Enhancing Nasopharyngeal Carcinoma Survival Prediction: Integrating Pre- and Post-Treatment MRI Radiomics with Clinical Data

Luong Huu Dang, Shih-Han Hung, Nhi Thao Ngoc Le, Wei-Kai Chuang, Jeng-You Wu, Ting-Chieh Huang, Nguyen Quoc Khanh Le

研究成果: 雜誌貢獻文章同行評審


Recurrences are frequent in nasopharyngeal carcinoma (NPC) despite high remission rates with treatment, leading to considerable morbidity. This study aimed to develop a prediction model for NPC survival by harnessing both pre- and post-treatment magnetic resonance imaging (MRI) radiomics in conjunction with clinical data, focusing on 3-year progression-free survival (PFS) as the primary outcome. Our comprehensive approach involved retrospective clinical and MRI data collection of 276 eligible NPC patients from three independent hospitals (180 in the training cohort, 46 in the validation cohort, and 50 in the external cohort) who underwent MRI scans twice, once within 2 months prior to treatment and once within 10 months after treatment. From the contrast-enhanced T1-weighted images before and after treatment, 3404 radiomics features were extracted. These features were not only derived from the primary lesion but also from the adjacent lymph nodes surrounding the tumor. We conducted appropriate feature selection pipelines, followed by Cox proportional hazards models for survival analysis. Model evaluation was performed using receiver operating characteristic (ROC) analysis, the Kaplan–Meier method, and nomogram construction. Our study unveiled several crucial predictors of NPC survival, notably highlighting the synergistic combination of pre- and post-treatment data in both clinical and radiomics assessments. Our prediction model demonstrated robust performance, with an accuracy of AUCs of 0.66 (95% CI: 0.536–0.779) in the training cohort, 0.717 (95% CI: 0.536–0.883) in the testing cohort, and 0.827 (95% CI: 0.684–0.948) in validation cohort in prognosticating patient outcomes. Our study presented a novel and effective prediction model for NPC survival, leveraging both pre- and post-treatment clinical data in conjunction with MRI features. Its constructed nomogram provides potentially significant implications for NPC research, offering clinicians a valuable tool for individualized treatment planning and patient counseling.
期刊Journal of imaging informatics in medicine
出版狀態打印前電子出版 - 4月 30 2024


深入研究「Enhancing Nasopharyngeal Carcinoma Survival Prediction: Integrating Pre- and Post-Treatment MRI Radiomics with Clinical Data」主題。共同形成了獨特的指紋。