Abstract 301P
Background
ES-SCLC accounts for 70% of SCLC cases, characterized by widespread metastasis, with a 5-year survival rate of only 5%. For the past three decades, the standard treatment for SCLC has been platinum-based doublet chemotherapy (chemo), but recent FDA approvals of immunotherapy (IO) combined with chemo offer new hope. Identifying biomarkers to predict response to chemo or chemoIO remains a key research focus. This study investigates whether baseline CT radiomic texture and tumor vessel features can predict treatment response in these patients.
Methods
This study analyzed 376 ES-SCLC patients across three institutions. Responders, defined by RECIST 1.1, included those with complete or partial response, while non-responders had stable or progressive diseases. Radiomic features reflecting tumor heterogeneity and quantitative vessel tortuosity (QVT) were extracted from pretreatment CT scans. The training dataset (St) included 65 patients treated with chemo at one site, while validation was conducted on a combined dataset (Sv, n=311) comprising 188 patients treated with chemo and 123 patients treated with chemoIO (chemo + atezolizumab) from two other sites. A linear discriminant classifier (LDA) trained on St was evaluated on Sv using the AUC metric. The Objective Response Rate (ORR) was also assessed to compare the effectiveness of treatment between the chemo and chemoIO groups.
Results
Among 253 patients treated with chemo, 186 (74%) responded, while 101 (82%) of 123 patients treated with chemoIO responded. Using five radiomic features, the AUC for predicting response was 0.78 (95% CI: 0.76–0.80) in St and 0.75 (95% CI: 0.73–0.77) in Sv. The ORR in the chemoIO arm, as predicted by classifier, was 79%, compared to 70% in the chemo-alone arm. However, the p-value for the ORR comparison was not statistically significant (P=0.1), consistent with IMpower133, which showed a slightly higher response rate with atezolizumab, but with no significant difference.
Conclusions
Radiomic texture and QVT features from baseline CT scans show promise in predicting response to chemo and chemoIO in ES-SCLC, with the potential to guide treatment decisions and improve precision medicine.
Legal entity responsible for the study
A. Madabhushi.
Funding
Research reported in this publication was supported by the National Cancer Institute under award numbers R01CA26820701A1, R01CA249992-01A1, R01CA202752-01A1, R01CA208236-01A1, R01CA216579-01A1, R01CA220581-01A1, R01CA257612-01A1, 1U01CA239055-01, 1U01CA248226-01, 1U54CA254566-01, National Heart, Lung, and Blood Institute 1R01HL15127701A1, R01HL15807101A1, National Institute of Biomedical Imaging and Bioengineering 1R43EB028736-01, National Center for Research Resources under award number 1 C06 RR12463-01, National Institutes of Health under Award Number P50CA217691 from the Career Enhancement Program. VA Merit Review Award IBX004121A from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service the Office of the Assistant Secretary of Defense for Health Affairs, through the Breast Cancer Research Program (W81XWH-19-1-0668), the Prostate Cancer Research Program (W81XWH-15-1-0558, W81XWH-20-1-0851), the Lung Cancer Research Program (W81XWH-18-1-0440, W81XWH-20-1-0595), the Peer Reviewed Cancer Research Program (W81XWH-18-1-0404, W81XWH-21-1-0345, W81XWH-21-1-0160), the Lung Cancer research Program Career Development Award (HT9425-24-1-0095).
Disclosure
A. Madabhushi: Financial Interests, Personal, Advisory Board: Picture Health, Aiforia Inc, SimBioSys, Frederick National Laboratory; Financial Interests, Personal, Member of Board of Directors: Elucid Bioimaging, Inspirata Inc; Financial Interests, Personal, Other: AstraZeneca; Financial Interests, Personal, Research Grant: Boehringer Ingelheim, Eli-Lilly, Bristol Myers Squibb. All other authors have declared no conflicts of interest.