Critical care management of acute intracerebral hemorrhage. Curr Treat Options Neurol. 2011;13:204-216. [PMID: 21222062 DOI: 10.1007/s11940-010-0109-2]

Decreasing false-positive detection of intracranial hemorrhage (ICH) using RAPID ICH 3

INTRODUCTION

The prompt detection of intracranial hemorrhage (ICH) on a non-contrast head CT (NCCT) is critical for the appropriate triage of patients, particularly in high volume/high acuity settings. Several automated ICH detection tools have been introduced; however, at present, most suffer from suboptimal specificity leading to false-positive notifications.

METHODS

NCCT scans from 4 large databases were evaluated for the presence of an ICH (IPH, IVH, SAH or SDH) of >0.4 ml using fully-automated RAPID ICH 3.0 as compared to consensus detection from at least two neuroradiology experts. Scans were excluded for (1) severe CT artifacts, (2) prior neurosurgical procedures, or (3) recent intravenous contrast. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by were determined.

RESULTS

A total of 881 studies were included. The automated software correctly identified 453/463 ICH-positive cases and 416/418 ICH-negative cases, resulting in a sensitivity of 97.84% and specificity 99.52%, positive predictive value 99.56%, and negative predictive value 97.65% for ICH detection. The positive and negative likelihood ratios for ICH detection were similarly favorable at 204.49 and 0.02 respectively. Mean processing time was <40 seconds.

CONCLUSIONS

In this large data set of nearly 900 patients, the automated software demonstrated high sensitivity and specificity for ICH detection, with rare false-positives.

Artificial Intelligence in Neuroradiology: A Review of Current Topics and Competition Challenges

There is an expanding body of literature that describes the application of deep learning and other machine learning and artificial intelligence methods with potential relevance to neuroradiology practice. In this article, we performed a literature review to identify recent developments on the topics of artificial intelligence in neuroradiology, with particular emphasis on large datasets and large-scale algorithm assessments, such as those used in imaging AI competition challenges. Numerous applications relevant to ischemic stroke, intracranial hemorrhage, brain tumors, demyelinating disease, and neurodegenerative/neurocognitive disorders were discussed. The potential applications of these methods to spinal fractures, scoliosis grading, head and neck oncology, and vascular imaging were also reviewed. The AI applications examined perform a variety of tasks, including localization, segmentation, longitudinal monitoring, diagnostic classification, and prognostication. While research on this topic is ongoing, several applications have been cleared for clinical use and have the potential to augment the accuracy or efficiency of neuroradiologists.

The impact on clinical outcomes after 1 year of implementation of an artificial intelligence solution for the detection of intracranial hemorrhage

BACKGROUND

To assess the effect of a commercial artificial intelligence (AI) solution implementation in the emergency department on clinical outcomes in a single level 1 trauma center.

METHODS

A retrospective cohort study for two time periods-pre-AI (1.1.2017-1.1.2018) and post-AI (1.1.2019-1.1.2020)-in a level 1 trauma center was performed. The ICH algorithm was applied to 587 consecutive patients with a confirmed diagnosis of ICH on head CT upon admission to the emergency department. Study variables included demographics, patient outcomes, and imaging data. Participants admitted to the emergency department during the same time periods for other acute diagnoses (ischemic stroke (IS) and myocardial infarction (MI)) served as control groups. Primary outcomes were 30- and 120-day all-cause mortality. The secondary outcome was morbidity based on Modified Rankin Scale for Neurologic Disability (mRS) at discharge.

RESULTS

Five hundred eighty-seven participants (289 pre-AI-age 71 ± 1, 169 men; 298 post-AI-age 69 ± 1, 187 men) with ICH were eligible for the analyzed period. Demographics, comorbidities, Emergency Severity Score, type of ICH, and length of stay were not significantly different between the two time periods. The 30- and 120-day all-cause mortality were significantly reduced in the post-AI group when compared to the pre-AI group (27.7% vs 17.5%; p = 0.004 and 31.8% vs 21.7%; p = 0.017, respectively). Modified Rankin Scale (mRS) at discharge was significantly reduced post-AI implementation (3.2 vs 2.8; p = 0.044).

CONCLUSION

The added value of this study emphasizes the introduction of artificial intelligence (AI) computer-aided triage and prioritization software in an emergent care setting that demonstrated a significant reduction in a 30- and 120-day all-cause mortality and morbidity for patients diagnosed with intracranial hemorrhage (ICH). Along with mortality rates, the AI software was associated with a significant reduction in the Modified Ranking Scale (mRs).

The Golden Hour: Early Interventions for Medical Emergencies during Pregnancy

Maternal mortality has increased in the last decades in the United States as a result of increased prevalence of coexisting medical diseases such as hypertension, diabetes, and both acquired and congenital heart diseases. Obstetricians and maternal-fetal medicine physicians should have the basic medical knowledge to initiate appropriate diagnostic and early therapeutic interventions since they may be the only provider available at the time of presentation. The goal of this article is not to extensively discuss the management of complex medical diseases during pregnancy, rather we provide a concise review of key early medical interventions that will likely result in improved clinical outcomes. KEY POINTS: · Obstetricians and maternal-fetal medicine physicians must be familiar with initial basic management of common medical emergencies.. · Management of these complex cases is ideally multidisciplinary.. · Residency/fellowship programs should include common disease management to improve maternal outcomes..

Sensitivity Analysis Highlights the Importance of Accurate Head Models for Electrical Impedance Tomography Monitoring of Intracerebral Hemorrhagic Stroke

OBJECTIVE

Electrical impedance tomography (EIT) has been proposed as a novel tool for diagnosing stroke. However, so far, the clinical feasibility is unresolved. In this study, we aim to investigate the need for accurate head modeling in EIT and how the inhomogeneities of the head contribute to the EIT measurement and affect its feasibility in monitoring the progression of a hemorrhagic stroke.

METHODS

We compared anatomically detailed six- and three-layer finite element models of a human head and computed the resulting scalp electrode potentials and the lead fields of selected electrode configurations. We visualized the resulting EIT measurement sensitivity distributions, computed the scalp electrode potentials, and examined the inverse imaging with selected cases. The effect of accurate tissue geometry and conductivity values on the EIT measurement is assessed with multiple different hemorrhagic perturbation locations and sizes.

RESULTS

Our results show that accurate tissue geometries and conductivity values inside the cranial cavity, especially the highly conductive cerebrospinal fluid, significantly affect EIT measurement sensitivity distribution and measured potentials.

CONCLUSIONS

We can conclude that the three-layer head models commonly used in EIT literature cannot depict the current paths correctly in the head. Thus, our study highlights the need to consider the detailed geometry of the cerebrospinal fluid (CSF) in EIT.

SIGNIFICANCE

The results clearly show that the CSF should be considered in the head EIT calculations.

Computational Approaches for Acute Traumatic Brain Injury Image Recognition

In recent years, there have been major advances in deep learning algorithms for image recognition in traumatic brain injury (TBI). Interest in this area has increased due to the potential for greater objectivity, reduced interpretation times and, ultimately, higher accuracy. Triage algorithms that can re-order radiological reading queues have been developed, using classification to prioritize exams with suspected critical findings. Localization models move a step further to capture more granular information such as the location and, in some cases, size and subtype, of intracranial hematomas that could aid in neurosurgical management decisions. In addition to the potential to improve the clinical management of TBI patients, the use of algorithms for the interpretation of medical images may play a transformative role in enabling the integration of medical images into precision medicine. Acute TBI is one practical example that can illustrate the application of deep learning to medical imaging. This review provides an overview of computational approaches that have been proposed for the detection and characterization of acute TBI imaging abnormalities, including intracranial hemorrhage, skull fractures, intracranial mass effect, and stroke.

Hematoma Expansion Context Guided Intracranial Hemorrhage Segmentation and Uncertainty Estimation

Accurate segmentation of the Intracranial Hemorrhage (ICH) in non-contrast CT images is significant for computer-aided diagnosis. Although existing methods have achieved remarkable results, none of them ever incorporated ICH's prior information in their methods. In this work, for the first time, we proposed a novel SLice EXpansion Network (SLEX-Net), which incorporated hematoma expansion in the segmentation architecture by directly modeling the spatial variation of hematoma expansion. Firstly, a new module named Slice Expansion Module (SEM) was built, which can effectively transfer contextual information between two adjacent slices by mapping predictions from one slice to another. Secondly, to perceive label correlation information from both upper and lower slices, we designed two information transmission paths: forward and backward slice expansion. By further exploiting intra-slice and inter-slice context with the information paths, the network significantly improved the accuracy and continuity of segmentation results. Moreover, the proposed SLEX-Net enables us to conduct an uncertainty estimation with one-time inference, which is much more efficient than existing methods. We evaluated the proposed SLEX-Net and compared it with some state-of-the-art methods. Experimental results demonstrate that our method makes significant improvements in all metrics on segmentation performance and outperforms other existing uncertainty estimation methods in terms of several metrics. The code will be available from https://github.com/JohnleeHIT/SLEX-Net.

Automated Cerebral Hemorrhage Detection Using RAPID

BACKGROUND AND PURPOSE

Intracranial hemorrhage (ICH) is an important event that is diagnosed on head NCCT. Increased NCCT utilization in busy hospitals may limit timely identification of ICH. RAPID ICH is an automated hybrid 2D-3D convolutional neural network application designed to detect ICH that may allow for expedited ICH diagnosis. We determined the accuracy of RAPID ICH for ICH detection and ICH volumetric quantification on NCCT.

MATERIALS AND METHODS

NCCT scans were evaluated for ICH by RAPID ICH. Consensus detection of ICH by 3 neuroradiology experts was used as the criterion standard for RAPID ICH comparison. ICH volume was also automatically determined by RAPID ICH in patients with intraparenchymal or intraventricular hemorrhage and compared with manually segmented ICH volumes by a single neuroradiology expert. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by RAPID ICH were determined.

RESULTS

We included 308 studies. RAPID ICH correctly identified 151/158 ICH cases and 143/150 ICH-negative cases, which resulted in high sensitivity (0.956, CI: 0.911-0.978), specificity (0.953, CI: 0.907-0.977), positive predictive value (0.956, CI: 0.911-0.978), and negative predictive value (0.953, CI: 0.907-0.977) for ICH detection. The positive likelihood ratio (20.479, CI 9.928-42.245) and negative likelihood ratio (0.046, CI 0.023-0.096) for ICH detection were similarly favorable. RAPID ICH volumetric quantification for intraparenchymal and intraventricular hemorrhages strongly correlated with expert manual segmentation (correlation coefficient r = 0.983); the median absolute error was 3 mL.

CONCLUSIONS

RAPID ICH is highly accurate in the detection of ICH and in the volumetric quantification of intraparenchymal and intraventricular hemorrhages.

Prediction of mortality after evacuation of supratentorial intracerebral hemorrhage using NSQIP data

Spontaneous intracerebral hemorrhage (sICH) is associated with high rates of morbidity and mortality. Neurosurgical clot evacuation is controversial but often a life saving maneuver in the setting of severe mass effect and cerebral herniation. Outcomes from large multicenter databases are sparsely reported. Patients who underwent craniotomy for evacuation of a supratentorial sICH between 2006 and 2017 were systematically extracted from the American College of Surgeons National Surgical Quality Improvement Program Participant Use Files. Our primary outcomes of interest were 30-day mortality, non-routine discharge disposition, and extended length of stay ([eLOS], defined as the top quartile for the cohort). Individual binary logistic regression models were constructed to query the associations between pre- and perioperative variables and each outcome. A total of 751 patients met the inclusion criteria. The 30-day mortality rate was 23.3% and increased from 2011 to 2017 (pooled OR 2.060 [95% CI 1.437 - 2.953]). Older age, morbid obesity, preoperative mechanical ventilation, preoperative systemic inflammatory response syndrome (SIRS) or septic shock, and thrombocytopenia were associated with mortality. Older age, race, and preoperative mechanical ventilation were associated with non-routine discharge. Patients who were mechanically ventilated or were insulin-dependent diabetics had greater odds of experiencing eLOS. A formula for estimating 30-day mortality was developed and found to have a strong linear association with actual mortality rates (R² = 0.777, p = 0.002). Preoperative mechanical ventilation is a consistent predictor of poor outcomes following surgery for supratentorial sICH. Mortality is also influenced by older age, body habitus, SIRS, septic shock, and thrombocytopenia.

Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT

BACKGROUND AND PURPOSE

Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT.

MATERIALS AND METHODS

This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation.

RESULTS

A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively.

CONCLUSIONS

A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.

Neuroscience step-down unit admission criteria for patients with intracerebral hemorrhage

OBJECTIVES

The goal of our study is to determine optimal criteria which can be used to avoid admission to neuroscience intensive care units for patients with intracerebral hemorrhage (ICH).

PATIENTS AND METHODS

This is a retrospective cohort study of 431 patients with primary ICH from January 2013 to the end of December 2015 and reviewed multiple admitting characteristics. Based on these needs, we tested the following step-down unit admission criteria: Supratentorial ICH, ICH volume <20 cc, no Intraventricular hemorrhage (IVH), systolic BP <200mmHg, no respiratory failure, GCS≥12. We classified 431 patients into two groups; 1-Patients who met step-down unit admission Criteria (71 patients). 2-Patients who didn't meet the criteria (360 patients).

RESULTS

In our patients, 16.5% fulfilled the criteria. Length of stay in the ICU was 1.43days in step-down unit admission criteria patients. None of the patients who fulfilled the criteria were readmitted to the ICU, compared to 3 readmissions among the group of patients who did not fulfill the criteria (P=0.82). None of these patients required a neurosurgical procedure vs 47 patients (10.9%) in the other group (P=0.04). Among patients who met the criteria, 83.1% were discharged home or rehab RR 0.33 CI (0.19-0.55), (P<0.0001).

CONCLUSION

We propose that patients who fulfill step-down unit admission criteria can be safely monitored in stroke unit and they have no need for ICU admission. Further studies are needed to validate these criteria in a prospective manner.

What intracranial pathologies are most likely to receive intervention? A preliminary study on referrals from an emergency centre with no on-site neurosurgical capabilities

Introduction

Access to neurosurgical facilities remains limited in resource-restricted medical environments worldwide, including Africa. Many hospitals refer patients to off-site facilities if they require intervention. Unnecessary referrals, however, can be detrimental to the patient and/or costly to the healthcare system itself. The aim of this study was to determine the frequency and associated intracranial pathology of patients who did and did not receive active neurosurgical intervention after having presented to an academic emergency centre at a hospital without on-site neurosurgical capabilities.

Methods

A one-year, retrospective record review of all patients who presented with potential neurosurgical pathology to a tertiary academic emergency centre in Johannesburg, South Africa was conducted.

Results

A total of 983 patients received a computed tomography brain scan for suspected neurosurgical pathology. There were 395 positive scans; 67.8% with traumatic brain injury (TBI) and 32.3% non-traumatic brain injury (non-TBI). Only 14.4% of patients received neurosurgical intervention, mostly non-TBI-related. The main intervention was a craniotomy for both TBI and non-TBI patients. The main TBI haemorrhages that received an intervention were subdural (SDH) (16.5%) and extradural (10.4%) haemorrhages. More than half the patients with non-TBI SDHs as well as those with aneurysms and subarachnoid haemorrhages received an intervention.

Discussion

Based on this study’s findings, in a resource-restricted setting, the patients who should receive preference for neurosurgical referral and intervention are (1) those with intracranial haemorrhages (2) those with non-traumatic SDH more than traumatic SDH and (3) those patients with non-traumatic subarachnoid haemorrhages caused by aneurysms.

NLRP3 is Required for Complement-Mediated Caspase-1 and IL-1beta Activation in ICH

Complement-mediated inflammation plays a vital role in intracerebral hemorrhage (ICH), implicating pro-inflammatory factor interleukin-1beta (IL-1β) secretion. Brain samples and contralateral hemiencephalon were all collected and detected by Western blot. NLRP3 expression was located by dual immunofluorescence staining at 1, 3, and 5 days post-ICH. Brain water content was examined post-ICH. The neural deficit scores were evaluated by observers blindly. ILs were detected by ELISA. SiRNAs targeting NLRP3 (siNLRP3), siASC, and siControl were injected to inhibit NLRP3 function. To test the complement activation via Nod-like receptor (NLR) family pyrin domain-containing 3 (NLRP3), normal rabbit complement (NRC) was injected with lipopolysaccharide (LPS) to facilitate the complement function. As a result, complement 3a (C3a) and complement 5a (C5a) were upregulated during the ICH-induced neuroinflammation, and ablation of C3 attenuates ICH-induced IL-1β release. Though the LPS rescues the neuroinflammation in the ICH model, C3 deficiency attenuates the LPS-induced inflammatory effect. The NLRP3 inflammasome was activated after ICH and was located in the microglial cell of the mouse brain, which exhibits a time-dependent manner. However, the number of NLRP3/Iba-1 dual-labeled cells in the C3^-/- group is less than that in the WT group in each time course, respectively. IL-1β and IL-18 released in perihematoma tissue, caspase-1-p20, brain water content, and behavioral outcomes were attenuated in the siNLRP3 and siASC groups than in the siControl and ICH groups. We also found that 5% of complement supplement enhances ICH-induced IL-1β release, while NLRP3 and ASC inhibition attenuates it. In conclusion, complement-induced ICH neuroinflammation depended on NLRP3 activation, which facilities LPS- and ICH-induced neuroinflammation, and NLRP3 is required for ICH-induced inflammation.

Steps to consider in the approach and management of critically ill patient with spontaneous intracerebral hemorrhage

Spontaneous intracerebral hemorrhage is a type of stroke associated with poor outcomes. Mortality is elevated, especially in the acute phase. From a pathophysiological point of view the bleeding must traverse different stages dominated by the possibility of re-bleeding, edema, intracranial hypertension, inflammation and neurotoxicity due to blood degradation products, mainly hemoglobin and thrombin. Neurological deterioration and death are common in early hours, so it is a true neurological-neurosurgical emergency. Time is brain so that action should be taken fast and accurately. The most significant prognostic factors are level of consciousness, location, volume and ventricular extension of the bleeding. Nihilism and early withdrawal of active therapy undoubtedly influence the final result. Although there are no proven therapeutic measures, treatment should be individualized and guided preferably by pathophysiology. The multidisciplinary teamwork is essential. Results of recently completed studies have birth to promising new strategies. For correct management it’s important to establish an orderly and systematic strategy based on clinical stabilization, evaluation and establishment of prognosis, avoiding secondary insults and adoption of specific individualized therapies, including hemostatic therapy and intensive control of elevated blood pressure. Uncertainty continues regarding the role of surgery.

Artificial neural networks based early clinical prediction of mortality after spontaneous intracerebral hemorrhage

Numerous outcome prediction models have been developed for mortality and functional outcome after spontaneous intracerebral haemorrhage (ICH). However, no outcome prediction model for ICH has considered the impact of care restriction. To develop and compare results of the artificial neural networks (ANN) and logistic regression (LR) models, based on initial clinical parameters, for prediction of mortality after spontaneous ICH. Analysis has been conducted on consecutive dataset of patients with spontaneous ICH, over 5-year period in tertiary care academic hospital. Patients older than 18 years were eligible for inclusion if they had been presented within 6 h from the start of symptoms and had evidence of spontaneous supratentorial ICH on initial brain computed tomography within 24 h. Initial clinical parameters have been used to develop LR and ANN prediction models for hospital mortality as outcome measure. Models have been accessed for discrimination and calibration abilities. We have analyzed 411 patients (199 males and 212 females) with spontaneous ICH, medically treated and not withdrawn from therapy, with average age of 67.35 years. From them, 256 (62.29%) patients died during hospital treatment and 155 (37.71%) patients survived. In the observed dataset, ANN model overall correctly classified outcome in 93.55% of patients, compared with 79.32% of correct classification for the LR model. Discrimination and calibration parameters indicate that both models show an adequate fit of expected and observed values, with superiority of ANN model. Our results favour the ANN model for prediction of mortality after spontaneous ICH. Further studies of the strengths and limitations of this method are needed with larger prospective samples.

Intracranial hemorrhage

Intracranial hemorrhage refers to any bleeding within the intracranial vault, including the brain parenchyma and surrounding meningeal spaces. This article focuses on the acute diagnosis and management of primary nontraumatic intracerebral hemorrhage and subarachnoid hemorrhage in the emergency department.

Management of intracerebral hemorrhage in 2020

Intracerebral hemorrhage (ICH) remains a common and deadly form of stroke, with virtually no greatly effective treatments aside from supportive and stroke unit care. Several surgical and medical therapies have been studied, but nothing has yet been found that greatly changes the pathophysiology. To achieve this, there will need to be substantial changes in treatment strategies. This article will focus on refinements to existing strategies and consider new approaches to the management of ICH. It will draw parallels with ischemic stroke treatments, and define the idea of ‘interventional therapy’ for ICH. It is suggested that reducing hematoma expansion could be compared with salvage of the ischemic penumbra, as a potential target for interventional ICH treatments. The concept of different time windows for the application of therapies according to the pathophysiology will be discussed. Finally, some novel treatment strategies are proposed, including an endovascular approach and ‘external, stereotactic cautery’, as future possibilities.