Association Between Dispatch of Mobile Stroke Units and Functional Outcomes Among Patients With Acute Ischemic Stroke in Berlin

Assessment of Clinical Scales for Detection of Large Vessel Occlusion in Ischemic Stroke Patients from the Dijon Stroke Registry

(1) Background: The limited availability of thrombectomy-capable stroke centres raises questions about pre-hospital triage of patients with suspected stroke (IS) due to large vessel occlusion (LVO). Aims: This study aimed to evaluate the diagnostic accuracy of clinical stroke severity scales available for LVO detection. (2) Methods: Patients with IS were prospectively identified among residents of Dijon, France, using a population-based registry (2013–2017). Clinical signs and arterial imaging data were collected. LVO was defined as an occlusion site affecting the terminal intracranial internal carotid artery, the M1 segment of the middle cerebral artery (MCA), or the basilar artery (restricted definition). A wide definition of LVO also included the M2 segment of the MCA. For each of the 16 evaluated scales, a receiver operator characteristic (ROC) analysis was performed, and the c-statistic representing the area under the ROC curve was evaluated to assess discrimination for predicting LVO. (3) Results: 971 patients were registered, including 123 patients (12.7%) with an LVO according to the restricted definition. The c-statistic for LVO detection ranged between 0.66 and 0.80 according to the different scales, with a sensibility varying from 70% to 98% and a specificity from 33% to 86%. According to the wide definition of LVO (174 patients, 17.9%), the c-statistic was slightly lower, ranging between 0.64 and 0.79. The sensitivity was 59% to 93%, and the specificity was 34% to 89%. (4) Conclusion: The clinical scales failed to combine a high sensitivity and a high specificity to detect LVO. Further studies are needed to determine the best strategy for pre-hospital triage of IS patients.

Building a Mobile Stroke Unit Based on 5G Technology - A Study Protocol

Background: In-time treatment of acute stroke is critical to saving people's lives and improving the quality of post-stroke life. A mobile stroke unit (MSU) with fifth-generation (5G) mobile networks strengthens the interaction of patient information and healthcare resources, thereby reducing response times and improving thrombolysis results. However, clinical evidence of better outcomes compared to regular care is still lacking. Method and Design: In this randomized controlled trial, 484 patients with acute stroke are allocated into the MSU and regular care groups. We establish medical records for each patient and conduct a follow-up of 90 days. The primary outcomes are functional results as defined by utility-weighted modified Rankin Scale (uw-mRS) 90 days after the incidence occurred, whereas secondary outcomes include the alarm to CT scan completed time, the alarm to treatment decision time, the alarm to thrombolytic time, quality of life, and symptomatic intracranial hemorrhage combined with NIHSS score as well as cost-effectiveness. Discussion: This study establishes an innovative MSU (based on 5G) to manage acute stroke, comparing its clinical and economic outcomes to regular care and informing decision-makers of the effectiveness of the stroke emergency system. Clinical Trial Registration: [http://www.chictr.org.cn/showproj.aspx?proj=63874], identifier [ChiCTR2000039695].

[Time is Brain - Preclinical Emergency Care for Acute Ischemic Stroke]

Stroke is one of the most common neurological emergencies and requires rapid detection and treatment (time is brain). There is still insufficient knowledge about stroke warning signs. It is therefore of crucial importance that trained personnel in the preclinical setting recognize the relevant warning symptoms and collect the necessary information to quickly refer the patient to the appropriate additional care structure. For this purpose, training of the emergency medical services (EMS) and the correct triage are of particular importance. The on-site assessment of a patient with a suspected stroke by EMS should include airway, breathing, vital functions, a basic neurological examination, blood glucose testing and cardiac monitoring.Patients with suspected acute ischemic stroke should be brought to the nearest hospital with a stroke unit, ideally connected with a tertiary stroke centre. From there, once the primary diagnosis has been carried out and appropriate therapy initiated, the patient can be transferred to a thrombectomy center if necessary. To improve supply times, teleradiological networking plays a major role both between clinics of different levels of care and in communication between pre- and intra-hospital care providers. Also, the use of mobile stroke units can improve preclinical stroke care and reduce delays in access to intravenous thrombolytic therapy and mechanical thrombectomy. The identification of preclinical biomarkers could also save time.

Case Report: Preliminary Images From an Electromagnetic Portable Brain Scanner for Diagnosis and Monitoring of Acute Stroke

Introduction: Electromagnetic imaging is an emerging technology which promises to provide a mobile, and rapid neuroimaging modality for pre-hospital and bedside evaluation of stroke patients based on the dielectric properties of the tissue. It is now possible due to technological advancements in materials, antennae design and manufacture, rapid portable computing power and network analyses and development of processing algorithms for image reconstruction. The purpose of this report is to introduce images from a novel, portable electromagnetic scanner being trialed for bedside and mobile imaging of ischaemic and haemorrhagic stroke. Methods: A prospective convenience study enrolled patients (January 2020 to August 2020) with known stroke to have brain electromagnetic imaging, in addition to usual imaging and medical care. The images are obtained by processing signals from encircling transceiver antennae which emit and detect low energy signals in the microwave frequency spectrum between 0.5 and 2.0 GHz. The purpose of the study was to refine the imaging algorithms. Results: Examples are presented of haemorrhagic and ischaemic stroke and comparison is made with CT, perfusion and MRI T2 FAIR sequence images. Conclusion: Due to speed of imaging, size and mobility of the device and negligible environmental risks, development of electromagnetic scanning scanner provides a promising additional modality for mobile and bedside neuroimaging.

Reflection on the Past, Present, and Future of Thrombolytic Therapy for Acute Ischemic Stroke

More than 25 years have passed since the US Food and Drug Administration approved IV recombinant tissue plasminogen activator (alteplase) for the treatment of acute ischemic stroke. This landmark decision brought a previously untreatable disease into a new therapeutic landscape, providing inspiration for clinicians and hope to patients. Since that time, the use of alteplase in the clinical setting has become standard of care, continually improving with quality measures such as door-to-needle times and other metrics of specialized stroke unit care. The past decade has seen more widespread use of alteplase in the prehospital setting with mobile stroke units and telestroke and beyond initial time windows via the use of CT perfusion or MRI. Simultaneously, the position of alteplase is being challenged by new lytics and by the concept of its bypass altogether in the era of endovascular therapy. We provide an overview of alteplase, including its earliest trials and how they have shaped the current therapeutic landscape of ischemic stroke treatment, and touch on new frontiers for thrombolytic therapy. We highlight the critical role of thrombolytic therapy in the past, present, and future of ischemic stroke care.

The level of urbanization influences acute ischemic stroke care: A nationwide ecological study from Germany

BACKGROUND AND PURPOSE

Regional differences in acute ischemic stroke (AIS) care are still reported for Germany but not fully understood. We aimed to analyze the impact of the level of urbanization on the application of proved treatment procedures and the incidence of hospitalized AIS cases in Germany.

METHODS

The level of urbanization of the 401 districts and district-free cities in Germany was defined according to the Federal Institute for Building, Urban Affairs and Spatial Research classification. Using nationwide administrative data, the application of intravenous thrombolysis (IVT), mechanical thrombectomy (MT), and the incidence of hospitalizations for AIS, were analyzed according to the place of residence of the patients. Data included all patients hospitalized for AIS in 2019 (n = 224,274) and sociodemographic information of 83,019,213 residents in Germany.

RESULTS

Sparsely populated districts had a significantly higher incidence of hospitalizations for AIS than cities (age-standardized: 271.8 versus 242.3 per 100,000 inhabitants, P < 0.001), but a lower use of MT (5.7% versus 8.4%, P < 0.001). In the adjusted negative binomial regression model, rurality remained an independent predictor for MT use and the incidence of AIS hospitalizations. The proportion of IVT did not significantly differ between sparsely populated districts and cities (15.6% versus 17.2%, P = 0.021).

CONCLUSIONS

Although there is a dense network of stroke units in Germany, the level of urbanization still influences AIS care, as we found a lower proportion of MT and a higher incidence of AIS hospitalizations in Germany's rural areas.

Ischemic Penumbra: A Personal View

The concept of the ischemic penumbra was defined over 40 years ago by Lindsay Symon and his group and is now an established principle of all acute ischemic stroke therapies. These reperfusion treatments rescue threatened, critically hypoperfused brain tissue and have been proven to improve clinical outcomes. We have been fortunate to have observed and played a small part in the penumbral story from its beginnings in the 1970s to its pivotal position today. Over this period, we have witnessed penumbral imaging evolve from positron emission tomography through to magnetic resonance imaging and now predominantly computed tomography perfusion, with the advent of automated imaging facilitating case selection for reperfusion therapies. We and others have conducted clinical trials using penumbral imaging to extend the time window for intravenous thrombolysis and select patients for thrombectomy. Together with the concept of fast- and slow-growing ischemic infarct patterns, this embeds the penumbral principle in everyday clinical management. The opportunity now exists to make penumbral imaging even more portable, affordable, and more widely available using mobile platforms, novel imaging techniques, digital linkage, and artificial intelligence.

Fifty Years of Acute Ischemic Stroke Treatment: A Personal History

BACKGROUND

It has been 50 years since the first explorations of the physiology of cerebral ischemia by measuring cerebral blood flow (CBF), and 25 years since the approval of tissue plasminogen activator for treating acute ischemic stroke. My personal career began and matured during those eras. Here, I provide my perspective on the evolution of acute stroke research and treatment from 1971 to the present, with some in-depth discussion of the National Institutes of Neurologic Disease and Stroke (NINDS) tissue-type plasminogen activator (tPA) stroke trial and development of mobile stroke units.

SUMMARY

Studies of CBF and metabolism in acute stroke patients revealed graded tissue injury that was dependent on the duration of ischemia. Subsequent animal research unraveled the biochemical cascade of events occurring at the cellular level after cerebral ischemia. After a decade of failed translation, the development of a relatively safe thrombolytic allowed us to achieve reperfusion and apply the lessons from earlier research to achieve positive clinical results. The successful conduct of the NINDS tPA stroke study coupled with positive outcomes from companion tPA studies around the world created the specialty of vascular neurology. This was followed by an avalanche of research in imaging, a focus on enhancing reperfusion through thrombectomy, and improving delivery of faster treatment culminating in mobile stroke units. Key Messages: The last half century has seen the birth and evolution of successful acute stroke treatment. More research is needed in developing new drugs and catheters to build on the advances we have already made with reperfusion and also in evolving our systems of care to get more patients treated more quickly in the prehospital setting. The history of stroke treatment over the last 50 years exemplifies that medical "science" is an evolving discipline worth an entire career's dedication. What was impossible 50 years ago is today's standard of care, what we claim as dogma today will be laughed at a decade from now, and what appears currently impossible will be tomorrow's realities.

Telemedicine-enabled ambulances and mobile stroke units for prehospital stroke management

The recognition and management of stroke in the prehospital setting has become increasingly important to improve patient outcomes. Several strategies to advance prehospital stroke care have been developed, including the mobile stroke unit and the telemedicine-enabled ambulance-or "mini-MSU." These strategies both incorporate ambulance-based audio-visual telemedicine evaluation with a vascular neurologist to facilitate faster treatment but differ in several areas including upfront and recurring costs, scalability or growth potential, ability to integrate into existing emergency medical services systems, and interoperability across multiple specialties or conditions. While both the mobile stroke unit and mini-mobile stroke unit model are valid approaches to improve stroke care, the authors aim to compare these models based on costs, scalability, integration, and interoperability in order to guide our prehospital leaders to find the best solutions for their communities.

State of the Art Stroke Imaging: A Current Perspective

Acute stroke is a widespread, debilitating disease. Fortunately, it also has one of the most effective therapeutic options available in medicine, endovascular treatment. Imaging plays a major role in the diagnosis of stroke and aids in appropriate therapy selection. Given the rapid accumulation of evidence for patient subgroups and concurrent broadening of therapeutic options and indications, it is important to recognize the benefits of certain imaging technologies for specific situations. An effective imaging protocol should: 1) be fast, 2) easily implementable, 3) produce reliable results, 4) have few contraindications, and 5) be safe, all with the goal of providing the patient the best chance of achieving a favorable outcome. In the following, we provide a review of the currently available imaging technologies, their advantages and disadvantages, as well as an overview of the future of stroke imaging. Finally, we offer a perspective.

Prospective, Multicenter, Controlled Trial of Mobile Stroke Units

BACKGROUND

Mobile stroke units (MSUs) are ambulances with staff and a computed tomographic scanner that may enable faster treatment with tissue plasminogen activator (t-PA) than standard management by emergency medical services (EMS). Whether and how much MSUs alter outcomes has not been extensively studied.

METHODS

In an observational, prospective, multicenter, alternating-week trial, we assessed outcomes from MSU or EMS management within 4.5 hours after onset of acute stroke symptoms. The primary outcome was the score on the utility-weighted modified Rankin scale (range, 0 to 1, with higher scores indicating better outcomes according to a patient value system, derived from scores on the modified Rankin scale of 0 to 6, with higher scores indicating more disability). The main analysis involved dichotomized scores on the utility-weighted modified Rankin scale (≥0.91 or <0.91, approximating scores on the modified Rankin scale of ≤1 or >1) at 90 days in patients eligible for t-PA. Analyses were also performed in all enrolled patients.

RESULTS

We enrolled 1515 patients, of whom 1047 were eligible to receive t-PA; 617 received care by MSU and 430 by EMS. The median time from onset of stroke to administration of t-PA was 72 minutes in the MSU group and 108 minutes in the EMS group. Of patients eligible for t-PA, 97.1% in the MSU group received t-PA, as compared with 79.5% in the EMS group. The mean score on the utility-weighted modified Rankin scale at 90 days in patients eligible for t-PA was 0.72 in the MSU group and 0.66 in the EMS group (adjusted odds ratio for a score of ≥0.91, 2.43; 95% confidence interval [CI], 1.75 to 3.36; P<0.001). Among the patients eligible for t-PA, 55.0% in the MSU group and 44.4% in the EMS group had a score of 0 or 1 on the modified Rankin scale at 90 days. Among all enrolled patients, the mean score on the utility-weighted modified Rankin scale at discharge was 0.57 in the MSU group and 0.51 in the EMS group (adjusted odds ratio for a score of ≥0.91, 1.82; 95% CI, 1.39 to 2.37; P<0.001). Secondary clinical outcomes generally favored MSUs. Mortality at 90 days was 8.9% in the MSU group and 11.9% in the EMS group.

CONCLUSIONS

In patients with acute stroke who were eligible for t-PA, utility-weighted disability outcomes at 90 days were better with MSUs than with EMS. (Funded by the Patient-Centered Outcomes Research Institute; BEST-MSU ClinicalTrials.gov number, NCT02190500.).

High-resolution CT with arch/neck/head CT angiography on a mobile stroke unit

BACKGROUND

Mobile stroke units (MSUs) performance dependability and diagnostic yield of 16-slice, ultra-fast CT with auto-injection angiography (CTA) of the aortic arch/neck/circle of Willis has not been previously reported.

METHODS

We performed a prospective observational study of the first-of-its kind MSU equipped with high resolution, 16-slice CT with multiphasic CTA. Field CT/CTA was performed on all suspected stroke patients regardless of symptom severity or resolution. Performance dependability, efficiency and diagnostic yield over 365 days was quantified.

RESULTS

1031 MSU emergency activations occurred; of these, 629 (61%) were disregarded with unrelated diagnoses, and 402 patients transported: 245 (61%) ischemic or hemorrhagic stroke, 17 (4%) transient ischemic attack, 140 (35%) other neurologic emergencies. Total time from non-contrast CT/CTA start to images ready for viewing was 4.0 (IQR 3.5-4.5) min. Hemorrhagic stroke totaled 24 (10%): aneurysmal subarachnoid hemorrhage 3, hemorrhagic infarct 1, and 20 intraparenchymal hemorrhages (median intracerebral hemorrhage score was 2 (IQR 1-3), 4 (20%) spot sign positive). In 221 patients with ischemic stroke, 73 (33%) received alteplase with 31.5% treated within 60 min of onset. CTA revealed large vessel occlusion in 66 patients (30%) of which 9 (14%) were extracranial; 27 (41%) underwent thrombectomy with onset to puncture time averaging 141±90 min (median 112 (IQR 90-139) min) with full emergency department (ED) bypass. No imaging needed to be repeated for image quality; all patients were triaged correctly with no inter-hospital transfer required.

CONCLUSIONS

MSU use of advanced imaging including multiphasic head/neck CTA is feasible, offers high LVO yield and enables full ED bypass.

Improving Outcomes After Stroke: From Stroke Units to Mobile Stroke Units

A proactive clinical approach to stroke care improved functional outcomes with implementation of specialized in-hospital stroke units, urgently delivered systemic thrombolysis, mechanical thrombectomy and most recently with mobile stroke units deployed in the field. An 18% absolute difference in outcomes as a shift across all modified Rankin Scale strata at 3 months in the recent Berlin study may not be explained by just 8.8% more patients treated within the golden hour for thrombolytic treatment from symptom onset. These findings parallel the findings in the largest controlled multi-center BEST-MSU trial (Benefits of Stroke Treatment Delivered Using a Mobile Stroke Unit) to date. A shortcoming in blinding of the investigators to the mode of transportation is similar to blinding to the endovascular treatment in PROBE (Prospective Randomized Open, Blinded End-Point) design used in thrombectomy trials. A faster access to stroke experts and brain imaging in the field for all patients suspect of stroke regardless symptom nature, severity, duration or resolution delivered by mobile stroke units is likely the reason for improved outcomes akin the impact observed in the initial multidisciplinary approach to in-hospital stroke units and reperfusion therapies delivery.

Prehospital Comprehensive Stroke Center vs Primary Stroke Center Triage in Patients With Suspected Large Vessel Occlusion Stroke

Importance

Endovascular therapy (EVT) improves functional outcomes in acute ischemic stroke (AIS) with large vessel occlusion (LVO). Whether implementation of a regional prehospital transport policy for comprehensive stroke center triage increases use of EVT is uncertain.

Objective

To evaluate the association of a regional prehospital transport policy that directly triages patients with suspected LVO stroke to the nearest comprehensive stroke center with rates of EVT.

Design, Setting, and Participants

This retrospective, multicenter preimplementation-postimplementation study used an interrupted time series analysis to compare treatment rates before and after implementation in patients with AIS arriving at 15 primary stroke centers and 8 comprehensive stroke centers in Chicago, Illinois, via emergency medical services (EMS) transport from December 1, 2017, to May 31, 2019 (9 months before and after implementation in September 2018). Data were analyzed from December 1, 2017, to May 31, 2019.

Interventions

Prehospital EMS transport policy to triage patients with suspected LVO stroke, using a 3-item stroke scale, to comprehensive stroke centers.

Main Outcomes and Measures

Rates of EVT before and after implementation among EMS-transported patients within 6 hours of AIS onset.

Results

Among 7709 patients with stroke, 663 (mean [SD] age, 68.5 [14.9] years; 342 women [51.6%] and 321 men [48.4%]; and 348 Black individuals [52.5%]) with AIS arrived within 6 hours of stroke onset by EMS transport: 310 of 2603 (11.9%) in the preimplementation period and 353 of 2637 (13.4%) in the postimplementation period. The EVT rate increased overall among all patients with AIS (preimplementation, 4.9% [95% CI, 4.1%-5.8%]; postimplementation, 7.4% [95% CI, 7.5%-8.5%]; P < .001) and among EMS-transported patients with AIS within 6 hours of onset (preimplementation, 4.8% [95% CI, 3.0%-7.8%]; postimplementation, 13.6% [95% CI, 10.4%-17.6%]; P < .001). On interrupted time series analysis among EMS-transported patients, the level change within 1 month of implementation was 7.15% (P = .04) with no slope change before (0.16%; P = .71) or after (0.08%; P = .89), which indicates a step rather than gradual change. No change in time to thrombolysis or rate of thrombolysis was observed (step change, 1.42%; P = .82). There were no differences in EVT rates in patients not arriving by EMS in the 6- to 24-hour window or by interhospital transfer or walk-in, irrespective of time window.

Conclusions and Relevance

Implementation of a prehospital transport policy for comprehensive stroke center triage in Chicago was associated with a significant, rapid, and sustained increase in EVT rate for patients with AIS without deleterious associations with thrombolysis rates or times.

Advances in mechanical thrombectomy for acute ischaemic stroke from large vessel occlusions

Advances in endovascular treatment of acute ischaemic stroke from intracranial large vessel occlusions have continued in the past decade. Here, we performed a detailed review of all the new trials and studies that had the highest evidence, the guidelines for mechanical thrombectomy, the selection of the particular population outside the guidelines and endovascular therapeutic strategies for acute ischemic stroke from occluded intracranial arteries.

Large Vessel Occlusion Stroke Detection in the Prehospital Environment

Purpose of Review

Endovascular therapy for acute ischemic stroke secondary to large vessel occlusion (LVO) is time-dependent. Prehospital patients with suspected LVO stroke should be triaged directly to specialized stroke centers for endovascular therapy. This review describes advances in LVO detection among prehospital suspected stroke patients.

Recent Findings

Clinical prehospital stroke severity tools have been validated in the prehospital setting. Devices including EEG, SSEPs, TCD, cranial accelerometry, and volumetric impedance phase-shift-spectroscopy have recently published data regarding LVO detection in hospital settings. Mobile stroke units bring thrombolysis and vessel imaging to patients.

Summary

The use of a prehospital stroke severity tool for LVO triage is now widely supported. Ease of use should be prioritized as there are no meaningful differences in diagnostic performance amongst tools. LVO diagnostic devices are promising, but none have been validated in the prehospital setting. Mobile stroke units improve patient outcomes and cost-effectiveness analyses are underway.

Use of Portable Imaging Modalities in Patients With Neurologic Disorders: A Case-Based Discussion

Imaging technologies have significantly improved over the past few decades and play a critical role in the diagnosis and management of patients with neurologic conditions. With the evolution of these technologies to portable versions, significant implications exist for current neurologic care as well as potential improvements for the future. This article serves to describe portable imaging technologies and their potential impact on the field of neurology highlighted through the case of a patient who presented with symptoms consistent with a stroke.

Impact of mobile stroke units

Since its first introduction in clinical practice in 2008, the concept of mobile stroke unit enabling prehospital stroke treatment has rapidly expanded worldwide. This review summarises current knowledge in this young field of stroke research, discussing topics such as benefits in reduction of delay before treatment, vascular imaging-based triage of patients with large-vessel occlusion in the field, differential blood pressure management or prehospital antagonisation of anticoagulants. However, before mobile stroke units can become routine, several questions remain to be answered. Current research, therefore, focuses on safety, long-term medical benefit, best setting and cost-efficiency as crucial determinants for the sustainability of this novel strategy of acute stroke management.

Ultraearly thrombolysis by an anesthesiologist in a mobile stroke unit: A prospective, controlled intervention study

BACKGROUND

Acute stroke treatment in mobile stroke units (MSU) is feasible and reduces time-to-treatment, but the optimal staffing model is unknown. We wanted to explore if integrating thrombolysis of acute ischemic stroke (AIS) in an anesthesiologist-based emergency medical services (EMS) reduces time-to-treatment and is safe.

METHODS

A nonrandomized, prospective, controlled intervention study.

INCLUSION CRITERIA

age ≥18 years, nonpregnant, stroke symptoms with onset ≤4 h. The MSU staffing is inspired by the Norwegian Helicopter Emergency Medical Services crew with an anesthesiologist, a paramedic-nurse and a paramedic. Controls were included by conventional ambulances in the same catchment area. Primary outcome was onset-to-treatment time. Secondary outcomes were alarm-to-treatment time, thrombolytic rate and functional outcome. Safety outcomes were symptomatic intracranial hemorrhage and mortality.

RESULTS

We included 440 patients. MSU median (IQR) onset-to-treatment time was 101 (71-155) minutes versus 118 (90-176) minutes in controls, p = 0.007. MSU median (IQR) alarm-to-treatment time was 53 (44-65) minutes versus 74 (63-95) minutes in controls, p < 0.001. Golden hour treatment was achieved in 15.2% of the MSU patients versus 3.7% in the controls, p = 0.005. The thrombolytic rate was higher in the MSU (81% vs 59%, p = 0.001). MSU patients were more often discharged home (adjusted OR [95% CI]: 2.36 [1.11-5.03]). There were no other significant differences in outcomes.

CONCLUSIONS

Integrating thrombolysis of AIS in the anesthesiologist-based EMS reduces time-to-treatment without negatively affecting outcomes. An MSU based on the EMS enables prehospital assessment of acute stroke in addition to other medical and traumatic emergencies and may facilitate future implementation.

3D dissimilar-siamese-u-net for hyperdense Middle cerebral artery sign segmentation

The hyperdense middle cerebral artery sign (HMCAS) representing a thromboembolus has been declared as a vital CT finding for intravascular thrombus in the diagnosis of acute ischemia stroke. Early recognition of HMCAS can assist in patient triage and subsequent thrombolysis or thrombectomy treatment. A total of 624 annotated head non-contrast-enhanced CT (NCCT) image scans were retrospectively collected from multiple public hospitals in Hong Kong. In this study, we present a deep Dissimilar-Siamese-U-Net (DSU-Net) that is able to precisely segment the lesions by integrating Siamese and U-Net architectures. The proposed framework consists of twin sub-networks that allow inputs of left and right hemispheres in head NCCT images separately. The proposed Dissimilar block fully explores the feature representation of the differences between the bilateral hemispheres. Ablation studies were carried out to validate the performance of various components of the proposed DSU-Net. Our findings reveal that the proposed DSU-Net provides a novel approach for HMCAS automatic segmentation and it outperforms the baseline U-Net and many state-of-the-art models for clinical practice.