aided analysis, and data were analyzed by Spearman correlation, sensitivity, and specificity and the positive and negative predictive values. RESULTS: Computer-aided nodule assessment and risk yield (CANARY) can noninvasively characterize pulmonary nodules of the adenocarcinoma spectrum. Unsupervised clustering analysis of high-resolution computed tomography data identified nine unique exemplars representing the basic radiologic building blocks of these lesions. The exemplar distribution within each nodule correlated well with the proportion of histologic tissue invasion, Spearman R = 0.87, p < 0.0001 and 0.89 and p < 0.0001 for the training and the validation set, respectively. Clustering of the exemplars in three-dimensional space corresponding to tissue invasion and lepidic growth was used to develop a CANARY decision algorithm that successfully categorized these pulmonary nodules as {"}aggressive{"} (invasive adenocarcinoma) or {"}indolent{"} (adenocarcinoma in situ and minimally invasive adenocarcinoma). Sensitivity, specificity, positive predictive value, and negative predictive value of this approach for the detection of aggressive lesions were 95.4, 96.8, 95.4, and 96.8{\%}, respectively, in the training set and 98.7, 63.6, 94.9, and 87.5{\%}, respectively, in the validation set. CONCLUSION: CANARY represents a promising tool to noninvasively risk stratify pulmonary nodules of the adenocarcinoma spectrum.",
keywords = "Computer-aided image analysis, Lung adenocarcinoma, Pulmonary nodules, Risk stratification",
author = "Fabien Maldonado and Boland, {Jennifer M.} and Sushravya Raghunath and Aubry, {Marie Christine} and Bartholmai, {Brian Jack} and {De Andrade}, Mariza and Hartman, {Thomas E.} and Karwoski, {Ronald A.} and Srinivasan Rajagopalan and Sykes, {Anne-Marie Gisele} and Ping Yang and Yi, {Eunhee S.} and Robb, {Richard A.} and Peikert, {Tobias D}",
year = "2013",
month = "4",
doi = "10.1097/JTO.0b013e3182843721",
language = "English (US)",
volume = "8",
pages = "452--460",
journal = "Journal of Thoracic Oncology",
issn = "1556-0864",
publisher = "International Association for the Study of Lung Cancer",
number = "4",

}

TY - JOUR

T1 - Noninvasive characterization of the histopathologic features of pulmonary nodules of the lung adenocarcinoma spectrum using computer-aided nodule assessment and risk yield (CANARY) - A pilot study

AU - Maldonado, Fabien

AU - Boland, Jennifer M.

AU - Raghunath, Sushravya

AU - Aubry, Marie Christine

AU - Bartholmai, Brian Jack

AU - De Andrade, Mariza

AU - Hartman, Thomas E.

AU - Karwoski, Ronald A.

AU - Rajagopalan, Srinivasan

AU - Sykes, Anne-Marie Gisele

AU - Yang, Ping

AU - Yi, Eunhee S.

AU - Robb, Richard A.

AU - Peikert, Tobias D

PY - 2013/4

Y1 - 2013/4

N2 - INTRODUCTION: Pulmonary nodules of the adenocarcinoma spectrum are characterized by distinctive morphological and radiologic features and variable prognosis. Noninvasive high-resolution computed tomography-based risk stratification tools are needed to individualize their management. METHODS: Radiologic measurements of histopathologic tissue invasion were developed in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum and validated in 86 consecutively resected nodules. Nodules were isolated and characterized by computer-aided analysis, and data were analyzed by Spearman correlation, sensitivity, and specificity and the positive and negative predictive values. RESULTS: Computer-aided nodule assessment and risk yield (CANARY) can noninvasively characterize pulmonary nodules of the adenocarcinoma spectrum. Unsupervised clustering analysis of high-resolution computed tomography data identified nine unique exemplars representing the basic radiologic building blocks of these lesions. The exemplar distribution within each nodule correlated well with the proportion of histologic tissue invasion, Spearman R = 0.87, p < 0.0001 and 0.89 and p < 0.0001 for the training and the validation set, respectively. Clustering of the exemplars in three-dimensional space corresponding to tissue invasion and lepidic growth was used to develop a CANARY decision algorithm that successfully categorized these pulmonary nodules as "aggressive" (invasive adenocarcinoma) or "indolent" (adenocarcinoma in situ and minimally invasive adenocarcinoma). Sensitivity, specificity, positive predictive value, and negative predictive value of this approach for the detection of aggressive lesions were 95.4, 96.8, 95.4, and 96.8%, respectively, in the training set and 98.7, 63.6, 94.9, and 87.5%, respectively, in the validation set. CONCLUSION: CANARY represents a promising tool to noninvasively risk stratify pulmonary nodules of the adenocarcinoma spectrum.

AB - INTRODUCTION: Pulmonary nodules of the adenocarcinoma spectrum are characterized by distinctive morphological and radiologic features and variable prognosis. Noninvasive high-resolution computed tomography-based risk stratification tools are needed to individualize their management. METHODS: Radiologic measurements of histopathologic tissue invasion were developed in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum and validated in 86 consecutively resected nodules. Nodules were isolated and characterized by computer-aided analysis, and data were analyzed by Spearman correlation, sensitivity, and specificity and the positive and negative predictive values. RESULTS: Computer-aided nodule assessment and risk yield (CANARY) can noninvasively characterize pulmonary nodules of the adenocarcinoma spectrum. Unsupervised clustering analysis of high-resolution computed tomography data identified nine unique exemplars representing the basic radiologic building blocks of these lesions. The exemplar distribution within each nodule correlated well with the proportion of histologic tissue invasion, Spearman R = 0.87, p < 0.0001 and 0.89 and p < 0.0001 for the training and the validation set, respectively. Clustering of the exemplars in three-dimensional space corresponding to tissue invasion and lepidic growth was used to develop a CANARY decision algorithm that successfully categorized these pulmonary nodules as "aggressive" (invasive adenocarcinoma) or "indolent" (adenocarcinoma in situ and minimally invasive adenocarcinoma). Sensitivity, specificity, positive predictive value, and negative predictive value of this approach for the detection of aggressive lesions were 95.4, 96.8, 95.4, and 96.8%, respectively, in the training set and 98.7, 63.6, 94.9, and 87.5%, respectively, in the validation set. CONCLUSION: CANARY represents a promising tool to noninvasively risk stratify pulmonary nodules of the adenocarcinoma spectrum.

KW - Computer-aided image analysis

KW - Lung adenocarcinoma

KW - Pulmonary nodules

KW - Risk stratification

UR - http://www.scopus.com/inward/record.url?scp=84875395563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875395563&partnerID=8YFLogxK

U2 - 10.1097/JTO.0b013e3182843721

DO - 10.1097/JTO.0b013e3182843721

M3 - Article

C2 - 23486265

AN - SCOPUS:84875395563

VL - 8

SP - 452

EP - 460

JO - Journal of Thoracic Oncology

JF - Journal of Thoracic Oncology

SN - 1556-0864

IS - 4

ER -