Neuroimaging and Interventional Radiology, National Institute of Mental Health and Neuro Sciences, Bangalore, Karnataka, 560029, India.
Advance Brain Imaging Facility, Cognitive Neuroscience Centre, National Institute of Mental Health and Neuro Sciences, Bangalore, Karnataka, 560029, India.
Eur Radiol. 2019 Jul;29(7):3496-3505. doi: 10.1007/s00330-019-5997-2. Epub 2019 Feb 8.
Experimental models have provided compelling evidence for the existence of neural networks in temporal lobe epilepsy (TLE). To identify and validate the possible existence of resting-state "epilepsy networks," we used machine learning methods on resting-state functional magnetic resonance imaging (rsfMRI) data from 42 individuals with TLE.
Probabilistic independent component analysis (PICA) was applied to rsfMRI data from 132 subjects (42 TLE patients + 90 healthy controls) and 88 independent components (ICs) were obtained following standard procedures. Elastic net-selected features were used as inputs to support vector machine (SVM). The strengths of the top 10 networks were correlated with clinical features to obtain "rsfMRI epilepsy networks."
SVM could classify individuals with epilepsy with 97.5% accuracy (sensitivity = 100%, specificity = 94.4%). Ten networks with the highest ranking were found in the frontal, perisylvian, cingulo-insular, posterior-quadrant, thalamic, cerebello-thalamic, and temporo-thalamic regions. The posterior-quadrant, cerebello-thalamic, thalamic, medial-visual, and perisylvian networks revealed significant correlation (r > 0.40) with age at onset of seizures, the frequency of seizures, duration of illness, and a number of anti-epileptic drugs.
IC-derived rsfMRI networks contain epilepsy-related networks and machine learning methods are useful in identifying these networks in vivo. Increased network strength with disease progression in these "rsfMRI epilepsy networks" could reflect epileptogenesis in TLE.
• ICA of resting-state fMRI carries disease-specific information about epilepsy. • Machine learning can classify these components with 97.5% accuracy. • "Subject-specific epilepsy networks" could quantify "epileptogenesis" in vivo.
实验模型为颞叶癫痫（TLE）中神经网络的存在提供了令人信服的证据。为了识别和验证静息状态“癫痫网络”的可能存在，我们使用机器学习方法对 42 名 TLE 患者的静息态功能磁共振成像（rsfMRI）数据进行分析。
对来自 132 名受试者（42 名 TLE 患者+90 名健康对照者）的 rsfMRI 数据应用概率独立成分分析（PICA），并按照标准程序获得 88 个独立成分（IC）。弹性网选择的特征被用作支持向量机（SVM）的输入。前 10 个网络的强度与临床特征相关联，以获得“rsfMRI 癫痫网络”。
SVM 能够以 97.5%的准确率（灵敏度=100%，特异性=94.4%）对个体进行分类。在前额、周围脑区、扣带回-岛叶、后象限、丘脑、小脑-丘脑和颞叶-丘脑区域发现了 10 个排名最高的网络。后象限、小脑-丘脑、丘脑、内侧视觉和周围脑区网络与发作起始年龄、发作频率、疾病持续时间和抗癫痫药物数量呈显著相关（r＞0.40）。
IC 衍生的 rsfMRI 网络包含与癫痫相关的网络，机器学习方法可用于在体内识别这些网络。这些“rsfMRI 癫痫网络”中随着疾病进展网络强度的增加可能反映了 TLE 的癫痫发生。
• 静息态 fMRI 的 ICA 携带与癫痫相关的疾病特异性信息。• 机器学习可以以 97.5%的准确率对这些成分进行分类。• “个体特异性癫痫网络”可在体内定量“癫痫发生”。
