Pathomic immune biomarkers define recurrence risk in early-stage melanoma

Background: There is an urgent need for biomarkers in early-stage melanoma because the benefit of adjuvant immunotherapy is marginal while the toxicity is considerable. Immune surveillance is a key mechanism limiting melanoma progression, but no immune biomarkers have yet been sufficiently validated for clinical use. Methods: We validate 3 digital pathology biomarkers, all previously trained in published cohorts and testable in formalin fixed paraffin embedded specimens, for correlation with recurrence free survival and distant metastatic free survival: (1) tumor infiltrating lymphocytes identified using artificial intelligence in digital images (eTILs), (2) nanoString melanoma immune profile (MIP), and (3) quantitative immunofluorescence of CD8+ cells. Results: Three immune biomarkers were validated and found to correlate with recurrence at 36 months by receiver operating curve analysis (eTILs area under the curve [AUC] = 0.706, P = .002; MIP AUC = 0.775, P < .001; and CD8% AUC = 0.682, P = .009) and define high and low risk groups using Kaplan Meier (KM) curves within the IIA-IIID population (P = .007 for eTILs and P < .001 for MIP and CD8%) and within the difficult to treat IIB-IIIA subset (P = .005, P < .001, P < .001, respectively). Immune biomarkers enhance clinical predictors (P = .012, P < .001, P = .004), and correlate with distant metastatic recurrence (P = .031, P = .047, P = .014, respectively). Network analysis shows that stage and depth combined with pathomic immune features yields the highest correlation with recurrence (AUC = 0.875, P < .001). Conclusions: Immune biomarkers should be prospectively validated in stage II-III melanoma for the purpose of avoiding overtreatment of low-risk patients and to stratify high-risk patients for clinical trials.