AI-based pathologic biomarker for pathologic downstaging in patients with muscle-invasive bladder cancer undergoing cystectomy after neoadjuvant nivolumab, gemcitabine, and cisplatin: BLAAST-1 Trial.

Abstract

e16566 Background: The BLASST-1 study is a multi-center phase II trial evaluating the combination of neoadjuvant nivolumab with gemcitabine-cisplatin (N+GC) for muscle-invasive bladder cancer (MIBC) patients undergoing radical cystectomy (RC). The primary endpoint was pathologic down staging (PaR; ≤pT1N0). We previously reported a PaR rate of 65.8% (Gupta S et al. ASCO GU 2020). Given the lack of validated and optimal biomarkers to predict PaR, we studied the association of an AI-based pathologic biomarker measuring pre-treatment morphological features with PaR. Methods: Forty-one patients with MIBC (cT2-T4a, N≤1, M0) and candidates for RC were enrolled between Feb 2018 and June 2019 (cT2N0 90%, cT3N0 7%, cT4N1 3%). Thirty-six patients had transurethral resection of bladder cancer (TURBT) with pre-treatment diagnostic specimens available for analysis. Patients received four cycles of N+GC followed by RC within 8 weeks. A board-certified pathologist selected diagnostic regions from TURBT-derived representative H&E diagnostic slides for each patient. To compute the pathological biomarker, a proprietary deep-learning algorithm (Valar Labs, Palo Alto, CA) first segmented nuclei from digital whole-slide images of the H&E specimens to extract quantitative histological features. The Valar pathologic biomarker was then computed from features associated with immune infiltration and morphological characteristics of neoplastic cells. The Valar biomarker was split based on unsupervised clustering into two groups: Valar-High was associated with PaR and Valar-Low with no PaR. PD-L1 cutoff of 1% was used for dichotomization. To compare the Valar biomarker with PD-L1, a subcohort of 33 patients with available PD-L1 scores were analyzed. T-tests and diagnostic performance metrics were used to distinguish between PaR response rates in each cluster group across tests. Results: Patients designated Valar-High (n=23) had higher PaR compared to no PaR in the Valar-Low (n=13) group (PAR 78.3% vs 38.4%, respectively, p<0.008). Compared to PD-L1, the Valar biomarker had higher sensitivity (85.7 vs 57.1%), specificity (66.6 vs 66%), positive predictive value (81.8 vs 75.0%), negative predictive value (72.7 vs 47.0%), and accuracy (78.8 vs 60.6%) across both cohorts. The Valar biomarker was not correlated to PD-L1 (r^2=0.029) or sex (22 male, 14 female). The combined Valar-High or PD-L1 High test had a high sensitivity for PaR (95.2%). Conclusions: In this hypothesis-generating study, pre-treatment morphological features measured by the AI-based Valar pathologic biomarker identified responders to neoadjuvant N+GC in MIBC. Further prospective studies are needed to study the prognostic vs. predictive utility of this biomarker.