摘要
目的癫痫脑电信号中的高频振荡节律是发作始发区的显著生物标记物,其精确检测对术前发作始发区定位至关重要。而复杂的检测和定位方法需要专门的软件将其封装处理,并提供直观的数据分析界面,以供研究者和临床医生使用,为此本文设计一种直观的高频振荡节律检测与发作始发区定位系统软件HFOLab。方法采用模块化的设计方法,将高频振荡节律检测方法和发作始发区定位方法设计为两个子模块,将检测结果可视化并输入定位子模块。考虑检测方法误报问题和人工检测需求,分别设计高频振荡节律辅助校验和辅助检测子模块,为专家校验和标记高频振荡节律提供直观依据。结果采用20名癫痫患者的脑电数据,对HFOLab进行初步试验。试验结果表明,HFOLab具有直观的数据分析界面,可对检测结果可视化,并为专家校验和标记高频振荡节律提供直观的依据。20名患者的高频振荡节律平均检测灵敏度(Ripples:92.4%;Fast ripples:90.3%)和平均误报率(Ripples:9.2%;Fast ripples:10.7%)良好,整体发作始发区定位灵敏度和特异性分别为78.9%和77.4%。结论HFOLab可有效检测高频振荡节律并定位发作始发区,可辅助专家校验和标记高频振荡节律,为应用高频振荡节律定位发作始发区的临床试验提供新的工具。
Objective High-frequency oscillations(HFOs)are regarded as promising biomarkers of epileptic seizure onset zones(SOZs).Accurate detection of HFOs is critical for the preoperative localization of SOZs.However,the detection and localization methods are usually relatively complex,and specialized software that packages them and provides an intuitive data analysis interface is needed for the researchers and clinicians.Thus,we design an intuitive HFO detection and SOZ localization system software HFOLab in this paper.Methods By using a modular design technique,we design the HFO detection method and the SOZ localization method in two submodules,and visualize the detection results and feed them into the localization submodule.Considering the false discovery problem of the detection method and the demand for manual detection,we also design two sub-modules of auxiliary verification and auxiliary detection of HFOs to provide intuitive references for experts to verify and mark of HFOs,respectively.Results Initial testing of HFOLab is performed by using EEG data from 20 epilepsy patients.The results show that HFOLab features an intuitive data analysis interface to visualize the detection results,and provides intuitive references for expert verification and marking of HFOs.The average sensitivity(Ripples:92.4%;Fast ripples:90.3%)and average false discovery rate(Ripples:9.2%;Fast ripples:10.7%)for the detection of HFOs are satisfactory,and the overall sensitivity and specificity for the localization of SOZs are 78.9%and 77.4%,respectively.Conclusions HFOLab is effective in detecting HFOs,localizing SOZs,and facilitating experts to verify and mark HFOs,and thus provides a new tool for clinical trials applying HFOs to localize SOZs.
作者
覃宏振
万雄波
杜玉晓
吴敏
QIN Hongzhen;WAN Xiongbo;DU Yuxiao;WU Min(School of Automation,China University of Geosciences,Wuhan 430074;Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems,Wuhan 430074;Engineering Research Center of Intelligent Technology for Geo-Exploration,Ministry of Education,Wuhan430074;School of Automation,Guangdong University of Technology,Guangzhou 510006)
出处
《北京生物医学工程》
2024年第3期267-273,279,共8页
Beijing Biomedical Engineering
基金
国家自然科学基金资助项目(61733016)
湖北省自然科学基金创新群体项目(2015CFA010)
高等学校学科创新引智计划项目(B17040)资助。
关键词
癫痫
高频振荡节律
发作始发区
检测
定位
Epilepsy
high⁃frequency oscillations
seizure onset zones
detection
localization