Posterior circulation stroke: machine learning-based detection of early ischemic changes in acute non-contrast CT scans

Unraveling Rescue Thrombectomy for Mild Large Vessel Occlusion Stroke Following Medical Management: Insights From a Multicenter Retrospective Study

BACKGROUND

Although rescue thrombectomy is performed in mild (National Institutes of Health Stroke Scale ≤ 5) large vessel occlusion (LVO) stroke patients who experience early neurological deterioration (END) following best medical management (BMM), clinical outcomes remain highly variable. This study aimed to identify key determinants influencing outcomes in this population.

METHODS

We retrospectively analyzed consecutive mild LVO patients who initially received BMM and later underwent rescue thrombectomy for END, across four centers between January 2019 and June 2024. END was defined as an NIHSS increase of ≥ 4 points or a total score of ≥ 6 within the first 24 h, without hemorrhage. Multivariable logistic regression was performed to identify factors associated with outcomes. Receiver operating characteristic curve analysis was performed to assess the predictive performance using the area under the curve (AUC).

RESULTS

Among 347 patients with mild LVO who underwent BMM, 66 patients who developed END and underwent rescue thrombectomy were included in this study. Of these, 31 (47.0%) achieved poor outcome (90-day modified Rankin Scale score of 3-6). Multivariable analysis identified prolonged deterioration-to-groin puncture time (OR: 1.79 per 10-minute increase, 95% CI: 1.48-2.54) and basilar artery occlusion (OR: 1.42, 95% CI: 1.16-2.08) were independently associated with poor outcomes. The AUC for predicting poor outcomes was 0.828 for deterioration-to-groin puncture time, 0.690 for basilar artery occlusion, and 0.906 for their combination.

CONCLUSION

Delayed initiation of thrombectomy and basilar artery occlusion were predictors for poor outcomes in patients who underwent rescue thrombectomy after BMM.

Early diagnosis and rapid thrombectomy with stent placement in distal vertebral artery stenosis (Mori Type C) with mild symptoms

Background: Vertebrobasilar artery occlusion (VBAO) is a life-threatening condition with often nonspecific symptoms, making early diagnosis challenging. Timely intervention is crucial, especially in cases involving distal vertebral artery stenosis. Case Report: A 65-year-old male presented with acute vertigo, dizziness, and visual disturbances, along with ipsilateral sixth cranial nerve palsy. His medical history included a treated abdominal aortic aneurysm, hypercholesterolemia, and hypertension. CT angiography (CTA) revealed an occlusion in the V4 segment of the right vertebral artery. CT perfusion imaging showed minimal perfusion delay in the right brainstem. The patient received intravenous thrombolysis (IVT) with tenecteplase, followed by mechanical thrombectomy (MT), partial recanalization was achieved. However, digital subtraction angiography (DSA) identified a critical stenosis (>90%) responsible for the occlusion, consistent with arteriosclerotic disease. Following intravenous administration of 500 mg acetylsalicylic acid, a Biotronik Orsiro 2.25 × 9 mm drug-eluting stent was placed, achieving complete recanalization (eTICI 3). Neurologic symptoms resolved completely post-intervention, and the patient received 300 mg clopidogrel. He was discharged with an MRS score of 0 within 3 days. Conclusion: This case highlights the effectiveness of a multimodal approach (IVT, MT, and stenting) in treating distal vertebral artery occlusion (Mori Type C). Early diagnosis and timely endovascular intervention led to rapid symptom resolution and complete neurological recovery. Follow-up ultrasound at 4 months confirmed good bilateral vertebral artery perfusion without restenosis, supporting the potential long-term benefits of this multimodal treatment approach. This case underscores the importance of advanced imaging for early detection and the role of thrombectomy and stenting in optimizing patient outcomes.

Automated ASPECTS Segmentation and Scoring Tool: a Method Tailored for a Colombian Telestroke Network

To evaluate our two non-machine learning (non-ML)-based algorithmic approaches for detecting early ischemic infarcts on brain CT images of patients with acute ischemic stroke symptoms, tailored to our local population, to be incorporated in our telestroke software. One-hundred and thirteen acute stroke patients, excluding hemorrhagic, subacute, and chronic patients, with accessible brain CT images were divided into calibration and test sets. The gold standard was determined through consensus among three neuroradiologist. Four neuroradiologist independently reported Alberta Stroke Program Early CT Scores (ASPECTSs). ASPECTSs were also obtained using a commercial ML solution (CMLS), and our two methods, namely the Mean Hounsfield Unit (HU) relative difference (RELDIF) and the density distribution equivalence test (DDET), which used statistical analyze the of the HUs of each region and its contralateral side. Automated segmentation was perfect for cortical regions, while minimal adjustment was required for basal ganglia regions. For dichotomized-ASPECTSs (ASPECTS < 6) in the test set, the area under the receiver operating characteristic curve (AUC) was 0.85 for the DDET method, 0.84 for the RELDIF approach, 0.64 for the CMLS, and ranged from 0.71-0.89 for the neuroradiologist. The accuracy was 0.85 for the DDET method, 0.88 for the RELDIF approach, and was ranged from 0.83 - 0.96 for the neuroradiologist. Equivalence at a margin of 5% was documented among the DDET, RELDIF, and gold standard on mean ASPECTSs. Noninferiority tests of the AUC and accuracy of infarct detection revealed similarities between both DDET and RELDIF, and the CMLS, and with at least one neuroradiologist. The alignment of our methods with the evaluations of neuroradiologist and the CMLS indicates the potential of our methods to serve as supportive tools in clinical settings, facilitating prompt and accurate stroke diagnosis, especially in health care settings, such as Colombia, where neuroradiologist are limited.

Thrombectomy in Stroke Patients with Large Vessel Occlusion and Mild Symptoms: Insights from a Multicenter Observational Study

To evaluate whether endovascular thrombectomy (EVT) combined with best medical management (BMM) is more effective than BMM alone in treating mild stroke patients (National Institutes of Health Stroke Scale score < 6) with large vessel occlusion (LVO). A multicentric retrospective cohort of patients with LVO and mild stroke within 24 h from symptom onset was included. Patients were divided into the primary EVT (EVTpri) group and the primary BMM (BMMpri) group according to the treatment strategy. Functional outcomes were compared after propensity score matching. Additionally, adjusted logistic regression analysis was used to assess the association between treatment strategy and functional outcomes. Finally, 419 patients were included, with 137 receiving EVTpri and 282 receiving BMMpri. After propensity score matching (EVTpri, 126 vs. BMMpri, 126), baseline characteristics were balanced between the two groups. No significant difference was observed in 3-month functional independence (modified Rankin Scale [mRS] 0-2, 78.6% vs. 76.2%. In the overall cohort, EVTpri was not associated with functional independence (adjusted odds ratio [aOR], 0.87; 95% confidence interval [CI], 0.43-1.47). However, patients in the EVTpri group were more likely to experience symptomatic intracranial hemorrhage (aOR, 1.27; 95% CI, 1.05-1.89). Subgroup analysis revealed that EVTpri was significantly associated with functional independence in vertebrobasilar occlusion subgroup (aOR, 1.78; 95% CI, 1.20-3.90). Our findings did not support the systematic use of EVT for mild stroke with LVO, except in cases of vertebrobasilar occlusion, which may represent a subgroup where EVTpri could provide significant benefits.

Association of blood pressure parameters on early neurological deterioration in patients with mild stroke and large vessel occlusion following medical management

OBJECTIVE

To explore the association between blood pressure (BP) metrics and early neurological deterioration of ischemic origin (ENDi) in patients with mild stroke and large vessel occlusion (LVO) undergoing best medical management (BMM).

METHODS

Data were collected from consecutive patients with mild stroke and LVO treated with BMM from January 2019 to December 2023. Admission systolic blood pressure (SBP), diastolic blood pressure (DBP), mean arterial pressure (MAP) and 24-h SBP variability were calculated. ENDi was defined as an National Institutes of Health Stroke Scale (NIHSS) score increase of ≥ 4 points within 24 h, excluding intracranial hemorrhage.

RESULTS

Among 347 patients, ENDi occurred in 42 (12.1%). The ENDi group exhibited higher admission SBP (158 vs. 131 mmHg, P < 0.001), SBP variability (32 vs. 14 mmHg, P < 0.001), and Tmax > 6 s volumes (63 vs. 40 ml, P < 0.001), and a greater proportion had vertebrobasilar occlusion (42.9% vs. 12.1%, P < 0.001). Multivariable analysis indicated that patients in the highest quartile for admission SBP (adjusted odds ratio [aOR] = 2.47, 95% confidence interval [CI] = 1.47-4.29), SBP variability (aOR = 2.57, 95% CI = 1.34-5.18), and Tmax > 6 s volumes (aOR = 2.09, 95% CI = 1.28-5.89) were independently associated with ENDi. Significant association also existed between vertebrobasilar occlusion and ENDi (aOR = 3.19, 95% CI = 1.76-6.74).

CONCLUSION

Significantly elevated admission SBP and large SBP variability were associated with the occurrence of ENDi in patients with mild stroke and LVO receiving BMM.

Nomogram for predicting early neurological deterioration in patients with mild large and medium vessel occlusion stroke intended for medical management: a multicenter retrospective study

BACKGROUND

Accurately forecasting early neurological deterioration of ischemic origin (ENDi) following medical management may aid in identifying candidates for thrombectomy. We aimed to develop and validate a nomogram to predict ENDi in patients with mild large and medium vessel occlusion stroke intended for medical management.

METHODS

Two hundred and forty-eight patients were enrolled (173 and 75 randomised into training and validation cohorts). The risk factors were identified using logistic regression analyses. A nomogram was constructed based on the risk factors identified. The discrimination, calibration, and clinical practicability of the nomogram were assessed using receiver operating characteristic curve (ROC) analysis, the Hosmer-Lemeshow test, and decision curve analysis (DCA), respectively.

RESULTS

ENDi was detected in 44 (17.7%) patients. Four predictors were identified in the training cohort and entered into the nomogram including age, symptom fluctuation characteristics, presence of core infarct, and occlusion site. ROC analysis showed that the area under the curve was 0.930 (95% CI 0.884 to 0.976) and 0.889 (95% CI 0.808 to 0.970) in the training and validation cohorts, respectively. The Hosmer-Lemeshow test yielded a mean absolute error of 0.025 and 0.038, respectively, for the two cohorts. The DCA showed that the nomogram model had superior practicality and accuracy across the majority of the threshold probabilities.

CONCLUSION

The proposed nomogram showed a favourable predictive performance for ENDi in patients with mild large and medium vessel occlusion stroke intended for medical management. For such patients, immediate thrombectomy or at least intensive medical monitoring may be reasonable to avoid delays in rescue thrombectomy.

Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis

Background

Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke.

Objectives

To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting.

Methods

Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care.

Results

A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher.

Limitations and conclusions

The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective.

Future work

Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice.

Study registration

This study is registered as PROSPERO CRD42021269609.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.

Prognostic value of the baseline magnetic resonance score in patients with acute posterior circulation ischaemic stroke after mechanical thrombectomy

AIM

To investigate the prognostic value of the composite posterior circulation Acute Stroke Prognosis Early Computed tomography (CT) Score (ASPECTS)-Collaterals (pcASCO) score, which combines diffusion-weighted imaging (DWI) posterior circulation ASPECTS (pcASPECTS) and the magnetic resonance angiography (MRA)-collateral circulation score at baseline among patients with acute posterior circulation ischaemic stroke after mechanical thrombectomy.

MATERIALS AND METHODS

Patients with acute posterior circulation ischaemic stroke who underwent mechanical thrombectomy were analysed retrospectively. The DWI-pcASPECTS and MRA-collateral circulation score before treatment and the modified Rankin Scale (mRS) at 90 days after treatment were used as the endpoints. An mRS ≤2 was defined as a good prognosis, and an mRS ≥3 was defined as a poor prognosis. Multivariate logistic regression was used to analyse independent predictors of functional outcome 90 days after mechanical thrombectomy.

RESULTS

Mechanical thrombectomy was performed in 57 patients; 38 patients had a good prognosis, 19 patients had a poor prognosis, and 33 patients were successfully recanalised. Univariate logistic regression found that National Institute of Health Stroke Scale (NIHSS) score (OR: 1.18, p<0.001), pcASPECTS (OR: 1.91, p=0.028) and pcASCO score (OR: 0.51, p=0.001) were factors of good functional outcome. Receiver operating characteristic curve (ROC curve) analysis showed that the diagnostic efficiency of the NIHSS and pcASCO was better (AUC = 0.88, 0.83, p<0.05) than that of the pcASPECTS (AUC = 0.65). The prediction model was established by age, NIHSS, and pcASCO, and the diagnostic efficiency of the prediction model was better (AUC = 0.94).

CONCLUSIONS

The composite MR-pcASCO score can be used as an important predictor of the prognosis of patients with acute posterior circulation ischaemic stroke after mechanical thrombectomy.

The clinical and imaging data fusion model for single-period cerebral CTA collateral circulation assessment

BACKGROUND

The Chinese population ranks among the highest globally in terms of stroke prevalence. In the clinical diagnostic process, radiologists utilize computed tomography angiography (CTA) images for diagnosis, enabling a precise assessment of collateral circulation in the brains of stroke patients. Recent studies frequently combine imaging and machine learning methods to develop computer-aided diagnostic algorithms. However, in studies concerning collateral circulation assessment, the extracted imaging features are primarily composed of manually designed statistical features, which exhibit significant limitations in their representational capacity. Accurately assessing collateral circulation using image features in brain CTA images still presents challenges.

METHODS

To tackle this issue, considering the scarcity of publicly accessible medical datasets, we combined clinical data with imaging data to establish a dataset named RadiomicsClinicCTA. Moreover, we devised two collateral circulation assessment models to exploit the synergistic potential of patients' clinical information and imaging data for a more accurate assessment of collateral circulation: data-level fusion and feature-level fusion. To remove redundant features from the dataset, we employed Levene's test and T-test methods for feature pre-screening. Subsequently, we performed feature dimensionality reduction using the LASSO and random forest algorithms and trained classification models with various machine learning algorithms on the data-level fusion dataset after feature engineering.

RESULTS

Experimental results on the RadiomicsClinicCTA dataset demonstrate that the optimized data-level fusion model achieves an accuracy and AUC value exceeding 86%. Subsequently, we trained and assessed the performance of the feature-level fusion classification model. The results indicate the feature-level fusion classification model outperforms the optimized data-level fusion model. Comparative experiments show that the fused dataset better differentiates between good and bad side branch features relative to the pure radiomics dataset.

CONCLUSIONS

Our study underscores the efficacy of integrating clinical and imaging data through fusion models, significantly enhancing the accuracy of collateral circulation assessment in stroke patients.

Emerging frontiers of artificial intelligence and machine learning in ischemic stroke: a comprehensive investigation of state-of-the-art methodologies, clinical applications, and unraveling challenges

At present, stroke remains the second highest cause of death globally and a leading cause of disability. From 1990 to 2019, the absolute number of strokes worldwide increased by 70.0%, and the prevalence of stroke increased by 85.0%, causing millions of deaths and disability. Ischemic stroke accounts for the majority of strokes, which is caused by arterial occlusion. Effective primary prevention strategies, early diagnosis, and timely interventions such as rapid reperfusion are in urgent implementation to control ischemic stroke. Otherwise, the stroke burden will probably continue to grow across the world as a result of population aging and an ongoing high prevalence of risk factors. To help with the diagnosis and management of ischemic stroke, newer techniques such as artificial intelligence (AI) are highly anticipated and may bring a new revolution. AI is a recent fast-growing research area which aims to mimic cognitive processes through a number of techniques such as machine learning (ML) methods of random forest learning (RFL) and convolutional neural networks (CNNs). With the help of AI, several momentous milestones have already been attained across diverse dimensions of ischemic stroke. In the context of predictive, preventive, and personalized medicine (PPPM/3PM), we aim to transform stroke care from a reactive to a proactive and individualized paradigm. In this way, AI demonstrates strong clinical utility across all three levels of prevention in ischemic stroke. In this paper, we synoptically illustrated the history and current situation of AI and ML. Then, we summarized their clinical applications and efficacy in the management of stroke. We finally provided an outlook on how AI approaches might contribute to enhancing favorable outcomes after stroke and proposed our suggestions on developing AI-based PPPM strategies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-023-00343-3.

Priorities for Advancements in Neuroimaging in the Diagnostic Workup of Acute Stroke

STAIR XII (12th Stroke Treatment Academy Industry Roundtable) included a workshop to discuss the priorities for advancements in neuroimaging in the diagnostic workup of acute ischemic stroke. The workshop brought together representatives from academia, industry, and government. The participants identified 10 critical areas of priority for the advancement of acute stroke imaging. These include enhancing imaging capabilities at primary and comprehensive stroke centers, refining the analysis and characterization of clots, establishing imaging criteria that can predict the response to reperfusion, optimizing the Thrombolysis in Cerebral Infarction scale, predicting first-pass reperfusion outcomes, improving imaging techniques post-reperfusion therapy, detecting early ischemia on noncontrast computed tomography, enhancing cone beam computed tomography, advancing mobile stroke units, and leveraging high-resolution vessel wall imaging to gain deeper insights into pathology. Imaging in acute ischemic stroke treatment has advanced significantly, but important challenges remain that need to be addressed. A combined effort from academic investigators, industry, and regulators is needed to improve imaging technologies and, ultimately, patient outcomes.

Automatic Evaluating of Multi-Phase Cranial CTA Collateral Circulation Based on Feature Fusion Attention Network Model

Stroke is one of the main causes of disability and death, and it can be divided into hemorrhagic stroke and ischemic stroke. Ischemic stroke is more common, and about 8 out of 10 stroke patients suffer from ischemic stroke. In clinical practice, doctors diagnose stroke by using computed tomography angiography (CTA) image to accurately evaluate the collateral circulation in stroke patients. This imaging information is of great significance in assisting doctors to determine the patient's treatment plan and prognosis. Currently, great progress has been made in the field of computer-aided diagnosis technology in medicine by using artificial intelligence. However, in related research based on deep learning algorithms, researchers usually only use single-phase data for training, lacking the temporal dimension information of multi-phase image data. This makes it difficult for the model to learn more comprehensive and effective collateral circulation feature representation, thereby limiting its performance. Therefore, combining data for training is expected to improve the accuracy and reliability of collateral circulation evaluation. In this study, we propose an effective hybrid mechanism to assist the feature encoding network in evaluating the degree of collateral circulation in the brain. By using a hybrid attention mechanism, additional guidance and regularization are provided to enhance the collateral circulation feature representation across multiple stages. Time dimension information is added to the input, and multiple feature-level fusion modules are designed in the multi-branch network. The first fusion module in the single-stage feature extraction network completes the fusion of deep and shallow vessel features in the single-branch network, followed by the multi-stage network feature fusion module, which achieves feature fusion for four stages. Tested on a dataset of multi-phase cranial CTA images, the accuracy rate exceeding 90.43%. The experimental results demonstrate that the addition of these modules can fully explore collateral vessel features, improve feature expression capabilities, and optimize the performance of deep learning network model.

DGA3-Net: A parameter-efficient deep learning model for ASPECTS assessment for acute ischemic stroke using non-contrast computed tomography

Detecting the early signs of stroke using non-contrast computerized tomography (NCCT) is essential for the diagnosis of acute ischemic stroke (AIS). However, the hypoattenuation in NCCT is difficult to precisely identify, and accurate assessments of the Alberta Stroke Program Early CT Score (ASPECTS) are usually time-consuming and require experienced neuroradiologists. To this end, this study proposes DGA3-Net, a convolutional neural network (CNN)-based model for ASPECTS assessment via detecting early ischemic changes in ASPECTS regions. DGA3-Net is based on a novel parameter-efficient dihedral group CNN encoder to exploit the rotation and reflection symmetry of convolution kernels. The bounding volume of each ASPECTS region is extracted from the encoded feature, and an attention-guided slice aggregation module is used to aggregate features from all slices. An asymmetry-aware classifier is then used to predict stroke presence via comparison between ASPECTS regions from the left and right hemispheres. Pre-treatment NCCTs of suspected AIS patients were collected retrospectively, which consists of a primary dataset (n = 170) and an external validation dataset (n = 90), with expert consensus ASPECTS readings as ground truth. DGA3-Net outperformed two expert neuroradiologists in regional stroke identification (F1 = 0.69) and ASPECTS evaluation (Cohen's weighted Kappa = 0.70). Our ablation study also validated the efficacy of the proposed model design. In addition, class-relevant areas highlighted by visualization techniques corresponded highly with various well-established qualitative imaging signs, further validating the learned representation. This study demonstrates the potential of deep learning techniques for timely and accurate AIS diagnosis from NCCT, which could substantially improve the quality of treatment for AIS patients.

Endovascular thrombectomy for basilar artery occlusion: translating research findings into clinical practice

BACKGROUND

Basilar artery occlusion is a rare and severe condition. The effectiveness of endovascular thrombectomy in patients with basilar artery occlusion was unclear until recently, because these patients were excluded from most trials of endovascular thrombectomy for large-vessel occlusion ischaemic stroke.

RECENT DEVELOPMENTS

The Basilar Artery International Cooperation Study (BASICS) and the Basilar Artery Occlusion Endovascular Intervention versus Standard Medical Treatment (BEST) trials, specifically designed to investigate the benefit of thrombectomy in patients with basilar artery occlusion, did not find significant evidence of a benefit of endovascular thrombectomy in terms of disability outcomes at 3 months after stroke. However, these trials suggested a potential benefit of endovascular thrombectomy in patients presenting with moderate-to-severe symptoms. Subsequently, the Endovascular Treatment for Acute Basilar Artery Occlusion (ATTENTION) and the Basilar Artery Occlusion Chinese Endovascular (BAOCHE) trials, which compared endovascular thrombectomy versus medical therapy within 24 h of onset, showed clear benefit of endovascular thrombectomy in reducing disability and mortality, particularly in patients with moderate-to-severe symptoms. The risk of intracranial haemorrhage with endovascular thrombectomy was similar to the risk in anterior circulation stroke. Thrombectomy was beneficial regardless of age, baseline characteristics, the presence of intracranial atherosclerotic disease, and time from symptom onset to randomisation. Therefore, the question of whether endovascular thrombectomy is beneficial in basilar artery occlusion now appears to be settled in patients with moderate-to-severe symptoms, and endovascular thrombectomy should be offered to eligible patients. WHERE NEXT?: Key outstanding issues are the potential benefits of endovascular thrombectomy in patients with mild symptoms, the use of intravenous thrombolysis in an extended time window (ie, after 4·5 h of symptom onset), and the optimal endovascular technique for thrombectomy. Dedicated training programmes and automated software to assist with the assessment of imaging prognostic markers could be useful in the selection of patients who might benefit from endovascular thrombectomy. Large international research networks should be built to address knowledge gaps in this field and allow the conduct of clinical trials with fast and consecutive enrolment and a diverse ethnic representation.

Machine learning and acute stroke imaging

BACKGROUND

In recent years, machine learning (ML) has had notable success in providing automated analyses of neuroimaging studies, and its role is likely to increase in the future. Thus, it is paramount for clinicians to understand these approaches, gain facility with interpreting ML results, and learn how to assess algorithm performance.

OBJECTIVE

To provide an overview of ML, present its role in acute stroke imaging, discuss methods to evaluate algorithms, and then provide an assessment of existing approaches.

METHODS

In this review, we give an overview of ML techniques commonly used in medical imaging analysis and methods to evaluate performance. We then review the literature for relevant publications. Searches were run in November 2021 in Ovid Medline and PubMed. Inclusion criteria included studies in English reporting use of artificial intelligence (AI), machine learning, or similar techniques in the setting of, and in applications for, acute ischemic stroke or mechanical thrombectomy. Articles that included image-level data with meaningful results and sound ML approaches were included in this discussion.

RESULTS

Many publications on acute stroke imaging, including detection of large vessel occlusion, detection and quantification of intracranial hemorrhage and detection of infarct core, have been published using ML methods. Imaging inputs have included non-contrast head CT, CT angiograph and MRI, with a range of performances. We discuss and review several of the most relevant publications.

CONCLUSIONS

ML in acute ischemic stroke imaging has already made tremendous headway. Additional applications and further integration with clinical care is inevitable. Thus, facility with these approaches is critical for the neurointerventional clinician.

Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set

OBJECTIVE

The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research.

MATERIALS AND METHODS

Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team.

RESULTS

The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones.

CONCLUSION

Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.

New imaging score for outcome prediction in basilar artery occlusion stroke

OBJECTIVE

In ischemic posterior circulation stroke, the utilization of standardized image scores is not established in daily clinical practice. We aimed to test a novel imaging score that combines the collateral status with the rating of the posterior circulation Acute Stroke Prognosis Early CT score (pcASPECTS). We hypothesized that this score (pcASCO) predicts functional outcome and malignant cerebellar edema (MCE).

METHODS

Ischemic stroke patients with acute BAO who received multimodal-CT and underwent thrombectomy on admission at two comprehensive stroke centers were analyzed. The posterior circulation collateral score by van der Hoeven et al was added to the pcASPECTS to define pcASCO as a 20-point score. Multivariable logistic regression analyses were performed to predict functional independence at day 90, assessed using modified Rankin Scale scores, and occurrence of MCE in follow-up CT using the established Jauss scale score as endpoints.

RESULTS

A total of 118 patients were included, of which 84 (71%) underwent successful thrombectomy. Based on receiver operating characteristic curve analysis, pcASCO ≥ 14 classified functional independence with higher discriminative power (AUC: 0.83, 95%CI: 0.71-0.91) than pcASPECTS (AUC: 0.74). In multivariable logistic regression analysis, pcASCO was significantly and independently associated with functional independence (aOR: 1.91, 95%CI: 1.25-2.92, p = 0.003), and MCE (aOR: 0.71, 95%CI: 0.53-0.95, p = 0.02).

CONCLUSION

The pcASCO could serve as a simple and feasible imaging tool to assess BAO stroke patients on admission and might be tested as a complementary tool to select patients for thrombectomy in uncertain situations, or to predict clinical outcome.

KEY POINTS

• The neurological assessment of basilar artery occlusion stroke patients can be challenging and there are yet no validated imaging scores established in daily clinical practice. • The pcASCO combines the rating of early ischemic changes with the status of the intracranial posterior circulation collaterals. • The pcASCO showed high diagnostic accuracy to predict functional outcome and malignant cerebellar edema and could serve as a simple and feasible imaging tool to support treatment selection in uncertain situations, or to predict clinical outcome.