AUTHOR=Qiu Lu , Zhang Xiuping , Mao Haixia , Fang Xiangming , Ding Wei , Zhao Lun , Chen Hongwei 

TITLE=Comparison of Comprehensive Morphological and Radiomics Features of Subsolid Pulmonary Nodules to Distinguish Minimally Invasive Adenocarcinomas and Invasive Adenocarcinomas in CT Scan

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.691112

DOI=10.3389/fonc.2021.691112

ISSN=2234-943X

ABSTRACT=Objective: 
To investigative the diagnostic performance of morphological model, radiomics model, and combined model in differentiating invasive adenocarcinomas (IACs) from minimally invasive adenocarcinomas (MIAs). 
Methods: 
This study retrospectively involved 307 patients who underwent chest computed tomography (CT) examination and presented as subsolid pulmonary nodules whose pathological findings were MIAs or IACs from January 2010 to May 2018. These patients were randomly assigned to training and validation group in a ratio of 4:1 for 10 times. 18 categories of morphological features of pulmonary nodules including internal and surrounding structure were labeled. Following radiomics features are extracted: first order features, shaped based features, Gray level cooccurrence matrix (GLCM) features, Gray level size zone matrix (GLSZM) features, Gray level run length matrix (GLRLM) features and Gray level dependence matrix (GLDM) features. Chi-square test and F1 test selected morphology features, and LASSO selected radiomics features. Logistic regression was used to establish models. Receiver operating characteristic (ROC) curves evaluated the effectiveness and Delong analysis compared ROC statistic difference among three models. 
Results:
In validation cohorts, areas under curve (AUC) of morphological model, radiomics model and combined model of distinguishing MIAs from IACs were 0.88, 0.87, 0.89, the sensitivity (SE) were 0.68, 0.81, 0.83 and specificity (SP) were 0.93, 0.79, 0.87. There was no statistically significant difference in AUC between three models (P> 0.05). 
Conclusion: 
Morphological model, radiomics model and combined model all have high efficiency in the differentiation between MIAs and IACs, and have potential to provide noninvasive assistant information for clinical decision-making.