Neoadjuvant immune checkpoint blockade in high-risk resectable melanoma

Abstract

Preclinical studies suggest that treatment with neoadjuvant immune checkpoint blockade is associated with enhanced survival and antigen-specific T cell responses compared with adjuvant treatment¹; however, optimal regimens have not been defined. Here we report results from a randomized phase 2 study of neoadjuvant nivolumab versus combined ipilimumab with nivolumab in 23 patients with high-risk resectable melanoma ( NCT02519322 ). RECIST overall response rates (ORR), pathologic complete response rates (pCR), treatment-related adverse events (trAEs) and immune correlates of response were assessed. Treatment with combined ipilimumab and nivolumab yielded high response rates (RECIST ORR 73%, pCR 45%) but substantial toxicity (73% grade 3 trAEs), whereas treatment with nivolumab monotherapy yielded modest responses (ORR 25%, pCR 25%) and low toxicity (8% grade 3 trAEs). Immune correlates of response were identified, demonstrating higher lymphoid infiltrates in responders to both therapies and a more clonal and diverse T cell infiltrate in responders to nivolumab monotherapy. These results describe the feasibility of neoadjuvant immune checkpoint blockade in melanoma and emphasize the need for additional studies to optimize treatment regimens and to validate putative biomarkers.

Figure 1.. Trial schema.

Patients with resectable clinical stage III or oligometastatic stage IV melanoma were stratified by stage and PD-L1 status and randomized in 1:1 ratio to neoadjuvant nivolumab 3 mg/kg for up to 4 doses (Arm A) or ipilimumab 3 mg/kg with nivolumab 1 mg/kg for up to 3 doses (Arm B), followed by surgical resection and then adjuvant nivolumab for 6 months. Primary endpoint of the trial was pathologic complete response (pCR) rate, defined as complete eradiation of tumor. Additional secondary endpoints included overall response rate by RECIST 1.1, survival outcomes, and immune correlates. Longitudinal tumor and blood samples were collected at baseline, prior to cycle 2, prior to cycle 3, and at the time of surgery followed by adjuvant blood collection every 3 months at the time of restaging.

Figure 2.. Radiographic and pathologic responses to neoadjuvant nivolumab and combination ipilimumab with nivolumab.

a, Waterfall plots of overall response rates (ORR) by RECIST 1.1 at 8 weeks and surgical pathologic complete responses (pCR) for the patients treated with nivolumab monotherapy (n=12, 25% RECIST ORR and pCR rate). Two of the patients progressed beyond resectability and did not receive surgical resection. b, Combination ipilimumab with nivolumab (n=11) yielded improved outcomes compared to nivolumab, 73% (95% CI 39–94%, p=0.039) RECIST ORR and 45% (95% CI 17–77%, p=0.40) pCR rate using two-sided Fisher’s Exact Test. c, Only one patient on the trial who had a pCR also had a radiographic complete response, with the other pathologic responders having partial responses.

Figure 3.. Kaplan-Meier Estimates of Survival.

a,b,c, Kaplan-Meier estimates of progression-free survival (PFS), distant metastasis-free survival (DMFS), and overall survival (OS) by two-sided log-rank test are shown by treatment group. Patients were followed for a median of 15.0 months (range 5.8–22.6) in nivolumab (N) monotherapy arm (n=12) and 15.6 months (range 5.8–24.4) in the combination therapy (I+N) arm (n=11). Median survival endpoints have not been reached. Combination ipilimumab with nivolumab resulted in improved survival outcomes compared to nivolumab monotherapy, though this did not reach significance. For PFS, survival rates of 82% (95% CI 45–95%) at 17.2 months (mo) with I+N versus 58% (27–80%) at 22.6 mo with N, p=0.19. For DMFS, rates of 91% (51–99%) at 17.2 mo with I+N versus 67% (34–86%) at 22.6 mo with N, p=0.17. For OS, rates of 100% (100–100%) at 24.4 mo with I+N versus 76% (31–94%) at 22.6 mo with N, p=0.18.

Figure 4.. Immune correlates of response to immune checkpoint blockade (ICB).

Longitudinal tumor biopsies were obtained at baseline and early on-treatment in patients on neoadjuvant ICB therapy. The tumor molecular and immune microenvironment was compared between non-responders (NR) and responders (R), with responders defined as patients achieving a complete or partial response by RECIST 1.1. a, Total mutational burden, defined as the sum of non-synonymous exonic mutations, is displayed (n=8 NR and 7 R). b,c, Quantification by immunohistochemistry of CD8 cell count density (n=11 NR and 10 R at baseline, n=11 NR and 9 R on-treatment) and PD-L1 H score (28–8 clone) (n=11 NR and 10 R at baseline, n=11 NR and 9 R on-treatment). d, Supervised hierarchical clustering summarizes expression of additional lymphoid markers (Granzyme B, CD4, FoxP3, CD20, and PD-1) using standard immunohistochemistry with blue indicating lower count density and red higher count density (or H score for PD-L1). e, Volcano plots of two-sided pairwise Mann-Whitney comparisons of multiplex immunohistochemistry marker expression between NR and R in baseline (green) and on-treatment (red) samples in the combined treatment arms (n=11 NR and 11 R at baseline, n=10 NR and 6 R on-treatment). Immune marker expression was assessed on CD45 positive cells and quantified as expression per area of assayed tissue. f, T cell clonality scores between NR and R at baseline (left, n=10 NR and 9 R) and on-treatment (right, n=10 NR and 9 R). g, Analysis of change in T cell repertoire was performed using differential abundance analysis. Clones that significantly increase (red) or decrease (blue) in frequency from baseline (closed circles) to on-treatment (open circles) are shown for whole clinical trial cohort. h,i, Change in T cell repertoire was assessed for number of significantly expanded clonotypes (n= 6 NR and 3 R for nivolumab treated patients, n=3 NR and 6 R for combination ICB treated patients) and Morisita Overlap index (n=6 NR ad 3 R for nivolumab treated patients, n=3 NR and 6 R for combination ICB treated patients). For a-c, f, h-I, Bar heights indicate median values, and interquartile ranges are presented in addition to individual data points. Comparisons were made using two-sided Mann-Whitney U tests.