Functional Connectivity Changes in Multiple-Frequency Bands in Acute Basal Ganglia Ischemic Stroke Patients: A Machine Learning Approach

Network Abnormalities in Ischemic Stroke: A Meta-analysis of Resting-State Functional Connectivity

Aberrant large-scale resting-state functional connectivity (rsFC) has been frequently documented in ischemic stroke. However, it remains unclear about the altered patterns of within- and across-network connectivity. The purpose of this meta-analysis was to identify the altered rsFC in patients with ischemic stroke relative to healthy controls, as well as to reveal longitudinal changes of network dysfunctions across acute, subacute, and chronic phases. A total of 24 studies were identified as eligible for inclusion in the present meta-analysis. These studies included 269 foci observed in 58 contrasts (558 patients with ischemic stroke; 526 healthy controls; 38.84% female). The results showed: (1) within-network hypoconnectivity in the sensorimotor network (SMN), default mode network (DMN), frontoparietal network (FPN), and salience network (SN), respectively; (2) across-network hypoconnectivity between the SMN and both of the SN and visual network, and between the FPN and both of the SN and DMN; and (3) across-network hyperconnectivity between the SMN and both of the DMN and FPN, and between the SN and both of the DMN and FPN. Meta-regression showed that hypoconnectivity between the DMN and the FPN became less pronounced as the ischemic stroke phase progressed from the acute to the subacute and chronic phases. This study provides the first meta-analytic evidence of large-scale rsFC dysfunction in ischemic stroke. These dysfunctional biomarkers could help identify patients with ischemic stroke at risk for cognitive, sensory, motor, and emotional impairments and further provide potential insight into developing diagnostic models and therapeutic interventions for rehabilitation and recovery.

Artificial intelligence for MRI stroke detection: a systematic review and meta-analysis

OBJECTIVES

This systematic review and meta-analysis aimed to assess the stroke detection performance of artificial intelligence (AI) in magnetic resonance imaging (MRI), and additionally to identify reporting insufficiencies.

METHODS

PRISMA guidelines were followed. MEDLINE, Embase, Cochrane Central, and IEEE Xplore were searched for studies utilising MRI and AI for stroke detection. The protocol was prospectively registered with PROSPERO (CRD42021289748). Sensitivity, specificity, accuracy, and area under the receiver operating characteristic (ROC) curve were the primary outcomes. Only studies using MRI in adults were included. The intervention was AI for stroke detection with ischaemic and haemorrhagic stroke in separate categories. Any manual labelling was used as a comparator. A modified QUADAS-2 tool was used for bias assessment. The minimum information about clinical artificial intelligence modelling (MI-CLAIM) checklist was used to assess reporting insufficiencies. Meta-analyses were performed for sensitivity, specificity, and hierarchical summary ROC (HSROC) on low risk of bias studies.

RESULTS

Thirty-three studies were eligible for inclusion. Fifteen studies had a low risk of bias. Low-risk studies were better for reporting MI-CLAIM items. Only one study examined a CE-approved AI algorithm. Forest plots revealed detection sensitivity and specificity of 93% and 93% with identical performance in the HSROC analysis and positive and negative likelihood ratios of 12.6 and 0.079.

CONCLUSION

Current AI technology can detect ischaemic stroke in MRI. There is a need for further validation of haemorrhagic detection. The clinical usability of AI stroke detection in MRI is yet to be investigated.

CRITICAL RELEVANCE STATEMENT

This first meta-analysis concludes that AI, utilising diffusion-weighted MRI sequences, can accurately aid the detection of ischaemic brain lesions and its clinical utility is ready to be uncovered in clinical trials.

KEY POINTS

There is a growing interest in AI solutions for detection aid. The performance is unknown for MRI stroke assessment. AI detection sensitivity and specificity were 93% and 93% for ischaemic lesions. There is limited evidence for the detection of patients with haemorrhagic lesions. AI can accurately detect patients with ischaemic stroke in MRI.

Relationship between temporal dynamics of intrinsic brain activity and motor function remodeling in patients with acute BGIS

Background

patients with acute basal ganglia ischemic stroke (BGIS) show changes in local brain activity represented by the amplitude of low-frequency fluctuation (ALFF), but the time-varying characteristics of this local nerve activity are still unclear. This study aimed to investigate the abnormal time-varying local brain activity of patients with acute BGIS by using the ALFF method combined with the sliding-window approach.

Methods

In this study, 34 patients with acute BGIS with motor dysfunction and 44 healthy controls (HCs) were recruited. The dynamic amplitude of low-frequency fluctuation (dALFF) was employed to detect the alterations in brain activity induced by acute BGIS patients. A two-sample t-test comparison was performed to compare the dALFF value between the two groups and a Spearman correlation analysis was conducted to assess the relationship between the local brain activity abnormalities and clinical characteristics.

Results

Compared with HCs, the activity of neurons in the left temporal pole (TP), parahippocampal gyrus (paraHIP), middle occipital gyrus (MOG), dorsolateral superior frontal gyrus (SFGdl), medial cingulate cortex (MCC), right rectus, precuneus (PCu) and right cerebellum crus1 were significantly increased in patients with BGIS. In addition, we found that there was a negative correlation (r = -0.458, p = 0.007) between the dALFF value of the right rectus and the scores of the National Institutes of Health Stroke Scale (NIHSS), and a positive correlation (r = 0.488, 0.499, p < 0.05) with the scores of the Barthel Index scale (BI) and the Fugl Meyer motor function assessment (FMA). ROC analysis results demonstrated that the area under the curves (AUC) of the right rectus was 0.880, p<0.001.

Conclusion

The pattern of intrinsic brain activity variability was altered in patients with acute BGIS compared with HCs. The abnormal dALFF variability might be a potential tool to assess motor function in patients with acute BGIS and potentially inform the diagnosis of this disease.

Altered Effective Connectivity of the Primary Motor Cortex in Transient Ischemic Attack

Objective

This study is aimed at exploring alteration in motor-related effective connectivity in individuals with transient ischemic attack (TIA).

Methods

A total of 48 individuals with TIA and 41 age-matched and sex-matched healthy controls (HCs) were recruited for this study. The participants were scanned using MRI, and their clinical characteristics were collected. To investigate motor-related effective connectivity differences between individuals with TIA and HCs, the bilateral primary motor cortex (M1) was used as the regions of interest (ROIs) to perform a whole-brain Granger causality analysis (GCA). Furthermore, partial correlation was used to evaluate the relationship between GCA values and the clinical characteristics of individuals with TIA.

Results

Compared with HCs, individuals with TIA demonstrated alterations in the effective connectivity between M1 and widely distributed brain regions involved in motor, visual, auditory, and sensory integration. In addition, GCA values were significantly correlated with high- and low-density lipoprotein cholesterols in individuals with TIA.

Conclusion

This study provides important evidence for the alteration of motor-related effective connectivity in TIA, which reflects the abnormal information flow between different brain regions. This could help further elucidate the pathological mechanisms of motor impairment in individuals with TIA and provide a new perspective for future early diagnosis and intervention for TIA.

Regional homogeneity alterations in multifrequency bands in patients with basal ganglia stroke: A resting-state functional magnetic resonance imaging study

Objective

The aim of this study was to investigate the spontaneous regional neural activity abnormalities in patients with acute basal ganglia ischemic stroke (BGIS) using a multifrequency bands regional homogeneity (ReHo) method and to explore whether the alteration of ReHo values was associated with clinical characteristics.

Methods

In this study, 34 patients with acute BGIS and 44 healthy controls (HCs) were recruited. All participants were examined by resting-state functional magnetic resonance imaging (rs-fMRI). The ReHo method was used to detect the alterations of spontaneous neural activities in patients with acute BGIS. A two-sample t-test comparison was performed to compare the ReHo value between the two groups, and a Pearson correlation analysis was conducted to assess the relationship between the regional neural activity abnormalities and clinical characteristics.

Results

Compared with the HCs, the patients with acute BGIS showed increased ReHo in the left caudate and subregions such as the right caudate and left putamen in conventional frequency bands. In the slow-5 frequency band, patients with BGIS showed decreased ReHo in the left medial cingulum of BGIS compared to the HCs and other subregions such as bilateral caudate and left putamen. No brain regions with ReHo alterations were found in the slow-4 frequency band. Moreover, we found that the ReHo value of left caudate was positively correlated with the NIHSS score.

Conclusion

Our findings revealed the alterations of ReHo in patients with acute BGIS in a specific frequency band and provided a new insight into the pathogenesis mechanism of BGIS. This study demonstrated the frequency-specific characteristics of ReHo in patients with acute BGIS, which may have a positive effect on the future neuroimaging studies.