AUTHOR=Tang Xin , Liang Jiangtao , Xiang Bolin , Yuan Changfeng , Wang Luoyu , Zhu Bin , Ge Xiuhong , Fang Min , Ding Zhongxiang 

TITLE=Positron Emission Tomography/Magnetic Resonance Imaging Radiomics in Predicting Lung Adenocarcinoma and Squamous Cell Carcinoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.803824

DOI=10.3389/fonc.2022.803824

ISSN=2234-943X

ABSTRACT=Objective: To investigate the value of positron emission tomography (PET)/ magnetic resonance imaging (MRI) radiomics in predicting the histological classification of lung adenocarcinoma and lung squamous cell carcinoma.
Methods: PET/MRI radiomics and clinical data were retrospectively collected from 61 patients with lung cancer. According to the pathological results (surgery or fiberscopy), patients were divided into two groups: lung adenocarcinoma and squamous cell carcinoma, which were set as positive for adenocarcinoma (40 cases) and negative for squamous cell carcinoma (21 cases). The radiomics characteristics most related to lung cancer classification were calculated and selected using radiomics software, and the two groups of lung cancer were randomly divided into a training set (70%) and a test set (30%). Maximum relevance and minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods were used to select the features from each of the 2600 features extracted from MRI and PET using an uAI Research Portal software (United Imaging Intelligence, China). Eight optimal features were finally retained by 5-fold cross-validation, PET/MRI fusion model was constructed, and the model prediction ability was evaluated by receiver operating characteristic (ROC) curve and area under the curve (AUC) difference. 
Results: AUC of PET/MRI model training group and test group were 0.886 (0.787-0.985) and 0.847 (0.648-1.000), respectively. PET/MRI radiomics features revealed different degrees of correlation with lung adenocarcinoma and squamous cell carcinoma classification, as well as significant differences. 
Conclusion: The prediction model constructed based on PET/MRI radiomics features can predict the preoperative histological classification of lung adenocarcinoma and squamous cell carcinoma without seminality and repeatability. It can also provide an objective basis for accurate clinical diagnosis and individualized treatment, thus having important guiding significance for clinical treatment.