Deep Learning Applications for Acute Stroke Management.

Brain imaging is essential to the clinical care of patients with stroke, a leading cause of disability and death worldwide. Whereas advanced neuroimaging techniques offer opportunities for aiding acute stroke management, several factors, including time delays, inter-clinician variability, and lack of systemic conglomeration of clinical information, hinder their maximal utility. Recent advances in deep machine learning (DL) offer new strategies for harnessing computational medical image analysis to inform decision making in acute stroke. We examine the current state of the field for DL models in stroke triage. First, we provide a brief, clinical practice-focused primer on DL. Next, we examine real-world examples of DL applications in pixel-wise labeling, volumetric lesion segmentation, stroke detection, and prediction of tissue fate postintervention. We evaluate recent deployments of deep neural networks and their ability to automatically select relevant clinical features for acute decision making, reduce inter-rater variability, and boost reliability in rapid neuroimaging assessments, and integrate neuroimaging with electronic medical record (EMR) data in order to support clinicians in routine and triage stroke management. Ultimately, we aim to provide a framework for critically evaluating existing automated approaches, thus equipping clinicians with the ability to understand and potentially apply DL approaches in order to address challenges in clinical practice. ANN NEUROL 2022;92:574-587.

Identification of White Matter Hyperintensities in Routine Emergency Department Visits Using Portable Bedside Magnetic Resonance Imaging.

Background White matter hyperintensity (WMH) on magnetic resonance imaging (MRI) of the brain is associated with vascular cognitive impairment, cardiovascular disease, and stroke. We hypothesized that portable magnetic resonance imaging (pMRI) could successfully identify WMHs and facilitate doing so in an unconventional setting. Methods and Results In a retrospective cohort of patients with both a conventional 1.5 Tesla MRI and pMRI, we report Cohen's kappa (κ) to measure agreement for detection of moderate to severe WMH (Fazekas ≥2). In a subsequent prospective observational study, we enrolled adult patients with a vascular risk factor being evaluated in the emergency department for a nonstroke complaint and measured WMH using pMRI. In the retrospective cohort, we included 33 patients, identifying 16 (49.5%) with WMH on conventional MRI. Between 2 raters evaluating pMRI, the interrater agreement on WMH was strong (κ=0.81), and between 1 rater for conventional MRI and the 2 raters for pMRI, intermodality agreement was moderate (κ=0.66, 0.60). In the prospective cohort we enrolled 91 individuals (mean age, 62.6 years; 53.9% men; 73.6% with hypertension), of which 58.2% had WMHs on pMRI. Among 37 Black and Hispanic individuals, the Area Deprivation Index was higher (versus White, 51.8±12.9 versus 37.9±11.9; P<0.001). Among 81 individuals who did not have a standard-of-care MRI in the preceding year, we identified WMHs in 43 of 81 (53.1%). Conclusions Portable, low-field imaging could be useful for identifying moderate to severe WMHs. These preliminary results introduce a novel role for pMRI outside of acute care and the potential role for pMRI to reduce disparities in neuroimaging.

Portable MRI to assess optic chiasm decompression after endoscopic endonasal resection of sellar and suprasellar lesions.

OBJECTIVE: Low-field portable MRI (pMRI) is a recent technological advancement with potential for broad applications. Compared with conventional MRI, pMRI is less resource-intensive with regard to operational costs and scan time. The application of pMRI in neurosurgical oncology has not been previously described. The goal of this study was to demonstrate the efficacy of pMRI in assessing optic nerve decompression after endoscopic endonasal surgery for sellar and suprasellar pathologies. METHODS: Patients who underwent endoscopic endonasal surgery for sellar and suprasellar lesions at a single institution and for whom pMRI and routine MRI were performed postoperatively were retrospectively reviewed to compare the two imaging systems. To assess the relative resolution of pMRI compared with MRI, the distance from the optic chiasm to the top of the third ventricle was measured, and the measurements were compared between paired equivalent slices on T2-weighted coronal images. The inter- and intrarater correlations were analyzed. RESULTS: Twelve patients were included in this study (10 with pituitary adenomas and 2 with craniopharyngiomas) with varying degrees of optic chiasm compression on preoperative imaging. Measurements were averaged across raters before calculating agreement between pMRI and MRI, which demonstrated significant interrater reliability (intraclass correlation coefficient [ICC] = 0.78, p < 0.01). Agreement between raters within the pMRI measurements was also significantly reliable (ICC = 0.93, p < 0.01). Finally, a linear mixed-effects model was specified to demonstrate that MRI measurement could be predicted using the pMRI measurement with the patient and rater set as random effects (pMRI ß coefficient = 0.80, p < 0.01). CONCLUSIONS: The results of this study suggest that resolution of pMRI is comparable to that of conventional MRI in assessing the optic chiasm position in relation to the third ventricle. Portable MRI sufficiently demonstrates decompression of the optic chiasm after endoscopic endonasal surgery. It can be an alternative strategy in cases in which cost, scan-time considerations, or lack of intraoperative MRI availability may preclude the ability to assess adequate optic nerve decompression after endoscopic endonasal surgery for sellar and suprasellar lesions.

Future of Neurology & Technology: Neuroimaging Made Accessible Using Low-Field, Portable MRI.

In the 20th century, the advent of neuroimaging dramatically altered the field of neurologic care. However, despite iterative advances since the invention of CT and MRI, little progress has been made to bring MR neuroimaging to the point of care. Recently, the emergence of a low-field (<1 T) portable MRI (pMRI) is setting the stage to revolutionize the landscape of accessible neuroimaging. Users can transport the pMRI into a variety of locations, using a standard 110-220 V wall outlet. In this article, we discuss current applications for pMRI, including in the acute and critical care settings, the barriers to broad implementation, and future opportunities.

Decrease in signal-related activity by visual training and repetitive visual stimulation.

While principles governing encoding mechanisms in visual perceptual learning (VPL) are well-known, findings regarding posttraining processing are still unrelated in terms of their underlying mechanisms. Here, we examined the effect of repetitive high-frequency visual stimulation (H-RVS) on VPL in an orientation detection task. Application of H-RVS after a single task session led to enhanced orientation detection performance (n = 12), but not in a sham condition (n = 12). If prior training-based VPL had been established by seven sessions in the detection task, H-RVS instead led to a performance impairment (n = 12). Both sham (n = 8) and low-frequency stimulation (L-RVS, n = 12) did not lead to a significant impairment. These findings may suggest reversal dynamics in which conditions of elevated network excitation lead to a decrease in a signal-related activity instead of a further increase. These reversal dynamics may represent a means to link various findings regarding posttraining processing.

Bedside monitoring of hypoxic ischemic brain injury using low-field, portable brain magnetic resonance imaging after cardiac arrest.

BACKGROUND: Assessment of brain injury severity is critically important after survival from cardiac arrest (CA). Recent advances in low-field MRI technology have permitted the acquisition of clinically useful bedside brain imaging. Our objective was to deploy a novel approach for evaluating brain injury after CA in critically ill patients at high risk for adverse neurological outcome. METHODS: This retrospective, single center study involved review of all consecutive portable MRIs performed as part of clinical care for CA patients between September 2020 and January 2022. Portable MR images were retrospectively reviewed by a blinded board-certified neuroradiologist (S.P.). Fluid-inversion recovery (FLAIR) signal intensities were measured in select regions of interest. RESULTS: We performed 22 low-field MRI examinations in 19 patients resuscitated from CA (68.4% male, mean [standard deviation] age, 51.8 [13.1] years). Twelve patients (63.2%) had findings consistent with HIBI on conventional neuroimaging radiology report. Low-field MRI detected findings consistent with HIBI in all of these patients. Low-field MRI was acquired at a median (interquartile range) of 78 (40-136) hours post-arrest. Quantitatively, we measured FLAIR signal intensity in three regions of interest, which were higher amongst patients with confirmed HIBI. Low-field MRI was completed in all patients without disruption of intensive care unit equipment monitoring and no safety events occurred. CONCLUSION: In a critically ill CA population in whom MR imaging is often not feasible, low-field MRI can be deployed at the bedside to identify HIBI. Low-field MRI provides an opportunity to evaluate the time-dependent nature of MRI findings in CA survivors.

Portable, low-field magnetic resonance imaging enables highly accessible and dynamic bedside evaluation of ischemic stroke.

Brain imaging is essential to the clinical management of patients with ischemic stroke. Timely and accessible neuroimaging, however, can be limited in clinical stroke pathways. Here, portable magnetic resonance imaging (pMRI) acquired at very low magnetic field strength (0.064 T) is used to obtain actionable bedside neuroimaging for 50 confirmed patients with ischemic stroke. Low-field pMRI detected infarcts in 45 (90%) patients across cortical, subcortical, and cerebellar structures. Lesions as small as 4 mm were captured. Infarcts appeared as hyperintense regions on T2-weighted, fluid-attenuated inversion recovery and diffusion-weighted imaging sequences. Stroke volume measurements were consistent across pMRI sequences and between low-field pMRI and conventional high-field MRI studies. Low-field pMRI stroke volumes significantly correlated with stroke severity and functional outcome at discharge. These results validate the use of low-field pMRI to obtain clinically useful imaging of stroke, setting the stage for use in resource-limited environments.

Methodology for Low-Field, Portable Magnetic Resonance Neuroimaging at the Bedside.

Neuroimaging is a critical component of triage and treatment for patients who present with neuropathology. Magnetic resonance imaging and non-contrast computed tomography are the gold standard for diagnosis and prognostication of patients with acute brain injuries. However, these modalities require intra-hospital transport to strict, access-controlled environments, which puts critically ill patients at risk for complications and secondary injuries. A novel, portable MRI (pMRI) device that can be deployed at the patient's bedside provides a needed solution. In a dual-center investigation, Yale New Haven Hospital has obtained regular neuroimaging on patients using the pMRI as part of routine clinical care in the Emergency Department and Intensive Care Unit (ICU) since August of 2020. Massachusetts General Hospital has begun using pMRI in the Neuroscience Intensive Care Unit since January 2021. This technology has expanded the population of patients who can receive MRI imaging by increasing accessibility and timeliness for scan completion by eliminating the need for transport and increasing the potential for serial monitoring. Here we describe our methods for screening, coordinating, and executing pMRI exams and provide further detail on how to scan specific patient populations.

Portable, bedside, low-field magnetic resonance imaging for evaluation of intracerebral hemorrhage.

Radiological examination of the brain is a critical determinant of stroke care pathways. Accessible neuroimaging is essential to detect the presence of intracerebral hemorrhage (ICH). Conventional magnetic resonance imaging (MRI) operates at high magnetic field strength (1.5-3 T), which requires an access-controlled environment, rendering MRI often inaccessible. We demonstrate the use of a low-field MRI (0.064 T) for ICH evaluation. Patients were imaged using conventional neuroimaging (non-contrast computerized tomography (CT) or 1.5/3 T MRI) and portable MRI (pMRI) at Yale New Haven Hospital from July 2018 to November 2020. Two board-certified neuroradiologists evaluated a total of 144 pMRI examinations (56 ICH, 48 acute ischemic stroke, 40 healthy controls) and one ICH imaging core lab researcher reviewed the cases of disagreement. Raters correctly detected ICH in 45 of 56 cases (80.4% sensitivity, 95%CI: [0.68-0.90]). Blood-negative cases were correctly identified in 85 of 88 cases (96.6% specificity, 95%CI: [0.90-0.99]). Manually segmented hematoma volumes and ABC/2 estimated volumes on pMRI correlate with conventional imaging volumes (ICC = 0.955, p = 1.69e-30 and ICC = 0.875, p = 1.66e-8, respectively). Hematoma volumes measured on pMRI correlate with NIH stroke scale (NIHSS) and clinical outcome (mRS) at discharge for manual and ABC/2 volumes. Low-field pMRI may be useful in bringing advanced MRI technology to resource-limited settings.