Acute hematoma expansion after spontaneous intracerebral hemorrhage: risk factors and impact on long-term prognosis

Hybrid clinical-radiomics model based on fully automatic segmentation for predicting the early expansion of spontaneous intracerebral hemorrhage: A multi-center study

BACKGROUND

Early prediction of hematoma expansion (HE) is important for the development of therapeutic strategies for spontaneous intracerebral hemorrhage (sICH). Radiomics can help to predict early hematoma expansion in intracerebral hemorrhage. However, complex image processing procedures, especially hematoma segmentation, are time-consuming and dependent on assessor experience. We provide a fully automated hematoma segmentation method, and construct a hybrid predictive model for risk stratification of hematoma expansion.

PURPOSE

To propose an automatic approach for predicting early hemorrhage expansion after spontaneous intracerebral hemorrhage using deep-learning and radiomics methods.

METHODS

A total of 258 patients with sICH were retrospectively enrolled for model construction and internal validation, while another two cohorts (n=87, 149) were employed for independent validation. For hemorrhage segmentation, an iterative segmentation procedure was performed to delineate the area using an nnU-Net framework. Radiomics models of intra-hemorrhage and multiscale peri-hemorrhage were established and evaluated, and the best discriminative-scale peri-hemorrhage radiomics model was selected for further analysis. Combining clinical factors and intra- and peri-hemorrhage radiomics signatures, a hybrid nomogram was constructed for the early HE prediction using multivariate logistic regression. For model validation, the receiver operating characteristic (ROC) curve analyses and DeLong test were used to evaluate the performances of the constructed models, and the calibration curve and decision curve analysis were performed for clinical application.

RESULTS

Our iterative auto-segmentation model showed satisfactory results for hematoma segmentation in all four cohorts. The Dice similarity coefficient of this hematoma segmentation model reached 0.90, showing an expert-level accuracy in hematoma segmentation. The consumed time of the efficient delineation was significantly decreased, from 18 min to less than 2 min, with the assistance of the auto-segmentation model. The radiomics model of 2-mm peri-hemorrhage had a preferable area under ROC curve (AUC) of 0.840 (95 % confidence interval [CI]: 0.768, 0.912) compared with the original (0-mm dilatation) model with an AUC of 0.796 (95 % CI: 0.717, 0.875). The clinical-radiomics hybrid model showed better performances for HE prediction, with AUC of 0.853, 0.852, 0.772, and 0.818 in the training, internal validation, and independent validation cohorts 1 and 2, respectively.

CONCLUSIONS

The fully automatic clinical-radiomics model based on deep learning and radiomics exhibits a good ability for hematoma segmentation and a favorable performance in stratifying HE risks.

Role and mechanisms of mast cells in brain disorders

Mast cells serve as crucial effector cells within the innate immune system and are predominantly localized in the skin, airways, gastrointestinal tract, urinary and reproductive tracts, as well as in the brain. Under physiological conditions, brain-resident mast cells secrete a diverse array of neuro-regulatory mediators to actively participate in neuroprotection. Meanwhile, as the primary source of molecules causing brain inflammation, mast cells also function as the "first responders" in brain injury. They interact with neuroglial cells and neurons to facilitate the release of numerous inflammatory mediators, proteases, and reactive oxygen species. This process initiates and amplifies immune-inflammatory responses in the brain, thereby contributing to the regulation of neuroinflammation and blood-brain barrier permeability. This article provides a comprehensive overview of the potential mechanisms through which mast cells in the brain may modulate neuroprotection and their pathological implications in various neurological disorders. It is our contention that the inhibition of mast cell activation in brain disorders could represent a novel avenue for therapeutic breakthroughs.

Swirl sign score system: a novel and practical tool for predicting hematoma expansion risk after spontaneous intracerebral haemorrhage

OBJECTIVE

To methodically analyse the swirl sign and construct a scoring system to predict the risk of hematoma expansion (HE) after spontaneous intracerebral haemorrhage (sICH).

METHODS

We analysed 231 of 683 sICH patients with swirl signs on baseline noncontrast CT (NCCT) images. The characteristics of the swirl sign were analysed, including the number, maximum diameter, shape, boundary, minimum CT value of the swirl sign, and the minimum distance from the swirl sign to the edge of the hematoma. In the development cohort, univariate and multivariate analyses were used to identify independent predictors of HE, and logistic regression analysis was used to construct the swirl sign score system. The swirl sign score system was verified in the validation cohort.

RESULTS

The number and the minimum CT value of the swirl sign were independent predictors of HE. The swirl sign score system was constructed (2 points for the number of swirl signs >1 and 1 point for the minimum CT value ≤41 Hounsfield units). The area under the curve of the swirl sign score system in predicting HE was 0.773 and 0.770 in the development and validation groups, respectively.

CONCLUSIONS

The swirl sign score system is an easy-to-use radiological grading scale that requires only baseline NCCT images to effectively identify subjects at high risk of HE.

ADVANCES IN KNOWLEDGE

Our newly developed semiquantitative swirl sign score system greatly improves the ability of swirl sign to predict HE.

Predicting hematoma expansion using machine learning: An exploratory analysis of the ATACH 2 trial

INTRODUCTION

Hematoma expansion (HE) in patients with intracerebral hemorrhage (ICH) is a key predictor of poor prognosis and potentially amenable to treatment. This study aimed to build a classification model to predict HE in patients with ICH using deep learning algorithms without using advanced radiological features.

METHODS

Data from the ATACH-2 trial (Antihypertensive Treatment of Acute Cerebral Hemorrhage) was utilized. Variables included in the models were chosen as per literature consensus on salient variables associated with HE. HE was defined as increase in either >33% or 6 mL in hematoma volume in the first 24 h. Multiple machine learning algorithms were employed using iterative feature selection and outcome balancing methods. 70% of patients were used for training and 30% for internal validation. We compared the ML models to a logistic regression model and calculated AUC, accuracy, sensitivity and specificity for the internal validation models respective models.

RESULTS

Among 1000 patients included in the ATACH-2 trial, 924 had the complete parameters which were included in the analytical cohort. The median [interquartile range (IQR)] initial hematoma volume was 9.93.mm3 [5.03-18.17] and 25.2% had HE. The best performing model across all feature selection groups and sampling cohorts was using an artificial neural network (ANN) for HE in the testing cohort with AUC 0.702 [95% CI, 0.631-0.774] with 8 hidden layer nodes The traditional logistic regression yielded AUC 0.658 [95% CI, 0.641-0.675]. All other models performed with less accuracy and lower AUC. Initial hematoma volume, time to initial CT head, and initial SBP emerged as most relevant variables across all best performing models.

CONCLUSION

We developed multiple ML algorithms to predict HE with the ANN classifying the best without advanced radiographic features, although the AUC was only modestly better than other models. A larger, more heterogenous dataset is needed to further build and better generalize the models.

Risk factors for unfavorable outcome after spontaneous intracerebral hemorrhage in elderly patients

BACKGROUND

Spontaneous intracerebral hemorrhage (SICH) of the elderly is a devastating form of stroke with a high morbidity and economic burden. There is still a limited understanding of the risk factors for an unfavorable outcome where a surgical therapy may be less meaningful. Thus, the aim of this study is to identify factors associated with unfavorable outcome and time to death in surgically treated elderly patients with SICH.

METHODS

We performed a single-center retrospective study of 70 patients (age > 60 years) with SICH operated between 2008 and 2020. Functional outcome was assessed by modified Rankin Scale. Various clinical and neuroradiological variables including type of neurosurgical treatment, anatomical location of hemorrhage, volumetry and distribution of hemorrhage were assessed. Univariate and multivariate logistic regression models were performed. Length of stay (LOS) and hospital costs are presented.

RESULTS

The overall mortality (mean follow-up time of 22 months) in this study was 32/70 patients (45.71%), 30-days mortality was 8/70 (11.42%), and 12-months mortality was 22/70 (31.43%). Average LOS was 73.5 days with a median of 58, 766 € estimated in hospital costs per patient. Multivariate analysis for 12-months mortality was significant for intraventricular hemorrhage (IVH) (p = 0.007, HR = 1.021, 95% CI = 1.006 - 1.037). ROC analysis for 12-months mortality for IVH volume >= 7 cm3 presented an are under the curve of 0.658.

CONCLUSIONS

We identified IVH volume > 7 cm3 as an independent prognostic risk factor for mortality in elderly patients after SICH. This may help clinicians in decision-making for this critical and growing subgroup of patients.

Medical versus neurosurgical treatment in ICH patients: a single center experience

BACKGROUND AND AIMS

The effect of surgical treatment for spontaneous intracerebral hemorrhage (ICH) remains uncertain. We conducted an observational retrospective cohort study on supra-centimeter spontaneous ICH treated with either neurosurgical or conservative management. The baseline demographics and risk factors were correlated with in-hospital mortality and 3 and 6-month survival rates stratified by management.

METHODS

We included all patients with evidence of spontaneous ICH > 1 cm detected by CT and admitted between august 2020 and march 2021 to the "SMM" Hospital in Perugia.

RESULTS

Onehundredandtwentytwo patients were included in the study, and 45% (n.55) were surgically treated. The mean age was 71.9 ± 15.3, and 61% (n.75) were males. Intra-hospital mortality ended up being 31% (n.38), 3 months-survival was 63% (n.77) and 6 months-survival was 60% (n.73). From the multivariate analysis of the surgical patients versus medical patient, we observed that the surgical patients were younger (67.5 ± 14.9 vs 75.5 ± 14.7 y; OR 0.87; Cl 95% 0.85-0.94; p 0.001), with greater ICH volume at the onset (61 ± 39.4 cc vs 51 ± 64 cc; OR 1.03; Cl 95% 1.005-1.07; p 0.05), more midline shift (7.61 ± 5.54 mm vs 4.09 ± 5.88 mm; OR 1.37; Cl 95% 1.045-1.79; p 0.023), and a higher ICH score (3 vs 2 mean ICH score; OR 21.12; Cl 95% 2.6-170.6; p 0.004). Intra-hospital mortality in the surgical group and in the conservative treatment group was respectively 33% vs 30%, 3 month-survival was 64% vs 63% and 6 month- survival were 60% in both groups.

CONCLUSIONS

Our patient cohort shows no overall benefit from surgery over conservative treatment, but surgical patients were younger and had larger ICH volume.

Revisiting the role of the complement system in intracerebral hemorrhage and therapeutic prospects

Intracerebral hemorrhage (ICH) is a stroke subtype characterized by non-traumatic rupture of blood vessels in the brain, resulting in blood pooling in the brain parenchyma. Despite its lower incidence than ischemic stroke, ICH remains a significant contributor to stroke-related mortality, and most survivors experience poor outcomes that significantly impact their quality of life. ICH has been accompanied by various complex pathological damage, including mechanical damage of brain tissue, hematoma mass effect, and then leads to inflammatory response, thrombin activation, erythrocyte lysis, excitatory amino acid toxicity, complement activation, and other pathological changes. Accumulating evidence has demonstrated that activation of complement cascade occurs in the early stage of brain injury, and the excessive complement activation after ICH will affect the occurrence of secondary brain injury (SBI) through multiple complex pathological processes, aggravating brain edema, and pathological brain injury. Therefore, the review summarized the pathological mechanisms of brain injury after ICH, specifically the complement role in ICH, and its related pathological mechanisms, to comprehensively understand the specific mechanism of different complements at different stages after ICH. Furthermore, we systematically reviewed the current state of complement-targeted therapies for ICH, providing a reference and basis for future clinical transformation of complement-targeted therapy for ICH.

Predictive value of hyperglycemia on prognosis in spontaneous intracerebral hemorrhage patients

Background

Spontaneous intracerebral hemorrhage (ICH) is the second most common cause of stroke and accounts for approximately 15-20% of all new stroke cases. Hematoma expansion is a potentially important therapeutic target that is amenable to treatment and independently predict outcome. Hyperglycemia is frequent in ICH patients, and affects cerebrovascular function, increasing the risk of cerebral vascular rupture. We recruited 170 ICH patients to explore the high risk factors of mortality and the association between hyperglycemia and early hematoma expansion.

Methods

A retrospective analysis of 170 patients with ICH who were grouped by survival and blood glucose level, death group (35 cases) and survival group (135 cases); 77 cases in the hyperglycemic group and 93 cases in the normoglycemic group. Recorded parameters, such as age, gender, past medical history, blood glucose, serum calcium, hematoma volume, and hematoma expansion. Group comparison used t-test, rank sum test and Fisher exact test. After these, logistic regression analysis and receiver operating characteristic (ROC) curves were performed.

Results

Among 170 ICH subjects(130 males and 40 females)，35 died and 77 exhibited hyperglycaemia. Compared with the survival group, the death group presented with higher Original Intracerebral Hemorrhage Scale (OICH) score, greater blood glucose, larger hemorrhage volume and lower Glasgow Coma Scale (GCS) score. The occurrence of hematoma expansion and massive hemorrhage volume in the hyperglycemic group were higher than in the normoglycemic group(P < 0.05). After adjustment for confounders variables, multivariate logistic analysis showed that blood glucose was an independent predictor of hematoma expansion (adjusted odd ratio:8.04, 95%CI:3.89-16.63, P < 0.01). Fasting blood glucose had better predictive value for hematoma expansion (AUC:0.95, 95%CI:0.92-0.99, P < 0.01).

Conclusion

Hyperglycemia is associated with higher mortality risk and could be a potential marker in the prediction of hematoma expansion.

Computed tomography in acute intracerebral hemorrhage: neuroimaging predictors of hematoma expansion and outcome

Intracerebral hemorrhage (ICH) accounts for 10–20% of all strokes worldwide and is associated with serious outcomes, including a 30-day mortality rate of up to 40%. Neuroimaging is pivotal in diagnosing ICH as early detection and determination of underlying cause, and risk for expansion/rebleeding is essential in providing the correct treatment. Non-contrast computed tomography (NCCT) is the most used modality for detection of ICH, identification of prognostic markers and measurements of hematoma volume, all of which are of major importance to predict outcome. The strongest predictors of 30-day mortality and functional outcome for ICH patients are baseline hematoma volume and hematoma expansion. Even so, exact hematoma measurement is rare in clinical routine practice, primarily due to a lack of tools available for fast, effective, and reliable volumetric tools. In this educational review, we discuss neuroimaging findings for ICH from NCCT images, and their prognostic value, as well as the use of semi-automatic and fully automated hematoma volumetric methods and assessment of hematoma expansion in prognostic studies.

Association between non-HDLC and 1-year prognosis in patients with spontaneous intracerebral haemorrhage: a prospective cohort study from 13 hospitals in Beijing

OBJECTIVES

Previous studies suggested an inverse association between lipoprotein cholesterols and bleeding risk, while limited data were available about the predictive value of lipoproteins on intracerebral haemorrhage (ICH). Our recent research series showed that higher non-high-density lipoprotein cholesterol (non-HDLC) was an independent predictor of favourable 3-month outcome in ICH patients, we thus aimed to further investigate the association between non-HDLC levels and 1-year functional outcomes after ICH.

DESIGN

Prospective multicentre cohort study.

SETTING

13 hospitals in Beijing, China.

PARTICIPANTS

A total of 666 ICH patients were included between December 2014 and September 2016.

METHODS

Non-HDLC was calculated by subtracting HDL-C from total cholesterol. Patients were then grouped by non-HDLC levels into three categories: <3.4 mmol/L, 3.4-4.2 mmol/L and ≥4.2 mmol/L. Both the univariate and multivariate logistic regressions were used to assess the association between non-HDLC levels and 1-year unfavourable functional outcomes (modified Rankin Scale ≥3) in ICH patients. Moreover, sensitivity analysis was performed in ICH patients without statin use after admission.

RESULTS

There were 33.5% (223/666) ICH patients identified with unfavourable functional outcomes at 1-year follow-up. In the univariate analysis, patients who achieved non-HDLC levels above 4.2 mmol/L had a 49% decreased risk of 1-year poor prognosis (OR 0.51, 95% CI 0.33 to 0.81). However, non-HDLC did not retain its independent prognostic value in multivariate analysis, the fully adjusted OR values were 1.00 (reference), 1.06 (0.63, 1.79) and 0.83 (0.45, 1.54) from the lowest to the highest non-HDLC group. Moreover, statin use after ICH onset made no difference to the long-term prognosis.

CONCLUSIONS

Non-HDLC was not an independent predictor for 1-year functional outcome in ICH patients, irrespective of poststroke statin use. The predictive value of well-recognised confounding factors was more dominant than non-HDLC on long-term prognosis.

Efficiency of a deep learning-based artificial intelligence diagnostic system in spontaneous intracerebral hemorrhage volume measurement

Background

Accurate measurement of hemorrhage volume is critical for both the prediction of prognosis and the selection of appropriate clinical treatment after spontaneous intracerebral hemorrhage (ICH). This study aimed to evaluate the performance and accuracy of a deep learning-based automated segmentation algorithm in segmenting spontaneous intracerebral hemorrhage (ICH) volume either with or without intraventricular hemorrhage (IVH) extension. We compared this automated pipeline with two manual segmentation techniques.

Methods

We retrospectively reviewed 105 patients with acute spontaneous ICH. Depending on the presence of IVH extension, patients were divided into two groups: ICH without (n = 56) and with IVH (n = 49). ICH volume of the two groups were segmented and measured using a deep learning-based artificial intelligence (AI) diagnostic system and computed tomography-based planimetry (CTP), and the ABC/2 score were used to measure hemorrhage volume in the ICH without IVH group. Correlations and agreement analyses were used to analyze the differences in volume and length of processing time among the three segmentation approaches.

Results

In the ICH without IVH group, the ICH volumes measured using AI and the ABC/2 score were comparable to CTP segmentation. Strong correlations were observed among the three segmentation methods (r = 0.994, 0.976, 0.974; P < 0.001; concordance correlation coefficient [CCC] = 0.993, 0.968, 0.967). But the absolute error of the ICH volume measured by the ABC/2 score was greater than that of the algorithm (P < 0.05). In the ICH with IVH group, there is no significant differences were found between algorithm and CTP(P = 0.614). The correlation and agreement between CTP and AI were strong (r = 0.996, P < 0.001; CCC = 0.996). The AI segmentation took a significantly shorter amount of time than CTP (P < 0.001), but was slightly longer than ABC/2 score technique (P = 0.002).

Conclusions

The deep learning-based AI diagnostic system accurately quantified volumes of acute spontaneous ICH with high fidelity and greater efficiency compared to the CTP measurement and more accurately than the ABC/2 scores. We believe this is a promising tool to help physicians achieve precise ICH quantification in practice.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-021-00657-6.

Challenging anticoagulation cases: A case of pulmonary embolism shortly after spontaneous brain bleeding

Venous thromboembolism (VTE) is a common complication after intracranial hemorrhage (ICH); the incidence has been reported to vary between 18% to 50% for deep vein thrombosis and between 0.5% to 5% for pulmonary embolism (PE). According to current clinical practice guidelines, patients with acute VTE should receive anticoagulant treatment for at least 3 months in the absence of contraindications. Anticoagulant treatment reduces mortality, prevents early recurrences and improves long-term outcome in patients with acute VTE. However, recent ICH is an absolute contraindication for anticoagulant treatment due to the potential increased risk of hematoma expansion or recurrent ICH. Hematoma expansion occurs in approximately a third of patients within 24 h following the diagnosis of a spontaneous ICH. The risk for recurrent ICH depends on patients' features as well as on the feature of index ICH. Limited evidence is available on the risks of therapeutic anticoagulation started shortly after ICH. Expert consensus around the introduction of therapeutic anticoagulation suggests delaying therapeutic anticoagulation for at least 2 weeks after spontaneous ICH, until the risk re-bleeding becomes acceptable. Vena cava filters should be inserted to reduce the risk for (non) fatal PE until therapeutic anticoagulation can be started; antithrombotic prophylaxis should be started as soon as possible to avoid recurrent VTE after vena cava filter insertion. For patients presenting PE with hemodynamic compromise, percutaneous embolectomy should be considered. Most patients will be able to receive anticoagulant treatment within 4 weeks following spontaneous ICH; direct oral anticoagulants are probably the treatment of choice for those ICH patients tolerating anticoagulant treatment.