A clinical-radiomics nomogram for the preoperative prediction of lung metastasis in colorectal cancer patients with indeterminate pulmonary nodules

Ting Dan Hu, Sheng Ping Wang, Lv Huang, Jia Zhou Wang, De Bing Shi, Yuan Li, Tong Tong, Weijun Peng

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objectives: To develop and validate a clinical-radiomics nomogram for preoperative prediction of lung metastasis for colorectal cancer (CRC) patients with indeterminate pulmonary nodules (IPN). Methods: 194 CRC patients with lung nodules were enrolled in this study (136 in the training cohort and 58 in the validation cohort). To evaluate the probability of lung metastasis, we developed three models, the clinical model with significant clinical risk factors, the radiomics model with radiomics features constructed by the least absolute shrinkage and selection operator algorithm, and the clinical-radiomics model with significant variables selected by the stepwise logistic regression. The Akaike information criterion (AIC) was used to compare the relative strength of different models, and the area under the curve (AUC) was used to quantify the predictive accuracy. The nomogram was developed based on the most appropriate model. Decision-curve analysis was applied to assess the clinical usefulness. Results: The clinical-radiomics model (AIC = 98.893) with the lowest AIC value compared with that of the clinical-only model (AIC = 138.502) or the radiomics-only model (AIC = 116.146) was identified as the best model. The clinical-radiomics nomogram was also successfully developed with favourable discrimination in both training cohort (AUC = 0.929, 95% CI: 0.885–0.974) and validation cohort (AUC = 0.922, 95% CI: 0.857–0.986), and good calibration. Decision-curve analysis confirmed the clinical utility of the clinical-radiomics nomogram. Conclusions: In CRC patients with IPNs, the clinical-radiomics nomogram created by the radiomics signature and clinical risk factors exhibited favourable discriminatory ability and accuracy for a metastasis prediction. Key Points: • Clinical features can predict lung metastasis of colorectal cancer patients. • Radiomics analysis outperformed clinical features in assessing the risk of pulmonary metastasis. • A clinical-radiomics nomogram can help clinicians predict lung metastasis in colorectal cancer patients.

Original languageEnglish (US)
Pages (from-to)439-449
Number of pages11
JournalEuropean Radiology
Volume29
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Nomograms
Colorectal Neoplasms
Neoplasm Metastasis
Lung
Area Under Curve
Decision Support Techniques
Calibration
Logistic Models

Keywords

  • Colorectal neoplasms
  • Decision making
  • Nomograms

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

A clinical-radiomics nomogram for the preoperative prediction of lung metastasis in colorectal cancer patients with indeterminate pulmonary nodules. / Hu, Ting Dan; Wang, Sheng Ping; Huang, Lv; Wang, Jia Zhou; Shi, De Bing; Li, Yuan; Tong, Tong; Peng, Weijun.

In: European Radiology, Vol. 29, No. 1, 01.01.2019, p. 439-449.

Research output: Contribution to journalArticle

Hu, Ting Dan ; Wang, Sheng Ping ; Huang, Lv ; Wang, Jia Zhou ; Shi, De Bing ; Li, Yuan ; Tong, Tong ; Peng, Weijun. / A clinical-radiomics nomogram for the preoperative prediction of lung metastasis in colorectal cancer patients with indeterminate pulmonary nodules. In: European Radiology. 2019 ; Vol. 29, No. 1. pp. 439-449.
@article{6fb30c4525f541ff908bd1d3f680e637,
title = "A clinical-radiomics nomogram for the preoperative prediction of lung metastasis in colorectal cancer patients with indeterminate pulmonary nodules",
abstract = "Objectives: To develop and validate a clinical-radiomics nomogram for preoperative prediction of lung metastasis for colorectal cancer (CRC) patients with indeterminate pulmonary nodules (IPN). Methods: 194 CRC patients with lung nodules were enrolled in this study (136 in the training cohort and 58 in the validation cohort). To evaluate the probability of lung metastasis, we developed three models, the clinical model with significant clinical risk factors, the radiomics model with radiomics features constructed by the least absolute shrinkage and selection operator algorithm, and the clinical-radiomics model with significant variables selected by the stepwise logistic regression. The Akaike information criterion (AIC) was used to compare the relative strength of different models, and the area under the curve (AUC) was used to quantify the predictive accuracy. The nomogram was developed based on the most appropriate model. Decision-curve analysis was applied to assess the clinical usefulness. Results: The clinical-radiomics model (AIC = 98.893) with the lowest AIC value compared with that of the clinical-only model (AIC = 138.502) or the radiomics-only model (AIC = 116.146) was identified as the best model. The clinical-radiomics nomogram was also successfully developed with favourable discrimination in both training cohort (AUC = 0.929, 95{\%} CI: 0.885–0.974) and validation cohort (AUC = 0.922, 95{\%} CI: 0.857–0.986), and good calibration. Decision-curve analysis confirmed the clinical utility of the clinical-radiomics nomogram. Conclusions: In CRC patients with IPNs, the clinical-radiomics nomogram created by the radiomics signature and clinical risk factors exhibited favourable discriminatory ability and accuracy for a metastasis prediction. Key Points: • Clinical features can predict lung metastasis of colorectal cancer patients. • Radiomics analysis outperformed clinical features in assessing the risk of pulmonary metastasis. • A clinical-radiomics nomogram can help clinicians predict lung metastasis in colorectal cancer patients.",
keywords = "Colorectal neoplasms, Decision making, Nomograms",
author = "Hu, {Ting Dan} and Wang, {Sheng Ping} and Lv Huang and Wang, {Jia Zhou} and Shi, {De Bing} and Yuan Li and Tong Tong and Weijun Peng",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s00330-018-5539-3",
language = "English (US)",
volume = "29",
pages = "439--449",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - A clinical-radiomics nomogram for the preoperative prediction of lung metastasis in colorectal cancer patients with indeterminate pulmonary nodules

AU - Hu, Ting Dan

AU - Wang, Sheng Ping

AU - Huang, Lv

AU - Wang, Jia Zhou

AU - Shi, De Bing

AU - Li, Yuan

AU - Tong, Tong

AU - Peng, Weijun

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Objectives: To develop and validate a clinical-radiomics nomogram for preoperative prediction of lung metastasis for colorectal cancer (CRC) patients with indeterminate pulmonary nodules (IPN). Methods: 194 CRC patients with lung nodules were enrolled in this study (136 in the training cohort and 58 in the validation cohort). To evaluate the probability of lung metastasis, we developed three models, the clinical model with significant clinical risk factors, the radiomics model with radiomics features constructed by the least absolute shrinkage and selection operator algorithm, and the clinical-radiomics model with significant variables selected by the stepwise logistic regression. The Akaike information criterion (AIC) was used to compare the relative strength of different models, and the area under the curve (AUC) was used to quantify the predictive accuracy. The nomogram was developed based on the most appropriate model. Decision-curve analysis was applied to assess the clinical usefulness. Results: The clinical-radiomics model (AIC = 98.893) with the lowest AIC value compared with that of the clinical-only model (AIC = 138.502) or the radiomics-only model (AIC = 116.146) was identified as the best model. The clinical-radiomics nomogram was also successfully developed with favourable discrimination in both training cohort (AUC = 0.929, 95% CI: 0.885–0.974) and validation cohort (AUC = 0.922, 95% CI: 0.857–0.986), and good calibration. Decision-curve analysis confirmed the clinical utility of the clinical-radiomics nomogram. Conclusions: In CRC patients with IPNs, the clinical-radiomics nomogram created by the radiomics signature and clinical risk factors exhibited favourable discriminatory ability and accuracy for a metastasis prediction. Key Points: • Clinical features can predict lung metastasis of colorectal cancer patients. • Radiomics analysis outperformed clinical features in assessing the risk of pulmonary metastasis. • A clinical-radiomics nomogram can help clinicians predict lung metastasis in colorectal cancer patients.

AB - Objectives: To develop and validate a clinical-radiomics nomogram for preoperative prediction of lung metastasis for colorectal cancer (CRC) patients with indeterminate pulmonary nodules (IPN). Methods: 194 CRC patients with lung nodules were enrolled in this study (136 in the training cohort and 58 in the validation cohort). To evaluate the probability of lung metastasis, we developed three models, the clinical model with significant clinical risk factors, the radiomics model with radiomics features constructed by the least absolute shrinkage and selection operator algorithm, and the clinical-radiomics model with significant variables selected by the stepwise logistic regression. The Akaike information criterion (AIC) was used to compare the relative strength of different models, and the area under the curve (AUC) was used to quantify the predictive accuracy. The nomogram was developed based on the most appropriate model. Decision-curve analysis was applied to assess the clinical usefulness. Results: The clinical-radiomics model (AIC = 98.893) with the lowest AIC value compared with that of the clinical-only model (AIC = 138.502) or the radiomics-only model (AIC = 116.146) was identified as the best model. The clinical-radiomics nomogram was also successfully developed with favourable discrimination in both training cohort (AUC = 0.929, 95% CI: 0.885–0.974) and validation cohort (AUC = 0.922, 95% CI: 0.857–0.986), and good calibration. Decision-curve analysis confirmed the clinical utility of the clinical-radiomics nomogram. Conclusions: In CRC patients with IPNs, the clinical-radiomics nomogram created by the radiomics signature and clinical risk factors exhibited favourable discriminatory ability and accuracy for a metastasis prediction. Key Points: • Clinical features can predict lung metastasis of colorectal cancer patients. • Radiomics analysis outperformed clinical features in assessing the risk of pulmonary metastasis. • A clinical-radiomics nomogram can help clinicians predict lung metastasis in colorectal cancer patients.

KW - Colorectal neoplasms

KW - Decision making

KW - Nomograms

UR - http://www.scopus.com/inward/record.url?scp=85048375645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048375645&partnerID=8YFLogxK

U2 - 10.1007/s00330-018-5539-3

DO - 10.1007/s00330-018-5539-3

M3 - Article

VL - 29

SP - 439

EP - 449

JO - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 1

ER -