Elaboration of a New Radiomics Strategy Based on Peritumoral and Intratumoral Features from Lung CT Images for the Pretherapy Prediction of the Histological Subtype in Patients with Nonsmall-Cell Lung Cancer

Abstract

Background: Pretherapy prediction of the histological subtype in patients with nonsmall-cell lung cancer (NSCLC) is of critical importance for determining optimal therapeutic strategy. This study aimed to evaluate a new radiomics strategy that incorporates peritumoral and intratumoral features extracted from lung CT images with ensemble learning for pretreatment prediction of two major subtypes of NSCLC, lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD).\ Methods: A total of 105 patients (47 LUSC and 58 LUAD) were involved in this study and were divided into training (n=73) and testing (n=32) cohorts. All patients underwent a preoperative CT scan. Seven categories of radiomics features were calculated from the intra- and peritumoral regions, constituting 3078 features from each patient’s dataset. Student’s t -tests in combination with three widely used feature selection methods, respectively, were adopted for dimension reduction and optimal feature subset determination. An ensemble classifier that was generated with five commonly used machine learning classifiers, was employed with the optimal features for classification model development, and the performance was quantitatively evaluated using the classification model with both training and testing cohorts for the prediction of LUSC and LUAD. Findings: The classification models developed by using optimal feature subsets determined from intratumoral region and peritumoral region with the ensemble classifier achieved mean area under the curve (AUC) of 0.87, 0.83 in the training cohort and 0.66, 0.60 in the testing cohort, respectively. The model developed by using the optimal feature subset selected from both intra- and peritumoral regions with the ensemble classifier achieved great performance improvement, with AUC of 0.87 and 0.78 in both cohorts, respectively. Interpretations: The proposed new radiomics strategy that extracts image features from the intra- and peritumoral regions with ensemble learning, could greatly improve the diagnostic performance for the histological subtype stratification in patients with NSCLC. Funding: This work was supported by the National Natural Science Foundation of China (No. 81901698), and Young Eagle plane of High Ambition Project (No. 2020CYJHXXP). Declaration of Interest: None to declare. Ethical Approval: This retrospective study was approved by the institutional ethics review board of Xijing Hospital, and informed content was waived.