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
- 基于CT的非侵入性集成机器学习放射组学标志物(EnmlbaRB)开发用于胃癌肿瘤相关中性粒细胞(TAN)浸润图谱绘制
- 纳入8个队列2170例胃癌患者的多中心研究,在6个独立队列(含177例抗PD-1治疗患者)中得到验证
- EnmlbaRB预测TAN状态的AUC达0.71,特异性80.74%,表现稳健
- TAN低表达患者5年总生存率显著优于高表达患者(如64.12% vs 46.78%,p < 0.05)
- 在抗PD-1队列中,TAN低表达亚组疾病控制率提高1.9倍(83.9% vs 44.1%;p < 0.001),中位无进展生存期显著延长(>41.9月 vs 6.2月;HR=0.162,p < 0.001)
- 首个经临床验证的胃癌TAN浸润无创检测方案,有助于预后评估及免疫治疗疗效预测