基于同步PET/MRI的个体[18F]FDG PET与功能MRI可能预测颞叶癫痫术后癫痫复发
本研究纳入39例单侧海马硬化所致内侧颞叶癫痫患者,术前用同步PET/MRI获取个体[18F]FDG PET代谢与功能MRI fALFF异常,结合临床数据构建机器学习模型预测术后1年癫痫复发;验证集中联合PET与fALFF的logistic回归模型AUC达0.905,高于单独PET的0.762和单独fALFF的0.810。
要点
- 对侧海马网络代谢与fALFF异常及发病年龄可识别不良手术结局。
- 联合[18F]FDG PET与fALFF的模型预测癫痫复发AUC为0.905。
- 单独[18F]FDG PET与单独fALFF的AUC分别为0.762和0.810。
核心结论
- 机器学习模型提示基于同步[18F]FDG PET/MRI的个体[18F]FDG PET与fMRI在对侧海马网络的变化可能作为不良手术结局的潜在生物标志物。
研究设计与样本
- 研究类型为采用同步PET/MRI的影像学研究,纳入39例接受前颞叶切除术的单侧mTLE-HS患者。
- 术后1年按Engel分级分为完全无发作组(Engel IA,n=22)与非无发作组(Engel IB-IV,n=17)。
- 术前[18F]FDG PET与fMRI来自同步PET/MRI扫描仪,个体葡萄糖代谢与fALFF以健康对照标准化评估。
- 异常指标与临床数据纳入梯度提升决策树和logistic回归机器学习框架预测癫痫复发。
- 预测价值在训练集与测试集中用ROC曲线评估。
关键影像表现/征象
- 对侧海马网络的[18F]FDG PET与fMRI变异以及发病年龄可有效识别不良手术结局。
诊断标准与关键数值
- 验证集中,联合[18F]FDG PET与fALFF的logistic回归模型预测癫痫复发的AUC最大为0.905。
- 单独[18F]FDG PET的AUC为0.762。
- 单独fALFF的AUC为0.810。
- 机器学习分类手术结局的准确率为90.5%。
临床应用与阅片要点
- 术前同步[18F]FDG PET/MRI可同时获取个体代谢与fALFF异常,用于评估mTLE-HS术后癫痫复发风险。
- 阅片时可关注对侧海马网络的代谢与功能异常,并结合发病年龄综合判断。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: To investigate the individual measures of brain glucose metabolism, neural activity obtained from simultaneous 18[F]FDG PET/MRI, and their association with surgical outcomes in medial temporal lobe epilepsy due to hippocampal sclerosis (mTLE-HS).
METHODS: Thirty-nine unilateral mTLE-HS patients who underwent anterior temporal lobectomy were classified as having completely seizure-free (Engel class IA; n = 22) or non-seizure-free (Engel class IB-IV; n = 17) outcomes at 1 year after surgery. Preoperative [18F]FDG PET and functional MRI (fMRI) were obtained from a simultaneous PET/MRI scanner, and individual glucose metabolism and fractional amplitude of low-frequency fluctuation (fALFF) were evaluated by standardizing these with respect to healthy controls. These abnormality measures and clinical data from each patient were incorporated into a machine learning framework (gradient boosting decision tree and logistic regression analysis) to estimate seizure recurrence. The predictive values of features were evaluated by the receiver operating characteristic (ROC) curve in the training and test cohorts.
RESULTS: The machine learning classification model showed [18F]FDG PET and fMRI variations in contralateral hippocampal network and age of onset identify unfavorable surgical outcomes effectively. In the validation dataset, the logistic regression model with [18F]FDG PET and fALFF obtained from simultaneous [18F]FDG PET/MRI gained the maximum area under the ROC curve of 0.905 for seizure recurrence, higher than 0.762 with 18[F]-FDG PET, and 0.810 with fALFF alone.
CONCLUSION: Machine learning model suggests individual [18F]FDG PET and fMRI variations in contralateral hippocampal network based on 18[F]-FDG PET/MRI could serve as a potential biomarker of unfavorable surgical outcomes.
KEY POINTS: • Individual [18F]FDG PET and fMRI obtained from preoperative [18F]FDG PET/MR were investigated. • Individual differences were further assessed based on a seizure propagation network. • Machine learning can classify surgical outcomes with 90.5% accuracy.
引用
- Wang, Guo, Cui, et al. Individual [18F]FDG PET and functional MRI based on simultaneous PET/MRI may predict seizure recurrence after temporal lobe epilepsy surgery. Eur Radiol. 2022. PMID: 35024947. doi:10.1007/s00330-021-08490-9
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。