A Serial MRI–based Deep Learning Model to Predict Survival in Patients with Locoregionally Advanced Nasopharyngeal Carcinoma
Authors:
- Jia KouJKJia Kou
- Jun-Yi PengJPJun-Yi Peng
- Wen-Bing LvWLWen-Bing Lv
- Chen-Fei WuCWChen-Fei Wu
- Zi-Hang ChenZCZi-Hang Chen
- Guan-Qun ZhouGZGuan-Qun Zhou
- Ya-Qin WangYWYa-Qin Wang
- Li LinLLLi Lin
- Li-Jun LuLi-Jun Lu
- Ying SunYSYing Sun
- 1 February 2025
- journal article
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 7 (2) , e230544
Abstract
A prognostic model incorporating pre- and posttreatment serial MRI acquisitions and clinical factors using deep learning methods showed good performance in survival prediction and risk stratification of patients with locoregionally advanced nasopharyngeal carcinoma.Keywords
Funding Information
- National Natural Science Foundation of China (92259202, 82273401)
- China Postdoctoral Science Foundation (2022TQ0389)
- Sun Yat-sen University Cancer Center (CIRP-SYSUCC-0010)
- Sanming Project of Medicine in Shenzen Municipality (SZSM202211017)
- Scholarship for Outstanding Young Physician-Scientists of Sun Yat-sen University Cancer Center (CKS-SYSUCC-2023003)
- National Postdoctoral Program for Innovative Talents (BX20230445)
This publication has 44 references indexed in Scilit:
- Functional-structural sub-region graph convolutional network (FSGCN): Application to the prognosis of head and neck cancer with PET/CT imagingComputer Methods and Programs in Biomedicine, 2023
- Delta radiomics: a systematic reviewLa radiologia medica, 2021
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Dynamic Risk Profiling Using Serial Tumor Biomarkers for Personalized Outcome PredictionCell, 2019
- Pretreatment MRI radiomics analysis allows for reliable prediction of local recurrence in non-metastatic T4 nasopharyngeal carcinomaEBioMedicine, 2019
- Intensity-modulated radiotherapy prolongs the survival of patients with nasopharyngeal carcinoma compared with conventional two-dimensional radiotherapy: A 10-year experience with a large cohort and long follow-upEuropean Journal of Cancer, 2015
- Comparing two correlated C indices with right‐censored survival outcome: a one‐shot nonparametric approachStatistics in Medicine, 2014
- Estimating and comparing time‐dependent areas under receiver operating characteristic curves for censored event times with competing risksStatistics in Medicine, 2013
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)European Journal of Cancer, 2009