A Pilot Clinical and Technical Validation of an Immersive Virtual Reality Platform for 3D Anatomical Modeling and Contouring in Support of Surgical and Radiation Oncology Treatment Planning.

The aim of this study was to validate a novel medical virtual reality (VR) platform used for medical image segmentation and contouring in radiation oncology and 3D anatomical modeling and simulation for planning medical interventions, including surgery. The first step of the validation was to verify quantitatively and qualitatively that the VR platform can produce substantially equivalent 3D anatomical models, image contours, and measurements to those generated with existing commercial platforms. To achieve this, a total of eight image sets and 18 structures were segmented using both VR and reference commercial platforms. The image sets were chosen to cover a broad range of scanner manufacturers, modalities, and voxel dimensions. The second step consisted of evaluating whether the VR platform could provide efficiency improvements for target delineation in radiation oncology planning. To assess this, the image sets for five pediatric patients with resected standard-risk medulloblastoma were used to contour target volumes in support of treatment planning of craniospinal irradiation, requiring complete inclusion of the entire cerebral-spinal volume. Structures generated in the VR and the commercial platforms were found to have a high degree of similarity, with dice similarity coefficient ranging from 0.963 to 0.985 for high-resolution images and 0.920 to 0.990 for lower resolution images. Volume, cross-sectional area, and length measurements were also found to be in agreement with reference values derived from a commercial system, with length measurements having a maximum difference of 0.22 mm, angle measurements having a maximum difference of 0.04°, and cross-sectional area measurements having a maximum difference of 0.16 mm2. The VR platform was also found to yield significant efficiency improvements, reducing the time required to delineate complex cranial and spinal target volumes by an average of 50% or 29 min.

Influence of Time of Admission on Endovascular Thrombectomy (EVT): Comparison of Outcomes During Business Hours Versus Off-Business Hours.

Purpose:To investigate the differences in endovascular thrombectomy (EVT) outcomes of patients treated for acute ischaemic stroke (AIS) during business versus off-business hours. Methods: A single-centre retrospective cohort study of patients with AIS treated with EVT from February 1, 2015, to May 31, 2021, was performed at a comprehensive stroke centre (CSC). Patients were divided into business (Monday to Friday, 8 AM-5 PM) versus off-business hours groups. The primary outcome was functional neurological disability, scored using the modified Rankin Scale (mRS) at 90 days. Secondary outcomes included the rate of successful reperfusion and procedural workflow time delays. Differences in proportions were assessed using Fisher's exact and Chi-Square tests as appropriate. For continuous variables, differences in medians between groups were assessed using Mann-Whitney U tests. Results: A total of 676 patients were included, with 399 patients (59%) comprising the off-business-hour group. No significant differences were seen in age, sex, ASPECTS score, or NIHSS at arrival. Off-business hours strokes had a longer delay between CSC arrival to groin puncture (minutes: 81 vs 44, P < .0001) and between imaging to groin puncture (minutes: 67 vs 32, P < .0001) compared to the business hours strokes. There were no differences in the rate of successful reperfusion (mTICI ≥2b) between groups (82% vs 83%, P = .61). At 90 days, 65% of patients in both groups had an mRS ≤2 (P = .91). Conclusion: Despite workflow delays in initiating EVT during off-business hours, there were no differences in the rate of successful reperfusion or functional outcomes.

Influence of Stroke-Onset Location on the Efficacy of Endovascular Thrombectomy: Comparison of Outcomes between In-Hospital versus Community-Onset Strokes.

BACKGROUND AND PURPOSE: Previous studies have suggested that patients experiencing an in-hospital stroke may face delays in treatment and worse outcomes compared with patients with community-onset strokes. However, most studies occurred when IV thrombolysis was the primary treatment. This study aimed to examine the outcomes of patients experiencing an in-hospital stroke in the endovascular thrombectomy era. MATERIALS AND METHODS: This was a single-center retrospective cohort study of patients older than 18 years of age with acute ischemic stroke treated with endovascular thrombectomy within 12 hours of stroke onset from January 1, 2015, to April 30, 2021. Patients were classified into 2 groups: in-hospital strokes and community-onset strokes. We compared the time metrics of stroke care delivery, the rate of successful reperfusion, and functional outcome as scored using the mRS score at 90 days (favorable outcome was defined as mRS 0-2). Differences in proportions were assessed using the Fisher exact and χ2 tests as appropriate. For continuous variables, differences in medians between groups were evaluated using Mann-Whitney U tests. RESULTS: A total of 676 consecutive patients were included, with 69 (10%) comprising the in-hospital stroke group. Patients experiencing in-hospital stroke were more likely to have diabetes (36% versus 18%, P = .02) and less likely to receive thrombolysis (25% versus 68%, P < .001) than those in the community-onset stroke group, but they were otherwise similar. Patients with in-hospital stroke had significantly faster overall time metrics, most notably from stroke recognition to imaging (median, 70 [interquartile range, 38-141] minutes versus 121 [74-228] minutes, P < .001). Successful recanalization was achieved in >75% in both groups (P = .39), with a median NIHSS score at discharge of <4 (P = .18). The 90-day mRS was similar in both groups, with a trend toward higher in-hospital mortality in the in-hospital stroke group (P = .06). CONCLUSIONS: Patients with in-hospital stroke had shorter workflow delays to initiation of endovascular thrombectomy compared with their community counterparts but with a similar rate of successful recanalization and clinical outcomes. Most important, 90-day mortality and mRS scores were equivalent between in-hospital stroke and community-onset stroke groups.

Deep learning prediction of renal anomalies for prenatal ultrasound diagnosis.

Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly in the field of medical imaging. In this study, we investigated the application of deep learning models in early detection of fetal kidney anomalies. To provide an enhanced interpretation of those models' predictions, we proposed an adapted two-class representation and developed a multi-class model interpretation approach for problems with more than two labels and variable hierarchical grouping of labels. Additionally, we employed the explainable AI (XAI) visualization tools Grad-CAM and HiResCAM, to gain insights into model predictions and identify reasons for misclassifications. The study dataset consisted of 969 ultrasound images from unique patients; 646 control images and 323 cases of kidney anomalies, including 259 cases of unilateral urinary tract dilation and 64 cases of unilateral multicystic dysplastic kidney. The best performing model achieved a cross-validated area under the ROC curve of 91.28% ± 0.52%, with an overall accuracy of 84.03% ± 0.76%, sensitivity of 77.39% ± 1.99%, and specificity of 87.35% ± 1.28%. Our findings emphasize the potential of deep learning models in predicting kidney anomalies from limited prenatal ultrasound imagery. The proposed adaptations in model representation and interpretation represent a novel solution to multi-class prediction problems.

Imaging Review of Pediatric Monogenic CNS Vasculopathy with Genetic Correlation.

Monogenic cerebral vasculopathy is a rare but progressively recognizable cause of pediatric cerebral vasculopathy manifesting as early as fetal life. These monogenic cerebral vasculopathies can be silent or manifest variably as fetal or neonatal distress, neurologic deficit, developmental delay, cerebral palsy, seizures, or stroke. The radiologic findings can be nonspecific, but the presence of disease-specific cerebral and extracerebral imaging features can point to a diagnosis and guide genetic testing, allowing targeted treatment. The authors review the existing literature describing the frequently encountered and rare monogenic cerebral vascular disorders affecting young patients and describe the relevant pathogenesis, with an attempt to categorize them based on the defective step in vascular homeostasis and/or signaling pathways and characteristic cerebrovascular imaging findings. The authors also highlight the role of imaging and a dedicated imaging protocol in identification of distinct cerebral and extracerebral findings crucial in the diagnostic algorithm and selection of genetic testing. Early and precise recognition of these entities allows timely intervention, preventing or delaying complications and thereby improving quality of life. It is also imperative to identify the specific pathogenic variant and pattern of inheritance for satisfactory genetic counseling and care of at-risk family members. Last, the authors present an image-based approach to these young-onset monogenic cerebral vasculopathies that is guided by the size and predominant radiologic characteristics of the affected vessel with reasonable overlap. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

HDAC1/2 inhibitor therapy improves multiple organ systems in aged mice.

Aging increases the risk of age-related diseases, imposing substantial healthcare and personal costs. Targeting fundamental aging mechanisms pharmacologically can promote healthy aging and reduce this disease susceptibility. In this work, we employed transcriptome-based drug screening to identify compounds emulating transcriptional signatures of long-lived genetic interventions. We discovered compound 60 (Cmpd60), a selective histone deacetylase 1 and 2 (HDAC1/2) inhibitor, mimicking diverse longevity interventions. In extensive molecular, phenotypic, and bioinformatic assessments using various cell and aged mouse models, we found Cmpd60 treatment to improve age-related phenotypes in multiple organs. Cmpd60 reduces renal epithelial-mesenchymal transition and fibrosis in kidney, diminishes dementia-related gene expression in brain, and enhances cardiac contractility and relaxation for the heart. In sum, our two-week HDAC1/2 inhibitor treatment in aged mice establishes a multi-tissue, healthy aging intervention in mammals, holding promise for therapeutic translation to promote healthy aging in humans.

Neuroimaging Scoring Tools to Differentiate Inflammatory Central Nervous System Small-Vessel Vasculitis: A Need for Artificial Intelligence/Machine Learning?-A Scoping Review.

Neuroimaging has a key role in identifying small-vessel vasculitis from common diseases it mimics, such as multiple sclerosis. Oftentimes, a multitude of these conditions present similarly, and thus diagnosis is difficult. To date, there is no standardized method to differentiate between these diseases. This review identifies and presents existing scoring tools that could serve as a starting point for integrating artificial intelligence/machine learning (AI/ML) into the clinical decision-making process for these rare diseases. A scoping literature review of EMBASE and MEDLINE included 114 articles to evaluate what criteria exist to diagnose small-vessel vasculitis and common mimics. This paper presents the existing criteria of small-vessel vasculitis conditions and mimics them to guide the future integration of AI/ML algorithms to aid in diagnosing these conditions, which present similarly and non-specifically.

Clinical Features, Non-Contrast CT Radiomic and Radiological Signs in Models for the Prediction of Hematoma Expansion in Intracerebral Hemorrhage.

PURPOSE: Rapid identification of hematoma expansion (HE) risk at baseline is a priority in intracerebral hemorrhage (ICH) patients and may impact clinical decision making. Predictive scores using clinical features and Non-Contract Computed Tomography (NCCT)-based features exist, however, the extent to which each feature set contributes to identification is limited. This paper aims to investigate the relative value of clinical, radiological, and radiomics features in HE prediction. METHODS: Original data was retrospectively obtained from three major prospective clinical trials ["Spot Sign" Selection of Intracerebral Hemorrhage to Guide Hemostatic Therapy (SPOTLIGHT)NCT01359202; The Spot Sign for Predicting and Treating ICH Growth Study (STOP-IT)NCT00810888] Patients baseline and follow-up scans following ICH were included. Clinical, NCCT radiological, and radiomics features were extracted, and multivariate modeling was conducted on each feature set. RESULTS: 317 patients from 38 sites met inclusion criteria. Warfarin use (p=0.001) and GCS score (p=0.046) were significant clinical predictors of HE. The best performing model for HE prediction included clinical, radiological, and radiomic features with an area under the curve (AUC) of 87.7%. NCCT radiological features improved upon clinical benchmark model AUC by 6.5% and a clinical & radiomic combination model by 6.4%. Addition of radiomics features improved goodness of fit of both clinical (p=0.012) and clinical & NCCT radiological (p=0.007) models, with marginal improvements on AUC. Inclusion of NCCT radiological signs was best for ruling out HE whereas the radiomic features were best for ruling in HE. CONCLUSION: NCCT-based radiological and radiomics features can improve HE prediction when added to clinical features.

Optimal CT perfusion thresholds for core and penumbra in acute posterior circulation infarction.

Background: At least 20% of strokes involve the posterior circulation (PC). Compared to the anterior circulation, posterior circulation infarction (POCI) are frequently misdiagnosed. CT perfusion (CTP) has advanced stroke care by improving diagnostic accuracy and expanding eligibility for acute therapies. Clinical decisions are predicated upon precise estimates of the ischaemic penumbra and infarct core. Current thresholds for defining core and penumbra are based upon studies of anterior circulation stroke. We aimed to define the optimal CTP thresholds for core and penumbra in POCI. Methods: Data were analyzed from 331-patients diagnosed with acute POCI enrolled in the International-stroke-perfusion-registry (INSPIRE). Thirty-nine patients with baseline multimodal-CT with occlusion of a large PC-artery and follow up diffusion weighted MRI at 24-48 h were included. Patients were divided into two-groups based on artery-recanalization on follow-up imaging. Patients with no or complete recanalisation were used for penumbral and infarct-core analysis, respectively. A Receiver operating curve (ROC) analysis was used for voxel-based analysis. Optimality was defined as the CTP parameter and threshold which maximized the area-under-the-curve. Linear regression was used for volume based analysis determining the CTP threshold which resulted in the smallest mean volume difference between the acute perfusion lesion and follow up MRI. Subanalysis of PC-regions was performed. Results: Mean transit time (MTT) and delay time (DT) were the best CTP parameters to characterize ischaemic penumbra (AUC = 0.73). Optimal thresholds for penumbra were a DT >1 s and MTT>145%. Delay time (DT) best estimated the infarct core (AUC = 0.74). The optimal core threshold was a DT >1.5 s. The voxel-based analyses indicated CTP was most accurate in the calcarine (Penumbra-AUC = 0.75, Core-AUC = 0.79) and cerebellar regions (Penumbra-AUC = 0.65, Core-AUC = 0.79). For the volume-based analyses, MTT >160% demonstrated best correlation and smallest mean-volume difference between the penumbral estimate and follow-up MRI (R 2 = 0.71). MTT >170% resulted in the smallest mean-volume difference between the core estimate and follow-up MRI, but with poor correlation (R 2 = 0.11). Conclusion: CTP has promising diagnostic utility in POCI. Accuracy of CTP varies by brain region. Optimal thresholds to define penumbra were DT >1 s and MTT >145%. The optimal threshold for core was a DT >1.5 s. However, CTP core volume estimates should be interpreted with caution.

Time Course of Early Hematoma Expansion in Acute Spot-Sign Positive Intracerebral Hemorrhage: Prespecified Analysis of the SPOTLIGHT Randomized Clinical Trial.

BACKGROUND: In the SPOTLIGHT trial (Spot Sign Selection of Intracerebral Hemorrhage to Guide Hemostatic Therapy), patients with a computed tomography (CT) angiography spot-sign positive acute intracerebral hemorrhage were randomized to rFVIIa (recombinant activated factor VIIa; 80 µg/kg) or placebo within 6 hours of onset, aiming to limit hematoma expansion. Administration of rFVIIa did not significantly reduce hematoma expansion. In this prespecified analysis, we aimed to investigate the impact of delays from baseline imaging to study drug administration on hematoma expansion. METHODS: Hematoma volumes were measured on the baseline CT, early post-dose CT, and 24 hours CT scans. Total hematoma volume (intracerebral hemorrhage+intraventricular hemorrhage) change between the 3 scans was calculated as an estimate of how much hematoma expansion occurred before and after studying drug administration. RESULTS: Of the 50 patients included in the trial, 44 had an early post-dose CT scan. Median time (interquartile range) from onset to baseline CT was 1.4 hours (1.2-2.6). Median time from baseline CT to study drug was 62.5 (55-80) minutes, and from study drug to early post-dose CT was 19 (14.5-30) minutes. Median (interquartile range) total hematoma volume increased from baseline CT to early post-dose CT by 10.0 mL (-0.7 to 18.5) in the rFVIIa arm and 5.4 mL (1.8-8.3) in the placebo arm (P=0.96). Median volume change between the early post-dose CT and follow-up scan was 0.6 mL (-2.6 to 8.3) in the rFVIIa arm and 0.7 mL (-1.6 to 2.1) in the placebo arm (P=0.98). Total hematoma volume decreased between the early post-dose CT and 24-hour scan in 44.2% of cases (rFVIIa 38.9% and placebo 48%). The adjusted hematoma growth in volume immediately post dose for FVIIa was 0.998 times that of placebo ([95% CI, 0.71-1.43]; P=0.99). The hourly growth in FFVIIa was 0.998 times that for placebo ([95% CI, 0.994-1.003]; P=0.50; Table 3). CONCLUSIONS: In the SPOTLIGHT trial, the adjusted hematoma volume growth was not associated with Factor VIIa treatment. Most hematoma expansion occurred between the baseline CT and the early post-dose CT, limiting any potential treatment effect of hemostatic therapy. Future hemostatic trials must treat intracerebral hemorrhage patients earlier from onset, with minimal delay between baseline CT and drug administration. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier: NCT01359202.

Childhood Cerebral Vasculitis : A Multidisciplinary Approach.

Cerebral vasculitis is increasingly recognized as a common cause of pediatric arterial stroke. It can present with focal neurological deficits, psychiatric manifestations, seizures, and encephalopathy. The etiopathogenesis of childhood cerebral vasculitis (CCV) is multifactorial, making an inclusive classification challenging. In this review, we describe the common and uncommon CCV with a comprehensive discussion of etiopathogenesis, the role of various imaging modalities, and advanced techniques in diagnosing CCV. We also highlight the implications of relevant clinical, laboratory, and genetic findings to reach the final diagnosis. Based on the clinicoradiological findings, a stepwise diagnostic approach is proposed to facilitate CCV diagnosis and rule out potential mimics. Identification of key clinical manifestations, pertinent blood and cerebrospinal fluid results, and evaluation of central nervous system vessels for common and disease-specific findings will be emphasized. We discuss the role of magnetic resonance imaging, MR angiography, and vessel wall imaging as the imaging investigation of choice, and reservation of catheter angiography as a problem-solving tool. We emphasize the utility of brain and leptomeningeal biopsy for diagnosis and exclusion of imitators and masqueraders.

Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

BACKGROUND: The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify computed tomography (CT) findings in traumatic brain injury (TBI). METHODS: Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of 4 databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities. RESULTS: A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on 2- or 3-dimensional CT imaging datasets. CONCLUSION: We identified several important TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors.

Rule-based natural language processing for automation of stroke data extraction: a validation study.

PURPOSE: Data extraction from radiology free-text reports is time consuming when performed manually. Recently, more automated extraction methods using natural language processing (NLP) are proposed. A previously developed rule-based NLP algorithm showed promise in its ability to extract stroke-related data from radiology reports. We aimed to externally validate the accuracy of CHARTextract, a rule-based NLP algorithm, to extract stroke-related data from free-text radiology reports. METHODS: Free-text reports of CT angiography (CTA) and perfusion (CTP) studies of consecutive patients with acute ischemic stroke admitted to a regional stroke center for endovascular thrombectomy were analyzed from January 2015 to 2021. Stroke-related variables were manually extracted as reference standard from clinical reports, including proximal and distal anterior circulation occlusion, posterior circulation occlusion, presence of ischemia or hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status. These variables were simultaneously extracted using a rule-based NLP algorithm. The NLP algorithm's accuracy, specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) were assessed. RESULTS: The NLP algorithm's accuracy was > 90% for identifying distal anterior occlusion, posterior circulation occlusion, hemorrhage, and ASPECTS. Accuracy was 85%, 74%, and 79% for proximal anterior circulation occlusion, presence of ischemia, and collateral status respectively. The algorithm confirmed the absence of variables from radiology reports with an 87-100% accuracy. CONCLUSIONS: Rule-based NLP has a moderate to good performance for stroke-related data extraction from free-text imaging reports. The algorithm's accuracy was affected by inconsistent report styles and lexicon among reporting radiologists.

Association of Endovascular Thrombectomy With Functional Outcome in Patients With Acute Stroke With a Large Ischemic Core.

BACKGROUND AND OBJECTIVES: Endovascular thrombectomy (EVT) is effective for patients with large vessel occlusion (LVO) stroke with smaller volumes of CT perfusion (CTP)-defined ischemic core. However, the benefit of EVT is unclear in those with a core volume >70 mL. We aimed to compare outcomes of EVT and non-EVT patients with an ischemic core volume ≥70 mL, hypothesizing that there would be a benefit from EVT for fair outcome (3-month modified Rankin scale [mRS] 0-3) after stroke. METHODS: A retrospective analysis of patients enrolled into a multicenter (Australia, China, and Canada) registry (2012-2020) who underwent CTP within 24 hours of stroke onset and had a baseline ischemic core volume ≥70 mL was performed. The primary outcome was the estimation of the association of EVT in patients with core volume ≥70 mL and within 70-100 and ≥100 mL subgroups with fair outcome. RESULTS: Of the 3,283 patients in the registry, 299 had CTP core volume ≥70 mL and 269 complete data (135 had core volume between 70 and 100 mL and 134 had core volume ≥100 mL). EVT was performed in 121 (45%) patients. EVT-treated patients were younger (median 69 vs 75 years; p = 0.011), had lower prestroke mRS, and smaller median core volumes (92 [79-116.5] mL vs 105.5 [85.75-138] mL, p = 0.004). EVT-treated patients had higher odds of achieving fair outcome in adjusted analysis (30% vs 13.9% in the non-EVT group; adjusted odds ratio [aOR] 2.1, 95% CI 1-4.2, p = 0.038). The benefit was seen predominantly in those with 70-100 mL core volume (71/135 [52.6%] EVT-treated), with 54.3% in the EVT-treated vs 21% in the non-EVT group achieving a fair outcome (aOR 2.5, 95% CI 1-6.2, p = 0.005). Of those with a core volume ≥100 mL, 50 of the 134 (37.3%) underwent EVT. Proportions of fair outcome were very low in both groups (8.1% vs 8.7%; p = 0.908). DISCUSSION: We found a positive association of EVT with the 3-month outcome after stroke in patients with a baseline CTP ischemic core volume 70-100 mL but not in those with core volume ≥100 mL. Randomized data to confirm these findings are required. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that EVT is associated with better motor outcomes 3 months after CTP-defined ischemic stroke with a core volume of 70-100 mL.

Using deep-learning in fetal ultrasound analysis for diagnosis of cystic hygroma in the first trimester.

OBJECTIVE: To develop and internally validate a deep-learning algorithm from fetal ultrasound images for the diagnosis of cystic hygromas in the first trimester. METHODS: All first trimester ultrasound scans with a diagnosis of a cystic hygroma between 11 and 14 weeks gestation at our tertiary care centre in Ontario, Canada were studied. Ultrasound scans with normal nuchal translucency were used as controls. The dataset was partitioned with 75% of images used for model training and 25% used for model validation. Images were analyzed using a DenseNet model and the accuracy of the trained model to correctly identify cases of cystic hygroma was assessed by calculating sensitivity, specificity, and the area under the receiver-operating characteristic (ROC) curve. Gradient class activation heat maps (Grad-CAM) were generated to assess model interpretability. RESULTS: The dataset included 289 sagittal fetal ultrasound images;129 cystic hygroma cases and 160 normal NT controls. Overall model accuracy was 93% (95% CI: 88-98%), sensitivity 92% (95% CI: 79-100%), specificity 94% (95% CI: 91-96%), and the area under the ROC curve 0.94 (95% CI: 0.89-1.0). Grad-CAM heat maps demonstrated that the model predictions were driven primarily by the fetal posterior cervical area. CONCLUSIONS: Our findings demonstrate that deep-learning algorithms can achieve high accuracy in diagnostic interpretation of cystic hygroma in the first trimester, validated against expert clinical assessment.

Imaging for Predicting Hemorrhagic Transformation of Acute Ischemic Stroke-A Narrative Review.

Hemorrhagic transformation is caused by extravasation of blood products from vessels after acute ischemic stroke. It is an undesirable and potentially devastating complication, which occurs in 10%-40% of clinical cases. Hemorrhagic transformation is classified into four subtypes based on European cooperative acute stroke study II. Predicting hemorrhagic complications at presentation can be useful life saving/altering decisions for the patient. Also, understanding the mechanisms of hemorrhagic transformation can lead to new treatments and intervention measures. We highlighted various imaging techniques that have been used to predict hemorrhagic transformation. Specifically, we looked at the usefulness of perfusion and permeability imaging for hemorrhagic transformation. Use of imaging to predict hemorrhagic transformation could change patient management that may lead to the prevention of hemorrhagic transformation before it occurs. We concluded that the current evidence is not strong enough to rely on these imaging parameters for predicting hemorrhagic transformation and more studies are required.

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 treatment and, more recently, with the development and refinement of endovascular treatment (EVT). Progress in neuroim-aging has supported the paradigm shift of stroke care, and advanced neuroimaging now has a fundamental role in triaging patients for both IV thrombolytic treatment 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 patients with AIS in the context of recent guidelines, highlighting controversial topics and providing guidance for clinical practice. The results of major randomized trials supporting EVT are reviewed. The 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.

Automating Stroke Data Extraction From Free-Text Radiology Reports Using Natural Language Processing: Instrument Validation Study.

BACKGROUND: Diagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews. OBJECTIVE: We aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports. METHODS: From the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data. RESULTS: The overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status. CONCLUSIONS: NLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.