Multimodality ultrasound imaging in stroke: current concepts and future focus

Stroke risk prediction by color Doppler ultrasound of carotid artery-based deep learning using Inception V3 and VGG-16

Purpose

This study aims to automatically classify color Doppler images into two categories for stroke risk prediction based on the carotid plaque. The first category is high-risk carotid vulnerable plaque, and the second is stable carotid plaque.

Method

In this research study, we used a deep learning framework based on transfer learning to classify color Doppler images into two categories: one is high-risk carotid vulnerable plaque, and the other is stable carotid plaque. The data were collected from the Second Affiliated Hospital of Fujian Medical University, including stable and vulnerable cases. A total of 87 patients with risk factors for atherosclerosis in our hospital were selected. We used 230 color Doppler ultrasound images for each category and further divided those into the training set and test set in a ratio of 70 and 30%, respectively. We have implemented Inception V3 and VGG-16 pre-trained models for this classification task.

Results

Using the proposed framework, we implemented two transfer deep learning models: Inception V3 and VGG-16. We achieved the highest accuracy of 93.81% by using fine-tuned and adjusted hyperparameters according to our classification problem.

Conclusion

In this research, we classified color Doppler ultrasound images into high-risk carotid vulnerable and stable carotid plaques. We fine-tuned pre-trained deep learning models to classify color Doppler ultrasound images according to our dataset. Our suggested framework helps prevent incorrect diagnoses caused by low image quality and individual experience, among other factors.

Percutaneous transluminal angioplasty and stenting for vertebral artery stenosis

BACKGROUND

Vertebral artery stenosis (narrowing of the vertebral artery) is an important cause of posterior circulation ischaemic stroke. Medical treatment (MT) e.g. controlling risk-factors and drug treatment, surgery, and endovascular treatment (ET) are the prevailing treatment strategies for symptomatic vertebral artery stenosis. ET consist s of percutaneous transluminal angioplasty (balloon catheter through the skin), with or without stenting. However, optimal management of people with symptomatic vertebral artery stenosis has not yet been established.

OBJECTIVES

To assess the safety and efficacy of percutaneous transluminal angioplasty, with or without stenting, combined with MT, compared to MT alone, in people with episodes of cerebral ischaemia due to vertebral artery stenosis.

SEARCH METHODS

We searched the Cochrane Stroke Group, MEDLINE, Embase, BIOSIS, and two other indexes in Web of Science, China Biological Medicine Database, Chinese Science and Technique Journals Database, China National Knowledge Infrastructure and Wanfang Data, as well as ClinicalTrials.gov trials register and the World Health Organization (WHO) International Clinical Trials Registry Platform to 23 July 2021.

SELECTION CRITERIA

We included all randomised controlled trials (RCTs) that compared ET plus MT with MT alone in treating people aged 18 years or over with symptomatic vertebral artery stenosis. We included all types of ET modalities (e.g. angioplasty alone, balloon-mounted stenting, and angioplasty followed by placement of a self-expanding stent). MT included risk factor control, antiplatelet therapy, lipid-lowering therapy, and individualised management for people with hypertension or diabetes.

DATA COLLECTION AND ANALYSIS

Two review authors independently screened potentially eligible studies, extracted data, and assessed trial quality and risk of bias.  We applied the GRADE approach to assess the certainty of evidence. The primary outcomes were 30-day post-randomisation death/stroke (short-term outcome) and fatal/non-fatal stroke after 30 days post-randomisation to completion of follow-up (long-term outcome).  MAIN RESULTS: We included three RCTs with 349 participants with symptomatic vertebral artery stenosis with a mean age of 64.4 years. The included RCTs were at low risk of bias overall. However, all included studies had a high risk of performance bias because blinding of the ET was not feasible. There was no significant difference in 30-day post-randomisation deaths/strokes between ET plus MT and MT alone (risk ratio (RR) 2.33, 95% confidence interval (CI) 0.77 to 7.07; 3 studies, 349 participants; low-certainty evidence). There were no significant differences between ET plus MT and MT alone in fatal/non-fatal strokes in the territory of the treated vertebral artery stenosis after 30 days post-randomisation to completion of follow-up (RR 0.51, 95% CI 0.26 to 1.01; 3 studies, 349 participants; moderate-certainty evidence), ischaemic or haemorrhagic stroke during the entire follow-up period (RR 0.77, 95% CI 0.44 to 1.32; 3 studies, 349 participants; moderate-certainty evidence), death during the entire follow-up period (RR 0.78, 95% CI 0.37 to 1.62; 3 studies, 349 participants; low-certainty evidence), and stroke or transient ischaemic attack (TIA) during the entire follow-up period (RR 0.65, 95% CI 0.39 to 1.06; 2 studies, 234 participants; moderate-certainty evidence).

AUTHORS' CONCLUSIONS

This Cochrane Review provides low- to moderate-certainty evidence indicating that there are no significant differences in either short- or long-term risks of stroke, death, or TIA between people with symptomatic vertebral artery stenosis treated with ET plus MT and those treated with MT alone.

The Role of Ultrasound as a Diagnostic and Therapeutic Tool in Experimental Animal Models of Stroke: A Review

Ultrasound is a noninvasive technique that provides real-time imaging with excellent resolution, and several studies demonstrated the potential of ultrasound in acute ischemic stroke monitoring. However, only a few studies were performed using animal models, of which many showed ultrasound to be a safe and effective tool also in therapeutic applications. The full potential of ultrasound application in experimental stroke is yet to be explored to further determine the limitations of this technique and to ensure the accuracy of translational research. This review covers the current status of ultrasound applied to monitoring and treatment in experimental animal models of stroke and examines the safety, limitations, and future perspectives.

Distribution Pattern of Atherosclerotic Stenosis in Chinese Patients with Stroke: A Multicenter Registry Study

The aim of this multicenter study was to demonstrate the distribution pattern of atherosclerotic stenosis and its trend with aging between extracranial and intracranial arteries and its distribution between the anterior and posterior circulations in Chinese patients hospitalized with ischemic stroke. In addition, the risk factors for the distribution pattern were illustrated. From June 2015 to May 2016, 9,346 patients with ischemic stroke from 20 hospitals were enrolled. Carotid artery ultrasonography and transcranial color-coded sonography/transcranial Doppler were used to evaluate the extracranial and intracranial arteries. The distribution pattern of atherosclerotic stenosis and its trend with aging were analyzed. Logistic regression was used to analyze the risk factors for the distribution pattern. Among the 9,346 patients, 2,882 patients (30.8%) had at least one artery with a degree of stenosis ≥50%. Among patients with arterial stenosis, the proportion of patients with intracranial artery stenosis was higher than those with extracranial artery stenosis (52.6% vs. 27.6%), and the proportion of anterior circulation artery stenosis was higher than that in the posterior circulation (52.2% vs.26.2%). With aging, the proportion of intracranial artery stenosis alone decreased; at the same time, the proportion of extracranial artery stenosis and extracranial plus intracranial artery stenosis increased (trend χ²=6.698, P=0.001). Hypertension (OR 1.416, P=0.008) and family history of stroke (OR 1.479, P=0.014) were risk factors for intracranial artery stenosis. Male, aging, and smoking were factors more related to extracranial artery stenosis. Aging (OR 1.022, P<0.001) and hypertension (OR 1.392, P=0.019) were related to posterior circulation artery stenosis. Intracranial arteries and anterior circulation arteries were susceptible to stenosis in Chinese patients with ischemic stroke. However, the distribution pattern of atherosclerotic stenosis was dynamic and varied with aging. Aging and different risk factors contribute to this distribution pattern.

Quantitative Ultrasound Imaging Pixel Analysis of the Intrinsic Plantar Muscle Tissue between Hemiparesis and Contralateral Feet in Post-Stroke Patients

Quantitative ultrasound imaging of the muscle tissue may be applied in the neurology field, due to B-mode grayscale pixels values could be used as potential biomarkers for disease progression and intervention effects in poststroke patients. Thus, the study aim was to compare and analyze the ultrasound imaging B-mode pixels differences between the intrinsic plantar muscles cross-sectional area (CSA) in hemiparetic and contralateral feet from poststroke patients by means of the Image J software. A case-control design and a convenience sampling method were used in order to recruit 22 feet from 11 poststroke patients. This total sample was divided into 11 hemiparetic feet and 11 contralateral feet. The Image J software was used in order to evaluate the interface distance, CSA as well as measure the pixels mean, standard deviation (SD) and count from all offline images in the flexor digitorum brevis, abductor hallucis (AbH), and flexor hallucis brevis muscles. Statistically significant differences (p = 0.003) were only shown for the pixels count in the AbH muscle. The rest of outcome measurements did not show any statistically significant difference (p > 0.05). Therefore, B-mode ultrasound imaging Image J software differences for the pixels count reduction were shown in the AbH muscle between hemiparetic and contralateral feet from poststroke patients. Further studies are necessary in order to apply our findings as potential biomarkers during the stroke disease course.

Transcranial sonography in psychiatry as a potential tool in diagnosis and research

OBJECTIVES

During the last two decades transcranial sonography (TCS) of the brain parenchyma evolved from a pure research tool to a clinical relevant neuroimaging method especially in Parkinson's disease and related movement disorders. The aim of this systematic review is to update and summarise the published TCS findings in psychiatric disorders and critically address the question whether TCS may be a valuable tool for the diagnosis or differential diagnosis of psychiatric disorders similarly to the field of movement disorders.

METHODS

This paper provides detailed information about the perspectives and limitations of TCS, including guidelines for the scanning procedures, assessment of midbrain structures and discusses the potential causes of the ultrasound abnormalities in psychiatric disorders.

RESULTS

Changes in the echogenicity of subcortical brain structures were detected in different disorders, such as obsessive-compulsive disorder, autism spectrum disorder, schizophrenia, panic disorder, attention-deficit/hyperactivity (ADHD), bipolar disorder and depressive disorder. Although the physical properties of brain tissue underlying the echogenic features in TCS are largely unknown, no alternative technique provides the same insight into the specific central nervous structural characteristics.

CONCLUSIONS

Urgent research questions to further clarify the underlying pathophysiological and structural alterations are further outlined to bring this promising technique to the clinic.