AUTHOR=Liu Jianjing , Sui Chunxiao , Bian Haiman , Li Yue , Wang Ziyang , Fu Jie , Qi Lisha , Chen Kun , Xu Wengui , Li Xiaofeng 

TITLE=Radiomics based on 18F-FDG PET/CT for prediction of pathological complete response to neoadjuvant therapy in non-small cell lung cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 14 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1425837

DOI=10.3389/fonc.2024.1425837

ISSN=2234-943X

ABSTRACT=Purpose: This study aimed to establish and evaluate the value of integrated models involving 18 F-FDG PET/CT-based radiomics and clinicopathological information in prediction of pathological complete response (pCR) to neoadjuvant therapy (NAT) for NSCLC.: A total of 106 eligible NSCLC patients were included in the study. After volume of interest (VOI) segmentation, 2016 PET-based and 2016 CT-based radiomic features were extracted. To select an optimal machine learning model, a total of 25 models were constructed based on five sets of machine learning classifiers combined with five sets of predictive feature resources, including PET-based alone radiomics, CT-based alone radiomics, PET/CT-based radiomics, clinicopathological features and PET/CT-based radiomics integrated with clinicopathological features. Area under the curves (AUCs) of receiver operator characteristic (ROC) curves were used as the main outcome to assess the model performance. Results: The hybrid PET/CT derived radiomic model outperformed PET alone and CT alone radiomic models in prediction of pCR to NAT. Moreover, addition of clinicopathological information further enhanced the predictive performance of PET/CT derived radiomic model. Ultimately, the support vector machine (SVM)-based PET/CT radiomics combined clinicopathological information presented an optimal predictive efficacy with an AUC of 0.925 (95% CI 0.869-0.981) in the training cohort and an AUC of 0.863 (95% CI 0.740-0.985) in the test cohort. The developed nomogram involving radiomics and pathological type was suggested as a convenient tool to enable clinical application.The 18 F-FDG PET/CT-based SVM-radiomics integrated with clinicopathological information was an optimal model to non-invasively predict pCR to NAC for NSCLC.