Noninvasive imaging-based assessment of tumor-associated neutrophils for prognosis and immunotherapy response in gastric cancer: a multicenter study - PubMed
3 months ago
- #Medical Imaging
- #Machine Learning
- #Immunotherapy
- Noninvasive CT-based ensemble machine learning radiomic biomarker (EnmlbaRB) developed for mapping tumor-associated neutrophils (TAN) infiltration in gastric cancer.
- Multicenter study involving 2,170 gastric cancer patients across eight cohorts, validated in six independent cohorts including 177 anti-PD-1-treated patients.
- EnmlbaRB predicted TAN status with an AUC of 0.71 and 80.74% specificity, showing robust performance.
- TAN-Low patients had significantly superior 5-year overall survival compared to TAN-High patients (e.g., 64.12% vs. 46.78%, p < 0.05).
- In anti-PD-1 cohorts, TAN-Low subgroups showed 1.9-fold higher disease control rates (83.9% vs 44.1%; p < 0.001) and prolonged median progression-free survival (>41.9 vs 6.2 months; HR = 0.162, p < 0.001).
- First clinically validated noninvasive solution for TAN infiltration mapping in gastric cancer, aiding in prognosis and immunotherapy response prediction.