Department of Nuclear Medicine and PET-CT Center, The Second Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China.
Eur J Nucl Med Mol Imaging. 2021 Jul;48(8):2476-2485. doi: 10.1007/s00259-020-05108-y. Epub 2021 Jan 9.
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, F-fluorodeoxyglucose positron emission tomography (F-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).
We retrospectively included 201 pediatric patients with TLE and 24 age-matched controls who underwent F-FDG PET-CT studies. F-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.
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).
The proposed deep learning framework for F-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.
NCT04169581. Registered November 13, 2019 Public site: https://clinicaltrials.gov/ct2/show/NCT04169581.
癫痫是最具致残性的神经障碍之一，影响所有年龄段，常导致严重后果。由于误诊很常见，许多儿科患者未能得到正确治疗。最近，正电子发射断层扫描（PET）技术已用于评估儿科癫痫。然而，由于癫痫灶边界不清，其代谢表现为低代谢或高代谢，通过视觉评估很难确定癫痫灶的位置。本研究旨在开发一种用于识别颞叶癫痫（TLE）患儿癫痫灶的新型基于对称性的 PET 成像深度学习框架。
我们回顾性纳入 201 例 TLE 患儿和 24 例年龄匹配的对照组，所有患者均行 F-氟脱氧葡萄糖（FDG）PET-CT 检查。使用 386 个对称性特征对 FDG PET 图像进行定量分析，并提出基于双立方体（PoC）的孪生卷积神经网络（CNN）用于精确定位癫痫灶，然后通过不对称指数（AI）自动计算预测的癫痫灶的代谢异常水平。通过与视觉评估、统计参数映射（SPM）软件和基于 Jensen-Shannon 散度的逻辑回归（JS-LR）分析比较，评价所提出框架的性能。
所提出的深度学习框架能够准确地检测到癫痫灶，其 Dice 系数为 0.51，明显高于 SPM（0.24，P < 0.01）和视觉评估（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 比 0.72）。与视觉评估（盲法或非盲法）相比，该方法对代谢水平的检测准确率更高（90%比 56%或 68%，P < 0.01）。
该 FDG PET 成像深度学习框架能准确、高效地识别癫痫灶，可能成为未来癫痫患者诊断的一种辅助手段。
NCT04169581。于 2019 年 11 月 13 日在临床试验注册网站注册。网址：https://clinicaltrials.gov/ct2/show/NCT04169581。
Zotero 插件
