Artificial intelligence (AI)–powered pathologic response (PathR) assessment of resection specimens after neoadjuvant atezolizumab in patients with non-small cell lung cancer: Results from the LCMC3 study.

Abstract

106 Background: PathR is an efficacy endpoint in Phase II and III neoadjuvant trials and is proposed as a surrogate for disease-free survival (DFS) and overall survival. Machine learning (ML)–based, automated approaches standardize quantification of areas of tumor bed and residual viable tumor. Here we show that automation may provide a scalable alternative to or complementary tool for manual assessment. Methods: We determined inter-reader variability for PathR among pathologists in the LCMC3 (NCT02927301) study and developed an AI-powered digital PathR assessment tool in line with manual consensus recommendations. Study cases were reviewed for PathR by a local site pathologist and 3 central expert pathologists (n = 127). When determined manually, major PathR (MPR) was defined as ≤10% viable tumor averaged per case. ML models were trained and validated by the PathAI research platform using digitized H&E-stained tumor sections. The digital PathR model predicted percent viable tumor for each case as the sum of the cancer epithelium area from each slide divided by the sum of tumor bed area for each slide. DFS (clinical cutoff: Oct 23, 2020) was reported for patients with manual and digital PathR assessment (n = 135). For digital MPR, we used a prevalence-matched cutoff that maintained the same proportion of patients as manual MPR. Results: Inter-reader agreement among 1 local and 3 central pathologists for manual PathR was good (n = 127; ICC = 0.87; 95% CI: 0.84-0.90). Agreement was 91% (κ = 0.82) on manual MPR and 98% (κ = 0.88) on pathologic complete response (pCR). 6 patients had unanimous pCR. Digital and manual PathR were strongly correlated (n = 135, Pearson r = 0.78) and digital PathR demonstrated an outstanding predictability for manual MPR (AUROC = 0.975). The range was 0%-60% for digital PathR and 0%-100% for manual PathR with a regression line slope < 1.0 (m = 0.303) indicating systematic differences between the methods, consistent with digital PathR using a high-resolution segmentation of cancer epithelium from stroma across each slide. Longer DFS was observed for MPR yes vs no with both digital and manual assessment (Table). Conclusions: This analysis showed good inter-reader agreement for manual and strong correlation of AI-powered digital and manual PathR. Comparable DFS rates for manual MPR and digital MPR are encouraging in the preliminary data. These data support further studies of digital PathR as a standardized and scalable tool to determine PathR. Clinical trial information: NCT02927301. [Table: see text]