Background/Objectives: Circulating tumor cells (CTCs) and large extracellular vesicles (LEVs) are key components of the liquid biopsy that provide minimally invasive access to tumor biology. A clinically relevant subset of CTCs coexpressing epithelial and immune markers (im.CTCs) has been described, yet the origin of this phenotype remains unclear. In this study, we investigated the cellular and molecular context underlying the emergence of immune marker expression on CTCs and LEVs. Methods: Using high-resolution immunofluorescence microscopy of patient-derived blood samples, we identified direct physical interactions between white blood cells (WBCs) and both im.CTCs and im.LEVs, exclusively in patients harboring im.CTCs. Results: In several cases, WBCs partially encapsulated CTCs and LEVs, and quantitative analysis revealed localized enrichment of immune membrane markers at the contact interface, distinguishing these events from random proximity. Proteomic profiling further identified CD4+ T cells as the predominant interacting immune cell type and confirmed the presence of CD45, CD3, and CD4 on the interacting CTCs and LEVs, matching their WBC counterparts. Conclusion: These findings support membrane transfer as a potential mechanism for the acquisition of immune markers by CTCs and LEVs and provide in vivo evidence of contact-dependent tumor-immune interactions in circulation with implications for immune modulation and clinical interpretation of the im.CTC phenotype.

Imaging Mass Cytometry (IMC) enables highly multiplexed, spatially resolved single-cell proteomics, providing simultaneous measurement of dozens of protein

Tumor-associated cells derived from a liquid biopsy are promising biomarkers for cancer detection, diagnosis, prognosis, and monitoring. However, their rarity, heterogeneity and plasticity make precise identification and biological characterization challenging for clinical utility. Enrichment-free approaches using whole slide imaging of all circulating cells offer a comprehensive and unbiased strategy for capturing the full spectrum of tumor-associated cell phenotypes. However, current analysis methods often depend on engineered features and manual expert review, making them sensitive to technical variations and subjective biases. These limitations highlight the need for a better feature representation to improve performance and reproducibility of applications in large-scale patient cohort analyses. In this study, we present a deep contrastive learning framework for learning features of all circulating cells, enabling robust identification and stratification of single cells in whole slide immunofluorescence microscopy images. We demonstrate performance of learned features in classification of diverse cell phenotypes in the liquid biopsy, achieving an accuracy of 92.64%. We further demonstrate that learned features improve performance in downstream applications such as outlier detection and clustering. Lastly, our feature representation enables automated identification and enumeration of distinct rare cell phenotypes, achieving average F1-score of 0.93 across cell lines mimicking circulating tumor cells and endothelial cells in contrived samples and average F1-score of 0.858 across CTC phenotypes in clinical samples. This workflow has significant implications for scalable analysis of tumor-associated cellular biomarkers in clinical prognosis and personalized treatment strategies.