Cerebral Small Vessel Disease: A Review Focusing on Pathophysiology, Biomarkers, and Machine Learning Strategies

Cognitive Impairment in Cerebral Small Vessel Disease Is Associated with Corpus Callosum Microstructure Changes Based on Diffusion MRI

The cerebral small vessel disease (cSVD) is one of the main causes of vascular and mixed cognitive impairment (CI), and it is associated, in particular, with brain ageing. An understanding of structural tissue changes in an intact cerebral white matter in cSVD might allow one to develop the sensitive biomarkers for early diagnosis and monitoring of disease progression.

PURPOSE OF THE STUDY

to evaluate microstructural changes in the corpus callosum (CC) using diffusion MRI (D-MRI) approaches in cSVD patients with different severity of CI and reveal the most sensitive correlations of diffusion metrics with CI.

METHODS

the study included 166 cSVD patients (51.8% women; 60.4 ± 7.6 years) and 44 healthy volunteers (65.9% women; 59.6 ± 6.8 years). All subjects underwent D-MRI (3T) with signal (diffusion tensor and kurtosis) and biophysical (neurite orientation dispersion and density imaging, NODDI, white matter tract integrity, WMTI, multicompartment spherical mean technique, MC-SMT) modeling in three CC segments as well as a neuropsychological assessment.

RESULTS

in cSVD patients, microstructural changes were found in all CC segments already at the subjective CI stage, which was found to worsen into mild CI and dementia. More pronounced changes were observed in the forceps minor. Among the signal models FA, MD, MK, RD, and RK, as well as among the biophysical models, MC-SMT (EMD, ETR) and WMTI (AWF) metrics exhibited the largest area under the curve (>0.85), characterizing the loss of microstructural integrity, the severity of potential demyelination, and the proportion of intra-axonal water, respectively. Conclusion: the study reveals the relevance of advanced D-MRI approaches for the assessment of brain tissue changes in cSVD. The identified diffusion biomarkers could be used for the clarification and observation of CI progression.

3D Quantitative-Amplified Magnetic Resonance Imaging (3D q-aMRI)

Amplified MRI (aMRI) is a promising new technique that can visualize pulsatile brain tissue motion by amplifying sub-voxel motion in cine MRI data, but it lacks the ability to quantify the sub-voxel motion field in physical units. Here, we introduce a novel post-processing algorithm called 3D quantitative amplified MRI (3D q-aMRI). This algorithm enables the visualization and quantification of pulsatile brain motion. 3D q-aMRI was validated and optimized on a 3D digital phantom and was applied in vivo on healthy volunteers for its ability to accurately measure brain parenchyma and CSF voxel displacement. Simulation results show that 3D q-aMRI can accurately quantify sub-voxel motions in the order of 0.01 of a voxel size. The algorithm hyperparameters were optimized and tested on in vivo data. The repeatability and reproducibility of 3D q-aMRI were shown on six healthy volunteers. The voxel displacement field extracted by 3D q-aMRI is highly correlated with the displacement measurements estimated by phase contrast (PC) MRI. In addition, the voxel displacement profile through the cerebral aqueduct resembled the CSF flow profile reported in previous literature. Differences in brain motion was observed in patients with dementia compared with age-matched healthy controls. In summary, 3D q-aMRI is a promising new technique that can both visualize and quantify pulsatile brain motion. Its ability to accurately quantify sub-voxel motion in physical units holds potential for the assessment of pulsatile brain motion as well as the indirect assessment of CSF homeostasis. While further research is warranted, 3D q-aMRI may provide important diagnostic information for neurological disorders such as Alzheimer's disease.

Insulin Resistance, a Risk Factor for Alzheimer's Disease: Pathological Mechanisms and a New Proposal for a Preventive Therapeutic Approach

Peripheral insulin resistance (IR) is a well-documented, independent risk factor for the development of type 2 diabetes, cardiovascular disease, cancer and cellular senescence. Recently, the brain has also been identified as an insulin-responsive region, where insulin acts as regulator of the brain metabolism. Despite the clear link between IR and the brain, the exact mechanisms underlying this relationship remain unclear. Therapeutic intervention in patients showing symptoms of neurodegenerative diseases has produced little or no results. It has been demonstrated that insulin resistance plays a significant role in the pathogenesis of neurodegenerative diseases, particularly cognitive decline. Peripheral and brain IR may represent a modifiable state that could be used to prevent major brain disorders. In this review, we will analyse the scientific literature supporting IR as a risk factor for Alzheimer's disease and suggest some therapeutic strategies to provide a new proposal for the prevention of brain IR and its consequences.

Pathogenesis of Cerebral Small Vessel Disease: Role of the Glymphatic System Dysfunction

Cerebral small vessel disease (CSVD) is a group of pathologies that affect the cerebral blood vessels. CSVD accounts for 25% of strokes and contributes to 45% of dementia. However, the pathogenesis of CSVD remains unclear, involving a variety of complex mechanisms. CSVD may result from dysfunction in the glymphatic system (GS). The GS contains aquaporin-4 (AQP-4), which is in the perivascular space, at the endfeet of the astrocyte. The GS contributes to the removal of waste products from the central nervous system, occupying perivascular spaces and regulating the exchange and movement of cerebrospinal fluid and interstitial fluid. The GS involves astrocytes and aquaporin channels, which are components of the blood-brain barrier, and problems with them may constitute the pathogenesis of CSVD. Vascular risk factors, including diabetes, dilate the perivascular space, disrupting the glymphatic system and the active regulation of AQP-4. CSVD exacerbation due to disorders of the GS is associated with multiple vasculopathies. Dysfunction of the glymphatic system and AQP-4 interferes with the functioning of the blood-brain barrier, which exacerbates CSVD. In a long-term follow-up of CSVD patients with microbleeds, lacunar infarcts, and white matter hyperintensity, several vascular risk factors, including hypertension, increased the risk of ischemic stroke. Dysfunction of the GS may be the cause of CSVD; however, the underlying treatment needs to be studied further.

High glycated albumin is associated with early neurological deterioration in patients with acute ischemic stroke

BACKGROUND

Glycated albumin (GA) is an indicator of glycemic variability over the past 2-4 weeks and has suitable characteristics for predicting the prognosis of ischemic stroke during the acute phase. This study evaluated the association between early neurological deterioration (END) and GA values in patients with acute ischemic stroke (AIS).

METHODS

We assessed consecutive patients with AIS between 2022 and 2023 at two large medical centers in Korea. END was defined as an increase of ≥ 2 in the total National Institutes of Health Stroke Scale (NIHSS) score or ≥ 1 in the motor NIHSS score within the first 72 h of admission. We evaluated various glycemic parameters including fasting glucose (mg/dL), hemoglobin A1c (%), and GA (%).

RESULTS

In total, 531 patients with AIS were evaluated (median age: 69 years, male sex: 66.3%). In the multivariable logistic regression analysis, GA value was positively associated with END (adjusted odds ratio [aOR] = 3.24, 95% confidence interval [CI]: 1.10-9.50). Initial NIHSS score (aOR = 1.04, 95% CI: 1.01-1.08) and thrombolytic therapy (aOR = 2.06, 95% CI: 1.14-3.73) were also associated with END. In a comparison of the predictive power of glycemic parameters for END, GA showed a higher area under the curve value on the receiver operating characteristic curve than fasting glucose and hemoglobin A1c.

CONCLUSIONS

High GA values were associated with END in patients with AIS. Furthermore, GA was a better predictor of END than fasting glucose or hemoglobin A1c.

Racial and ethnic differences in restarting antiplatelet therapy in patients with primary intracranial hemorrhage: a systematic review and meta-analysis

BACKGROUND

There has long been clinical disagreement over the resumption of antiplatelet therapy in patients with primary intracranial hemorrhage (ICH). This meta-analysis aimed to systematically evaluate the efficacy and safety of restarting antiplatelet therapy after ICH among different races and ethnicities.

METHODS

All relevant medical studies involving adults with antiplatelet-associated ICH published in PubMed, The Cochrane Library and Chinese National Knowledge Infrastructure from inception to March 2024 were sourced. Outcome measures were thromboembolic events (stroke and myocardial infarction) and recurrence of ICH. After assessing study heterogeneity and publication bias, we performed a meta-analysis using random-effects model to assess the strength of association between resumption of antiplatelet therapy and our outcomes.The review was not registered and the review protocol was not prepared.

RESULTS

Thirty-five studies were included, with 9758 ICH patients. Subgroup analysis revealed that restarting antiplatelet therapy was associated with a significantly higher risk of recurrence or aggravation of cerebral hemorrhage in Asians[OR = 1.48, 95% CI (1.13-1.94), P = 0.004]; in Caucasians, on the contrary, reinitiation of antiplatelet therapy was not associated with a significantly higher risk of recurrence or aggravation of cerebral hemorrhage [OR = 0.85, 95% CI (0.67-1.06), P = 0.149]. Reinitiation of antiplatelet therapy was associated with a significantly lower risk of cerebral infarction [OR = 0.61, 95% CI (0.39-0.96), P = 0.033]. Restarting antiplatelet therapy after cerebral hemorrhage was not associated with a higher incidence rate of mortality [OR = 0.79, 95% CI (0.57, 1.08), P = 0.138], myocardial infarction [OR = 2.40, 95%CI (0.53,10.79), P = 0.253], hemiparesis [OR = 0.38, 95%CI (0.03,4.81), P = 0.451], neurological deficit [OR = 0.86,95%CI(0.32,2.33),P = 0.766].

CONCLUSION

Reinstitution of antiplatelet therapy after ICH was associated with a lower risk of thromboembolic complications.Resumption of antiplatelet therapy was not associated with a higher incidence of cerebral hemorrhage in Caucasians, but may be associated with a higher risk of cerebral hemorrhage recurrence in Asian populations.

A novel rat model of cerebral small vessel disease based on vascular risk factors of hypertension, aging, and cerebral hypoperfusion

Cerebral small vessel disease (CSVD) is a major cause of vascular cognitive impairment and functional loss in elderly patients. Progressive remodeling of cerebral microvessels due to arterial hypertension or other vascular risk factors, such as aging, can cause dementia or stroke. Typical imaging characteristics of CSVD include cerebral microbleeds (CMB), brain atrophy, small subcortical infarctions, white matter hyperintensities (WMH), and enlarged perivascular spaces (EPVS). Nevertheless, no animal models that reflect all the different aspects of CSVD have been identified. Here, we generated a new CSVD animal model using D-galactose (D-gal) combined with cerebral hypoperfusion in spontaneously hypertensive rats (SHR), which showed all the hallmark pathological features of CSVD and was based on vascular risk factors. SHR were hypodermically injected with D-gal (400 mg/kg/d) and underwent modified microcoil bilateral common carotid artery stenosis surgery. Subsequently, neurological assessments and behavioral tests were performed, followed by vascular ultrasonography, electron microscopy, flow cytometry, and histological analyses. Our rat model showed multiple cerebrovascular pathologies, such as CMB, brain atrophy, subcortical small infarction, WMH, and EPVS, as well as the underlying causes of CSVD pathology, including oxidative stress injury, decreased cerebral blood flow, structural and functional damage to endothelial cells, increased blood-brain barrier permeability, and inflammation. The use of this animal model will help identify new therapeutic targets and subsequently aid the development and testing of novel therapeutic interventions. Main process of the study: Firstly, we screened for optimal conditions for mimicking aging by injecting D-gal into rats for 4 and 8 weeks. Subsequently, we performed modified microcoil BCAS intervention for 4 and 8 weeks in rats to screen for optimal hypoperfusion conditions. Finally, based on these results, we combined D-gal for 8 weeks and modified microcoil BCAS for 4 weeks to explore the changes in SHR.

Effect of high-fat diet on cerebral pathological changes of cerebral small vessel disease in SHR/SP rats

Cerebral small vessel diseases (CSVD) are neurological disorders associated with microvessels, manifested pathologically as white matter (WM) changes and cortical microbleeds, with hypertension as a risk factor. Additionally, a high-fat diet (HFD) can affect peripheral vessel health. Our study explored how HFD affects cerebral small vessels in normotensive WKY, hypertensive SHR, and SHR/SP rats. The MRI results revealed that HFD specifically increased WM hyperintensity in SHR/SP rats. Pathologically, it increased WM pallor and vacuolation in SHR and SHR/SP rats. Levels of blood-brain barrier (BBB) protein claudin 5 were decreased in SHR and SHR/SP compared to WKY, with HFD having minimal impact on these levels. Conversely, collagen IV levels remained consistent among the rat strains, which were increased by HFD. Consequently, HFD caused vessel leakage in all rat strains, particularly within the corpus callosum of SHR/SP rats. To understand the underlying mechanisms, we assessed the levels of hypoxia-inducible factor-1α (HIF-1α), Gp91-phox, and neuroinflammatory markers astrocytes, and microglia were increased in SHR and SHR/SP compared to WKY and were further elevated by HFD in all rat strains. Gp91-phox was also increased in SHR and SHR/SP compared to WKY, with HFD causing an increase in WKY but little effect in SHR and SHR/SP. In conclusion, our study demonstrates that HFD, in combined with hypertension, intensifies cerebral pathological alterations in CSVD rats. This exacerbation involves increased oxidative stress and HIF-1α in cerebral vessels, triggering neuroinflammation, vascular basement membrane remodeling, IgG leakage, and ultimately WM damage.

Analysis of radiological features in patients with post-stroke depression and cognitive impairment

Post-stroke depression (PSD) and post-stroke cognitive impairment (PSCI) are common complications following a stroke, significantly impacting the quality of life and survival time of survivors. Currently, the comorbidity of PSCI and PSD is receiving increasing attention, as they share some common clinical characteristics, mechanisms, risk factors, radiological features, and treatment strategies. They influence each other, with the clinical prevalence of PSD comorbid with PSCI reaching as high as 26.15 %. The prevention, screening, diagnosis, and treatment of PSD and PSCI require collaboration across clinical, radiological, and neuropsychological evaluations. This paper aims to summarize the common radiological features of both conditions from a radiological perspective, which may aid in identifying early screening and predictive imaging biomarkers.

Hypothyroidism's effect on stroke limited to specific subtypes: A Mendelian randomization study

BACKGROUND

The association between hypothyroidism and stroke remains controversial and the association between hypothyroidism and stroke subtypes has not been satisfactorily researched. This study aimed to explore the causal effect of hypothyroidism on the risk of stroke and its subtypes by Mendelian randomization (MR) analysis.

METHODS

Single nucleotide polymorphisms (SNPs) were selected from published genome-wide association studies (GWAS) meta-analysis as instrumental variables (IVs) for hypothyroidism. As outcomes, summary GWAS data for stroke and its subtypes were obtained from two other large GWAS meta-analyses, including any stroke (AS), any ischemic stroke (AIS), large vessel stroke (LAS), cardiogenic embolic stroke (CES), small vessel stroke (SVS), and intracranial hemorrhage (ICH). Univariate Mendelian randomization (UVMR) and multivariate Mendelian randomization (MVMR) were used to assess the causal effect of hypothyroidism on stroke and its subtypes.

RESULTS

In UVMR, genetically predicted hypothyroidism was significantly associated with LAS (OR = 1.14, 95CI = 1.02-1.27) and SVS (OR = 1.14, 95CI = 1.04-1.25), but not with AS, AIS, CES, and ICH. The results of the MVMR showed that after adjusting for smoking, alcohol consumption, hypertension, diabetes, low-density lipoprotein cholesterol (LDL-c), and body mass index (BMI), the causal association between hypothyroidism and SVS remained significant, while the association between hypothyroidism and LAS became nonsignificant.

CONCLUSION

Hypothyroidism is causally associated with risk for LAS and SVS, but not for other stroke subtypes. Hypothyroidism may be an independent risk factor for SVS, and vascular risk factors play an important role in hypothyroidism causing LAS.

Is cerebral small vessel disease a central nervous system interstitial fluidopathy?

A typical anatomical congregate and functionally distinct multicellular cerebrovascular dynamic confer diverse blood-brain barrier (BBB) and microstructural permeabilities to conserve the health of brain parenchymal and its microenvironment. This equanimity presupposes the glymphatic system that governs the flow and clearance of metabolic waste and interstitial fluids (ISF) through venous circulation. Following the introduction of glymphatic system concept, various studies have been carried out on cerebrospinal fluid (CSF) and ISF dynamics. These studies reported that the onset of multiple diseases can be attributed to impairment in the glymphatic system, which is newly referred as central nervous system (CNS) interstitial fluidopathy. One such condition includes cerebral small vessel disease (CSVD) with poorly understood pathomechanisms. CSVD is an umbrella term to describe a chronic progressive disorder affecting the brain microvasculature (or microcirculation) involving small penetrating vessels that supply cerebral white and deep gray matter. This review article proposes CSVD as a form of "CNS interstitial fluidopathy". Linking CNS interstitial fluidopathy with CSVD will open a better insight pertaining to the perivascular space fluid dynamics in CSVD pathophysiology. This may lead to the development of treatment and therapeutic strategies to ameliorate the pathology and adverse effect of CSVD.

Lower cerebrovascular reactivity in prefrontal cortex and weaker negative functional connectivity between prefrontal cortex and insula contribute to white matter hyperintensity-related anxiety or depression

BACKGROUND

White matter hyperintensities (WMHs) are associated with higher anxiety or depression (A/D) incidence. We investigated associations of WMHs with A/D, cerebrovascular reactivity (CVR), and functional connectivity (FC) to identify potential pathomechanisms.

METHODS

Participants with WMH (n = 239) and normal controls (NCs, n = 327) were assessed for A/D using the Hamilton Anxiety Rating Scale (HAMA) and Hamilton Depression Rating Scale (HAMD). The CVR and FC maps were constructed from resting-state functional MRI. Two-way analysis of covariance with fixed factors A/D and WMH was performed to identify regional CVR abnormalities. Seed-based FC analyses were then conducted on regions with WMH × A/D interaction effects on CVR. Logistic regression models were constructed to examine the utility of these measurements for identifying WMH-related A/D.

RESULTS

Participants with WMH related A/D exhibited significantly greater CVR in left insula and lower CVR in right superior frontal gyrus (SFG.R), and HAMA scores were negatively correlated with CVR in SFG.R (r = -0.156, P = 0.016). Insula-SFG.R negative FC was significantly weaker in WMH patients with suspected or definite A/D. A model including CVR plus FC changes identified WMH-associated A/D with highest sensitivity and specificity. In contrast, NCs with A/D exhibited greater CVR in prefrontal cortex and stronger FC within the default mode network (DMN) and between the DMN and executive control network.

LIMITATIONS

This cross-sectional study requires validation by longitudinal and laboratory studies.

CONCLUSIONS

Impaired CVR in SFG.R and weaker negative FC between prefrontal cortex and insula may contribute to WMH-related A/D, providing potential diagnostic imaging markers and therapeutic targets.

Impact of Immune Cells on Stroke Limited to Specific Subtypes: Evidence from Mendelian Randomization Study

INTRODUCTION

Stroke is one of the common diseases that pose a severe threat to human health, with immune cells playing a crucial role in its onset and recovery. However, the specific mechanisms and causal relationships of different immune cell groups in various clinical stroke subtypes are unclear. This study explored the causal relationship between immune cells and stroke and its subtypes using Mendelian randomization (MR) analysis.

METHODS

Data from genome-wide association studies were analyzed using inverse-variance weighted (IVW), MR-Egger, and weighted median methods for MR analysis, along with heterogeneity tests, sensitivity analysis, and pleiotropy analysis.

RESULTS

CD45RA+CD28-CD8+ T cell %T cell (OR 1.002, 95% CI 1.001-1.003; PFDR = 0.02), CD27 on CD24+CD27+ B cell (OR 1.127, 95% CI 1.061-1.198; PFDR = 0.04), CD27 on IgD-CD38dim B cell (OR 1.138, 95% CI 1.076-1.203; PFDR = 0.005), and CD27 on switched memory B cell (OR 1.144, 95% CI 1.076-1.216; PFDR = 0.01) were found to increase the risk of large artery stroke. Switched memory B cell %lymphocyte (OR 1.206, 95% CI 1.103-1.318; PFDR = 0.02) increased the risk of small vessel stroke. Reverse MR analysis did not reveal any reverse causal associations. Furthermore, by substituting the outcome data, a secondary MR analysis was conducted to validate the primary findings.

CONCLUSION

Our study reveals several causal links between immune phenotypes and stroke and its different subtypes, highlighting the complex interactions between the immune system and stroke. These findings provide new directions for further uncovering the biological basis of stroke and assist in advancing research on early interventions and treatment strategies.

Spatiotemporal consistency analysis of cerebral small vessel disease: an rs-fMRI study

Introduction

Cerebral small vessel disease (SVD) affects older adults, but traditional approaches have limited the understanding of the neural mechanisms of SVD. This study aimed to explore the effects of SVD on brain regions and its association with cognitive decline using the four-dimensional (spatiotemporal) consistency of local neural activity (FOCA) method.

Methods

Magnetic resonance imaging data from 42 patients with SVD and 38 healthy controls (HCs) were analyzed using the FOCA values. A two-sample t test was performed to compare the differences in FOCA values in the brain between the HCs and SVD groups. Pearson correlation analysis was conducted to analyze the association of various brain regions with SVD scores.

Results

The results revealed that the FOCA values in the right frontal_inf_oper, right temporal_pole_sup, and default mode network decreased, whereas those in the temporal_inf, hippocampus, basal ganglia, and cerebellum increased, in patients with SVD. Most of these varying brain regions were negatively correlated with SVD scores.

Discussion

This study suggested that the FOCA approach might have the potential to provide useful insights into the understanding of the neurophysiologic mechanisms of patients with SVD.

Response to electroconvulsive therapy in elderly patients with late-onset bipolar disorder: The impact of cerebral small vessel disease

OBJECTIVES

Cerebral Small Vessel Disease (CSVD) is a chronic, progressive vascular disorder that confers increased vulnerability to psychiatric syndromes, including late-life mood disorders. In this study, we investigated the impact of CSVD on electroconvulsive therapy (ECT) outcomes in patients with late-onset bipolar disorder (BD).

METHODS

A sample of 54 non-demented elderly patients (≥60 years) with late-onset BD and treatment-resistant major depression, mixed state, or catatonia who underwent bilateral ECT were included in this naturalistic observational study. A diagnosis of CSVD was established based on brain neuroimaging performed before ECT. All patients were evaluated before and after ECT using the Brief Psychiatric Rating Scale (BPRS), the Hamilton Rating Scale for Depression (HAM-D), and the Clinical Global Impression scale (CGI).

RESULTS

Of the total sample, 19 patients were diagnosed with CSVD (35.2%). No significant differences were observed at baseline between patients with and without CSVD. Overall, a response was obtained in 66%-68.5% of patients, with remission in 56.2%. No significant differences in ECT outcomes were found between those with and without CSVD, and both groups exhibited substantial improvements in symptom severity following ECT.

CONCLUSIONS

The outcome of ECT in late-onset BD was not influenced by the presence of CSVD. This finding aligns with previous research on unipolar depression. Accordingly, ECT should be considered for elderly patients with late-onset BD, regardless of the presence of CSVD.

Aldosteronism is associated with more severe cerebral small vessel disease in hypertensive intracerebral hemorrhage

Primary aldosteronism is associated with various types of cardiovascular and cerebrovascular damage independently of hypertension. Although chronic hypertension and related cerebral arteriosclerosis are the main risk factors for intracerebral hemorrhage, the effects of aldosteronism remain poorly understood. We enrolled 90 survivors of hypertensive intracerebral hemorrhage, 21 of them with aldosteronism and 69 with essential hypertension as controls in this study. Clinical parameters and neuroimaging markers of cerebral small vessel disease were recorded, and its correlations with aldosteronism were investigated. Our results showed that the aldosteronism group (55.2 ± 9.7 years, male 47.6%) had similar hypertension severity but exhibited a higher cerebral microbleed count (interquartile range) (8.5 [2.0‒25.8] vs 3 [1.0‒6.0], P = 0.005) and higher severity of dilated perivascular space in the basal ganglia (severe perivascular space [number >20], 52.4% vs. 24.6%, P = 0.029; large perivascular space [>3 mm], 52.4% vs. 20.3%, P = 0.010), compared to those with essential hypertension (53.8 ± 11.7 years, male 73.9%). In multivariate models, aldosteronism remained an independent predictor of a higher (>10) microbleed count (odds ratio = 8.60, P = 0.004), severe perivascular space (odds ratio = 4.00, P = 0.038); the aldosterone-to-renin ratio was associated with dilated perivascular space (P = 0.043) and large perivascular space (P = 0.008). In conclusions, survivors of intracerebral hemorrhage with aldosteronism showed a tendency towards more severe hypertensive arteriopathy than the essential hypertension counterparts independently of blood pressure; aldosteronism may contribute to dilated perivascular space around the deep perforating arteries. Aldosteronism is associated with more severe cerebral small vessel disease in hypertensive intracerebral hemorrhage.

Contour attention network for cerebrovascular segmentation from TOF-MRA volumetric images

BACKGROUND

Cerebrovascular segmentation is a crucial step in the computer-assisted diagnosis of cerebrovascular pathologies. However, accurate extraction of cerebral vessels from time-of-flight magnetic resonance angiography (TOF-MRA) data is still challenging due to the complex topology and slender shape.

PURPOSE

The existing deep learning-based approaches pay more attention to the skeleton and ignore the contour, which limits the segmentation performance of the cerebrovascular structure. We aim to weight the contour of brain vessels in shallow features when concatenating with deep features. It helps to obtain more accurate cerebrovascular details and narrows the semantic gap between multilevel features.

METHODS

This work proposes a novel framework for priority extraction of contours in cerebrovascular structures. We first design a neighborhood-based algorithm to generate the ground truth of the cerebrovascular contour from original annotations, which can introduce useful shape information for the segmentation network. Moreover, We propose an encoder-dual decoder-based contour attention network (CA-Net), which consists of the dilated asymmetry convolution block (DACB) and the Contour Attention Module (CAM). The ancillary decoder uses the DACB to obtain cerebrovascular contour features under the supervision of contour annotations. The CAM transforms these features into a spatial attention map to increase the weight of the contour voxels in main decoder to better restored the vessel contour details.

RESULTS

The CA-Net is thoroughly validated using two publicly available datasets, and the experimental results demonstrate that our network outperforms the competitors for cerebrovascular segmentation. We achieved the average dice similarity coefficient (D S C $DSC$ ) of 68.15 and 99.92% in natural and synthetic datasets. Our method segments cerebrovascular structures with better completeness.

CONCLUSIONS

We propose a new framework containing contour annotation generation and cerebrovascular segmentation network that better captures the tiny vessels and improve vessel connectivity.

Relationships between intracranial arterial dolichoectasia and small vessel disease in patients with ischaemic stroke: a systematic review and meta-analysis

BACKGROUND

Intracranial arterial dolichoectasia (IADE) is a common arterial finding of dilation, elongation, or both, affecting large intracranial vessels, and associated with vascular risk factors, including hypertension. Associations of IADE with neuroimaging cerebral small vessel disease (CSVD) may be relevant for diagnosis and prognosis in patients with stroke. The study aimed to conduct an updated systematic review and meta-analysis of observational studies to investigate the relationships of IADE with well-defined CSVD markers in patients with ischaemic stroke.

METHODS

We systematically searched PubMed, Embase, and Scopus for studies on IADE in ischaemic stroke patients with fulfilling predefined inclusion criteria. We pooled data to conduct a meta-analysis to compare the prevalence of SVD markers between patients with and without IADE groups using risk ratios (RRs) and 95% confidence intervals (CIs).

RESULTS

From 157 retrieved abstracts, we included six studies from seven publications comprising 6102 patients with ischaemic stroke. The mean age of patients was 52.8 years, and 3691 (60.5%) were male. IADE was diagnosed in 11.4% (95% CI 8.9-13.9) (761) of included patients; 51.8% (3160) had hypertension. Compared to patients without IADE, individuals diagnosed with IADE had a significantly increased prevalence of lacune (RR 1.67, 95% CI 1.36-2.06, P < 0.01, I2 = 0.00%), cerebral microbleeds (CMBs) (RR 2.56, 95% CI 1.53-4.28, P < 0.01, I2 = 84.95%) and white matter hyperintensities (WMHs) (RR 2.17, 95% CI 1.84-2.56, P < 0.01, I2 = 0.00%).

CONCLUSIONS

In patients with ischaemic stroke, IADE is associated with a higher prevalence of CSVD markers, including lacunes, CMBs, and WMHs. Further studies are needed to clarify the mechanisms underlying these associations and their potential relevance for the understanding, diagnosis, and treatment of CSVD.

Unraveling the link: white matter damage, gray matter atrophy and memory impairment in patients with subcortical ischemic vascular disease

Introduction

Prior MRI studies have shown that patients with subcortical ischemic vascular disease (SIVD) exhibited white matter damage, gray matter atrophy and memory impairment, but the specific characteristics and interrelationships of these abnormal changes have not been fully elucidated.

Materials and methods

We collected the MRI data and memory scores from 29 SIVD patients with cognitive impairment (SIVD-CI), 29 SIVD patients with cognitive unimpaired (SIVD-CU) and 32 normal controls (NC). Subsequently, the thicknesses and volumes of the gray matter regions that are closely related to memory function were automatically assessed using FreeSurfer software. Then, the volume, fractional anisotropy (FA), mean diffusivity (MD), amplitude of low-frequency fluctuation (ALFF) and regional homogeneity (ReHo) values of white matter hyperintensity (WMH) region and normal-appearing white matter (NAWM) were obtained using SPM, DPARSF, and FSL software. Finally, the analysis of covariance, spearman correlation and mediation analysis were used to analyze data.

Results

Compared with NC group, patients in SIVD-CI and SIVD-CU groups showed significantly abnormal volume, FA, MD, ALFF, and ReHo values of WMH region and NAWM, as well as significantly decreased volume and thickness values of gray matter regions, mainly including thalamus, middle temporal gyrus and hippocampal subfields such as cornu ammonis (CA) 1. These abnormal changes were significantly correlated with decreased visual, auditory and working memory scores. Compared with the SIVD-CU group, the significant reductions of the left CA2/3, right amygdala, right parasubiculum and NAWM volumes and the significant increases of the MD values in the WMH region and NAWM were found in the SIVD-CI group. And the increased MD values were significantly related to working memory scores. Moreover, the decreased CA1 and thalamus volumes mediated the correlations between the abnormal microstructure indicators in WMH region and the decreased memory scores in the SIVD-CI group.

Conclusion

Patients with SIVD had structural and functional damages in both WMH and NAWM, along with specific gray matter atrophy, which were closely related to memory impairment, especially CA1 atrophy and thalamic atrophy. More importantly, the volumes of some temporomesial regions and the MD values of WMH regions and NAWM may be potentially helpful neuroimaging indicators for distinguishing between SIVD-CI and SIVD-CU patients.

Monocyte to high-density lipoprotein cholesterol ratio is associated with cerebral small vessel diseases

BACKGROUND

Inflammation is a major pathological mechanism underlying cerebrovascular disease. Recently, a new inflammatory marker based on the ratio between monocyte count and high-density lipoprotein (HDL) cholesterol has been proposed. In this study, we evaluated the relationship between monocyte-to-HDL cholesterol ratio (MHR) and cerebral small vessel disease (cSVD) lesions in health check-up participants.

METHODS

This study was a retrospective cross-sectional study based on a registry that prospectively collected health check-up participants between 2006 and 2013. Three cSVD subtypes were measured on brain magnetic resonance imaging. White matter hyperintensity (WMH) volume, and lacunes and cerebral microbleeds (CMBs) were quantitatively and qualitatively measured, respectively. The MHR was calculated according to the following formula: MHR = monocyte counts (× 103/μL) / HDL cholesterol (mmol/L).

RESULTS

In total, 3,144 participants were evaluated (mean age: 56 years, male sex: 53.9%). In multivariable analyzes adjusting for confounders, MHR was significantly associated with WMH volume [β = 0.099, 95% confidence interval (CI) = 0.025 to 0.174], lacune [adjusted odds ratio (aOR) = 1.43, 95% CI = 1.07-1.91], and CMB (aOR = 1.51, 95% CI = 1.03-2.19). In addition, MHR showed a positive quantitative relationship with cSVD burden across all three subtypes: WMH (P < 0.001), lacunes (P < 0.001), and CMBs (P < 0.001).

CONCLUSIONS

High MHR was closely associated with cSVD in health check-up participants. Because these associations appear across all cSVD subtypes, inflammation appears to be a major pathological mechanism in the development of various cSVDs.

Modifiable vascular risk factors contribute to stroke in 1080 NOTCH3 R544C carriers in Taiwan Biobank

BACKGROUND AND AIM

Previous studies have suggested cardiovascular risk factors increase the risk of not only common sporadic stroke but also of stroke in patients with monogenic stroke disorders including CADASIL. We investigated the effects of the NOTCH3 Arg544Cys (R544C) variant and associated vascular risk factors on stroke in the Taiwanese population.

METHODS

This study was conducted using data from the Taiwan Biobank, consisting of at least 130,000 Han Chinese participants. The genotype was derived from customized genome-wide arrays for 650,000 to 750,000 single-nucleotide polymorphisms (SNPs). Individuals with NOTCH3 R544C were subsequently matched with noncarriers based on the propensity score at a 1:10 ratio by demographic and cardiovascular risk factors. The odds ratio (OR) for stroke or other phenotypes in NOTCH3 R544C carriers and matched noncarriers was then calculated. Univariate and multivariate regression analyses were performed on cardiovascular risk factors in NOTCH3 R544C carriers with and without stroke. The polygenic risk score (PRS) model, adopted from the UK Biobank, was then applied to evaluate the role of NOTCH3 R544C in stroke.

RESULTS

From the 114,282 participants with both genotype and questionnaire results, 1080 (0.95%) harbored the pathogenic NOTCH3 R544C variant. When compared to the matched controls (n = 10,800), the carriers presented with a history of stroke (OR: 2.52, 95% confidence interval (CI) (1.45, 4.37)), dementia (OR: 30.1, 95% CI (3.13, 289.43)), and sibling history of stroke (OR: 2.48, 95% CI (1.85, 3.34)) phenotypes. The risk of stroke increased with every 10-year increase in age (p = 0.006, Cochran-Mantel-Haenszel test). Among NOTCH3 R544C carriers, 16 (1.3%) of the 1080 carriers with a stroke history were older, male, and more likely to have hypertension, diabetes, dyslipidemia, and a family history of stroke. In the stepwise multivariate analysis, hypertension (OR: 11.28, 95% CI (3.54, 43.3)) and diabetes mellitus (OR: 4.10, 95% CI (1.31, 12.4)) were independently associated with stroke. Harboring the NOTCH3 R544C variant in the Taiwan Biobank is comparable with a 6.74 standard deviations increase in individual's polygenic risk score for stroke.

CONCLUSION

While the NOTCH3 R544C variant alone increased the risk of stroke, modifiable vascular risk factors also played a role in the occurrence of stroke in Taiwanese community-dwelling individuals carrying the NOTCH3 variant.

Causal Association between Tea Intake and Acute Cerebrovascular Events: A Multivariate Mendelian Randomized Study in European Populations

BACKGROUND

Numerous research works have investigated the association between tea consumption and the risk of acute cerebrovascular events; however, the results are inconsistent.

OBJECTIVES

We used Mendelian randomization (MR) to evaluate the causal association between tea intake and several acute cerebrovascular events, including any ischemic stroke, large atherosclerotic stroke (LAS), cardiogenic embolic stroke (CES), small vessel stroke (SVS), intracranial hemorrhage (ICH), and subarachnoid hemorrhage (SAH).

METHODS

We obtained summary genome-wide association study (GWAS) data on tea intake and acute cerebrovascular events in populations of European ancestry. The GWAS on tea intake is derived from the UK Biobank, where we have chosen single-nucleotide polymorphisms (SNPs) closely associated with it as instrumental variables. We also obtained summary data on ischemic stroke from a GWAS meta-analysis, as well as summary data on ICH and SAH from the FinnGen study. We first explored the causal association between tea intake and several acute cerebrovascular events using univariate Mendelian randomization (UVMR), and then further assessed the causal association between tea intake and SVS using multivariate Mendelian randomization (MVMR) corrected for multiple confounders.

RESULTS

In UVMR, genetically predicted increases in tea intake were linked to a lower risk of SVS (OR: 0.58; 95% CI: 0.39, 0.86). There was no causal association between tea intake and the risk of other acute cerebrovascular events. In the MVMR, our results show that there was still a significant causal association between drinking tea and SVS, after adjusting body mass index, total cholesterol, low-density lipoprotein cholesterol, diabetes, hypertension, smoking, and alcohol consumption.

CONCLUSION

This MR study provides new genetic evidence that increased tea intake reduces the risk of SVS in the European population. However, possibly because of limited statistical power, the study did not find that tea consumption reduced the risk of several other acute cerebrovascular events.

Evidence-based evaluation of adjuvant therapy with Chinese medicine for cerebral small vessel disease: A systematic review and meta-analysis

BACKGROUND

As the population ages, the prevalence of cerebral small vessel disease (CSVD) steadily increases, resulting in a significant economic burden on society. In East Asian nations, Chinese medicine has been used extensively to teat CSVD and has been reported to improve the cognitive function of patients. The present study aimed to comprehensively assess the efficacy and safety of Chinese medicine as adjuvant therapy for CSVD.

METHODS

A literature search of the CNKI, Wanfang, VIP, SinoMed, Medline, Cochrane Library, and ChiCTR databases were searched for RCTs investigating the use of TCM as an adjuvant in the treatment of CSVD, published up to July 27, 2023, was performed. Based on the Cochrane Collaboration Network bias risk assessment criteria, Review Manager version 5.3 was used to perform a meta-analysis.

RESULTS

Meta-analysis of 27 RCTs, including 2554 subjects, revealed that the majority of the RCTs exhibited risk for ambiguous bias. The findings demonstrated that the use of Chinese medicine as an adjuvant treatment for CSVD effectively enhanced the cognitive function, as evidenced by improvements in the MMSE score (mean difference (MD) = 2.42, 95% confidence interval (CI) [1.79,3.17], P < .00001), MoCA score (MD = 2.39, 95% CI [1.78,2.99], P < .00001) and ADL score (MD = 4.13, 95% CI [1.74,6.51], P = .0007). Furthermore, the study also demonstrated the advantages of Chinese medicine adjuvant therapy in enhancing the Chinese medicine syndrome score (MD = -2.57, 95% CI [-3.31, -1.83], P < .00001), CRP (MD = -1.35, 95% CI [-2.27, -0.43], P = .004), Hcy (MD = -3.44,95% CI [-4.05, -2.83], P < .00001), and blood flow velocity (CBV) (MD = 1.37,95% CI [0.24,2.50], P = .02). Moreover, there was no statistical difference in the incidence of adverse reactions between the 2 groups.

CONCLUSION

Findings of the present study indicate that the Chinese medicine, as an adjuvant to conventional treatment, appeared to be efficacious in enhancing cognitive function, reducing Chinese medicine syndrome score, improving blood biochemical markers, and improving cerebral blood flow perfusion in patients with CSVD, without any notable adverse reactions. However, it is imperative to validate these conclusions in future high-quality investigations.

Genetics in Ischemic Stroke: Current Perspectives and Future Directions

Ischemic stroke is a heterogeneous condition influenced by a combination of genetic and environmental factors. Recent advancements have explored genetics in relation to various aspects of ischemic stroke, including the alteration of individual stroke occurrence risk, modulation of treatment response, and effectiveness of post-stroke functional recovery. This article aims to review the recent findings from genetic studies related to various clinical and molecular aspects of ischemic stroke. The potential clinical applications of these genetic insights in stratifying stroke risk, guiding personalized therapy, and identifying new therapeutic targets are discussed herein.

Nonhypertensive White Matter Hyperintensities in Stroke: Risk Factors, Neuroimaging Characteristics, and Prognosis

BACKGROUND

This study explored the risk factors, neuroimaging features, and prognostic implications of nonhypertensive white matter hyperintensity (WMH) in patients with acute ischemic stroke and transient ischemic attack.

METHODS AND RESULTS

We included 2283 patients with hypertension and 1003 without from a pool of 10 602. Associations of moderate-to-severe WMH with known risk factors, functional outcome, and a composite of recurrent stroke, myocardial infarction, and all-cause mortality were evaluated. A subset of 351 patients without hypertension and age- and sex-matched pairs with hypertension and moderate-to-severe WMH was created for a detailed topographic examination of WMH, lacunes, and microbleeds. Approximately 35% of patients without hypertension and 65% of patients with hypertensive stroke exhibited moderate-to-severe WMH. WMH was associated with age, female sex, and previous stroke, irrespective of hypertension. In patients without hypertension, WMH was associated with initial systolic blood pressure and was more common in the anterior temporal region. In patients with hypertension, WMH was associated with small vessel occlusion as a stroke mechanism and was more frequent in the periventricular region near the posterior horn of the lateral ventricle. The higher prevalence of occipital microbleeds in patients without hypertension and deep subcortical lacunes in patients with hypertension were also observed. Associations of moderate-to-severe WMH with 3-month functional outcome and 1-year cumulative incidence of the composite outcome were significant (both P<0.01), although the latter lost significance after adjustments. The associations between WMH and outcomes were consistent across hypertensive status.

CONCLUSIONS

One-third of patients without hypertension with stroke have moderate-to-severe WMH. The pathogenesis of WMH may differ between patients without and with hypertension, but its impact on outcome appears similar.

Alzheimer's Related Neurodegeneration Mediates Air Pollution Effects on Medial Temporal Lobe Atrophy

Exposure to ambient air pollution, especially particulate matter with aerodynamic diameter <2.5 μm (PM2.5) and nitrogen dioxide (NO2), are environmental risk factors for Alzheimer's disease and related dementia. The medial temporal lobe (MTL) is an important brain region subserving episodic memory that atrophies with age, during the Alzheimer's disease continuum, and is vulnerable to the effects of cerebrovascular disease. Despite the importance of air pollution it is unclear whether exposure leads to atrophy of the MTL and by what pathways. Here we conducted a longitudinal study examining associations between ambient air pollution exposure and MTL atrophy and whether putative air pollution exposure effects resembled Alzheimer's disease-related neurodegeneration or cerebrovascular disease-related neurodegeneration. Participants included older women (n = 627; aged 71-87) who underwent two structural brain MRI scans (MRI-1: 2005-6; MRI-2: 2009-10) as part of the Women's Health Initiative Memory Study of Magnetic Resonance Imaging. Regionalized universal kriging was used to estimate annual concentrations of PM2.5 and NO2 at residential locations aggregated to 3-year averages prior to MRI-1. The outcome was 5-year standardized change in MTL volumes. Mediators included voxel-based MRI measures of the spatial pattern of neurodegeneration of Alzheimer's disease (Alzheimer's disease pattern similarity scores [AD-PS]) and whole-brain white matter small-vessel ischemic disease (WM-SVID) volume as a proxy of global cerebrovascular damage. Structural equation models were constructed to examine whether the associations between exposures with MTL atrophy were mediated by the initial level or concurrent change in AD-PS score or WM-SVID while adjusting for sociodemographic, lifestyle, clinical characteristics, and intracranial volume. Living in locations with higher PM2.5 (per interquartile range [IQR]=3.17μg/m3) or NO2 (per IQR=6.63ppb) was associated with greater MTL atrophy (βPM2.5 = -0.29, 95% confidence interval [CI]=[-0.41,-0.18]; βNO2 =-0.12, 95%CI=[-0.23,-0.02]). Greater PM2.5 was associated with larger increases in AD-PS (βPM2.5 = 0.23, 95%CI=[0.12,0.33]) over time, which partially mediated associations with MTL atrophy (indirect effect= -0.10; 95%CI=[-0.15, -0.05]), explaining approximately 32% of the total effect. NO2 was positively associated with AD-PS at MRI-1 (βNO2=0.13, 95%CI=[0.03,0.24]), which partially mediated the association with MTL atrophy (indirect effect= -0.01, 95% CI=[-0.03,-0.001]). Global WM-SVID at MRI-1 or concurrent change were not significant mediators between exposures and MTL atrophy. Findings support the mediating role of Alzheimer's disease-related neurodegeneration contributing to MTL atrophy associated with late-life exposures to air pollutants. Alzheimer's disease-related neurodegeneration only partially explained associations between exposure and MTL atrophy suggesting the role of multiple neuropathological processes underlying air pollution neurotoxicity on brain aging.

White matter hyperintensities combined with serum NLRP3 in diagnosis of cognitive impairment in patients with cerebral small vessel disease

Background: White matter hyperintensities (WMH) are widely used for the diagnosis of cerebral small vessel disease (CSVD). However, whether NLRP3 is correlated with cognitive impairment after CSVD is still not clear.Objective: This study aimed to investigate the diagnostic value of WMHs combined with NLRP3 for cognitive impairment after CSVD.Methods: This prospective observational study enrolled a total of 188 CSVD patients from September 2019 to May 2022. All patients received brain MRI assessment and WMH Fazekas score, as well as WMH volume, was recorded. Serum NLRP3 level was measured by ELISA. Patients' cognitive function was measured by MoCA after 6 months of diagnosis of CSVD. The serum levels of C reactive protein (CRP), interleukin (IL)-6, total cholesterol (TC), triglyceride (TG), high-density leptin cholesterol (HDL) and low-density leptin cholesterol (LDL) were recordedResults: CSVD patients with cognitive impairment had significantly higher Fazekas scores, WMH volumes, serum NLRP3 and IL-6 levels compared to patients without cognitive impairment. A positive correlation was found among Fazekas scores, WMH volumes and NLRP3 levels. The combination of WMH volume and NLRP3 could achieve a better specificity for the diagnosis of cognitive impairment. Coronary syndrome history, WMH volume and NLRP3 were found as independent risk factors for cognitive impairment after CSVD.Conclusion: Fazekas scores, WMH volume and serum NLRP3 levels are associated with cognitive impairment after CSVD and have the potential to be used as diagnostic biomarkers.

Shape-Aware 3D Small Vessel Segmentation with Local Contrast Guided Attention

The automated segmentation and analysis of small vessels from in vivo imaging data is an important task for many clinical applications. While current filtering and learning methods have achieved good performance on the segmentation of large vessels, they are sub-optimal for small vessel detection due to their apparent geometric irregularity and weak contrast given the relatively limited resolution of existing imaging techniques. In addition, for supervised learning approaches, the acquisition of accurate pixel-wise annotations in these small vascular regions heavily relies on skilled experts. In this work, we propose a novel self-supervised network to tackle these challenges and improve the detection of small vessels from 3D imaging data. First, our network maximizes a novel shape-aware flux-based measure to enhance the estimation of small vasculature with non-circular and irregular appearances. Then, we develop novel local contrast guided attention(LCA) and enhancement(LCE) modules to boost the vesselness responses of vascular regions of low contrast. In our experiments, we compare with four filtering-based methods and a state-of-the-art self-supervised deep learning method in multiple 3D datasets to demonstrate that our method achieves significant improvement in all datasets. Further analysis and ablation studies have also been performed to assess the contributions of various modules to the improved performance in 3D small vessel segmentation. Our code is available at https://github.com/dengchihwei/LCNetVesselSeg.

Disrupted Gray Matter Networks Associated with Cognitive Dysfunction in Cerebral Small Vessel Disease

This study aims to investigate the disrupted topological organization of gray matter (GM) structural networks in cerebral small vessel disease (CSVD) patients with cerebral microbleeds (CMBs). Subject-wise structural networks were constructed from GM volumetric features of 49 CSVD patients with CMBs (CSVD-c), 121 CSVD patients without CMBs (CSVD-n), and 74 healthy controls. The study used graph theory to analyze the global and regional properties of the network and their correlation with cognitive performance. We found that both the control and CSVD groups exhibited efficient small-world organization in GM networks. However, compared to controls, CSVD-c and CSVD-n patients exhibited increased global and local efficiency (Eglob/Eloc) and decreased shortest path lengths (Lp), indicating increased global integration and local specialization in structural networks. Although there was no significant global topology change, partially reorganized hub distributions were found between CSVD-c and CSVD-n patients. Importantly, regional topology in nonhub regions was significantly altered between CSVD-c and CSVD-n patients, including the bilateral anterior cingulate gyrus, left superior parietal gyrus, dorsolateral superior frontal gyrus, and right MTG, which are involved in the default mode network (DMN) and sensorimotor functional modules. Intriguingly, the global metrics (Eglob, Eloc, and Lp) were significantly correlated with MoCA, AVLT, and SCWT scores in the control group but not in the CSVD-c and CSVD-n groups. In contrast, the global metrics were significantly correlated with the SDMT score in the CSVD-s and CSVD-n groups but not in the control group. Patients with CSVD show a disrupted balance between local specialization and global integration in their GM structural networks. The altered regional topology between CSVD-c and CSVD-n patients may be due to different etiological contributions, which may offer a novel understanding of the neurobiological processes involved in CSVD with CMBs.

Causal Effect of the 25-Hydroxyvitamin D Concentration on Cerebral Small Vessel Disease: A Mendelian Randomization Study

BACKGROUND

Previous observational studies reported that a lower serum 25-hydroxyvitamin D [25(OH)D] concentration is associated with a higher burden of cerebral small vessel disease (cSVD). The causality of this association is uncertain, but it would be clinically important, given that 25(OH)D can be a target for intervention. We tried to examine the causal effect of 25(OH)D concentration on cSVD-related phenotypes using a Mendelian randomization approach.

METHODS

Genetic instruments for each serum 25(OH)D concentration and cSVD-related phenotypes (lacunar stroke, white matter hyperintensity, cerebral microbleeds, and perivascular spaces) were derived from large-scale genome-wide association studies. We performed 2-sample Mendelian randomization analyses with multiple post hoc sensitivity analyses. A bidirectional Mendelian randomization approach was also used to explore the possibility of reverse causation.

RESULTS

We failed to find any significant causal effect of 25(OH)D concentration on cSVD-related phenotypes (odds ratio [95% CI], 1.00 [0.87-1.16], 1.01 [0.96-1.07], 1.06 [0.85-1.33], 1.00 [0.97-1.03], 1.02 [0.99-1.04], 1.01 [0.99-1.04] for lacunar stroke, white matter hyperintensity, cerebral microbleeds, and white matter, basal ganglia, hippocampal perivascular spaces, respectively). These results were reproduced in the sensitivity analyses accounting for genetic pleiotropy. Conversely, when we examined the effects of cSVD phenotypes on 25(OH)D concentration, cerebral microbleeds were negatively associated with 25(OH)D concentration (0.94 [0.92-0.96]).

CONCLUSIONS

Given the adequate statistical power (>0.8) of the analyses, our findings suggest that the previously reported association between 25(OH)D concentration and cSVD phenotypes might not be causal and partly attributed to reverse causation.

Brain structure-function coupling associated with cognitive impairment in cerebral small vessel disease

Cerebral small vessel disease (CSVD) is a common chronic and progressive disease that can lead to mental and cognitive impairment. Damage to brain structure and function may play an important role in the neuropsychiatric disorders of patients with CSVD. Increasing evidence suggests that functional changes are accompanied by structural changes in corresponding brain regions. Thus, normal structure-function coupling is essential for optimal brain performance, and disrupted structure-function coupling can be found in many neurological and psychiatric disorders. To date, most studies on patients with CSVD have focused on separate structures or functions, including reductions in white matter volume and blood flow, which lead to cognitive dysfunction. However, there are few studies on brain structure-function coupling in patients with CSVD. In recent years, with the rapid development of multilevel (voxel-wise, neurovascular, regional level, and network level) brain structure-functional coupling analysis methods based on multimodal magnetic resonance imaging (MRI), new evidence has been provided to reveal the correlation between brain function and structural abnormalities and cognitive impairment. Therefore, studying brain structure-function coupling has a potential significance in the exploration and elucidation of the neurobiological mechanism of cognitive impairment in patients with CSVD. This article mainly describes the currently popular brain structure-function coupling analysis technology based on multimodal MRI and the important research progress of these coupling technologies on CSVD and cognitive impairment to provide a perspective for the study of the pathogenesis and early diagnosis of CSVD.

Astrocytic CXCL5 hinders microglial phagocytosis of myelin debris and aggravates white matter injury in chronic cerebral ischemia

BACKGROUND

Chronic cerebral ischemia induces white matter injury (WMI) contributing to cognitive decline. Both astrocytes and microglia play vital roles in the demyelination and remyelination processes, but the underlying mechanism remains unclear. This study aimed to explore the influence of the chemokine CXCL5 on WMI and cognitive decline in chronic cerebral ischemia and the underlying mechanism.

METHODS

Bilateral carotid artery stenosis (BCAS) model was constructed to mimic chronic cerebral ischemia in 7-10 weeks old male mice. Astrocytic Cxcl5 conditional knockout (cKO) mice were constructed and mice with Cxcl5 overexpressing in astrocytes were generated by stereotactic injection of adeno-associated virus (AAV). WMI was evaluated by magnetic resonance imaging (MRI), electron microscopy, histological staining and western blotting. Cognitive function was examined by a series of neurobehavioral tests. The proliferation and differentiation of oligodendrocyte progenitor cells (OPCs), phagocytosis of microglia were analyzed via immunofluorescence staining, western blotting or flow cytometry.

RESULTS

CXCL5 was significantly elevated in the corpus callosum (CC) and serum in BCAS model, mainly expressed in astrocytes, and Cxcl5 cKO mice displayed improved WMI and cognitive performance. Recombinant CXCL5 (rCXCL5) had no direct effect on the proliferation and differentiation of OPCs in vitro. Astrocytic specific Cxcl5 overexpression aggravated WMI and cognitive decline induced by chronic cerebral ischemia, while microglia depletion counteracted this effect. Recombinant CXCL5 remarkably hindered microglial phagocytosis of myelin debris, which was rescued by inhibition of CXCL5 receptor C-X-C motif chemokine receptor 2 (CXCR2).

CONCLUSION

Our study revealed that astrocyte-derived CXCL5 aggravated WMI and cognitive decline by inhibiting microglial phagocytosis of myelin debris, suggesting a novel astrocyte-microglia circuit mediated by CXCL5-CXCR2 signaling in chronic cerebral ischemia.

Mutations in ARHGEF15 cause autosomal dominant hereditary cerebral small vessel disease and osteoporotic fracture

Cerebral small vessel disease (CSVD) is a prominent cause of ischemic and hemorrhagic stroke and a leading cause of vascular dementia, affecting small penetrating vessels of the brain. Despite current advances in genetic susceptibility studies, challenges remain in defining the causative genes and the underlying pathophysiological mechanisms. Here, we reported that the ARHGEF15 gene was a causal gene linked to autosomal dominant inherited CSVD. We identified one heterozygous nonsynonymous mutation of the ARHGEF15 gene that cosegregated completely in two families with CSVD, and a heterozygous nonsynonymous mutation and a stop-gain mutation in two individuals with sporadic CSVD, respectively. Intriguingly, clinical imaging and pathological findings displayed severe osteoporosis and even osteoporotic fractures in all the ARHGEF15 mutation carriers. In vitro experiments indicated that ARHGEF15 mutations resulted in RhoA/ROCK2 inactivation-induced F-actin cytoskeleton disorganization in vascular smooth muscle cells and endothelial cells and osteoblast dysfunction by inhibiting the Wnt/β-catenin signaling pathway in osteoblast cells. Furthermore, Arhgef15-e(V368M)1 transgenic mice developed CSVD-like pathological and behavioral phenotypes, accompanied by severe osteoporosis. Taken together, our findings provide strong evidence that loss-of-function mutations of the ARHGEF15 gene cause CSVD accompanied by osteoporotic fracture.

StynMedGAN: Medical images augmentation using a new GAN model for improved diagnosis of diseases

Deep networks require a considerable amount of training data otherwise these networks generalize poorly. Data Augmentation techniques help the network generalize better by providing more variety in the training data. Standard data augmentation techniques such as flipping, and scaling, produce new data that is a modified version of the original data. Generative Adversarial networks (GANs) have been designed to generate new data that can be exploited. In this paper, we propose a new GAN model, named StynMedGAN for synthetically generating medical images to improve the performance of classification models.  StynMedGAN builds upon the state-of-the-art styleGANv2 that has produced remarkable results generating all kinds of natural images. We introduce a regularization term that is a normalized loss factor in the existing discriminator loss of styleGANv2. It is used to force the generator to produce normalized images and penalize it if it fails. Medical imaging modalities, such as X-Rays, CT-Scans, and MRIs are different in nature, we show that the proposed GAN extends the capacity of styleGANv2 to handle medical images in a better way. This new GAN model (StynMedGAN) is applied to three types of medical imaging: X-Rays, CT scans, and MRI to produce more data for the classification tasks. To validate the effectiveness of the proposed model for the classification, 3 classifiers (CNN, DenseNet121, and VGG-16) are used. Results show that the classifiers trained with StynMedGAN-augmented data outperform other methods that only used the original data. The proposed model achieved 100%, 99.6%, and 100% for chest X-Ray, Chest CT-Scans, and Brain MRI respectively. The results are promising and favor a potentially important resource that can be used by practitioners and radiologists to diagnose different diseases.

Low vitamin D status is associated with inflammatory response in older patients with cerebral small vessel disease

OBJECTIVES

This study aimed to determine the association of the NF-κB inflammatory signaling pathway with vitamin D status in older cerebral small vessel disease (SVD) patients.

METHODS

We measured serum 25(OH)D, pro-and anti-inflammatory cytokines, and mRNA levels of the vitamin D-activating enzyme, CYP27B1, as well as NF-kB, COX-2, the chemokine-CCL2, IL-1β, IL-6, TNF-α, TGF-β, and IL-10, in cerebral SVD patients aged ≥60 years presenting with vascular dementia and age and gender-matched healthy controls.

RESULTS

Low vitamin D status (insufficiency: serum 25(OH)D 12-20 ng/ml; deficiency: ≤12 ng/ml) was more prevalent among patients compared to controls. The mRNA levels of NF-kB, COX-2, CCL2, IL-1β, and IL-6, and serum levels of pro-inflammatory cytokines (IL-1α, IL-1β, IL-6, and TNF-α) were significantly higher in cases compared to controls. There was a significant correlation between CYP27B1 and NF-kB, COX-2, CCL2, and IL-1β gene expression. Serum IL-1α, IL-1β, and IL-6 concentrations and the expression of CCL-2, NF-kB2, and NF-kB3 genes were higher in vitamin D-deficient subjects compared to vitamin D-sufficient subjects. There was a significant negative correlation between serum 25(OH)D and IL-1α, IL-6, and TNF-α, and a positive correlation between 25(OH)D and IL-10.

CONCLUSION

Low vitamin D is associated with an inflammatory response via NF-kB signaling, which could play a role in the etio-pathogenesis of SVD. Further large-scale studies are required to validate our findings.

Roles of NG2 Glia in Cerebral Small Vessel Disease

Cerebral small vessel disease (CSVD) is one of the most prevalent pathologic processes affecting 5% of people over 50 years of age and contributing to 45% of dementia cases. Increasing evidence has demonstrated the pathological roles of chronic hypoperfusion, impaired cerebral vascular reactivity, and leakage of the blood-brain barrier in CSVD. However, the pathogenesis of CSVD remains elusive thus far, and no radical treatment has been developed. NG2 glia, also known as oligodendrocyte precursor cells, are the fourth type of glial cell in addition to astrocytes, microglia, and oligodendrocytes in the mammalian central nervous system. Many novel functions for NG2 glia in physiological and pathological states have recently been revealed. In this review, we discuss the role of NG2 glia in CSVD and the underlying mechanisms.

Pathophysiology, cellular and molecular mechanisms of large and small vessel diseases

Cerebrovascular disease (CVD) is the second most common cause of cognitive impairment and dementia in aged population. CVD presents in a myriad number of clinical ways based on the functional location of pathology. While primary clinical emphasis has been placed on motor, speech and visual deficits, vascular cognitive decline is a vastly under recognized and devastating condition afflicting millions of Americans. CVD, a disease of the blood vessels that supply blood to brain involves an integration between small and large vessels. Cerebral large vessel diseases (LVD) are associated with atherosclerosis, artery-to-artery embolism, intracardiac embolism and a large vessel stroke leading to substantial functional disability. Cerebral small vessel disease (SVD) is critically involved in stroke, brain hemorrhages, cognitive decline and functional loss in elderly patients. An evolving understanding of cellular and molecular mechanisms emphasizes that inflammatory vascular changes contribute to systemic pathologic conditions of the central nervous systems (CNS), with specific clinical presentations including, cognitive decline. Advances in an understanding of pathophysiology of disease processes and therapeutic interventions may help improve outcomes. This review will focus on large and small vessels diseases and their relationship to vascular cognitive decline, atherosclerosis, stroke, and inflammatory neurodegeneration. We will also emphasize the molecular and cellular mechanisms, as well as genetic and epigenetic factors associated with LVD and SVD.

Rupture risk prediction of cerebral aneurysms using a novel convolutional neural network-based deep learning model

BACKGROUND

Cerebral aneurysms should be treated before rupture because ruptured aneurysms result in serious disability. Therefore, accurate prediction of rupture risk is important and has been estimated using various hemodynamic factors.

OBJECTIVE

To suggest a new way to predict rupture risk in cerebral aneurysms using a novel deep learning model based on hemodynamic parameters for better decision-making about treatment.

METHODS

A novel convolutional neural network (CNN) model was used for rupture risk prediction retrospectively of 123 aneurysm cases. To include the effect of hemodynamic parameters into the CNN, the hemodynamic parameters were first calculated using computational fluid dynamics and fluid-structure interaction. Then, they were converted into images for training the CNN using a novel approach. In addition, new data augmentation methods were devised to obtain sufficient training data. A total of 53,136 images generated by data augmentation were used to train and test the CNN.

RESULTS

The CNNs trained with wall shear stress (WSS), strain, and combination images had area under the receiver operating characteristics curve values of 0.716, 0.741, and 0.883, respectively. Based on the cut-off values, the CNN trained with WSS (sensitivity: 0.5, specificity: 0.79) or strain (sensitivity: 0.74, specificity: 0.71) images alone was not highly predictive. However, the CNN trained with combination images of WSS and strain showed a sensitivity and specificity of 0.81 and 0.82, respectively.

CONCLUSION

CNN-based deep learning algorithm using hemodynamic factors, including WSS and strain, could be an effective tool for predicting rupture risk in cerebral aneurysms with good predictive accuracy.

Critical closing pressure as a new hemodynamic marker of cerebral small vessel diseases burden

Purpose

To investigate cerebrovascular hemodynamics, including critical closing pressure (CrCP) and pulsatility index (PI), and their independent relationship with cerebral small vessel disease (CSVD) burden in patients with small-vessel occlusion (SVO).

Methods

We recruited consecutive patients with SVO of acute cerebral infarction who underwent brain magnetic resonance imaging (MRI), transcranial Doppler (TCD) and CrCP during admission. Cerebrovascular hemodynamics were assessed using TCD. We used the CSVD score to rate the total MRI burden of CSVD. Multiple regression analysis was used to determine parameters related to CSVD burden or CrCP.

Results

Ninety-seven of 120 patients (mean age, 64.51 ± 9.99 years; 76% male) completed the full evaluations in this study. We observed that CrCP was an independent determinant of CSVD burden in four models [odds ratio, 1.41; 95% confidence interval (CI), 1.17-1.71; P < 0.001] and correlated with CSVD burden [β (95% CI): 0.05 (0.04-0.06); P < 0.001]. In ROC analysis, CrCP was considered as a predictor of CSVD burden, and AUC was 86.2% (95% CI, 78.6-93.9%; P < 0.001). Multiple linear regression analysis showed that CrCP was significantly correlated with age [β (95% CI): 0.27 (0.06 to 0.47); P = 0.012], BMI [β (95% CI): 0.61 (0.00-1.22)] and systolic BP [β (95% CI): 0.16 (0.09-0.23); P < 0.001].

Conclusions

CrCP representing cerebrovascular tension is an independent determinant and predictor of CSVD burden. It was significantly correlated with age, BMI and systolic blood pressure. These results provide new insights in the mechanism of CSVD development.

[Disruption of corpus callosum microstructural integrity by diffusion MRI as a predictor of progression of cerebral microangiopathy]

OBJECTIVE

To assess the microstructural integrity of the corpus callosum in patients with cerebral small vessel disease (cSVD) using signal and biophysical diffusion MRI models and to identify the most sensitive markers of disease progression.

MATERIAL AND METHODS

Diffusion MRI (3 Tesla) was performed in 166 patients (51.8% women; mean age 60.4±7.6) with cSVD and cognitive impairment of varying severity and in 44 healthy volunteers (65.9% women; mean age 59.6±6.8), followed by calculation of signal (diffusion tensor and diffusion kurtosis) and biophysical (WMTI, NODDI, MC-SMT) models, from which profiles of three corpus callosum segments were constructed.

RESULTS

The best results were obtained for metrics in the forceps minor and body of the corpus callosum. Among the metrics of the signal models in the forceps minor, fraction anisotropy (FA) and mean diffusion (MD), which characterize the overall loss of microstructural integrity and increase in extra-axonal water, as well as indirect markers of demyelination when considering transverse diffusion parameters (radial diffusion and radial kurtosis), had the larger area under the curve according to the ROC analysis. Among the metrics of the biophysical models in the forceps minor, a larger area under the curve was found in the MC-SMT model for extra-axonal transverse diffusion (ETR), mean diffusion (EMD), and intra-axonal water fraction (INTRA), and in the WMTI model for intra-axonal water fraction (AWF). ETR had high inverse correlations with INTRA and AWF, while INTRA and AWF had high direct intercorrelations.

CONCLUSION

Metrics of signaling (FA, MD, RD, RK) and biophysical patterns (ETR, EMD, INTRA, AWF) in the forceps minor and the corpus callosum body can be considered as indicators of cSVD progression. They indicate disease progression, mainly by an increase in extra-axonal water with the development of demyelination and tissue degeneration in the corpus callosum.

Association between polymorphisms in miRNAs and ischemic stroke: A meta-analysis

BACKGROUND

Atherosclerosis remains a predominant cause of ischemic stroke (IS). Four miRNA polymorphisms associated with arteriosclerosis mechanism were meta-analyzed to explore whether they had predictive significance for IS.

METHODS

PubMed, Excerpta Medica database, Web of Science, Cochrane Library, Scopus, China National Knowledge Infrastructure, and China Wanfang Database were searched for relevant case-control studies published before September 2022. Two researchers independently reviewed the studies and extracted the data. Data synthesis was carried out on eligible studies. Meta-analysis, subgroup analysis, sensitivity analysis, and publication bias analysis were performed using Stata software 16.0.

RESULTS

Twenty-two studies were included, comprising 8879 cases and 12,091 controls. The results indicated that there were no significant associations between miR-146a C>G (rs2910164), miR-196a2 T>C (rs11614913) and IS risk in the overall analyses, but miR-149 T>C (rs2292832) and miR-499 A>G (rs3746444) increased IS risk under the allelic model, homozygote model and recessive model. The subgroup analyses based on Trial of Org 101072 in Acute Stroke Treatment classification indicated that rs2910164 increased small artery occlusion (SAO) risk under the allelic model, heterozygote model and dominant model; rs11614913 decreased the risk of SAO under the allelic model, homozygote model, heterozygote model and dominant model.

CONCLUSION

This Meta-analysis showed that all 4 single nucleotide polymorphisms were associated with the risk of IS or SAO, even though the overall and subgroup analyses were not entirely consistent.

Prevalence of motoric cognitive risk syndrome among older adults: a systematic review and meta-analysis

OBJECTIVE

Motoric cognitive risk syndrome (MCR) is a newly proposed pre-dementia syndrome. Several studies on the prevalence of MCR have been published; however, the data vary across studies with different epidemiological characteristics. Thus, this study aimed to quantitatively analyse the overall prevalence and associated epidemiological characteristics of MCR among older adults aged ≥ 60 years.

METHODS

The Cochrane Library, PubMed, Web of Science, CINAHL, Embase, Scopus, PsycInfo, China National Knowledge Infrastructure, Weipu Database, China Biology Medicine disc and Wanfang Database were searched from their inception to January 2022. A modified Newcastle-Ottawa Scale evaluated the risk of bias. Statistical heterogeneity among the included studies was analysed using Cochran's Q and I² tests. A random effect model calculated pooled prevalence owing to study heterogeneity. Begg's and Egger's tests were used to assess the publication bias. Additionally, subgroup analysis and meta-regression were performed based on different epidemiological characteristics to determine heterogeneity sources.

RESULTS

Sixty-two studies comprising 187,558 samples were obtained. The pooled MCR prevalence was 9.0% (95% confidence interval: 8.3-9.8). A higher MCR prevalence was observed in females, older adults with a low educational level, depression and cardiovascular risk factors, South American populations, and studies with small sample sizes and cross-section designs. Furthermore, subjective cognitive complaint using scale score and gait speed using instrument gait showed higher MCR prevalence.

CONCLUSION

MCR is common in older adults, and various epidemiological characteristics influence its prevalence. Thus, preventive measures are required for older adults with higher MCR prevalence.

Catalpol relieved angiotensin II-induced blood-brain barrier destruction via inhibiting the TLR4 pathway in brain endothelial cells

CONTEXT

Catalpol is a major bioactive constituent of Rehmannia glutinosa Libosch (Scrophulariaceae), a traditional Chinese medicine, which is widely used in multiple diseases, including hypertension.

OBJECTIVES

To explore whether catalpol protects against angiotensin II (Ang II)-triggered blood-brain barrier (BBB) leakage.

MATERIALS AND METHODS

The bEnd.3 cells and BBB models were pre-treated with or without catalpol (50, 200 and 500 μM) or TAK-242 (1 μM) for 2 h and then with Ang II (0.1 μM) or LPS (1 μg/mL) for 24 h. Cell viability was determined by the MTT assay. The levels of Toll-like receptor 4 (TLR4), myeloid differentiation factor 88 (MyD88), inducible nitric oxide synthase (iNOS), tumour necrosis factor-α (TNF-α), caveolin-1 (Cav-1) and p-eNOS/eNOS were tested by western blot. The BBB permeability was evaluated by the flux of bovine serum albumin-fluorescein isothiocyanate (BSA-FITC) across monolayers. nuclear factor kappa-B (NF-κB) p65 nuclear translocation was explored by immunofluorescence staining.

RESULTS

Ang II (0.1 μM) decreased the cell viability to 86.52 ± 1.79%, elevated the levels of TLR4, MyD88, iNOS, TNF-α and Cav-1 respectively to 3.7-, 1.5-, 2.3-, 2.2- and 2.7-fold, reduced the level of p-eNOS/eNOS to 1.6-fold in bEnd.3 cells, and eventually increased BBB permeability. Catalpol dose-dependently reversed these changes at 50-500 μM. Meanwhile, catalpol (500 μM) inhibited the upregulated levels of TLR4 pathway-related proteins and NF-κB p65 nuclear translocation, decreased the enhanced transcytosis, and relieved the BBB disruption caused by both LPS (the TLR4 activator) and Ang II. The effects are same as TAK-242 (the TLR4 inhibitor).

CONCLUSIONS

Catalpol relieved the Ang II-induced BBB damage, which indicated catalpol has high potential for the treatment of hypertension-induced cerebral small vessel disease (cSVD).

Deconstruction of Risk Prediction of Ischemic Cardiovascular and Cerebrovascular Diseases Based on Deep Learning

Over the years, with the widespread use of computer technology and the dramatic increase in electronic medical data, data-driven approaches to medical data analysis have emerged. However, the analysis of medical data remains challenging due to the mixed nature of the data, the incompleteness of many records, and the high level of noise. This paper proposes an improved neural network DBN-LSTM that combines a deep belief network (DBN) with a long short-term memory (LSTM) network. The subset of feature attributes processed by CFS-EGA is used for training, and the optimal selection test of the number of hidden layers is performed on the upper DBN in the process of training DBN-LSTM. At the same time, the validation set is combined to determine the hyperparameters of the LSTM. Construct the DNN, CNN, and long short-term memory (LSTM) network for comparative analysis with DBN-LSTM. Use the classification method to compare the average of the final results of the two experiments. The results show that the prediction accuracy of DBN-LSTM for cardiovascular and cerebrovascular diseases reaches 95.61%, which is higher than the three traditional neural networks.

Mesenchymal Stem Cell-Derived Extracellular Vesicles as Proposed Therapy in a Rat Model of Cerebral Small Vessel Disease

Mesenchymal stem cell-derived extracellular vesicles (MSC-EVs) have been employed in the past decade as therapeutic agents in various diseases, including central nervous system (CNS) disorders. We currently aimed to use MSC-EVs as potential treatment for cerebral small vessel disease (CSVD), a complex disorder with a variety of manifestations. MSC-EVs were intranasally administrated to salt-sensitive hypertension prone SBH/y rats that were DOCA-salt loaded (SBH/y-DS), which we have previously shown is a model of CSVD. MSC-EVs accumulated within brain lesion sites of SBH/y-DS. An in vitro model of an inflammatory environment in the brain demonstrated anti-inflammatory properties of MSC-EVs. Following in vivo MSC-EV treatment, gene set enrichment analysis (GSEA) of SBH/y-DS cortices revealed downregulation of immune system response-related gene sets. In addition, MSC-EVs downregulated gene sets related to apoptosis, wound healing and coagulation, and upregulated gene sets associated with synaptic signaling and cognition. While no specific gene was markedly altered upon treatment, the synergistic effect of all gene alternations was sufficient to increase animal survival and improve the neurological state of affected SBH/y-DS rats. Our data suggest MSC-EVs act as microenvironment modulators, through various molecular pathways. We conclude that MSC-EVs may serve as beneficial therapeutic measure for multifactorial disorders, such as CSVD.

Multi-modality artificial intelligence in digital pathology

In common medical procedures, the time-consuming and expensive nature of obtaining test results plagues doctors and patients. Digital pathology research allows using computational technologies to manage data, presenting an opportunity to improve the efficiency of diagnosis and treatment. Artificial intelligence (AI) has a great advantage in the data analytics phase. Extensive research has shown that AI algorithms can produce more up-to-date and standardized conclusions for whole slide images. In conjunction with the development of high-throughput sequencing technologies, algorithms can integrate and analyze data from multiple modalities to explore the correspondence between morphological features and gene expression. This review investigates using the most popular image data, hematoxylin-eosin stained tissue slide images, to find a strategic solution for the imbalance of healthcare resources. The article focuses on the role that the development of deep learning technology has in assisting doctors' work and discusses the opportunities and challenges of AI.