Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer with limited treatment options, which warrants identification of novel therapeutic targets. Deciphering nuances in the tumor microenvironment (TME) may unveil insightful links between anti-tumor immunity and clinical outcomes, yet such connections remain underexplored. Here we employed a dataset derived from imaging mass cytometry of 58 TNBC patient specimens at single-cell resolution and performed in-depth quantifications with a suite of multi-scale computational algorithms. We detected distinct cell distribution patterns among clinical subgroups, potentially stemming from different infiltration related to tumor vasculature and fibroblast heterogeneity. Spatial analysis also identified ten recurrent cellular neighborhoods (CNs) - a collection of local TME characteristics with unique cell components. Coupling of the prevalence of pan-immune and perivasculature immune hotspot CNs, enrichment of inter-CN interactions was associated with improved survival. Using a deep learning model trained on engineered spatial data, we can with high accuracy (mean AUC of 5-fold cross-validation = 0.71) how a separate cohort of patients in the NeoTRIP clinical trial will respond to treatment based on baseline TME features. These data reinforce that the TME architecture is structured in cellular compositions, spatial organizations, vasculature biology, and molecular profiles, and suggest novel imaging-based biomarkers for treatment development in the context of TNBC.
Keywords: Cellular neighborhoods; Clinical trial; Deep learning; Immuno-oncology; NeoTRIP; Prognostic biomarkers; Triple-negative breast cancer; Tumor microenvironment; spatial architecture.