Radiomic signatures associated with tumor immune heterogeneity predict survival in locally recurrent nasopharyngeal carcinoma

作者：Da-Feng Lin, Hailin Li, Ting Liu, Xiaofei Lv, Chuanmiao Xie, Xiaomin Ou, Jian Guan, Ye Zhang, Wenbin Yan, Meilin He, Mengyuan Mao, Xun Zhao, Lianzhen Zhong, Wenhui Chen, Qiuyan Chen, Hai‐Qiang Mai, Roujun Peng, Jie Tian, Lin‐Quan Tang, Di Dong · 发表于：JNCI Journal of the National Cancer Institute · 年份：2024 · DOI：10.1093/jnci/djae081 · 被引用次数：31 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Head and Neck Cancer Studies、Cancer Immunotherapy and Biomarkers

BACKGROUND: The prognostic value of traditional clinical indicators for locally recurrent nasopharyngeal carcinoma is limited because of their inability to reflect intratumor heterogeneity. We aimed to develop a radiomic signature to reveal tumor immune heterogeneity and predict survival in locally recurrent nasopharyngeal carcinoma. METHODS: This multicenter, retrospective study included 921 patients with locally recurrent nasopharyngeal carcinoma. A machine learning signature and nomogram based on pretreatment magnetic resonance imaging features were developed for predicting overall survival in a training cohort and validated in 2 independent cohorts. A clinical nomogram and an integrated nomogram were constructed for comparison. Nomogram performance was evaluated by concordance index and receiver operating characteristic curve analysis. Accordingly, patients were classified into risk groups. The biological characteristics and immune infiltration of the signature were explored by RNA-sequencing analysis. RESULTS: The machine learning signature and nomogram demonstrated comparable prognostic ability to a clinical nomogram, achieving concordance indexes of 0.729, 0.718, and 0.731 in the training, internal, and external validation cohorts, respectively. Integration of the signature and clinical variables statistically improved the predictive performance. The proposed signature effectively distinguished patients between risk groups with statistically distinct overall survival r...