Stroke and Stroke Mimics: Diagnosis and Treatment

Predicting Hypoperfusion Lesion and Target Mismatch in Stroke from Diffusion-weighted MRI Using Deep Learning

Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.

Salivary Xanthine Oxidase as a Potential Biomarker in Stroke Diagnostics

Stroke is one of the most common cerebrovascular diseases. Despite significant progress in understanding stroke pathogenesis, cases are still increasing. Thus, laboratory biomarkers of stroke are sought to allow rapid and non-invasive diagnostics. Ischemia-reperfusion injury is an inflammatory process with characteristic cellular changes leading to microvascular disruption. Several studies have shown that hyperactivation of xanthine oxidase (XO) is a major pathogenic factor contributing to brain dysfunction. Given the critical role of XO in stroke complications, this study aimed to evaluate the activity of the enzyme and its metabolic products in the saliva of stroke subjects. Thirty patients in the subacute phase of stroke were included in the study: 15 with hemorrhagic stroke and 15 with ischemic stroke. The control group consisted of 30 healthy subjects similar to the cerebral stroke patients regarding age, gender, and status of the periodontium, dentition, and oral hygiene. The number of individuals was determined a priori based on our previous experiment (power of the test = 0.8; α = 0.05). The study material was mixed non‐stimulated whole saliva (NWS) and stimulated saliva (SWS). We showed that activity, specific activity, and XO output were significantly higher in NWS of ischemic stroke patients than in hemorrhagic stroke and healthy controls. Hydrogen peroxide and uric acid levels were also considerably higher in NWS of ischemic stroke patients. Using receiver operating curve (ROC) analysis, we demonstrated that XO-specific activity in NWS distinguishes ischemic stroke from hemorrhagic stroke (AUC: 0.764) and controls (AUC: 0.973) with very high sensitivity and specificity. Saliva collection is stress-free, requires no specialized medical personnel, and allows continuous monitoring of the patient’s condition through non-invasive sampling multiple times per day. Salivary XO also differentiates with high accuracy (100%) and specificity (93.75%) between stroke patients with mild to moderate cognitive decline (AUC = 0.988). Thus, salivary XO assessment may be a potential screening tool for a comprehensive neuropsychological evaluation. To summarize, our study demonstrates the potential utility of salivary XO in the differential diagnosis of stroke.

Salivary cytokine profile in patients with ischemic stroke

Inflammation plays a crucial role in stroke pathogenesis. Thus, it is not surprising that cytokines, chemokines, and growth factors have been advocated in stroke diagnostics. Our study is the first to evaluate the salivary cytokine profile in patients with ischemic stroke. Twenty-five patients with subacute ischemic stroke and an age-, sex-, and oral hygiene status-matched control group were enrolled in the study. The number of patients was set a priori based on our previous experiment (α = 0.05, test power = 0.9). Salivary concentrations of tumor necrosis factor α (TNF-α), interleukin 6 (IL-6), and interleukin 10 (IL-10) were assessed using an ELISA method. We showed that salivary TNF-α and IL-6 were significantly higher, whereas IL-10 content was statistically lower in both non-stimulated (NWS) and stimulated (SWS) whole saliva of ischemic stroke patients. However, evaluation of cytokines in NWS rather than in SWS may be of greater diagnostic value. Of particular note is salivary TNF-α, which may indicate cognitive/physical impairment in post-stroke individuals. This parameter distinguishes stroke patients from healthy controls and correlates with cognitive decline and severity of functional impairment. It also differentiates (with high sensitivity and specificity) stroke patients with normal cognition from mild to moderate cognitive impairment. Saliva may be an alternative to blood for assessing cytokines in stroke patients, although further studies on a larger patient population are needed.

Controversies in Imaging of Patients with Acute Ischemic Stroke: AJR Expert Panel Narrative Review

The development of reperfusion therapies has profoundly impacted stroke care, initially with the advent of IV thrombolytic (IVT) treatment and, more recently, with the development and refinement of endovascular treatment (EVT). Progress in neuroimaging has supported the paradigm shift of stroke care, and advanced neuroimaging now has a fundamental role in triaging patients for both IVT and EVT. As the standard of care for acute ischemic stroke (AIS) evolves, controversies remain in certain clinical scenarios. This article explores the use of multimodality imaging for treatment selection of AIS in the context of recent guidelines, highlighting controversial topics and providing guidance for clinical practice. Results of major randomized trials supporting EVT are reviewed. Advantages and disadvantages of CT, CTA, MRI, and MRA in stroke diagnosis are summarized, with attention to level 1 evidence supporting the role of vascular imaging and perfusion imaging. Patient selection is compared between approaches based on time thresholds and physiologic approaches based on infarct core measurement using imaging. Moreover, various imaging approaches to core measurement are described. As ongoing studies push treatment boundaries, advanced imaging is expected to help identify a widening range of patients who may benefit from therapy.

Artificial intelligence in clinical decision support and outcome prediction - applications in stroke

Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.

Neuroimaging and deep learning for brain stroke detection - A review of recent advancements and future prospects

BACKGROUND AND OBJECTIVE

In recent years, deep learning algorithms have created a massive impact on addressing research challenges in different domains. The medical field also greatly benefits from the use of improving deep learning models which save time and produce accurate results. This research aims to emphasize the impact of deep learning models in brain stroke detection and lesion segmentation. This is achieved by discussing the state of the art approaches proposed by the recent works in this field.

METHODS

In this study, the advancements in stroke lesion detection and segmentation were focused. The survey analyses 113 research papers published in different academic research databases. The research articles have been filtered out based on specific criteria to obtain the most prominent insights related to stroke lesion detection and segmentation.

RESULTS

The features of the stroke lesion vary based on the type of imaging modality. To develop an effective method for stroke lesion detection, the features need to be carefully extracted from the input images. This review takes an attempt to categorize and discuss the different deep architectures employed for stroke lesion detection and segmentation, based on the underlying imaging modality. This further assists in understanding the relevance of the two-deep neural network components in medical image analysis namely Convolutional Neural Network (CNN) and Fully Convolutional Network (FCN). It hints at other possible deep architectures that can be proposed for better results towards stroke lesion detection. Also, the emerging trends and breakthroughs in stroke detection have been detailed in this evaluation.

CONCLUSION

This work concludes by examining the technical and non-technical challenges faced by researchers and indicate the future implications in stroke detection. It could support the bio-medical researchers to propose better solutions for stroke lesion detection.