Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.
Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.
复制标题
DOI：
10.1002/hbm.25340
复制
发表时间：
2021-05
影响因子：
4.8
通讯作者：
Lee RR
中科院分区：
文献类型：
--
作者：
Huang MX;Huang CW;Harrington DL;Robb-Swan A;Angeles-Quinto A;Nichols S;Huang JW;Le L;Rimmele C;Matthews S;Drake A;Song T;Ji Z;Cheng CK;Shen Q;Foote E;Lerman I;Yurgil KA;Hansen HB;Naviaux RK;Dynes R;Baker DG;Lee RR
战斗相关轻度创伤性脑损伤（cmTBI）是退伍军人和现役军人持续身体，认知，情感和行为残疾的主要原因。cmTBI的准确诊断是具有挑战性的，因为症状谱是广泛的，传统的神经成像技术是不敏感的基础神经病理学。本研究开发了一种新的深度学习神经网络方法3D-MEGNET，并将其应用于来自59名症状性cmTBI个体和42名战斗部署健康对照（HC）的静息态脑磁图（rs-MEG）源幅成像数据。测试了单个频带和所有频带一起的分析模型。全频率模型结合了delta-theta（1-7 Hz）、alpha（8-12 Hz）、beta（15-30 Hz）和gamma（30-80 Hz）频带，优于基于单个频带的模型。优化的3D-MEGNET方法区分cmTBI个体与HC具有出色的灵敏度（99.9 ± 0.38%）和特异性（98.9 ± 1.54%）。受试者操作特征曲线分析显示诊断准确率为0.99。伽马和δ-θ波段模型优于α和β波段模型。在cmTBI个体中，而不是对照组中，超δ-θ和γ-波段活动与神经心理学测试的较低表现相关，而低α和β-波段活动也与较低的神经心理学测试表现相关。这项研究提供了一个综合框架，用于将大型源成像变量集浓缩为cmTBI中具有高诊断准确性和认知相关性的区域和频率的最佳组合。全频率模型比单独的每个频带模型提供了更多的区分能力。这种方法提供了一个有效的路径，最佳的表征行为相关的神经影像学功能的神经和精神疾病。这项研究开发了一种新的静息态脑磁图（rs‐MEG）源幅成像方法，3D‐MEGNET，使用深度学习。优化的3D-MEGNET方法结合了所有频段的rs-MEG数据，以高灵敏度、特异性和诊断准确性区分了战斗相关轻度创伤性脑损伤（cmTBI）患者和战斗部署的健康对照者。这项研究提供了一个综合框架，用于将大型源成像变量集浓缩为cmTBI中具有高诊断准确性和认知相关性的区域和频率的最佳组合。
Combat‐related mild traumatic brain injury (cmTBI) is a leading cause of sustained physical, cognitive, emotional, and behavioral disabilities in Veterans and active‐duty military personnel. Accurate diagnosis of cmTBI is challenging since the symptom spectrum is broad and conventional neuroimaging techniques are insensitive to the underlying neuropathology. The present study developed a novel deep‐learning neural network method, 3D‐MEGNET, and applied it to resting‐state magnetoencephalography (rs‐MEG) source‐magnitude imaging data from 59 symptomatic cmTBI individuals and 42 combat‐deployed healthy controls (HCs). Analytic models of individual frequency bands and all bands together were tested. The All‐frequency model, which combined delta‐theta (1–7 Hz), alpha (8–12 Hz), beta (15–30 Hz), and gamma (30–80 Hz) frequency bands, outperformed models based on individual bands. The optimized 3D‐MEGNET method distinguished cmTBI individuals from HCs with excellent sensitivity (99.9 ± 0.38%) and specificity (98.9 ± 1.54%). Receiver‐operator‐characteristic curve analysis showed that diagnostic accuracy was 0.99. The gamma and delta‐theta band models outperformed alpha and beta band models. Among cmTBI individuals, but not controls, hyper delta‐theta and gamma‐band activity correlated with lower performance on neuropsychological tests, whereas hypo alpha and beta‐band activity also correlated with lower neuropsychological test performance. This study provides an integrated framework for condensing large source‐imaging variable sets into optimal combinations of regions and frequencies with high diagnostic accuracy and cognitive relevance in cmTBI. The all‐frequency model offered more discriminative power than each frequency‐band model alone. This approach offers an effective path for optimal characterization of behaviorally relevant neuroimaging features in neurological and psychiatric disorders. This study developed a novel resting‐state magnetoencephalography (rs‐MEG) source‐magnitude imaging method, 3D‐MEGNET, using deep learning. The optimized 3D‐MEGNET method combining rs‐MEG data from all frequency bands distinguished individuals with combat‐related mild traumatic brain injury (cmTBI) from combat‐deployed healthy controls with high sensitivity, specificity, and diagnostic accuracy. This study provides an integrated framework for condensing large source‐imaging variable sets into optimal combinations of regions and frequencies with high diagnostic accuracy and cognitive relevance in cmTBI.
登录
查看更多内容
DOI：
10.1097/rmr.0000000000000062
发表时间：
2015-10
期刊：
Topics in magnetic resonance imaging : TMRI
影响因子：
--
作者：
Douglas DB;Iv M;Douglas PK;Anderson A;Vos SB;Bammer R;Zeineh M;Wintermark M
通讯作者：
Wintermark M
DOI：
10.1016/j.nicl.2015.09.011
发表时间：
2015
期刊：
NeuroImage. Clinical
影响因子：
--
作者：
Dimitriadis SI;Zouridakis G;Rezaie R;Babajani-Feremi A;Papanicolaou AC
通讯作者：
Papanicolaou AC
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
影响因子：
3.5
作者：
Gross, J;Ioannides, AA
通讯作者：
Ioannides, AA
影响因子：
3.3
作者：
Eo, Taejoon;Jun, Yohan;Hwang, Dosik
通讯作者：
Hwang, Dosik