AUTHOR=Wu Linyu , Gao Chen , Xiang Ping , Zheng Sisi , Pang Peipei , Xu Maosheng 

TITLE=CT-Imaging Based Analysis of Invasive Lung Adenocarcinoma Presenting as Ground Glass Nodules Using Peri- and Intra-nodular Radiomic Features

JOURNAL=Frontiers in Oncology

VOLUME=Volume 10 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.00838

DOI=10.3389/fonc.2020.00838

ISSN=2234-943X

ABSTRACT=Objective: To evaluate whether radiomic features extracted from intra and perinodular lesions can enhance the ability to differentiate between invasive lung adenocarcinoma (IA), minimally invasive adenocarcinoma (MIA) and adenocarcinoma in situ (AIS) manifesting as ground-glass nodules. 
Materials and Methods: This retrospective study included 120 patients with a total of 121 pathologically confirmed lung adenocarcinomas (85 IA and 36 AIS/MIA) between January 2015 to May 2019. Patients divided into training (n=84) and validation sets (n=37) randomly. The intranodular, perinodular, and gross region of interests (ROI) were delineated with manual annotation. Image features were quantitatively extracted from each ROI on CT images. The mRMR feature ranking method and LASSO classifier were used to eliminate usefulness features. A combined clinical-radiomic model was constructed by multivariable logistic regression analysis. The predicted performances of different models were evaluated using receiver operating curve (ROC) and calibration curve.
Results: The gross radiomic signature (AUC: training set = 0.896; validation set = 0.876) showed a good ability to discriminate infiltration of adenocarcinoma, comparing to intranodular (AUC: training set = 0.862; validation set = 0.852) or perinodular radiomic signature (AUC: training set = 0.825; validation set = 0.820). The AUC of the combined clinical-radiomic model was 0.917 for the training and 0.876 for the validation cohort, respectively. 
Conclusions: The gross radiomic signature of intranodular and perinodular regions improved the prediction ability and aided predicting the invasiveness of lung adenocarcinoma appearing as GGNs.