Abstract
BackgroundThe present study compared the predictive performance of pretreatment computed tomography (CT)-based radiomics signatures and clinicopathological and CT morphological factors for ligand programmed death-ligand 1 (PD-L1) expression level and tumor mutation burden (TMB) status and further explored predictive models in patients with advanced-stage non-small cell lung cancer (NSCLC).MethodsA total of 120 patients with advanced-stage NSCLC were enrolled in this retrospective study and randomly assigned to a training dataset or validation dataset. Here, 462 radiomics features were extracted from region-of-interest (ROI) segmentation based on pretreatment CT images. The least absolute shrinkage and selection operator (LASSO) and logistic regression were applied to select radiomics features and develop combined models with clinical and morphological factors for PD-L1 expression and TMB status prediction. Ten-fold cross-validation was used to evaluate the accuracy, and the predictive performance of these models was assessed using receiver operating characteristic (ROC) and area under the curve (AUC) analyses.ResultsThe PD-L1-positive expression level correlated with differentiation degree (p = 0.005), tumor shape (p = 0.006), and vascular convergence (p = 0.007). Stage (p = 0.023), differentiation degree (p = 0.017), and vacuole sign (p = 0.016) were associated with TMB status. Radiomics signatures showed good performance for predicting PD-L1 and TMB with AUCs of 0.730 and 0.759, respectively. Predictive models that combined radiomics signatures with clinical and morphological factors dramatically improved the predictive efficacy for PD-L1 (AUC = 0.839) and TMB (p = 0.818). The results were verified in the validation datasets.ConclusionsQuantitative CT-based radiomics features have potential value in the classification of PD-L1 expression levels and TMB status. The combined model further improved the predictive performance and provided sufficient information for the guiding of immunotherapy in clinical practice, and it deserves further analysis.
Highlights
Non-small cell lung cancer (NSCLC) accounts for 75%–85% of all lung cancers
Predictive models that combined radiomics signatures with clinical and morphological factors dramatically improved the predictive efficacy for programmed deathligand 1 (PD-L1) (AUC = 0.839) and tumor mutation burden (TMB) (p = 0.818)
Antibodies binding on the PD-1/PD-L1 have been identified in non-small cell lung cancer (NSCLC) patients who were not sensitive to platinum-based chemotherapy [5, 6]
Summary
Non-small cell lung cancer (NSCLC) accounts for 75%–85% of all lung cancers. Approximately 80% of NSCLC cases are diagnosed at an advanced stage, when curative surgery is not an ideal option [1]. Systemic platinum-based doublet chemotherapy is the standard treatment strategy and may provide survival benefits for locally advanced patients, with progression-free survival (PFS) of 3.6–4.8 months and median overall survival (mOS) ranging from 7.9 to 10.3 months [2] These limited and unsatisfactory survival times have necessitated the development of novel treatment modalities, such as immunotherapy, for patients with advanced-stage NSCLC [3]. The present study compared the predictive performance of pretreatment computed tomography (CT)-based radiomics signatures and clinicopathological and CT morphological factors for ligand programmed death-ligand 1 (PD-L1) expression level and tumor mutation burden (TMB) status and further explored predictive models in patients with advanced-stage non-small cell lung cancer (NSCLC)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.