Abstract
Growing evidence suggests that the efficacy of immunotherapy in non-small cell lung cancers (NSCLCs) is associated with the immune microenvironment within the tumor. We aimed to explore radiologic phenotyping using a radiomics approach to assess the immune microenvironment in NSCLC. Two independent NSCLC cohorts (training and test sets) were included. Single-sample gene set enrichment analysis was used to determine the tumor microenvironment, where type 1 helper T (Th1) cells, type 2 helper T (Th2) cells, and cytotoxic T cells were the targets for prediction with computed tomographic (CT) radiomic features. Multiple algorithms were in the modeling followed by final model selection. The training dataset comprised 89 NSCLCs and the test set included 60 cases of lung squamous cell carcinoma and adenocarcinoma. A total of 239 CT radiomic features were used. A linear discriminant analysis model was selected for the final model of Th2 cell group prediction. The area under the curve value of the final model on the test set was 0.684. Predictors of the linear discriminant analysis model were skewness (total and outer pixels), kurtosis, variance (subsampled from delta [subtraction inner pixels from outer pixels]), and informational measure of correlation. The performances of radiomics on test set of Th1 and cytotoxic T cell were not accurate enough to be predictable. A radiomics approach can be used to interrogate an entire tumor in a noninvasive manner and provide added diagnostic value to identify the immune microenvironment of NSCLC, in particular, Th2 cell signatures.
Highlights
We evaluated a total of 239 computed tomographic (CT) radiomic features, which were divided into seven groups as follows: three physical features, 59 histogram-based features, 10 shape features, 95 local features, 63 filter-based features (LoG filter), three fractal model-based features, and six sigmoid features
Random forest, penalized discriminant analysis, and bagged classification and regression tree (CART) models performed well in the training set of Th1 cells (AUC = 0.751, 0.711, and 0.741, respectively) and cytotoxic T cells (AUC = 0.681, 0.674, and 0.647, respectively) predictions (Tables 3 and 4)
Through a prediction performance test using a The Cancer Genome Atlas (TCGA) test set, we demonstrated that the radiomic prediction for Th2 cell signatures of non-small cell lung cancers (NSCLCs) was feasible (AUC = 0.684), even though the performances of radiomics on the test set of Th1 and cytotoxic T cells were not accurate enough to be predictable
Summary
Immune checkpoint blockade therapy, an anti-cancer treatment that potentiates the ability of the immune system to recognize and destroy cancer cells, has become a standard in the care of PLOS ONE | https://doi.org/10.1371/journal.pone.0231227 April 6, 2020Radiomics for tumor microenvironment in NSCLCNational Research Foundation of Korea grant funded by the Korean government (Ministry of Science, ICT, & Future Planning) (No NRF2016R1A2B4013046 and NRF2017M2A2A7A02018568) URL of each funder website: https://www.mohw.go.kr and http:// english.msip.go.kr The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
