Neuroimaging of Acute Intracerebral Hemorrhage

CT histogram analysis to distinguish between acute intracerebral hemorrhage and cavernous hemangioma

OBJECTIVE

Acute intracerebral hemorrhage (AICH) and cerebral cavernous hemangioma (CCM) are two common cerebral hemorrhage diseases with partially overlapping CT findings and clinical symptoms, making it hard to distinguish between them. The current study used histogram analysis based on CT images to differentiate between CCM and AICH and test its diagnosis performance.

METHODS

This retrospective study included 158 patients with CCM and 137 patients with AICH. The histograms of brain CT plain scan images of both groups were extracted using Python code and included 18 histogram parameters of the lesions. The most effective parameters were selected by univariate logistic regression analysis and Spearman correlation analysis and included in the final multivariate logistic regression model. The sample was randomly divided into the training set and the validation set by 7:3. The ROC curve was constructed to evaluate the discriminant efficiency of the final logistic regression model in distinguishing between AICH and CCM.

RESULTS

The univariate analysis identified seven significant histogram parameters with the following final logistic regression model: F = 3.731 + 2.6411 × 10-9 × Energy-1.192 × Kurtosis-0.003 × Minimum-1.449 × Skewness + 2.5002 × 10-10 × Total Energy-1.103 × Uniformity+0.009 × Variance. The model showed good diagnostic performance in distinguishing between AICH and CCM, with an AUC of 0.876, sensitivity of 70.8%, and specificity of 91.9% in the training set, and an AUC of 0.870, sensitivity of 82.9%, and specificity of 85.1% in the validation set.

CONCLUSIONS

The histogram analysis of brain CT images can be used as an auxiliary method to distinguish between AICH and CCM effectively.

Assessment of large-scale imaging practices in patients with acute brain hemorrhage in French emergency departments: Emergency imaging practices in hemorrhagic stroke

OBJECTIVE

Intracerebral hemorrhage (ICH) is a life-threatening condition, where imaging plays a crucial role but remains poorly standardized. Our main objective was to analyze the imaging protocols used during the acute phase of ICH and ascertain the proportion of patients diagnosed with secondary hemorrhage.

PATIENTS AND METHODS

A multicenter retrospective observational study was conducted across over 100 French hospitals affiliated with a national tele-imaging network dedicated to emergency imaging. Among patients managed in the "Stroke Alert" pathway for suspected acute stroke from March 2021 to April 2023, those with ICH diagnosed within 24 h of symptoms onset were identified. Their imaging reports were reviewed to identify the imaging modality used and protocols performed and investigate whether a secondary cause was identified.

RESULTS

Of the 18,356 patients included in the "Stroke Alert" pathway, 662 cerebral hemorrhages were identified (3.6 %). Computed tomography (CT) was the most widely used imaging modality in the acute phase (71.8 % of examinations). Vascular imaging was performed in 78 % of patients with cerebral hemorrhage, most often CT angiography or TOF magnetic resonance angiography. A secondary cause was identified in 8.2 % (54/662) of cerebral hemorrhages, including vascular imaging in the vast majority of cases (92.6 %).

CONCLUSION

Optimization and standardization of imaging protocols in the acute phase of ICH is essential to improve the detection of its secondary causes, particularly vascular, requiring urgent treatment. Vascular imaging improves their early detection.

Cerebral Amyloid Angiopathy-Related Inflammation and Biopsy-Positive Primary Angiitis of the CNS: A Comparative Study

BACKGROUND AND OBJECTIVES

Cerebral amyloid angiopathy-related inflammation (CAA-RI) and biopsy-positive primary angiitis of the CNS (BP-PACNS) have overlapping clinicoradiologic presentations. It is unknown whether clinical and radiologic features can differentiate CAA-RI from BP-PACNS and whether both diseases have different relapse rates. The objectives of this study were to compare clinicoradiologic presentations and relapse rates in patients with CAA-RI vs BP-PACNS.

METHODS

Patients with CAA-RI and BP-PACNS were enrolled from 2 retrospective multicenter cohorts. Patients with CAA-RI were biopsy-positive or met probable clinicoradiologic criteria. Patients with BP-PACNS had histopathologic confirmation of CNS angiitis, with no secondary etiology. A neuroradiologist read brain MRIs, blinded to the diagnosis of CAA-RI or BP-PACNS. Clinicoradiologic features were compared using univariable logistic regression models. Relapse rates were compared using a univariable Fine-Gray subdistribution hazard model, with death as a competing risk.

RESULTS

This study enrolled 104 patients with CAA-RI (mean age 73 years, 48% female sex) and 52 patients with BP-PACNS (mean age 45 years, 48% female sex). Patients with CAA-RI more often had white matter hyperintense lesions meeting the probable CAA-RI criteria (93% vs 51%, p < 0.001), acute subarachnoid hemorrhage (15% vs 2%, p = 0.02), cortical superficial siderosis (27% vs 4%, p < 0.001), ≥1 lobar microbleed (94% vs 26%, p < 0.001), past intracerebral hemorrhage (17% vs 4%, p = 0.04), ≥21 visible centrum semiovale perivascular spaces (34% vs 4%, p < 0.01), and leptomeningeal enhancement (70% vs 27%, p < 0.001). Patients with BP-PACNS more often had headaches (56% vs 31%, p < 0.01), motor deficits (56% vs 36%, p = 0.02), and nonischemic parenchymal gadolinium enhancement (82% vs 16%, p < 0.001). The prevalence of acute ischemic lesions was 18% in CAA-RI and 22% in BP-PACNS (p = 0.57). The features with the highest specificity for CAA-RI were acute subarachnoid hemorrhage (98%), cortical superficial siderosis (96%), past intracerebral hemorrhage (96%), and ≥21 visible centrum semiovale perivascular spaces (96%). The probable CAA-RI criteria had a 71% sensitivity (95% CI 44%-90%) and 91% specificity (95% CI 79%-98%) in differentiating biopsy-positive CAA-RI from BP-PACNS. The rate of relapse in the first 2 years after remission was lower in CAA-RI than in BP-PACNS (hazard ratio 0.46, 95% CI 0.22-0.96, p = 0.04).

CONCLUSION

Clinicoradiologic features differed between patients with CAA-RI and those with BP-PACNS. Specific markers for CAA-RI were hemorrhagic signs of subarachnoid involvement, past intracerebral hemorrhage, ≥21 visible centrum semiovale perivascular spaces, and the probable CAA-RI criteria. A biopsy remains necessary for diagnosis in some cases of CAA-RI. The rate of relapse in the first 2 years after disease remission was lower in CAA-RI than in BP-PACNS.

Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis

BACKGROUND

Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking.

MATERIALS AND METHODS

PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively.

RESULTS

A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P =0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P =0.001).

CONCLUSION

This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.

Neuro-imaging in intracerebral hemorrhage: updates and knowledge gaps

Intracerebral hemorrhage (ICH) is characterized by hematoma development within the brain's parenchyma, contributing significantly to the burden of stroke. While non-contrast head computed tomography (CT) remains the gold standard for initial diagnosis, this review underscores the pivotal role of magnetic resonance imaging (MRI) in ICH management. Beyond diagnosis, MRI offers invaluable insights into ICH etiology, prognosis, and treatment. Utilizing echo-planar gradient-echo or susceptibility-weighted sequences, MRI demonstrates exceptional sensitivity and specificity in identifying ICH, aiding in differentiation of primary and secondary causes. Moreover, MRI facilitates assessment of hemorrhage age, recognition of secondary lesions, and evaluation of perihematomal edema progression, thus guiding tailored therapeutic strategies. This comprehensive review discusses the multifaceted utility of MRI in ICH management, highlighting its indispensable role in enhancing diagnostic accuracy as well as aiding in prognostication. As MRI continues to evolve as a cornerstone of ICH assessment, future research should explore its nuanced applications in personalized care paradigms.

Diagnostic test accuracy of machine learning algorithms for the detection intracranial hemorrhage: a systematic review and meta-analysis study

BACKGROUND

This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage (ICH) on computed tomography (CT) scans.

METHODS

Until May 2023, systematic searches were conducted in ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE for studies that evaluated the diagnostic precision of ML model-assisted ICH detection. Patients with and without ICH as the target condition who were receiving CT-Scan were eligible for the research, which used ML algorithms based on radiologists' reports as the gold reference standard. For meta-analysis, pooled sensitivities, specificities, and a summary receiver operating characteristics curve (SROC) were used.

RESULTS

At last, after screening the title, abstract, and full paper, twenty-six retrospective and three prospective, and two retrospective/prospective studies were included. The overall (Diagnostic Test Accuracy) DTA of retrospective studies with a pooled sensitivity was 0.917 (95% CI 0.88-0.943, I2 = 99%). The pooled specificity was 0.945 (95% CI 0.918-0.964, I2 = 100%). The pooled diagnostic odds ratio (DOR) was 219.47 (95% CI 104.78-459.66, I2 = 100%). These results were significant for the specificity of the different network architecture models (p-value = 0.0289). However, the results for sensitivity (p-value = 0.6417) and DOR (p-value = 0.2187) were not significant. The ResNet algorithm has higher pooled specificity than other algorithms with 0.935 (95% CI 0.854-0.973, I2 = 93%).

CONCLUSION

This meta-analysis on DTA of ML algorithms for detecting ICH by assessing non-contrast CT-Scans shows the ML has an acceptable performance in diagnosing ICH. Using ResNet in ICH detection remains promising prediction was improved via training in an Architecture Learning Network (ALN).

Absolute and relative iodine concentrations in the spot sign and haematoma for prediction of haematoma expansion in spontaneous intracerebral haemorrhage

AIM

To explore the predictive value of absolute and relative iodine concentrations in the spot sign (SS) and haematoma on gemstone spectral imaging (GSI) for haematoma expansion (HE).

MATERIALS AND METHODS

Patients with spontaneous intracerebral haemorrhage (ICH) who underwent computed tomography (CT) angiography using GSI were divided into an SS-positive group and an SS-negative group. In the SS-positive group, absolute and relative iodine concentrations in the SS (aICIS and rICIS, respectively) were measured. In the SS-negative group, absolute and relative iodine concentrations in haematoma (aICIH and rICIH, respectively) were measured. The area under the receiver operating characteristic curve (AUC-ROC) was used to investigate the HE predictive performance of aICIS, rICIS, and their combination in the SS-positive group, as well as the HE predictive performance of aICIH, rICIH, and their combination in the SS-negative group. The risk variables for HE in the two groups were investigated separately using logistic regression.

RESULTS

A total of 123 spontaneous ICH patients were enrolled. In the SS-positive group, the AUC of aICIS, rICIS, and their combination for predicting HE were 0.853, 0.893, and 0.922, respectively. rICIS was demonstrated to be a standalone predictor of HE via logistic regression. In the SS-negative group, aICIH, rICIH, and their combination had AUC-ROC values of 0.552, 0.783, and 0.851, respectively, to predict HE. According to multivariate analysis, rICIH was a reliable predictor of HE.

CONCLUSION

Absolute and relative iodine concentrations in the SS and haematoma can predict HE.

Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage

Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. Material and Methods: A total of 7421 computed tomography (CT) datasets between January 2007–July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. Results: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52–11.03) for the convolutional neural network (CNN), 9.96 h (8.68–11.32) for the radiomics model, 13.38 h (11.21–15.74) for rater 1 and 11.21 h (9.61–12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). Conclusions: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies.

Neuromonitoring in Children with Cerebrovascular Disorders

BACKGROUND

Cerebrovascular disorders are an important cause of morbidity and mortality in children. The acute care of a child with an ischemic or hemorrhagic stroke or cerebral sinus venous thrombosis focuses on stabilizing the patient, determining the cause of the insult, and preventing secondary injury. Here, we review the use of both invasive and noninvasive neuromonitoring modalities in the care of pediatric patients with arterial ischemic stroke, nontraumatic intracranial hemorrhage, and cerebral sinus venous thrombosis.

METHODS

Narrative review of the literature on neuromonitoring in children with cerebrovascular disorders.

RESULTS

Neuroimaging, near-infrared spectroscopy, transcranial Doppler ultrasonography, continuous and quantitative electroencephalography, invasive intracranial pressure monitoring, and multimodal neuromonitoring may augment the acute care of children with cerebrovascular disorders. Neuromonitoring can play an essential role in the early identification of evolving injury in the aftermath of arterial ischemic stroke, intracranial hemorrhage, or sinus venous thrombosis, including recurrent infarction or infarct expansion, new or recurrent hemorrhage, vasospasm and delayed cerebral ischemia, status epilepticus, and intracranial hypertension, among others, and this, is turn, can facilitate real-time adjustments to treatment plans.

CONCLUSIONS

Our understanding of pediatric cerebrovascular disorders has increased dramatically over the past several years, in part due to advances in the neuromonitoring modalities that allow us to better understand these conditions. We are now poised, as a field, to take advantage of advances in neuromonitoring capabilities to determine how best to manage and treat acute cerebrovascular disorders in children.

Role of SIRT3 in neurological diseases and rehabilitation training

Sirtuin3 (SIRT3) is a deacetylase that plays an important role in normal physiological activities by regulating a variety of substrates. Considerable evidence has shown that the content and activity of SIRT3 are altered in neurological diseases. Furthermore, SIRT3 affects the occurrence and development of neurological diseases. In most cases, SIRT3 can inhibit clinical manifestations of neurological diseases by promoting autophagy, energy production, and stabilization of mitochondrial dynamics, and by inhibiting neuroinflammation, apoptosis, and oxidative stress (OS). However, SIRT3 may sometimes have the opposite effect. SIRT3 can promote the transfer of microglia. Microglia in some cases promote ischemic brain injury, and in some cases inhibit ischemic brain injury. Moreover, SIRT3 can promote the accumulation of ceramide, which can worsen the damage caused by cerebral ischemia-reperfusion (I/R). This review comprehensively summarizes the different roles and related mechanisms of SIRT3 in neurological diseases. Moreover, to provide more ideas for the prognosis of neurological diseases, we summarize several SIRT3-mediated rehabilitation training methods.

Imaging features and ultraearly hematoma growth in intracerebral hemorrhage associated with COVID-19

Purpose

Intracerebral hemorrhage (ICH) is an uncommon but deadly event in patients with COVID-19 and its imaging features remain poorly characterized. We aimed to describe the clinical and imaging features of COVID-19-associated ICH.

Methods

Multicenter, retrospective, case–control analysis comparing ICH in COVID-19 patients (COV19 +) versus controls without COVID-19 (COV19 −). Clinical presentation, laboratory markers, and severity of COVID-19 disease were recorded. Non-contrast computed tomography (NCCT) markers (intrahematoma hypodensity, heterogeneous density, blend sign, irregular shape fluid level), ICH location, and hematoma volume (ABC/2 method) were analyzed. The outcome of interest was ultraearly hematoma growth (uHG) (defined as NCCT baseline ICH volume/onset-to-imaging time), whose predictors were explored with multivariable linear regression.

Results

A total of 33 COV19 + patients and 321 COV19 − controls with ICH were included. Demographic characteristics and vascular risk factors were similar in the two groups. Multifocal ICH and NCCT markers were significantly more common in the COV19 + population. uHG was significantly higher among COV19 + patients (median 6.2 mL/h vs 3.1 mL/h, p = 0.027), and this finding remained significant after adjustment for confounding factors (systolic blood pressure, antiplatelet and anticoagulant therapy), in linear regression (B(SE) = 0.31 (0.11), p = 0.005). This association remained consistent also after the exclusion of patients under anticoagulant treatment (B(SE) = 0.29 (0.13), p = 0.026).

Conclusions

ICH in COV19 + patients has distinct NCCT imaging features and a higher speed of bleeding. This association is not mediated by antithrombotic therapy and deserves further research to characterize the underlying biological mechanisms.