Background: There are no current standard of care options for patients (pts) with muscle-invasive bladder cancer (MIBC) ineligible for cisplatin-based chemotherapy (cisplatin). This trial investigated the safety and efficacy of escalating doses of neoadjuvant atezolizumab (ATZ) prior to radical cystectomy (RC) (NCT02451423). Methods: This single-arm, single institution, phase II trial investigated treatment with 1 (n=6), 2 (n=6) or 3 (n=11) cycles of ATZ (1200 mg IV every 3 weeks) in pts with MIBC. Key inclusion criteria were urothelial carcinoma of the bladder (T2-T4a,N0-1,M0), cisplatin-ineligibility, and eligibility for RC. High-risk pts (>pT2 or LN+ at RC) could receive adjuvant ATZ for up to 16 total cycles. Primary efficacy endpoint was pathologic complete response (pCR; pT0/Ta/TisN0). Secondary endpoints included rate of pathologic downstaging (≤T1N0), 2-year recurrence-free survival (RFS), overall survival (OS), and biomarker assessments of pre and post-treatment biopsies. Pts had RC between 7/2016 and 6/2021. The censor date for survival outcomes was 9/10/2023, representing the final efficacy analysis. Results: A total of 23 pts received ATZ; 1 pt was excluded from efficacy analyses due to lack of confirmed MIBC (≥T2). Among 22 included pts, median age was 70, 74% were men, 83% Caucasian; reasons for cisplatin-ineligibility were renal impairment (37%), hearing loss (27%) or neuropathy (9%); remainder declined cisplatin (27%). At enrollment, cT2/T3/T4 rates were 77%, 14%, and 9%, while 9% were cLN+. All pts completed intended treatment and had RC in the defined timeframe (>3 weeks from last and <12 weeks from first treatment). pCR at RC was 14% (3/22), occurring in pts receiving 1 and 2 cycles of ATZ. Pathologic downstaging (≤pT1N0) was achieved in 23% (5/22), occurring at all three dose levels. Adjuvant ATZ was given to 8 pts. Another 4 pts received off-study adjuvant therapy with cisplatin (3) or nivolumab (1). After median follow-up of 51.4 months from RC, mRFS and mOS were Not Reached. Two-year RFS and OS were 77% and 90%. In 13 pts with available paired pre and post treatment samples, there was significant increase in T-cell % following ATZ (Wilcoxon signed rank test, p<0.05), driven by increase in % and density of CD8+ T-cells (p<0.05). All T-cell populations were significantly more abundant in tumor than in adjacent normal tissue post-treatment but not pre-treatment (CD3⁺,CD3⁺CD8⁺, CD3⁺CD4⁺, p<0.001 for all; CD4⁺FOXP3⁺, p=0.01). Conclusions: Neoadjuvant ATZ results in durable long-term survival rates in cisplatin-ineligible pts with MIBC. These data are comparable to previously reported trials with immunotherapy based regimens, despite a lower pCR rate. Changes suggestive of T-cell migration into the tumor microenvironment were observed following ATZ treatment. Clinical trial information: NCT02451423.