1222P - Predicting pathological complete response to neoadjuvant chemoimmunotherapy in resected NSCLC with radiomic signatures

Background

Approximately 25% of NSCLC patients are eligible for curative surgery, but few achieve pathological complete responses (pCR) with neoadjuvant chemotherapy. Trials have shown pCR rates exceeding 15% with perioperative immunotherapy (IO). However, traditional predictors like PD-L1 expression are insufficient for predicting pCR. This study evaluates whether radiomic texture and tumor vessel features on pre-treatment CT scans can predict pCR in resectable NSCLC patients receiving neoadjuvant IO therapy before surgery.

Methods

The study comprised 62 NSCLC patients (median age: 68, range: 34 to 80) from the Cleveland Clinic. They underwent neoadjuvant platinum-doublet chemotherapy with an anti-PD-1 inhibitor before surgery. Pathological responses were evaluated based on residual viable tumor percentage, defining pCR as 0% residual tumor. Radiomic features capturing tumor heterogeneity and quantitative vessel tortuosity (QVT) were extracted from pre-treatment CT images. Patients were split into training (St = 20) and validation (Sv = 42) sets, ensuring equal pCR and non-pCR representation in St. A linear discriminant classifier (LDA) trained on St was evaluated on Sv using the area under the curve (AUC) metric.

Results

Among the 62 patients analyzed, 21 (34%) achieved a pCR upon surgical assessment. Using four radiomic features, the AUC for predicting pCR was 0.86 (95% CI: 0.82–0.9) in St and 0.81 (95% CI: 0.77–0.84) in Sv. A significant difference was found between patients with and without pCR, in low and high PD-L1 groups (P = 0.0023). Integrating radiomics and PD-L1 expression enhanced predictive performance in Sv (AUC = 0.83). Baseline tumor volume before surgery showed no significant correlation with achieving a pCR (r = 0.02, P = 0.83). Conversely, vessel curvature correlated negatively with pCR (r = -0.28, P = 0.027). This may hinder therapeutic agent delivery to tumor cells via narrower lumens, potentially reducing pCR likelihood.

Conclusions

Identifying patients likely to achieve pCR aids in treatment planning. Initial findings suggest radiomic texture and QVT features from baseline CT predict pCR likelihood in NSCLC patients, warranting large-scale, multisite validation.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

Anant 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 Kidney Precision Medicine Project (KPMP) Glue Grant and sponsored research agreements from Bristol Myers-Squibb, Boehringer Ingelheim, Eli-Lilly, and AstraZeneca.

Disclosure

A. Madabhushi: Financial Interests, Personal, Advisory Board, Serve on SAB and consult: SimbioSys; Financial Interests, Personal, Advisory Board: Aiforia, Picture Health; Financial Interests, Personal, Full or part-time Employment: Picture Health; Financial Interests, Personal, Ownership Interest: Picture Health, Elucid Bioimaging, Inspirata Inc; Financial Interests, Personal, Royalties: Picture Health, Elucid Bioimaging; Financial Interests, Institutional, Funding: AstraZeneca, Bristol Myers Squibb, Boehringer Ingelheim, Eli Lilly. All other authors have declared no conflicts of interest.