深度学习框架用于儿童颞叶癫痫的18F-FDG PET影像诊断
本研究回顾性纳入201例儿童颞叶癫痫患者和24例年龄匹配对照,开发基于对称性特征和孪生卷积神经网络的深度学习框架,用于18F-FDG PET图像中癫痫灶的识别与定位。该框架检测癫痫灶的Dice系数为0.51,显著高于SPM的0.24(P<0.01),代谢异常水平检测准确率90%,显著高于盲法或非盲法视觉评估的56%或68%(P<0.01)。
要点
- 深度学习框架可较准确定位儿童颞叶癫痫的PET代谢异常灶,Dice系数0.51。
- 该框架代谢水平检测准确率90%,优于视觉评估的56%或68%。
- 框架分类AUC为0.93,高于JS-LR的0.72。
核心结论
- 基于18F-FDG PET的深度学习框架能准确高效识别儿童颞叶癫痫的癫痫灶,可能作为未来癫痫诊断的计算机辅助方法。
研究设计与样本
- 回顾性纳入201例儿童颞叶癫痫患者和24例年龄匹配对照,均行18F-FDG PET-CT检查。
- 利用386个对称性特征,提出基于pair-of-cube(PoC)的孪生卷积神经网络(CNN)定位癫痫灶,并自动计算不对称指数(AI)评估代谢异常水平。
- 将框架性能与视觉评估、统计参数映射(SPM)软件及基于Jensen-Shannon散度的逻辑回归(JS-LR)分析进行比较。
主要发现
- 所提深度学习框架检测癫痫灶的Dice系数为0.51,显著高于SPM的0.24(P<0.01),并显著(或边缘显著)高于视觉评估的0.31-0.44(P=0.005-0.27)。
- PoC分类的曲线下面积(AUC)高于JS-LR(0.93 vs. 0.72)。
- 所提方法代谢水平检测准确率显著高于盲法或非盲法视觉评估(90% vs. 56%或68%,P<0.01)。
关键数值与推荐
- 癫痫灶定位准确性以Dice系数衡量:深度学习框架0.51,SPM 0.24,视觉评估0.31-0.44。
- 分类性能以AUC衡量:PoC 0.93,JS-LR 0.72。
- 代谢水平检测准确率:深度学习方法90%,盲法视觉评估56%,非盲法视觉评估68%。
临床怎么用
- 该框架可作为计算机辅助工具,帮助核医学科医生在儿童颞叶癫痫的18F-FDG PET图像中更准确地定位癫痫灶和判断代谢异常水平。
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)。
原文
PURPOSE: Epilepsy is one of the most disabling neurological disorders, which affects all age groups and often results in severe consequences. Since misdiagnoses are common, many pediatric patients fail to receive the correct treatment. Recently, 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) imaging has been used for the evaluation of pediatric epilepsy. However, the epileptic focus is very difficult to be identified by visual assessment since it may present either hypo- or hyper-metabolic abnormality with unclear boundary. This study aimed to develop a novel symmetricity-driven deep learning framework of PET imaging for the identification of epileptic foci in pediatric patients with temporal lobe epilepsy (TLE). METHODS: We retrospectively included 201 pediatric patients with TLE and 24 age-matched controls who underwent 18F-FDG PET-CT studies. 18F-FDG PET images were quantitatively investigated using 386 symmetricity features, and a pair-of-cube (PoC)-based Siamese convolutional neural network (CNN) was proposed for precise localization of epileptic focus, and then metabolic abnormality level of the predicted focus was calculated automatically by asymmetric index (AI). Performances of the proposed framework were compared with visual assessment, statistical parametric mapping (SPM) software, and Jensen-Shannon divergence-based logistic regression (JS-LR) analysis. RESULTS: The proposed deep learning framework could detect the epileptic foci accurately with the dice coefficient of 0.51, which was significantly higher than that of SPM (0.24, P < 0.01) and significantly (or marginally) higher than that of visual assessment (0.31-0.44, P = 0.005-0.27). The area under the curve (AUC) of the PoC classification was higher than that of the JS-LR (0.93 vs. 0.72). The metabolic level detection accuracy of the proposed method was significantly higher than that of visual assessment blinded or unblinded to clinical information (90% vs. 56% or 68%, P < 0.01). CONCLUSION: The proposed deep learning framework for 18F-FDG PET imaging could identify epileptic foci accurately and efficiently, which might be applied as a computer-assisted approach for the future diagnosis of epilepsy patients. TRIAL REGISTRATION: NCT04169581. Registered November 13, 2019 Public site: https://clinicaltrials.gov/ct2/show/NCT04169581.
引用
- Zhang Q, Liao Y, Wang X, et al. A deep learning framework for 18F-FDG PET imaging diagnosis in pediatric patients with temporal lobe epilepsy. Eur J Nucl Med Mol Imaging. 2021. PMID: 33420912. doi:10.1007/s00259-020-05108-y
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。