Novel spatial immune-based risk prediction platform can predict hepatocellular carcinoma recurrence

A research team led by Prof. Sun Cheng from the University of Science and Technology of China (USTC), in collaboration with researchers from the Agency for Science, Technology and Research and Chinese Academy of Agricultural Sciences, has successfully developed a novel spatial immune-based hepatocellular carcinoma (HCC) recurrence risk prediction platform.

The study is published in Nature.

HCC represents the third leading cause of cancer-related mortality globally, with postoperative recurrence rates reaching up to 70%. Precise prediction of HCC recurrence remains challenging due to the complex spatial heterogeneity and dynamic interplay within the tumor immune microenvironment (TIME).

To address this critical clinical gap, the research team developed the Tumor Immune MicroEnvironment Spatial (TIMES) scoring system, which quantitatively characterizes the spatial distribution patterns of immune cells within the tumor microenvironment. This system integrates whole-slide imaging (WSI) with an AI-driven spatial analysis algorithm to enable comprehensive assessment of tumor-immune interactions.

The TIMES system is based on the spatial expression profiles of five key biomarkers (SPON2, ZFP36L2, ZFP36, VIM, and HLA-DRB1) and enables high-precision recurrence risk prediction. High-dimensional analysis identified SPON2 as the most predictive biomarker, with its expression pattern in NK cell subsets closely correlated with HCC prognosis.

Comparative spatial immune profiling demonstrated that non-recurrent HCC patients exhibited significant enrichment of CD57+ NK cells at the invasive tumor front compared to recurrent patients. This regional immune heterogeneity, not captured by conventional histopathological grading, provides crucial prognostic information.

The research team elucidated the molecular mechanism by which SPON2 regulates NK cell function. Three-dimensional migration assays confirmed that SPON2 promoted the directional migration of NK cells toward tumor cells. Cytotoxicity assays demonstrated that SPON2⁺NK cells exhibit enhanced cytolytic activity and significantly promoted the activation of CD8⁺ T lymphocytes.

In NK cell-specific SPON2 knockout mouse models, the researchers observed decreased IFN-γ secretion and impaired NK cell infiltration, leading to accelerated tumor progression. These findings confirmed that SPON2⁺NK cells represented a highly activated subset suppressing HCC recurrence.

The TIMES scoring model was developed using the XGBoost machine learning algorithm trained on a multiplex immunofluorescence dataset from 61 HCC patients. When validated in an independent cohort, the TIMES system achieved an accuracy of 82.2% and a specificity of 85.7%, outperforming existing clinical prediction models.

To facilitate clinical application, the research team has developed an open-access online tool, enabling clinicians to upload standard immunohistochemistry-stained images and receive comprehensive reports containing TIMES scores and personalized recurrence risk assessments. Notably, the core algorithms and computational frameworks underlying the TIMES system have been patented, and the research team is actively pursuing industry collaborations to standardize protocols and accelerate clinical implementation.

This study not only delivers a practical predictive tool for clinical decision-making but also advances our fundamental understanding of immune mechanisms driving HCC recurrence, laying the foundation for SPON2⁺ NK cell-targeted immunotherapy strategies.