2023 World Conference on Lung Cancer (Posters)-P1.21. Radiomic Signature of Identifies Outcome and Prognosis to Immune Checkpoint Inhibitors (ICI) in PD-L1 Low Non-small Cell Lung Cancer (NSCLC)

P1.21. Radiomic Signature of Identifies Outcome and Prognosis to Immune Checkpoint Inhibitors (ICI) in PD-L1 Low Non-small Cell Lung Cancer (NSCLC) - PDF(Abstract)

Back to course

Pdf Summary

The study presented at WCLC 2023 focused on developing an AI-powered radiomic signature to predict the outcomes of immunotherapy in non-small cell lung cancer (NSCLC) patients. The researchers aimed to identify biomarkers that can effectively stratify patients who will benefit from immunotherapy, especially in the PD-L1 low patient population where there is no validated biomarker.<br /><br />The study included data from 231 NSCLC patients treated with immune checkpoint inhibitors (ICI) at two institutions. A deep learning segmentation model was used to delineate target lesions within the lung on pre-treatment chest CT scans. Radiomic features were then extracted from these lesions. A predictive model was trained using a Cox proportional hazards model and a radiomic risk score was generated.<br /><br />The results showed that the radiomic risk score was significantly associated with both progression-free survival (PFS) and overall survival (OS) in the testing set of patients. The risk score also predicted the best overall response (BOR). Importantly, in the subset of PD-L1 negative patients, the risk groups based on the radiomic risk score were prognostic of PFS and OS. Patients with low radiomic risk had a higher response rate to immunotherapy, while patients with high radiomic risk had a lower response rate.<br /><br />The findings suggest that the radiomic signature can effectively stratify NSCLC patients on immunotherapy, independent of PD-L1 status. This could be valuable in identifying additional patients who may benefit from immunotherapy and preventing non-responders from experiencing immune-related adverse events. However, further validation in larger cohorts is needed.<br /><br />In conclusion, this study demonstrates the potential of an AI-powered radiomic signature as a biomarker for predicting immunotherapy outcomes in NSCLC. It has the potential to better target immunotherapy and reduce overtreatment, particularly in PD-L1 low NSCLC patients.

Asset Subtitle

Nathaniel Braman

Meta Tag

Speaker Nathaniel Braman

Topic Pathology & Biomarkers: Biomarkers for Immuno-oncology

Keywords

WCLC 2023

AI-powered radiomic signature

immunotherapy

non-small cell lung cancer

NSCLC

biomarkers

PD-L1 low patients

immune checkpoint inhibitors

radiomic risk score

progression-free survival