White matter lesion (WML) of presumed vascular origin is one of the common imaging manifestations of cerebral small vessel diseases, which is the main reason of cognitive impairment and even vascular dementia in the elderly. However, there is a lack of early and effective diagnostic methods currently. In recent years, studies of diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) have shown that cognitive impairment in patients with WMLs is associated with disrupted white matter microstructural and brain network connectivity. Therefore, it’s speculated that DTI and rs-fMRI can be effective in early imaging diagnosis of WMLs-related cognitive impairment. This article reviews the role and significance of DTI and rs-fMRI in WMLs-related cognitive impairment.
ObjectiveTo explore the effect mechanism of rehabilitation therapy post incomplete spinal cord injury (ISCI) in the view of graph theoretic analysis of the whole brain regions by the means of resting state functional magnetic resonance imaging (rs-fMRI).MethodsPatients with ISCI admitted to the Department of Rehabilitation Medicine of Tsinghua University Affiliated Beijing Tsinghua Changgung Hospital from January 2017 to June 2020 were selected and healthy subjects recruited in the same period were also selected. The patients were given comprehensive rehabilitation treatment for 2 weeks, including physical therapy, functional electrical stimulation treadwheel, walking training, etc. Healthy subjects and patients before and after treatment course were examined by rs-fMRI. While patients were assessed using the motor and sensory scores of American Spinal Injury Association (ASIA), muscle tone assessment, pain assessment, Walking Index for spinal cord injury (WISCI) as well as the Spinal Cord Independence Measure (SCIM).ResultsA total of 23 ISCI patients and 22 healthy subjects were included. After 2 weeks of treatment, ASIA lower limb motor function scores (P<0.001), ASIA sensory scores (P=0.005), Visual Analogue Scale (VAS) (P=0.027), WISCI (P=0.005) and SCIM (P<0.001) scores of the patients were significantly improved compared with before treatment. Before treatment, compared with healthy subjects, ISCI patients had lower betweenness centrality (BC) in the brain regions of R38, lower local efficiency (LE) in L21, L22, L39, L41, L42, L44, L48, R22, R39 and lower weighted degree (WD) in L22, L39, L41, L44, L48, R22, R39. After treatment, compared with the healthy subjects, the BC of R5, R6, R7, AR111 and AL112 of ISCI patients increased and in R6 and AR94, the clustering coefficient increased. The LE and WD of L21 and R21 in ISCI patients after treatment were higher than those before treatment.ConclusionsThe functional analysis of the whole brain network based on graph analysis can sensitively reflect the changes of brain network remodeling in patients with ISCI. Spinal cord injury can cause the decline of graph theoretical attributes of the auditory center-related brain regions. After rehabilitation treatment, the sensorimotor cortex, auditory center and extravertebral brain regions information transmitting ability in the whole brain network are improved, suggesting that rehabilitation training may participate in brain function remodeling by activating the sensorimotor center and non-motor center-related brain regions.
Currently, about one-third of patients with anti-epilepsy drug or resective surgery continue to have sezure, the mechanism remin unknown. Up to date, the main target for presurgical evaluation is to determene the EZ and SOZ. Since the early nineties of the last century network theory was introduct into neurology, provide new insights into understanding the onset, propagation and termination. Focal seizure can impact the function of whole brain, but the abnormal pattern is differet to generalized seizure. Brain network is a conception of mathematics. According to the epilepsy, network node and hub are related to the treatment. Graphy theory and connectivity are main algorithms. Understanding the mechanism of epilepsy deeply, since study the theory of epilepsy network, can improve the planning of surgery, resection epileptogenesis zone, seizure onset zone and abnormal node of hub simultaneously, increase the effect of resectiv surgery and predict the surgery outcome. Eventually, develop new drugs for correct the abnormal network and increase the effect. Nowadays, there are many algorithms for the brain network. Cooperative study by the clinicans and biophysicists instituted standard and extensively applied algorithms is the precondition of widely used clinically.
The deep learning-based automatic detection of epilepsy electroencephalogram (EEG), which can avoid the artificial influence, has attracted much attention, and its effectiveness mainly depends on the deep neural network model. In this paper, an attention-based multi-scale residual network (AMSRN) was proposed in consideration of the multiscale, spatio-temporal characteristics of epilepsy EEG and the information flow among channels, and it was combined with multiscale principal component analysis (MSPCA) to realize the automatic epilepsy detection. Firstly, MSPCA was used for noise reduction and feature enhancement of original epilepsy EEG. Then, we designed the structure and parameters of AMSRN. Among them, the attention module (AM), multiscale convolutional module (MCM), spatio-temporal feature extraction module (STFEM) and classification module (CM) were applied successively to signal reexpression with attention weighted mechanism as well as extraction, fusion and classification for multiscale and spatio-temporal features. Based on the Children’s Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) public dataset, the AMSRN model achieved good results in sensitivity (98.56%), F1 score (98.35%), accuracy (98.41%) and precision (98.43%). The results show that AMSRN can make good use of brain network information flow caused by seizures to enhance the difference among channels, and effectively capture the multiscale and spatio-temporal features of EEG to improve the performance of epilepsy detection.