Detailed spatial immunophenotyping of primary melanomas reveals immune cell subpopulations associated with patient outcome

Abstract

While the tumor immune microenvironment (TIME) of metastatic melanoma has been well characterized, the primary melanoma TIME is comparatively poorly understood. Additionally, although the association of tumor-infiltrating lymphocytes with primary melanoma patient outcome has been known for decades, it is not considered in the current AJCC melanoma staging system. Detailed immune phenotyping of advanced melanoma has revealed multiple immune biomarkers, including the presence of CD8+ T-cells, for predicting response to immunotherapies. However, in primary melanomas, immune biomarkers are lacking and CD8+ T-cells have yet to be extensively characterized. As recent studies combining immune features and clinicopathologic characteristics have created more accurate predictive models, this study sought to characterize the TIME of primary melanomas and identify predictors of patient outcome. We first phenotyped CD8+ T cells in fresh stage II primary melanomas using flow cytometry (n = 6), identifying a CD39+ tumor-resident CD8+ T-cell subset enriched for PD-1 expression. We then performed Opal multiplex immunohistochemistry and quantitative pathology-based immune profiling of CD8+ T-cell subsets, along with B cells, NK cells, Langerhans cells and Class I MHC expression in stage II primary melanoma specimens from patients with long-term follow-up (n = 66), comparing patients based on their recurrence status at 5 years after primary diagnosis. A CD39+CD103+PD-1- CD8+ T-cell population (P2) comprised a significantly higher proportion of intratumoral and stromal CD8+ T-cells in patients with recurrence-free survival (RFS) ≥5 years vs those with RFS <5 years (p = 0.013). Similarly, intratumoral B cells (p = 0.044) and a significantly higher B cell density at the tumor/stromal interface were associated with RFS. Both P2 and B cells localized in significantly closer proximity to melanoma cells in patients who remained recurrence-free (P2 p = 0.0139, B cell p = 0.0049). Our results highlight how characterizing the TIME in primary melanomas may provide new insights into how the complex interplay of the immune system and tumor can modify the disease outcomes. Furthermore, in the context of current clinical trials of adjuvant anti-PD-1 therapies in high-risk stage II primary melanoma, assessment of B cells and P2 could identify patients at risk of recurrence and aid in long-term treatment decisions at the point of primary melanoma diagnosis.

Keywords: Clinicopathological features; T cell phenotypes; immunophenotyping; primary melanoma; spatial pathology.

Figure 1

CD39+ tumor-resident CD8+ T cells are enriched for PD-1 in primary melanoma. (A) Flow cytometry was used to determine the residency status of CD8+ T cells in primary melanoma tissue dissociates (n = 6). Statistical differences were calculated using a non-parametric Kruskal-Wallis test (B) CD8+ T cell expression of CD39 was quantified. (C) CD39 expression was quantified in CD8+ T cell populations delineated by residency. (D) PD-1 expression was assessed by CD39 expression and tumor residency in CD8+ T cells. *p<0.05; **p<0.01, ***p<0.001.

Figure 2

Assessing the composition of the primary melanoma intratumoral immune infiltrate finds CD39+CD103+PD-1- (P2) CD8+ T cells and B cells associated with improved outcome. (A) Two sections of primary melanoma FFPE samples were separately stained for CD8+ T cells and immune cells using Opal mIHC. Cells from separate sections were aligned to create a single spatial plot for each tumor. (n=64) (B) 20X resolution images of sections stained for T cell panel (left) and immune cell panel (right). (C) All immune cell populations were quantified per mm² of tumor. Statistical differences were calculated using a Mann-Whitney unpaired non-parametric test. (D) Correlation plot of all immune cell populations, including % of each CD8+ T cell population, % Class I MHC positivity, and cells/mm² of T cells, CD8+ T cells, B cells, NK cells and Langerhans cells (LC). (E) Tumor composition, intratumoral immune population composition, and % of Class I MHC+ melanoma were calculated. (F) Each of the 8 CD8+ T cell populations were quantified as a % of the total intratumoral CD8+ T cell compartment. (G) Composition of the intratumoral CD8+ T cell compartment overall was compared based on patient outcome. (H) Composition of the intratumoral CD8+ T cell compartment for individual patients. *p<0.05; **p<0.01, ***p<0.001.

Figure 3

Proximity of melanoma to immune cell populations. (A) Cells from both panels were aligned and plotted onto a single spatial plot. Distances from melanoma to the nearest cell of each immune phenotype were calculated. (B) Average distance from melanoma to each immune phenotype was compared based on patient outcome. (C) % of melanoma cells within 20µm of each immune phenotype was compared based on patient outcome. Statistical differences were calculated using a Mann-Whitney unpaired non-parametric test.

Figure 4

Analysis of the tumor margin finds increased B cells in the stroma. (A) A 400µm region surrounding the tumor margin was subdivided into 8 50um-diameter bands extending into the tumor and stroma. (B) Immune cells were quantified per mm² in each band within the margin region and compared between outcome groups. (C) CD8+ T cell subsets were quantified per mm² within each band of the margin region and compared between outcome groups. Overall significance is shown in the legend, significance per margin region is shown on the graph. Statistical differences were calculated using a 2-way ANOVA. *p<0.05; **p<0.01, ***p<0.001, ****p<0.0001.

Figure 5

A combination of clinicopathologic characteristics with P1 CD8+ T cells is more predictive of patient outcome than Breslow thickness alone. A random survival forest model with exhaustive feature selection was fitted to identify the most predictive variables. RFS in the discovery cohort and validation cohorts were compared based on the three following factors: Breslow thickness (A–D), an MVA including P1 per mm² of tumor, Breslow thickness, ulceration, mitoses, and nodal status (Model 1, B–E), and an MVA including %P2 of tumor CD8+ T cells, P1 per mm² of tumor, Breslow thickness, ulceration, mitoses, and nodal status (Model 2, C–F). Kaplan-Meier curves (left) were plotted for each model. High risk and low risk groups were determined using cutoffs which maximized the sensitivity and specificity of the ROC analysis. Prognostic index (PI) cutoff values for high risk were ≥0.18 in Breslow thickness, ≥9.810 (equivalent to ≥2.25mm Breslow thickness), ≥10.102 in Model 1, and ≥9.469 in Model 2, with low-risk values being below these cutoffs. Statistical differences were calculated using a log-rank test. A prognostic index plot shows the cutoff value, indicated by a dotted line, between high- and low-risk patients (middle). ROC curve analysis was reported at 1,2,3,4, and 5 years after diagnosis (right).