TY - JOUR
T1 - A machine learning-based prediction of the micropapillary/solid growth pattern in invasive lung adenocarcinoma with radiomics
AU - He, Bingxi
AU - Song, Yongxiang
AU - Wang, Lili
AU - Wang, Tingting
AU - She, Yunlang
AU - Hou, Likun
AU - Zhang, Lei
AU - Wu, Chunyan
AU - Babu, Benson A.
AU - Bagci, Ulas
AU - Waseem, Tayab
AU - Yang, Minglei
AU - Xie, Dong
AU - Chen, Chang
N1 - Funding Information:
Lung Cancer Collaborative Group. Financial supports from Shanghai Health Commission (2019SY072 & 2018ZHYL0102), Shanghai Pulmonary Hospital Research Fund (FK18001 & FKGG1805), Clinical Research Foundation of Shanghai Pulmonary Hospital (FK1944), Medicine and Public Health Scientific Projects in Zhejiang Province (2020KY270), and Huamei Key Research Foundation (2019HMZD05) were appreciated. Funding: This study was supported by Shanghai Health Commission (2019SY072 & 2018ZHYL0102), Shanghai Pulmonary Hospital Research Fund (FK18001 & FKGG1805), Clinical Research Foundation of Shanghai Pulmonary Hospital (FK1944), Medicine and Public Health Scientific Projects in Zhejiang Province (2020KY270), and Huamei Key Research Foundation (2019HMZD05).
Publisher Copyright:
© 2021 Translational Lung Cancer Research.
PY - 2021/2
Y1 - 2021/2
N2 - Background: Micropapillary/solid (MP/S) growth patterns of lung adenocarcinoma are vital for making clinical decisions regarding surgical intervention. This study aimed to predict the presence of a MP/S component in lung adenocarcinoma using radiomics analysis. Methods: Between January 2011 and December 2013, patients undergoing curative invasive lung adenocarcinoma resection were included. Using the "PyRadiomics"package, we extracted 90 radiomics features from the preoperative computed tomography (CT) images. Subsequently, four prediction models were built by utilizing conventional machine learning approaches fitting into radiomics analysis: A generalized linear model (GLM), Naïve Bayes, support vector machine (SVM), and random forest classifiers. The models' accuracy was assessed using a receiver operating curve (ROC) analysis, and the models' stability was validated both internally and externally. Results: A total of 268 patients were included as a primary cohort, and 36.6% (98/268) of them had lung adenocarcinoma with an MP/S component. Patients with an MP/S component had a higher rate of lymph node metastasis (18.4% versus 5.3%) and worse recurrence-free and overall survival. Five radiomics features were selected for model building, and in the internal validation, the four models achieved comparable performance of MP/S prediction in terms of area under the curve (AUC): GLM, 0.74 [95% confidence interval (CI): 0.65-0.83]; Naïve Bayes, 0.75 (95% CI: 0.65-0.85); SVM, 0.73 (95% CI: 0.61-0.83); and random forest, 0.72 (95% CI: 0.63-0.81). External validation was performed using a test cohort with 193 patients, and the AUC values were 0.70, 0.72, 0.73, and 0.69 for Naïve Bayes, SVM, random forest, and GLM, respectively. Conclusions: Radiomics-based machine learning approach is a very strong tool for preoperatively predicting the presence of MP/S growth patterns in lung adenocarcinoma, and can help customize treatment and surveillance strategies.
AB - Background: Micropapillary/solid (MP/S) growth patterns of lung adenocarcinoma are vital for making clinical decisions regarding surgical intervention. This study aimed to predict the presence of a MP/S component in lung adenocarcinoma using radiomics analysis. Methods: Between January 2011 and December 2013, patients undergoing curative invasive lung adenocarcinoma resection were included. Using the "PyRadiomics"package, we extracted 90 radiomics features from the preoperative computed tomography (CT) images. Subsequently, four prediction models were built by utilizing conventional machine learning approaches fitting into radiomics analysis: A generalized linear model (GLM), Naïve Bayes, support vector machine (SVM), and random forest classifiers. The models' accuracy was assessed using a receiver operating curve (ROC) analysis, and the models' stability was validated both internally and externally. Results: A total of 268 patients were included as a primary cohort, and 36.6% (98/268) of them had lung adenocarcinoma with an MP/S component. Patients with an MP/S component had a higher rate of lymph node metastasis (18.4% versus 5.3%) and worse recurrence-free and overall survival. Five radiomics features were selected for model building, and in the internal validation, the four models achieved comparable performance of MP/S prediction in terms of area under the curve (AUC): GLM, 0.74 [95% confidence interval (CI): 0.65-0.83]; Naïve Bayes, 0.75 (95% CI: 0.65-0.85); SVM, 0.73 (95% CI: 0.61-0.83); and random forest, 0.72 (95% CI: 0.63-0.81). External validation was performed using a test cohort with 193 patients, and the AUC values were 0.70, 0.72, 0.73, and 0.69 for Naïve Bayes, SVM, random forest, and GLM, respectively. Conclusions: Radiomics-based machine learning approach is a very strong tool for preoperatively predicting the presence of MP/S growth patterns in lung adenocarcinoma, and can help customize treatment and surveillance strategies.
KW - Computed tomography
KW - Lung adenocarcinoma
KW - Machine learning
KW - Prediction
KW - Radiomics
UR - http://www.scopus.com/inward/record.url?scp=85103076902&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85103076902&partnerID=8YFLogxK
U2 - 10.21037/tlcr-21-44
DO - 10.21037/tlcr-21-44
M3 - Article
C2 - 33718035
AN - SCOPUS:85103076902
VL - 10
SP - 955
EP - 964
JO - Translational Lung Cancer Research
JF - Translational Lung Cancer Research
SN - 2226-4477
IS - 2
ER -