Spatial Proximity and Relative Distribution of Tumor-Infiltrating Lymphocytes and Macrophages Predict Survival in Melanoma.

Tumor microenvironment plays a crucial role in primary cutaneous melanoma (CM) progression. Although the role of tumor-infiltrating lymphocyte (TIL) density has been known for a long time, its spatial distribution and impact with or without tumor-associated macrophages (TAMs) remain controversial. Herein, we investigated spatial proximity between tumor cells and immune cells in 113 primary CM and its correlation with disease-free (DFS) and overall survival (OS). The study cohort included clinical stage II (n = 79) and stage III (n = 34) primary CM with a Breslow thickness of >2 mm (with a median age of 64 years, including 72 men and 41 women). In univariate models, patients with SOX10+ melanoma cells with high proximity to CD8+ TILs in a 20 µm radius showed longer DFS (hazard ratio [HR], 0.58; 95% CI, 0.36-0.93; P = .025) and OS (HR, 0.55; 95% CI, 0.32-0.92; P = .023). Furthermore, at multivariate combined analysis, patients with SOX10+ melanoma cells with high proximity to CD8+ TILs or low proximity to CD163+ TAMs in a 20 µm radius showed an increased OS (aHR, 0.37; 95% CI, 0.14-0.96; P = .04) compared with melanoma patients with low proximity to CD8+ TILs or high proximity to CD163+ TAMs. In a subgroup analysis including 92 patients, a significant negative impact on DFS (aHR, 4.49; 95% CI, 1.73-11.64; P = .002) and OS (aHR, 3.97; 95% CI, 1.37-11.49; P = .01) was observed in sentinel lymph node (SLN)-negative patients with a high proximity of CD163+ TAMs to CD8+ TILs. These findings could help identify high-risk patients in the context of thick melanoma and a negative SLN. Our study suggests the importance of quantifying not only the density of immune cells but also the individual and combined relative spatial distributions of tumor cells and immune cells for clinical outcomes in SLN-negative primary CM patients.

Tumor-Infiltrating Lymphocyte Recognition in Primary Melanoma by Deep Learning Convolutional Neural Network.

The presence of tumor-infiltrating lymphocytes (TILs) is associated with a favorable prognosis of primary melanoma (PM). Recently, artificial intelligence (AI)-based approach in digital pathology was proposed for the standardized assessment of TILs on hematoxylin and eosin-stained whole slide images (WSIs). Herein, the study applied a new convolution neural network (CNN) analysis of PM WSIs to automatically assess the infiltration of TILs and extract a TIL score. A CNN was trained and validated in a retrospective cohort of 307 PMs including a training set (237 WSIs, 57,758 patches) and an independent testing set (70 WSIs, 29,533 patches). An AI-based TIL density index (AI-TIL) was identified after the classification of tumor patches by the presence or absence of TILs. The proposed CNN showed high performance in recognizing TILs in PM WSIs, showing 100% specificity and sensitivity on the testing set. The AI-based TIL index correlated with conventional TIL evaluation and clinical outcome. The AI-TIL index was an independent prognostic marker associated directly with a favorable prognosis. A fully automated and standardized AI-TIL appeared to be superior to conventional methods at differentiating the PM clinical outcome. Further studies are required to develop an easy-to-use tool to assist pathologists to assess TILs in the clinical evaluation of solid tumors.

Effects of Molecular Heterogeneity on Survival of Patients With BRAFV600-Mutated Melanoma Treated With Vemurafenib With or Without Cobimetinib in the coBRIM Study.

PURPOSE: The treatment of advanced BRAFV600-mutated melanomas with BRAF inhibitors (BRAFi) has improved survival, but the efficacy of BRAFi varies among individuals and the development of acquired resistance to BRAFi through reactivation of mitogen-activated protein kinase (MAPK) signaling is common. We performed an exploratory, retrospective analysis to investigate the effects of BRAFV600 allelic balance, coexisting oncogene mutations, cell proliferation signaling levels, and loss of PTEN expression on progression-free survival (PFS) in patients in the phase III coBRIM study, which compared the combination of the MEK inhibitor cobimetinib with the BRAFi vemurafenib versus vemurafenib as monotherapy. METHODS: Baseline tumor samples from the intention-to-treat population were analyzed by targeted deep sequencing at a median coverage of 3,600× and by immunohistochemistry for cell proliferation markers, BRAFV600E, and PTEN. The association of these biomarkers with PFS was assessed by Cox proportional hazards modeling. Gene expression in relation to loss of PTEN was profiled by RNA sequencing in 205 patient samples and 42 BRAFV600-mutated melanoma cell lines. RESULTS: Neither BRAFV600 allelic balance nor coexisting mutations in the RAS/RAF/RTK pathway affected PFS in either treatment group. Increased baseline MAPK signaling and cell proliferation did not affect PFS in patients treated with cobimetinib combined with vemurafenib. PTEN loss was associated with reduced PFS in patients treated with vemurafenib alone but not in patients treated with cobimetinib combined with vemurafenib. CONCLUSION: Deeper inhibition of the MAPK pathway through targeting of both MEK and BRAF may override the effects of tumor heterogeneity and improve PFS in all patients with advanced BRAFV600 melanoma.