基于深度神经网络的颞叶癫痫18F-FDG PET术后复发预测研究
Deep neural networks analysis of 18F-FDG PET imaging in postoperative patients with temporal lobe epilepsy
吴环华 1陈少波 2尚靖杰 3周海玲 4吴彪 3弓健 3凌雪英 3郭强 5徐浩3
作者信息
- 1. 暨南大学附属第一医院核医学科,广州 510630;暨南大学附属顺德医院中心实验室,佛山 528305
- 2. 暨南大学信息科学技术学院,广州 510632
- 3. 暨南大学附属第一医院核医学科,广州 510630
- 4. 湛江中心人民医院放射科,湛江 524045
- 5. 广东三九脑科医院癫痫中心,广州 510510
- 折叠
摘要
目的 基于深度残差神经网络(ResNet)分析术前18F-FDG PET影像及患者临床特征,预测难治性颞叶癫痫(TLE)患者术后复发状况.方法 回顾性分析2014年1月至2020年6月期间暨南大学附属第一医院诊治的220例难治性TLE患者[男132例、女88例,年龄23.0(20.0,30.2)岁]的术前18F-FDG PET影像及临床资料.采用ResNet对预处理好的PET图像及临床特征进行高通量特征提取,并进行区分TLE患者的术后复发预测任务.评估模型的预测性能,并将其ROC曲线分析所得AUC与经典的生存分析Cox比例风险模型的AUC进行比较(Delong检验).结果 基于PET影像联合临床特征,ResNet预测难治性TLE患者术后12、24、36个月复发的AUC分别为0.895±0.073、0.861±0.058 和 0.754±0.111,Cox 比例风险回归模型相应 AUC 依次为 0.717±0.093、0.697±0.081 和0.645±0.087(z 值:-3.00、-2.98、-1.09,P 值:0.011、0.018、0.310),其中 ResNet 对术后 12 个月内复发事件的预测效果最佳.结论 ResNet模型有望在临床实践中用于TLE患者术后随访,帮助对术后患者进行风险分层个体化管理.
Abstract
Objective To predict the short-term postoperative recurrence status of patients with re-fractory temporal lobe epilepsy(TLE)by analyzing preoperative 18F-FDG PET images and patients'clinical characteristics based on deep residual neural network(ResNet).Methods Retrospective analysis was con-ducted on preoperative 18F-FDG PET images and clinical data of 220 patients with refractory TLE(132 males and 88 females,age 23.0(20.0,30.2)years))in the First Affiliated Hospital of Jinan University between January 2014 and June 2020.ResNet was used to perform high-throughput feature extraction on preprocessed PET images and clinical features,and to perform a postoperative recurrence prediction task for differentia-ting patients with TLE.The predictive performance of ResNet model was evaluated by ROC curve analysis,and the AUC was compared with that of classical Cox proportional risk model using Delong test.Results Based on PET images combined with clinical feature training,AUCs of the ResNet in predicting 12-,24-,and 36-month postoperative recurrence were 0.895±0.073,0.861±0.058 and 0.754±0.111,respectively,which were 0.717±0.093,0.697±0.081 and 0.645±0.087 for Cox proportional hazards model respectively(z values:-3.00,-2.98,-1.09,P values:0.011,0.018,0.310).The ResNet showed best predictive effect for recurrence events within 12 months after surgery.Conclusion The ResNet model is expected to be used in clinical practice for postoperative follow-up of patients with TLE,helping for risk stratification and indi-vidualized management of postoperative patients.
关键词
癫痫,颞叶/复发/神经网络(计算机)/正电子发射断层显像术/氟脱氧葡萄糖F18/预测Key words
Epilepsy,temporal lobe/Recurrence/Neural networks(computer)/Positron-emis-sion tomography/Fluorodeoxyglucose F18/Forecasting引用本文复制引用
基金项目
国家自然科学基金(82371998)
广州市科技计划(2023A03J1035)
广州市科技计划-市校联合资助项目(SL2022A03J01222)
出版年
2024
NETL
NSTL
万方数据