Publication

A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma

Cui, X., Heuvelmans, M. A., Fan, S., Han, D., Zheng, S., Du, Y., Zhao, Y., Sidorenkov, G., Groen, H. J. M., Dorrius, M. D., Oudkerk, M., de Bock, G. H., Vliegenthart, R. & Ye, Z., Jul-2020, In : Clinical lung cancer. 21, 4, p. 314-+ 16 p.

Research output: Contribution to journalArticleAcademicpeer-review

APA

Cui, X., Heuvelmans, M. A., Fan, S., Han, D., Zheng, S., Du, Y., ... Ye, Z. (2020). A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma. Clinical lung cancer, 21(4), 314-+. https://doi.org/10.1016/j.cllc.2020.01.014

Author

Cui, Xiaonan ; Heuvelmans, Marjolein A ; Fan, Shuxuan ; Han, Daiwei ; Zheng, Sunyi ; Du, Yihui ; Zhao, Yingru ; Sidorenkov, Grigory ; Groen, Harry J M ; Dorrius, Monique D ; Oudkerk, Matthijs ; de Bock, Geertruida H ; Vliegenthart, Rozemarijn ; Ye, Zhaoxiang. / A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma. In: Clinical lung cancer. 2020 ; Vol. 21, No. 4. pp. 314-+.

Harvard

Cui, X, Heuvelmans, MA, Fan, S, Han, D, Zheng, S, Du, Y, Zhao, Y, Sidorenkov, G, Groen, HJM, Dorrius, MD, Oudkerk, M, de Bock, GH, Vliegenthart, R & Ye, Z 2020, 'A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma', Clinical lung cancer, vol. 21, no. 4, pp. 314-+. https://doi.org/10.1016/j.cllc.2020.01.014

Standard

A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma. / Cui, Xiaonan; Heuvelmans, Marjolein A; Fan, Shuxuan; Han, Daiwei; Zheng, Sunyi; Du, Yihui; Zhao, Yingru; Sidorenkov, Grigory; Groen, Harry J M; Dorrius, Monique D; Oudkerk, Matthijs; de Bock, Geertruida H; Vliegenthart, Rozemarijn; Ye, Zhaoxiang.

In: Clinical lung cancer, Vol. 21, No. 4, 07.2020, p. 314-+.

Research output: Contribution to journalArticleAcademicpeer-review

Vancouver

Cui X, Heuvelmans MA, Fan S, Han D, Zheng S, Du Y et al. A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma. Clinical lung cancer. 2020 Jul;21(4):314-+. https://doi.org/10.1016/j.cllc.2020.01.014


BibTeX

@article{6fc77084317c47078d3130426d0f2bfb,
title = "A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma",
abstract = "It is essential to identify the subsolid nodules subtype preoperatively to select the optimal treatment algorithm. We developed and validated an imaging reporting system using a classification and regression tree model that based on computed tomography imaging characteristics (291 cases in training group, 146 cases in testing group). The model showed high sensitivity and accuracy of classification. Our model can help clinicians to make follow-up recommendations or decisions for surgery for clinical patients with a subsolid nodule.Objectives: To develop an imaging reporting system for the classification of 3 adenocarcinoma subtypes of computed tomography (CT)-detected subsolid pulmonary nodules (SSNs) in clinical patients. Methods: Between November 2011 and October 2017, 437 pathologically confirmed SSNs were retrospectively identified. SSNs were randomly divided 2:1 into a training group (291 cases) and a testing group (146 cases). CT-imaging characteristics were analyzed using multinomial univariable and multivariable logistic regression analysis to identify discriminating factors for the 3 adenocarcinoma subtypes (pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma). These factors were used to develop a classification and regression tree model. Finally, an SSN Imaging Reporting System (SSN-IRS) was constructed based on the optimized classification model. For validation, the classification performance was evaluated in the testing group. Results: Of the CT-derived characteristics of SSNs, qualitative density (nonsolid or part-solid), core (non-core or core), semantic features (pleural indentation, vacuole sign, vascular invasion), and diameter of solid component (>= 6 mm or >6 mm), were the most important factors for the SSN-IRS. The total sensitivity, specificity, and diagnostic accuracy of the SSN-IRS was 89.0{\%} (95{\%} confidence interval [CI], 84.8{\%}-92.4{\%}), 74.6{\%} (95{\%} CI, 70.8{\%}-78.1{\%}), and 79.4{\%} (95{\%} CI, 76.5{\%}-82.0{\%}) in the training group and 84.9{\%} (95{\%} CI, 78.1{\%}-90.3{\%}), 68.5{\%} (95{\%} CI, 62.8{\%}-73.8{\%}), and 74.0{\%} (95{\%} CI, 69.6{\%}-78.0{\%}) in the testing group, respectively. Conclusions: The SSN-IRS can classify 3 adenocarcinoma subtypes using CT-based characteristics of subsolid pulmonary nodules. This classification tool can help clinicians to make follow-up recommendations or decisions for surgery in clinical patients with SSNs. (C) 2020 The Author(s). Published by Elsevier Inc.",
keywords = "Decision trees, Diagnosis, Lung, Solitary pulmonary nodule, X-ray computed tomography, GROUND-GLASS OPACITY, MINIMALLY INVASIVE ADENOCARCINOMA, DECISION TREE, LUNG, CT, CLASSIFICATION, DIAGNOSIS, RESECTION, SECTION, CANCER",
author = "Xiaonan Cui and Heuvelmans, {Marjolein A} and Shuxuan Fan and Daiwei Han and Sunyi Zheng and Yihui Du and Yingru Zhao and Grigory Sidorenkov and Groen, {Harry J M} and Dorrius, {Monique D} and Matthijs Oudkerk and {de Bock}, {Geertruida H} and Rozemarijn Vliegenthart and Zhaoxiang Ye",
note = "Copyright {\circledC} 2020 The Author(s). Published by Elsevier Inc. All rights reserved.",
year = "2020",
month = "7",
doi = "10.1016/j.cllc.2020.01.014",
language = "English",
volume = "21",
pages = "314--+",
journal = "Clinical lung cancer",
issn = "1525-7304",
publisher = "CIG MEDIA GROUP, LP",
number = "4",

}

RIS

TY - JOUR

T1 - A Subsolid Nodules Imaging Reporting System (SSN-IRS) for Classifying 3 Subtypes of Pulmonary Adenocarcinoma

AU - Cui, Xiaonan

AU - Heuvelmans, Marjolein A

AU - Fan, Shuxuan

AU - Han, Daiwei

AU - Zheng, Sunyi

AU - Du, Yihui

AU - Zhao, Yingru

AU - Sidorenkov, Grigory

AU - Groen, Harry J M

AU - Dorrius, Monique D

AU - Oudkerk, Matthijs

AU - de Bock, Geertruida H

AU - Vliegenthart, Rozemarijn

AU - Ye, Zhaoxiang

N1 - Copyright © 2020 The Author(s). Published by Elsevier Inc. All rights reserved.

PY - 2020/7

Y1 - 2020/7

N2 - It is essential to identify the subsolid nodules subtype preoperatively to select the optimal treatment algorithm. We developed and validated an imaging reporting system using a classification and regression tree model that based on computed tomography imaging characteristics (291 cases in training group, 146 cases in testing group). The model showed high sensitivity and accuracy of classification. Our model can help clinicians to make follow-up recommendations or decisions for surgery for clinical patients with a subsolid nodule.Objectives: To develop an imaging reporting system for the classification of 3 adenocarcinoma subtypes of computed tomography (CT)-detected subsolid pulmonary nodules (SSNs) in clinical patients. Methods: Between November 2011 and October 2017, 437 pathologically confirmed SSNs were retrospectively identified. SSNs were randomly divided 2:1 into a training group (291 cases) and a testing group (146 cases). CT-imaging characteristics were analyzed using multinomial univariable and multivariable logistic regression analysis to identify discriminating factors for the 3 adenocarcinoma subtypes (pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma). These factors were used to develop a classification and regression tree model. Finally, an SSN Imaging Reporting System (SSN-IRS) was constructed based on the optimized classification model. For validation, the classification performance was evaluated in the testing group. Results: Of the CT-derived characteristics of SSNs, qualitative density (nonsolid or part-solid), core (non-core or core), semantic features (pleural indentation, vacuole sign, vascular invasion), and diameter of solid component (>= 6 mm or >6 mm), were the most important factors for the SSN-IRS. The total sensitivity, specificity, and diagnostic accuracy of the SSN-IRS was 89.0% (95% confidence interval [CI], 84.8%-92.4%), 74.6% (95% CI, 70.8%-78.1%), and 79.4% (95% CI, 76.5%-82.0%) in the training group and 84.9% (95% CI, 78.1%-90.3%), 68.5% (95% CI, 62.8%-73.8%), and 74.0% (95% CI, 69.6%-78.0%) in the testing group, respectively. Conclusions: The SSN-IRS can classify 3 adenocarcinoma subtypes using CT-based characteristics of subsolid pulmonary nodules. This classification tool can help clinicians to make follow-up recommendations or decisions for surgery in clinical patients with SSNs. (C) 2020 The Author(s). Published by Elsevier Inc.

AB - It is essential to identify the subsolid nodules subtype preoperatively to select the optimal treatment algorithm. We developed and validated an imaging reporting system using a classification and regression tree model that based on computed tomography imaging characteristics (291 cases in training group, 146 cases in testing group). The model showed high sensitivity and accuracy of classification. Our model can help clinicians to make follow-up recommendations or decisions for surgery for clinical patients with a subsolid nodule.Objectives: To develop an imaging reporting system for the classification of 3 adenocarcinoma subtypes of computed tomography (CT)-detected subsolid pulmonary nodules (SSNs) in clinical patients. Methods: Between November 2011 and October 2017, 437 pathologically confirmed SSNs were retrospectively identified. SSNs were randomly divided 2:1 into a training group (291 cases) and a testing group (146 cases). CT-imaging characteristics were analyzed using multinomial univariable and multivariable logistic regression analysis to identify discriminating factors for the 3 adenocarcinoma subtypes (pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma). These factors were used to develop a classification and regression tree model. Finally, an SSN Imaging Reporting System (SSN-IRS) was constructed based on the optimized classification model. For validation, the classification performance was evaluated in the testing group. Results: Of the CT-derived characteristics of SSNs, qualitative density (nonsolid or part-solid), core (non-core or core), semantic features (pleural indentation, vacuole sign, vascular invasion), and diameter of solid component (>= 6 mm or >6 mm), were the most important factors for the SSN-IRS. The total sensitivity, specificity, and diagnostic accuracy of the SSN-IRS was 89.0% (95% confidence interval [CI], 84.8%-92.4%), 74.6% (95% CI, 70.8%-78.1%), and 79.4% (95% CI, 76.5%-82.0%) in the training group and 84.9% (95% CI, 78.1%-90.3%), 68.5% (95% CI, 62.8%-73.8%), and 74.0% (95% CI, 69.6%-78.0%) in the testing group, respectively. Conclusions: The SSN-IRS can classify 3 adenocarcinoma subtypes using CT-based characteristics of subsolid pulmonary nodules. This classification tool can help clinicians to make follow-up recommendations or decisions for surgery in clinical patients with SSNs. (C) 2020 The Author(s). Published by Elsevier Inc.

KW - Decision trees

KW - Diagnosis

KW - Lung

KW - Solitary pulmonary nodule

KW - X-ray computed tomography

KW - GROUND-GLASS OPACITY

KW - MINIMALLY INVASIVE ADENOCARCINOMA

KW - DECISION TREE

KW - LUNG

KW - CT

KW - CLASSIFICATION

KW - DIAGNOSIS

KW - RESECTION

KW - SECTION

KW - CANCER

U2 - 10.1016/j.cllc.2020.01.014

DO - 10.1016/j.cllc.2020.01.014

M3 - Article

C2 - 32273256

VL - 21

SP - 314-+

JO - Clinical lung cancer

JF - Clinical lung cancer

SN - 1525-7304

IS - 4

ER -

ID: 122004234