Noninvasive imaging-based assessment of tumor-associated neutrophils for prognosis and immunotherapy response in gastric cancer: a multicenter study

• Evidence before this study. • Prior research established tumor-associated neutrophils (TANs) as key mediators of immunosuppression and therapy resistance in gastric cancer, but their assessment relied entirely on invasive biopsies that preclude dynamic monitoring. While radiomics has been explored for gastric cancer diagnosis, no existing study had successfully linked CT imaging features to TANs-driven tumor microenvironment dynamics or immunotherapy response prediction. Our systematic PubMed search using “radiomics” AND “tumor-associated neutrophils” confirmed this critical gap—zero publications addressed non-invasive TANs quantification. • Added value of this study. • This study introduces EnmlbaRB, the first non-invasive biomarker capable of dynamically classifying TANs status in gastric cancer directly from routine CT scans. By applying an innovative five-tier machine learning architecture to a large, multicenter cohort, EnmlbaRB eliminates the need for repeated invasive biopsies to profile this critical immune component. Crucially, it provides clinically transformative insights: it enables real-time tracking of neutrophil-driven TME changes, robustly identifies patients with strikingly different survival outcomes, and demonstrates exceptional power to predict who will benefit most from immunotherapy. TAN-Low patients classified by EnmlbaRB showed significantly superior survival and derived substantially greater clinical benefit from anti-PD-1 therapy, achieving markedly higher disease control rates and much longer progression-free survival compared to TAN-High patients. This breakthrough provides clinicians with a practical tool for dynamic TME monitoring and precision immunotherapy selection. • Implications of all the available evidence. • The evidence from this multicenter study signifies a major advance in gastric cancer management. EnmlbaRB transforms standard CT scans into a powerful tool for non-invasive TANs surveillance, moving beyond the limitations of biopsies. This allows for routine monitoring of a key immunosuppressive element in the TME during treatment. More importantly, its ability to reliably identify immunotherapy beneficiaries (TAN-Low patients) offers a direct pathway to optimize treatment decisions, improve patient outcomes, and avoid ineffective therapy in non-responders. The validated machine learning framework also establishes a new standard for non-invasive tumor microenvironment modeling, with potential applications across various cancer types. Future work integrating this approach with complementary techniques promises even deeper insights for precision immuno-oncology. Tumor-associated neutrophils (TAN) critically promote gastric cancer progression. However, current assessment relies on invasive biopsies that preclude serial monitoring. Noninvasive tools to quantify TAN infiltration are urgently required. To develop and validate a noninvasive, CT-based ensemble machine learning radiomic biomarker for mapping TAN infiltration in gastric cancer, and to assess its utility for prognosis stratification and the prediction of response to anti-PD-1 immunotherapy. In this multicenter study of 2,170 gastric cancer patients across eight cohorts, we developed EnmlbaRB, an ensemble machine-learning-based CT radiomic biomarker. Portal venous-phase scans were processed to extract features, with mRMR-Boruta algorithms identifying 11 radiomic signatures (six peritumoral and five intratumoral signatures). These were integrated via a five-tier heterogeneous stacking architecture supervised by the immunohistochemistry-derived CD66b + TAN status (high/medium/low). The validation spanned six independent cohorts, including 177 anti-PD-1-treated patients. External validation demonstrated robust performance: EnmlbaRB predicted TAN status with an AUC of 0.71 (95%CI: 0.65–0.78) and 80.74% specificity. Critically, TAN-Low patients exhibited significantly superior 5-year overall survival compared to TAN-High across all cohorts (e.g., SYSUCC cohort: 64.12% vs. 46.78%, p < 0.05). In the anti-PD-1 cohorts, the TAN-Low subgroups achieved 1.9-fold higher disease control rates (83.9% vs 44.1%; p < 0.001) and significantly prolonged median progression-free survival (>41.9 vs 6.2 months; HR = 0.162, p < 0.001), establishing clear clinical utility for immunotherapy stratification. This study is the first clinically validated noninvasive solution for mapping the TAN infiltration status in gastric cancer. EnmlbaRB effectively stratified the patients based on survival outcomes and immunotherapy responsiveness. This paradigm empowers clinicians to personalize therapeutic sequencing based on evolving TAN biology, thereby addressing the critical need for adaptive treatment strategies for advanced gastric cancer management.