Performance of radiomics models derived from different CT reconstruction parameters for lung cancer risk prediction.

ABSTRACT:

Background

This study analysed the performance of radiomics features extracted from computed tomography (CT) images with different reconstruction parameters in differentiating malignant and benign pulmonary nodules.

Methods

We evaluated routine chest CT images acquired from 148 participants with pulmonary nodules, which were pathologically diagnosed during surgery in West China Hospital, including a 5 mm unenhanced lung window, a 5 mm unenhanced mediastinal window, a 5 mm contrast-enhanced mediastinal window and a 1 mm unenhanced lung window. The pulmonary nodules were segmented, and 1409 radiomics features were extracted for each window. Then, we created 15 cohorts consisting of single windows or multiple windows. Univariate correlation analysis and principal component anal

SUBMITTER: Zhang R 

PROVIDER: S-EPMC10116652 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature