Immune Spatial Organization Predicts Distant Metastasis Risk in Aggressive Localized Prostate Cancer.

Abstract

Computational pathology has emerged as an attractive option for improving risk stratification in prostate cancer (PCa), but most approaches either lack interpretability or focus solely on tumor morphology. We aimed to identify an interpretable, immune microenvironment-derived computational pathology biomarker for PCa. We identified two cohorts (Discovery and Validation) with M0 PCa (n=490) who were treated with radical prostatectomy with H&E-stained whole-slide images (WSIs) and data on distant metastasis (DM). We identified a third cohort from TCGA with M0 PCa (n=326) with prostatectomy WSIs and bulk sequencing. Immune cells were identified from WSIs using a deep learning method (CellViT), and spatially dense immune clusters were quantified using DBSCAN. CIBERSORTx was utilized for immune cell deconvolution and TRUST4 for immune receptor repertoire reconstruction. Median follow-up was 12.6 (Discovery) and 8.1 years (Validation). 14% (n=37, Discovery) and 17% (n=38, Validation) had Gleason 8-10 disease. Immune cell abundance was not associated with DM. In Discovery, increased immune cluster was associated with decreased risk of DM for Gleason 8-10 (adjusted hazard ratio 0.42, 95% confidence interval 0.19-0.93) but not Gleason 6-7 (1.26, 0.77-2.05; Pint=0.020), with similar results in Validation (Gleason 8-10 0.60, 0.37-0.98; Gleason 6-7 1.19, 0.74-1.91; Pint=0.043). In Gleason 8-10 but not 6-7, high-cluster samples were enriched for CD8+ T cells, activated memory CD4+ T cells, Tregs (P≤0.037), and clonal T cell populations (P≤0.039). These findings propose immune spatial clustering as a novel, interpretable computational pathology biomarker and provide insight into the unique immune features of high-grade PCa.