Cleveland Clinic Foundation, Cleveland, OH
Khalid Jazieh , Mohammadhadi Khorrami , Anas M. Saad , Mohamed M. Gad , Vidya Sankar Viswanathan , Pingfu Fu , Prabhakar Rajiah , Anant Madabhushi , Nathan A. Pennell
Background: The current management of stage III non-small cell lung cancer (NSCLC) is chemoradiation followed by durvalumab consolidation. There are no robust biomarkers that predict benefit from this regimen. We evaluated the utility of novel imaging biomarkers (radiomics) to distinguish patients with stage III NSCLC who will benefit from treatment from those likely to progress despite therapy. Methods: Patients with stage III NSCLC treated at our center with chemoradiation and durvalumab from July 2017 - July 2019 were identified. We collected patient clinical outcomes, subtype of NSCLC, and PD-L1 expression as well as pre-treatment CT images. Images were split into training and test sets. Lung tumors were contoured on 3D-Slicer software and 1542 radiomic features capturing both intra- and peritumoral texture patterns were extracted. The primary endpoint of this study was progression-free survival (PFS), and the secondary objective was difference in PFS within high PD-L1 (≥50%) and low PDL1 (<50%) groups. We used the least absolute shrinkage and selection operator (LASSO) Cox regression model to build the radiomic signature for PFS. A risk score was computed according to a linear combination of selected features and their corresponding coefficients. High- and low-risk groups were defined based on median radiomics risk score. Multivariable Cox regression analysis was performed to evaluate the effect of each factor on PFS. We performed Kaplan–Meier survival analysis and log-rank tests to assess prognostic ability of the features. Results: We identified 118 patients who fit our criteria with available CT images and randomly divided them into a training (n=59) and a test set (n=59). The radiomic risk score was calculated using a linear combination of the top six selected features with corresponding coefficients. In a multivariable analysis using clinicopathologic and radiomic signatures, the radiomics risk-score and PD-L1 expression were found to be significantly associated with PFS in training (risk-score: HR = 2.3, 95% CI: [1.46 – 3.63], P = 0.0003; PD-L1: HR = 0.31, 95% CI: [0.081 – 0.96], P = 0.038) and test sets (risk-score: HR= 2.56, 95% CI: [1.75 – 4], P = 8.7e-05; PD-L1: HR = 0.27, 95% CI: [0.048 – 0.58], P = 0.005). Kaplan-Meier analyses showed a significantly shorter PFS in the high-risk radiomics group versus the low-risk group (P < 0.0001). The radiomics risk scores were also predictive of significant differences in PFS within both the low (p=0.0005) and high (p=0.0007) PD-L1 groups. Conclusions: Radiomic biomarkers from pre-treatment CT images in stage III NSCLC patients were predictive of PFS to chemoradiation followed by durvalumab and could predict outcomes regardless of PD-L1 level. Pre-treatment radiomics may allow early prediction of benefit and expedite more aggressive treatment for high-risk patients. Additional validation of these imaging biomarkers is warranted.
Disclaimer
This material on this page is ©2024 American Society of Clinical Oncology, all rights reserved. Licensing available upon request. For more information, please contact licensing@asco.org
Abstract Disclosures
2023 ASCO Annual Meeting
First Author: George R. Simon
2022 ASCO Annual Meeting
First Author: Udit Nindra
2020 ASCO Virtual Scientific Program
First Author: Khalid Jazieh
2023 ASCO Annual Meeting
First Author: Nicky Wong Zhun Hong