Machine Learning Automated Detection of Large Vessel Occlusion From Mobile Stroke Unit Computed Tomography Angiography

Mobile stroke units: Beyond thrombolysis

In the last decade, mobile stroke units (MSUs) have shown the potential to transform prehospital stroke care, marking a paradigm shift in delivering ultra-rapid thrombolysis and streamlining triage processes. These units bring acute stroke care directly to patients, significantly shortening treatment times. This review outlines the rationale for MSU care and discusses the potential applications beyond the original purpose of delivering thrombolysis, including large vessel occlusion detection, intracerebral hemorrhage management, and innovative forms of prehospital research.

Deep learning-assisted diagnosis of large vessel occlusion in acute ischemic stroke based on four-dimensional computed tomography angiography

Purpose

To develop deep learning models based on four-dimensional computed tomography angiography (4D-CTA) images for automatic detection of large vessel occlusion (LVO) in the anterior circulation that cause acute ischemic stroke.

Methods

This retrospective study included 104 LVO patients and 105 non-LVO patients for deep learning models development. Another 30 LVO patients and 31 non-LVO patients formed the time-independent validation set. Four phases of 4D-CTA (arterial phase P1, arterial-venous phase P2, venous phase P3 and late venous phase P4) were arranged and combined and two input methods was used: combined input and superimposed input. Totally 26 models were constructed using a modified HRNet network. Assessment metrics included the areas under the curve (AUC), accuracy, sensitivity, specificity and F1 score. Kappa analysis was performed to assess inter-rater agreement between the best model and radiologists of different seniority.

Results

The P1 + P2 model (combined input) had the best diagnostic performance. In the internal validation set, the AUC was 0.975 (95%CI: 0.878-0.999), accuracy was 0.911, sensitivity was 0.889, specificity was 0.944, and the F1 score was 0.909. In the time-independent validation set, the model demonstrated consistently high performance with an AUC of 0.942 (95%CI: 0.851-0.986), accuracy of 0.902, sensitivity of 0.867, specificity of 0.935, and an F1 score of 0.901. The best model showed strong consistency with the diagnostic efficacy of three radiologists of different seniority (k = 0.84, 0.80, 0.70, respectively).

Conclusion

The deep learning model, using combined arterial and arterial-venous phase, was highly effective in detecting LVO, alerting radiologists to speed up the diagnosis.

Prehospital identification of acute ischaemic stroke with large vessel occlusion: a retrospective study from western Norway

BACKGROUND

In 2019, the emergency medical services (EMS) covering the western Norway Regional Health Authority area implemented its version of the prehospital clinical criteria G-FAST (Gaze deviation, Facial palsy, Arm weakness, Visual loss, Speech disturbance) to detect acute ischaemic stroke (AIS) with large vessel occlusion (LVO). For patients with gaze deviation and at least one other G-FAST symptom, a primary stroke centre (PSC) may be bypassed and the patient taken directly to a comprehensive stroke centre (CSC) for rapid endovascular treatment (EVT) evaluation. The study aim was to investigate the efficacy of the G-FAST criteria for LVO patient selection and direct transfer to a CSC.

METHODS

This retrospective study included patients with code-red emergency medical communication centre (EMCC) stroke suspicion ambulance dispatch between August to December 2020. Stroke suspicion was defined as having at least one G-FAST symptom at EMS arrival. We obtained patient data from dispatches from EMCCs, EMS records and local EVT registries. Clinical features, CT images, and reperfusion treatment were recorded. The test characteristics for gaze deviation plus one other G-FAST symptom in detecting LVO were determined.

RESULTS

Among 643 patients, 59 were diagnosed with LVO at hospital arrival. In this group, seven fulfilled the G-FAST criteria for direct transport to a CSC at EMS arrival on scene, resulting in a sensitivity of 12% (95% CI 5% to 23%). The specificity was 99.66% (95% CI 98.77% to 99.96%), the positive predictive value 78%, and the negative predictive value 92%. EVT was performed in 64% (38/59) of LVO cases. Median time from PSC arrival to start of EVT at a CSC was 163 min.

CONCLUSION

The use of local G-FAST prehospital criteria by EMS personnel to identify patients with AIS with LVO is not suitable for selection of patients with LVO for direct transfer to a CSC.

A self-supervised learning approach for registration agnostic imaging models with 3D brain CTA

Deep learning-based neuroimaging pipelines for acute stroke typically rely on image registration, which not only increases computation but also introduces a point of failure. In this paper, we propose a general-purpose contrastive self-supervised learning method that converts a convolutional deep neural network designed for registered images to work on a different input domain, i.e., with unregistered images. This is accomplished by using a self-supervised strategy that does not rely on labels, where the original model acts as a teacher and a new network as a student. Large vessel occlusion (LVO) detection experiments using computed tomographic angiography (CTA) data from 402 CTA patients show the student model achieving competitive LVO detection performance (area under the receiver operating characteristic curve [AUC] = 0.88 vs. AUC = 0.81) compared to the teacher model, even with unregistered images. The student model trained directly on unregistered images using standard supervised learning achieves an AUC = 0.63, highlighting the proposed method's efficacy in adapting models to different pipelines and domains.

Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease

Introduction

Cerebrovascular diseases are known to cause significant morbidity and mortality to the general population. In patients with cerebrovascular disease, prompt clinical evaluation and radiographic interpretation are both essential in optimizing clinical management and in triaging patients for critical and potentially life-saving neurosurgical interventions. With recent advancements in the domains of artificial intelligence (AI) and machine learning (ML), many AI and ML algorithms have been developed to further optimize the diagnosis and subsequent management of cerebrovascular disease. Despite such advances, further studies are needed to substantively evaluate both the diagnostic accuracy and feasibility of these techniques for their application in clinical practice. This review aims to analyze the current use of AI and MI algorithms in the diagnosis of, and clinical decision making for cerebrovascular disease, and to discuss both the feasibility and future applications of utilizing such algorithms.

Methods

We review the use of AI and ML algorithms to assist clinicians in the diagnosis and management of ischemic stroke, hemorrhagic stroke, intracranial aneurysms, and arteriovenous malformations (AVMs). After identifying the most widely used algorithms, we provide a detailed analysis of the accuracy and effectiveness of these algorithms in practice.

Results

The incorporation of AI and ML algorithms for cerebrovascular patients has demonstrated improvements in time to detection of intracranial pathologies such as intracerebral hemorrhage (ICH) and infarcts. For ischemic and hemorrhagic strokes, commercial AI software platforms such as RapidAI and Viz.AI have bene implemented into routine clinical practice at many stroke centers to expedite the detection of infarcts and ICH, respectively. Such algorithms and neural networks have also been analyzed for use in prognostication for such cerebrovascular pathologies. These include predicting outcomes for ischemic stroke patients, hematoma expansion, risk of aneurysm rupture, bleeding of AVMs, and in predicting outcomes following interventions such as risk of occlusion for various endovascular devices. Preliminary analyses have yielded promising sensitivities when AI and ML are used in concert with imaging modalities and a multidisciplinary team of health care providers.

Conclusion

The implementation of AI and ML algorithms to supplement clinical practice has conferred a high degree of accuracy, efficiency, and expedited detection in the clinical and radiographic evaluation and management of ischemic and hemorrhagic strokes, AVMs, and aneurysms. Such algorithms have been explored for further purposes of prognostication for these conditions, with promising preliminary results. Further studies should evaluate the longitudinal implementation of such techniques into hospital networks and residency programs to supplement clinical practice, and the extent to which these techniques improve patient care and clinical outcomes in the long-term.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

Deep-learning based detection of vessel occlusions on CT-angiography in patients with suspected acute ischemic stroke

Swift diagnosis and treatment play a decisive role in the clinical outcome of patients with acute ischemic stroke (AIS), and computer-aided diagnosis (CAD) systems can accelerate the underlying diagnostic processes. Here, we developed an artificial neural network (ANN) which allows automated detection of abnormal vessel findings without any a-priori restrictions and in <2 minutes. Pseudo-prospective external validation was performed in consecutive patients with suspected AIS from 4 different hospitals during a 6-month timeframe and demonstrated high sensitivity (≥87%) and negative predictive value (≥93%). Benchmarking against two CE- and FDA-approved software solutions showed significantly higher performance for our ANN with improvements of 25-45% for sensitivity and 4-11% for NPV (p ≤ 0.003 each). We provide an imaging platform ( https://stroke.neuroAI-HD.org ) for online processing of medical imaging data with the developed ANN, including provisions for data crowdsourcing, which will allow continuous refinements and serve as a blueprint to build robust and generalizable AI algorithms.

SELF-SUPERVISED LEARNING WITH RADIOLOGY REPORTS, A COMPARATIVE ANALYSIS OF STRATEGIES FOR LARGE VESSEL OCCLUSION AND BRAIN CTA IMAGES

Scarcity of labels for medical images is a significant barrier for training representation learning approaches based on deep neural networks. This limitation is also present when using imaging data collected during routine clinical care stored in picture archiving communication systems (PACS), as these data rarely have attached the high-quality labels required for medical image computing tasks. However, medical images extracted from PACS are commonly coupled with descriptive radiology reports that contain significant information and could be leveraged to pre-train imaging models, which could serve as starting points for further task-specific fine-tuning. In this work, we perform a head-to-head comparison of three different self-supervised strategies to pre-train the same imaging model on 3D brain computed tomography angiogram (CTA) images, with large vessel occlusion (LVO) detection as the downstream task. These strategies evaluate two natural language processing (NLP) approaches, one to extract 100 explicit radiology concepts (Rad-SpatialNet) and the other to create general-purpose radiology reports embeddings (DistilBERT). In addition, we experiment with learning radiology concepts directly or by using a recent self-supervised learning approach (CLIP) that learns by ranking the distance between language and image vector embeddings. The LVO detection task was selected because it requires 3D imaging data, is clinically important, and requires the algorithm to learn outputs not explicitly stated in the radiology report. Pre-training was performed on an unlabeled dataset containing 1,542 3D CTA - reports pairs. The downstream task was tested on a labeled dataset of 402 subjects for LVO. We find that the pre-training performed with CLIP-based strategies improve the performance of the imaging model to detect LVO compared to a model trained only on the labeled data. The best performance was achieved by pre-training using the explicit radiology concepts and CLIP strategy.

Prehospital stroke management and mobile stroke units

PURPOSE OF REVIEW

Delayed presentation at the hospital contributes to poorer patient outcomes and undertreatment of acute stroke patients. This review will discuss recent developments in prehospital stroke management and mobile stroke units aimed to improve timely access to treatment within the past 2 years and will point towards future directions.

RECENT FINDINGS

Recent progress in research into prehospital stroke management and mobile stroke units ranges from interventions aimed at improving patients' help-seeking behaviour, to the education of emergency medical services team members, to the use of innovative referral methods, such as diagnostic scales, and finally to evidence of improved outcomes by the use of mobile stroke units.

SUMMARY

Understanding is increasing about the need for optimizing stroke management over the entire stroke rescue chain with the goal of improving access to highly effective time-sensitive treatment. In the future, we can expect that novel digital technologies and artificial intelligence will become relevant in effective interaction between prehospital and in-hospital stroke-treating teams, with beneficial effects on patients' outcomes.

Spatial CT perfusion data helpful in automatically locating vessel occlusions for acute ischemic stroke patients

Introduction

Locating a vessel occlusion is important for clinical decision support in stroke healthcare. The advent of endovascular thrombectomy beyond proximal large vessel occlusions spurs alternative approaches to locate vessel occlusions. We explore whether CT perfusion (CTP) data can help to automatically locate vessel occlusions.

Methods

We composed an atlas with the downstream regions of particular vessel segments. Occlusion of these segments should result in the hypoperfusion of the corresponding downstream region. We differentiated between seven-vessel occlusion locations (ICA, proximal M1, distal M1, M2, M3, ACA, and posterior circulation). We included 596 patients from the DUtch acute STroke (DUST) multicenter study. Each patient CTP data set was processed with perfusion software to determine the hypoperfused region. The downstream region with the highest overlap with the hypoperfused region was considered to indicate the vessel occlusion location. We assessed the indications from CTP against expert annotations from CTA.

Results

Our atlas-based model had a mean accuracy of 86% and could achieve substantial agreement with the annotations from CTA according to Cohen's kappa coefficient (up to 0.68). In particular, anterior large vessel occlusions and occlusions in the posterior circulation could be located with an accuracy of 80 and 92%, respectively.

Conclusion

The spatial layout of the hypoperfused region can help to automatically indicate the vessel occlusion location for acute ischemic stroke patients. However, variations in vessel architecture between patients seemed to limit the capacity of CTP data to distinguish between vessel occlusion locations more accurately.

Access to Mechanical Thrombectomy for Stroke: Center Qualifications, Prehospital Management, and Geographic Disparities

Mechanical thrombectomy (MT) became the "gold-standard" treatment for most patients with acute ischemic stroke due to anterior circulation large vessel occlusion. With such a remarkable paradigm shift, it is important that this modality of treatment becomes widely and homogeneously available throughout the United States and other countries. Although the time window for MT is large (24 hours in selected patients), time is still a major determinant of outcome. Several variables are involved in achieving timely access of MT for the majority of the population: prehospital management systems, transportation models, in-hospital workflow organization, accreditation and infrastructure of centers, training of neurointervention professionals, and geographic distribution of centers. The current situation in the United States regarding MT access is marked by geographic and socioeconomic disparities. We provide an overview of current challenges and solutions in achieving more universal access to MT for the population.

Segmentation of acute stroke infarct core using image-level labels on CT-angiography

Acute ischemic stroke is a leading cause of death and disability in the world. Treatment decisions, especially around emergent revascularization procedures, rely heavily on size and location of the infarct core. Currently, accurate assessment of this measure is challenging. While MRI-DWI is considered the gold standard, its availability is limited for most patients suffering from stroke. Another well-studied imaging modality is CT-Perfusion (CTP) which is much more common than MRI-DWI in acute stroke care, but not as precise as MRI-DWI, and it is still unavailable in many stroke hospitals. A method to determine infarct core using CT-Angiography (CTA), a much more available imaging modality albeit with significantly less contrast in stroke core area than CTP or MRI-DWI, would enable significantly better treatment decisions for stroke patients throughout the world. Existing deep-learning-based approaches for stroke core estimation have to face the trade-off between voxel-level segmentation / image-level labels and the difficulty of obtaining large enough samples of high-quality DWI images. The former occurs when algorithms can either output voxel-level labeling which is more informative but requires a significant effort by annotators, or image-level labels that allow for much simpler labeling of the images but results in less informative and interpretable output; the latter is a common issue that forces training either on small training sets using DWI as the target or larger, but noisier, dataset using CT-Perfusion (CTP) as the target. In this work, we present a deep learning approach including a new weighted gradient-based approach to obtain stroke core segmentation with image-level labeling, specifically the size of the acute stroke core volume. Additionally, this strategy allows us to train using labels derived from CTP estimations. We find that the proposed approach outperforms segmentation approaches trained on voxel-level data and the CTP estimation themselves.