Predicting chemotherapy response in non-small-cell lung cancer via computed tomography radiomic features: Peritumoral, intratumoral, or combined?

Abstract

PurposeThis study aims to evaluate the ability of peritumoral, intratumoral, or combined computed tomography (CT) radiomic features to predict chemotherapy response in non-small cell lung cancer (NSCLC).MethodsAfter excluding subjects with incomplete data or other types of treatments, 272 (Dataset 1) and 43 (Dataset 2, external validation) NSCLC patients who were only treated with chemotherapy as the first-line treatment were enrolled between 2015 and 2019. All patients were divided into response and nonresponse based on the response evaluation criteria in solid tumors, version 1.1. By using 3D slicer and morphological operations in python, the intra- and peritumoral regions of lung tumors were segmented from pre-treatment CT images (unenhanced) and confirmed by two experienced radiologists. Then radiomic features (the first order, texture, shape, et al.) were extracted from the above regions of interest. The models were trained and tested in Dataset 1 and further validated in Dataset 2. The performance of models was compared using the area under curve (AUC), confusion matrix, accuracy, precision, recall, and F1-score.ResultsThe radiomic model using features from the peritumoral region of 0–3 mm outperformed that using features from 3–6, 6–9, 9–12 mm peritumoral region, and intratumoral region (AUC: 0.95 versus 0.87, 0.86, 0.85, and 0.88). By the fusion of features from 0–3 and 3–6 mm peritumoral regions, the logistic regression model achieved the best performance, with an AUC of 0.97. This model achieved an AUC of 0.85 in the external cohort. Moreover, among the 20 selected features, seven features differed significantly between the two groups (p < 0.05).ConclusionsCT radiomic features from both the peri- and intratumoral regions can predict chemotherapy response in NSCLC using machine learning models. Combined features from two peritumoral regions yielded better predictions.

Radiomics model based on intratumoral and peritumoral features for predicting major pathological response in non-small cell lung cancer receiving neoadjuvant immunochemotherapy

“…). Additionally, it was demonstrated that different of peritumoral regions are associated with differences in treatment response (36) and exhibit distinct texture feature expressions (37). Our study confirmed a strong correlation between the peritumoral microenvironment and neoadjuvant immunochemotherapy in NSCLC.…”

The value of intratumoral and peritumoral radiomics features in differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes

“…Currently, several studies revealed that the radiomics model of the +3 mm peritumoral area effectively predicted chemotherapy response or EGFR mutation in non-small-cell lung cancer ( 19 , 29 , 30 ). This study of differentiating LPA and Non-LPA lung cancer also obtained the same peritumoral area (the PTV 0~+3 model had the best AUC in peritumoral models).…”

Using CT radiomic features based on machine learning models to subtype adrenal adenoma

“…Second, the Least Absolute Shrinkage and Selection Operator (LASSO) was employed to identify the final discriminative features. LASSO improves both prediction accuracy and model interpretability by combining the superior qualities of ridge regression and subset selection [ 28 ] and therefore is commonly used for feature selection [ 29 , 30 ]. LASSO can reduce the coefficient of variables (that have little effect on the regression) to 0 during the fitting process, hence achieving variable screening and complexity adjustment [ 31 , 32 ].…”