利用高频振荡和机器学习定位致痫区域。
Localizing epileptogenic regions using high-frequency oscillations and machine learning.
作者信息
Weiss Shennan A, Waldman Zachary, Raimondo Federico, Slezak Diego, Donmez Mustafa, Worrell Gregory, Bragin Anatol, Engel Jerome, Staba Richard, Sperling Michael
机构信息
Departments of Neurology & Neuroscience, Thomas Jefferson University, Philadelphia, PA 19107, USA.
Department of Computer Science, Faculty of Exact & Natural Sciences, University of Buenos Aires, Buenos Aires, Argentina.
出版信息
Biomark Med. 2019 Apr;13(5):409-418. doi: 10.2217/bmm-2018-0335. Epub 2019 May 2.
Abstract
Pathological high frequency oscillations (HFOs) are putative neurophysiological biomarkers of epileptogenic brain tissue. Utilizing HFOs for epilepsy surgery planning offers the promise of improved seizure outcomes for patients with medically refractory epilepsy. This review discusses possible machine learning strategies that can be applied to HFO biomarkers to better identify epileptogenic regions. We discuss the role of HFO rate, and utilizing features such as explicit HFO properties (spectral content, duration, and power) and phase-amplitude coupling for distinguishing pathological HFO (pHFO) events from physiological HFO events. In addition, the review highlights the importance of neuroanatomical localization in machine learning strategies.
摘要
病理性高频振荡（HFOs）被认为是致痫脑组织的神经生理生物标志物。利用HFOs进行癫痫手术规划有望改善药物难治性癫痫患者的癫痫发作预后。本文综述了可能适用于HFO生物标志物的机器学习策略，以更好地识别致痫区域。我们讨论了HFO发生率的作用，以及利用诸如明确的HFO特性（频谱内容、持续时间和功率）和相位-振幅耦合等特征来区分病理性HFO（pHFO）事件与生理性HFO事件。此外，本文综述强调了神经解剖定位在机器学习策略中的重要性。
相似文献
1
Localizing epileptogenic regions using high-frequency oscillations and machine learning.利用高频振荡和机器学习定位致痫区域。
Biomark Med. 2019 Apr;13(5):409-418. doi: 10.2217/bmm-2018-0335. Epub 2019 May 2.
2
Scalp-HFO indexes are biomarkers for the lateralization and localization of the epileptogenic zone in preoperative assessment.头皮高频振荡指数是术前评估中致痫区定位和侧化的生物标志物。
J Neurophysiol. 2021 Oct 1;126(4):1148-1158. doi: 10.1152/jn.00212.2021. Epub 2021 Sep 8.
3
Machine learning-based classification of physiological and pathological high-frequency oscillations recorded by stereoelectroencephalography.基于机器学习的立体脑电图记录的生理和病理高频振荡分类
Seizure. 2023 Dec;113:58-65. doi: 10.1016/j.seizure.2023.11.005. Epub 2023 Nov 10.
4
Self-Supervised Data-Driven Approach Defines Pathological High-Frequency Oscillations in Human.自监督数据驱动方法定义人类病理性高频振荡。
medRxiv. 2024 Nov 5:2024.07.10.24310189. doi: 10.1101/2024.07.10.24310189.
5
Practical measurements distinguishing physiological and pathological stereoelectroencephalography channels based on high-frequency oscillations in the human brain.基于人类大脑高频振荡的生理和病理立体脑电图通道的实用测量。
Epilepsia Open. 2024 Aug;9(4):1287-1299. doi: 10.1002/epi4.12950. Epub 2024 May 29.
6
Refining epileptogenic high-frequency oscillations using deep learning: a reverse engineering approach.利用深度学习优化致痫性高频振荡：一种逆向工程方法。
Brain Commun. 2021 Nov 3;4(1):fcab267. doi: 10.1093/braincomms/fcab267. eCollection 2022.
7
Clinical utility of interictal high-frequency oscillations recorded with subdural macroelectrodes in partial epilepsy.脑表面电极记录的癫痫间期高频振荡在部分性癫痫中的临床应用价值。
J Clin Neurol. 2012 Mar;8(1):22-34. doi: 10.3988/jcn.2012.8.1.22. Epub 2012 Mar 31.
8
Temporal and morphological characteristics of high-frequency oscillations in an acute in vivo model of epilepsy.癫痫急性在体模型中高频振荡的时间和形态特征。
Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:4896-4899. doi: 10.1109/EMBC48229.2022.9871323.
9
Mapping the coherence of ictal high frequency oscillations in human extratemporal lobe epilepsy.绘制人类颞叶外癫痫发作期高频振荡的连贯性图谱。
Epilepsia. 2015 Mar;56(3):393-402. doi: 10.1111/epi.12918. Epub 2015 Jan 29.
10
Epileptogenic high-frequency oscillations present larger amplitude both in mesial temporal and neocortical regions.致痫性高频振荡在颞叶内侧和新皮质区域均呈现出更大的振幅。
Front Hum Neurosci. 2022 Sep 29;16:984306. doi: 10.3389/fnhum.2022.984306. eCollection 2022.
引用本文的文献
1
Spikes on ripples are better interictal biomarkers of epilepsy than spikes or ripples.与棘波或慢波相比，涟漪上的棘波是更好的癫痫发作间期生物标志物。
Brain Commun. 2025 Feb 8;7(1):fcaf056. doi: 10.1093/braincomms/fcaf056. eCollection 2025.
2
Networks through the lens of high-frequency oscillations.从高频振荡视角看网络
Front Netw Physiol. 2024 Nov 28;4:1462672. doi: 10.3389/fnetp.2024.1462672. eCollection 2024.
3
A Review of EEG-based Localization of Epileptic Seizure Foci: Common Points with Multimodal Fusion of Brain Data.基于脑电图的癫痫发作灶定位综述：与脑数据多模态融合的共同点
J Med Signals Sens. 2024 Jul 25;14:19. doi: 10.4103/jmss.jmss_11_24. eCollection 2024.
4
Practical measurements distinguishing physiological and pathological stereoelectroencephalography channels based on high-frequency oscillations in the human brain.基于人类大脑高频振荡的生理和病理立体脑电图通道的实用测量。
Epilepsia Open. 2024 Aug;9(4):1287-1299. doi: 10.1002/epi4.12950. Epub 2024 May 29.
5
Pathological and Physiological High-frequency Oscillations on Electroencephalography in Patients with Epilepsy.癫痫患者脑电图的病理性和生理性高频振荡。
Neurosci Bull. 2024 May;40(5):609-620. doi: 10.1007/s12264-023-01150-6. Epub 2023 Nov 24.
6
Capturing the power of seizures: an empirical mode decomposition analysis of epileptic activity in the mouse hippocampus.捕捉癫痫发作的力量：小鼠海马体癫痫活动的经验模态分解分析
Front Mol Neurosci. 2023 May 15;16:1121479. doi: 10.3389/fnmol.2023.1121479. eCollection 2023.
7
Epileptogenic high-frequency oscillations present larger amplitude both in mesial temporal and neocortical regions.致痫性高频振荡在颞叶内侧和新皮质区域均呈现出更大的振幅。
Front Hum Neurosci. 2022 Sep 29;16:984306. doi: 10.3389/fnhum.2022.984306. eCollection 2022.
8
An approach for reliably identifying high-frequency oscillations and reducing false-positive detections.一种可靠识别高频振荡并减少假阳性检测的方法。
Epilepsia Open. 2022 Dec;7(4):674-686. doi: 10.1002/epi4.12647. Epub 2022 Sep 14.
9
Decoding Intracranial EEG With Machine Learning: A Systematic Review.利用机器学习解码颅内脑电图：一项系统综述。
Front Hum Neurosci. 2022 Jun 27;16:913777. doi: 10.3389/fnhum.2022.913777. eCollection 2022.
10
Transformer-Based High-Frequency Oscillation Signal Detection on Magnetoencephalography From Epileptic Patients.基于Transformer的癫痫患者脑磁图高频振荡信号检测
Front Mol Biosci. 2022 Mar 4;9:822810. doi: 10.3389/fmolb.2022.822810. eCollection 2022.
本文引用的文献
1
Ripple oscillations in the left temporal neocortex are associated with impaired verbal episodic memory encoding.左侧颞叶新皮质中的涟漪振荡与言语情景记忆编码受损有关。
Epilepsy Behav. 2018 Nov;88:33-40. doi: 10.1016/j.yebeh.2018.08.018. Epub 2018 Sep 11.
2
Removing high-frequency oscillations: A prospective multicenter study on seizure outcome.去除高频震荡：一项关于癫痫结局的前瞻性多中心研究。
Neurology. 2018 Sep 11;91(11):e1040-e1052. doi: 10.1212/WNL.0000000000006158. Epub 2018 Aug 17.
3
Interictal stereotactic-EEG functional connectivity in refractory focal epilepsies.难治性局灶性癫痫的发作间期立体定向脑电图功能连接。
Brain. 2018 Oct 1;141(10):2966-2980. doi: 10.1093/brain/awy214.
4
Visually validated semi-automatic high-frequency oscillation detection aides the delineation of epileptogenic regions during intra-operative electrocorticography.术中皮质脑电图时，可视化验证的半自动高频振荡检测有助于癫痫灶的定位。
Clin Neurophysiol. 2018 Oct;129(10):2089-2098. doi: 10.1016/j.clinph.2018.06.030. Epub 2018 Jul 20.
5
High-Frequency Oscillations in the Normal Human Brain.正常人脑的高频振荡。
Ann Neurol. 2018 Sep;84(3):374-385. doi: 10.1002/ana.25304. Epub 2018 Aug 25.
6
Surgical resection of ripple onset predicts outcome in pediatric epilepsy.涟漪起始的外科切除可预测儿科癫痫的结果。
Ann Neurol. 2018 Sep;84(3):331-346. doi: 10.1002/ana.25295. Epub 2018 Sep 4.
7
The spike onset zone: The region where epileptic spikes start and from where they propagate.棘波起始区：癫痫棘波起始的区域，也是它们传播的区域。
Neurology. 2018 Aug 14;91(7):e666-e674. doi: 10.1212/WNL.0000000000005998. Epub 2018 Jul 13.
8
Getting the best outcomes from epilepsy surgery.从癫痫手术中获得最佳结果。
Ann Neurol. 2018 Apr;83(4):676-690. doi: 10.1002/ana.25205. Epub 2018 Apr 10.
9
Stereotyped high-frequency oscillations discriminate seizure onset zones and critical functional cortex in focal epilepsy.刻板的高频振荡可区分局灶性癫痫的发作起始区和关键功能皮层。
Brain. 2018 Mar 1;141(3):713-730. doi: 10.1093/brain/awx374.
10
Spatial variation in high-frequency oscillation rates and amplitudes in intracranial EEG.颅内 EEG 中高频振荡率和幅度的空间变化。
Neurology. 2018 Feb 20;90(8):e639-e646. doi: 10.1212/WNL.0000000000004998. Epub 2018 Jan 24.
Zotero 插件