Blood pressure reduction and noncontrast CT markers of intracerebral hemorrhage expansion

Prediction of hematoma expansion in spontaneous intracerebral hemorrhage using a multimodal neural network

Hematoma expansion occasionally occurs in patients with intracerebral hemorrhage (ICH), associating with poor outcome. Multimodal neural networks incorporating convolutional neural network (CNN) analysis of images and neural network analysis of tabular data are known to show promising results in prediction and classification tasks. We aimed to develop a reliable multimodal neural network model that comprehensively analyzes CT images and clinical variables to predict hematoma expansion. We retrospectively enrolled ICH patients at four hospitals between 2017 and 2021, assigning patients from three hospitals to the training and validation dataset and patients from one hospital to the test dataset. Admission CT images and clinical variables were collected. CT findings were evaluated by experts. Three types of models were developed and trained: (1) a CNN model analyzing CT images, (2) a multimodal CNN model analyzing CT images and clinical variables, and (3) a non-CNN model analyzing CT findings and clinical variables with machine learning. The models were evaluated on the test dataset, focusing first on sensitivity and second on area under the receiver operating curve (AUC). Two hundred seventy-three patients (median age, 71 years [59-79]; 159 men) in the training and validation dataset and 106 patients (median age, 70 years [62-82]; 63 men) in the test dataset were included. Sensitivity and AUC of a CNN model were 1.000 (95% confidence interval [CI] 0.768-1.000) and 0.755 (95% CI 0.704-0.807); those of a multimodal CNN model were 1.000 (95% CI 0.768-1.000) and 0.799 (95% CI 0.749-0.849); and those of a non-CNN model were 0.857 (95% CI 0.572-0.982) and 0.733 (95% CI 0.625-0.840). We developed a multimodal neural network model incorporating CNN analysis of CT images and neural network analysis of clinical variables to predict hematoma expansion in ICH. The model was externally validated and showed the best performance of all the models.

Quantitative imaging for predicting hematoma expansion in intracerebral hemorrhage: A multimodel comparison

BACKGROUND

Several studies report that radiomics provides additional information for predicting hematoma expansion in intracerebral hemorrhage (ICH). However, the comparison of diagnostic performance of radiomics for predicting revised hematoma expansion (RHE) remains unclear.

METHODS

The cohort comprised 312 consecutive patients with ICH. A total of 1106 radiomics features from seven categories were extracted using Python software. Support vector machines achieved the best performance in both the training and validation datasets. Clinical factors models were constructed to predict RHE. Receiver operating characteristic curve analysis was used to assess the abilities of non-contrast computed tomography (NCCT) signs, radiomics features, and combined models to predict RHE.

RESULTS

We finally selected the top 21 features for predicting RHE. After univariate analysis, 4 clinical factors and 5 NCCT signs were selected for inclusion in the prediction models. In the training and validation dataset, radiomics features had a higher predictive value for RHE (AUC = 0.83) than a single NCCT sign and expansion-prone hematoma. The combined prediction model including radiomics features, clinical factors, and NCCT signs achieved higher predictive performances for RHE (AUC = 0.88) than other combined models.

CONCLUSIONS

NCCT radiomics features have a good degree of discrimination for predicting RHE in ICH patients. Combined prediction models that include quantitative imaging significantly improve the prediction of RHE, which may assist in the risk stratification of ICH patients for anti-expansion treatments.

Association of pulse pressure with hematoma expansion in patients with spontaneous supratentorial intracerebral hemorrhage

Objective

Recent reports have demonstrated that a wider pulse pressure upon admission is correlated with heightened in-hospital mortality following spontaneous supratentorial intracerebral hemorrhage (ssICH). However, the underlying mechanism remains ambiguous. We investigated whether a wider pulse pressure was associated with hematoma expansion (HE).

Methods

Demographic information, clinical features, and functional outcomes of patients diagnosed with ssICH were retrospectively collected and analyzed. Multivariate logistic regression was conducted to identify independent predictors of HE. Weighted logistic regression, restricted cubic spline models, and propensity score matching (PSM) were employed to estimate the association between pulse pressure and HE.

Results

We included 234 eligible adult ssICH patients aged 60 (51-71) years, and 55.56% were male. The mean pulse pressure was 80.94 ± 23.32 mmHg. Twenty-seven patients (11.54%) developed early HE events, and 116 (49.57%) experienced a poor outcome (modified Rankin scale 3-6). A wider mean pulse pressure as a continuous variable was a predictor of HE [odds ratios (OR) 1.026, 95% confidence interval (CI) 1.007-1.046, p = 0.008] in multivariate analysis. We transformed pulse pressure into a dichotomous variable based on its cutoff value. After adjusting for confounding of HE variables, the occurrence of HE in patients with ssICH with wider pulse pressure levels (≥98 mmHg) had 3.78 times (OR 95% CI 1.47-9.68, p = 0.006) compared to those with narrower pulse pressure levels (<98 mmHg). A linear association was observed between pulse pressure and increased HE risk (P for overall = 0.036, P for nonlinear = 0.759). After 1:1 PSM (pulse pressure ≥98 mmHg vs. pulse pressure <98 mmHg), the rates of HE events and poor outcome still had statistically significant in wider-pulse pressure group [HE, 12/51 (23.53%) vs. 4/51 [7.84%], p = 0.029; poor outcome, 34/51 (66.67%) vs. 19/51 (37.25%), p = 0.003].

Conclusion

Widened acute pulse pressure (≥98 mmHg) levels at admission are associated with increased risks of early HE and unfavorable outcomes in patients with ssICH.

Machine-learning-based performance comparison of two-dimensional (2D) and three-dimensional (3D) CT radiomics features for intracerebral haemorrhage expansion

AIM

To investigate the value of non-contrast CT (NCCT)-based two-dimensional (2D) radiomics features in predicting haematoma expansion (HE) after spontaneous intracerebral haemorrhage (ICH) and compare its predictive ability with the three-dimensional (3D) signature.

MATERIALS AND METHODS

Three hundred and seven ICH patients who received baseline NCCT within 6 h of ictus from two stroke centres were analysed retrospectively. 2D and 3D radiomics features were extracted in the manner of one-to-one correspondence. The 2D and 3D models were generated by four different machine-learning algorithms (regularised L1 logistic regression, decision tree, support vector machine and AdaBoost), and the receiver operating characteristic (ROC) curve was used to compare their predictive performance. A robustness analysis was performed according to baseline haematoma volume.

RESULTS

Each feature type of 2D and 3D modalities used for subsequent analyses had excellent consistency (mean ICC >0.9). Among the different machine-learning algorithms, pairwise comparison showed no significant difference in both the training (mean area under the ROC curve [AUC] 0.858 versus 0.802, all p>0.05) and validation datasets (mean AUC 0.725 versus 0.678, all p>0.05), and the 10-fold cross-validation evaluation yielded similar results. The AUCs of the 2D and 3D models were comparable either in the binary or tertile volume analysis (all p>0.5).

CONCLUSION

NCCT-derived 2D radiomics features exhibited acceptable and similar performance to the 3D features in predicting HE, and this comparability seemed unaffected by initial haematoma volume. The 2D signature may be preferred in future HE-related radiomic works given its compatibility with emergency condition of ICH.

Burden, risk factors, neurosurgical evacuation outcomes, and predictors of mortality among traumatic brain injury patients with expansive intracranial hematomas in Uganda: a mixed methods study design

BACKGROUND

Expansive intracranial hematomas (EIH) following traumatic brain injury (TBI) continue to be a public health problem in Uganda. Data is limited regarding the neurosurgical outcomes of TBI patients. This study investigated the neurosurgical outcomes and associated risk factors of EIH among TBI patients at Mulago National Referral Hospital (MNRH).

METHODS

A total of 324 subjects were enrolled using a prospective cohort study. Socio-demographic, risk factors and complications were collected using a study questionnaire. Study participants were followed up for 180 days. Univariate, multivariable, Cox regression analyses, Kaplan Meir survival curves, and log rank tests were sequentially conducted. P-values of < 0.05 at 95% Confidence interval (CI) were considered to be statistically significant.

RESULTS

Of the 324 patients with intracranial hematomas, 80.6% were male. The mean age of the study participants was 37.5 ± 17.4 years. Prevalence of EIH was 59.3% (0.59 (95% CI: 0.54 to 0.65)). Participants who were aged 39 years and above; PR = 1.54 (95% CI: 1.20 to 1.97; P = 0.001), and those who smoke PR = 1.21 (95% CI: 1.00 to 1.47; P = 0.048), and presence of swirl sign PR = 2.26 (95% CI: 1.29 to 3.95; P = 0.004) were found to be at higher risk for EIH. Kaplan Meier survival curve indicated that mortality at the 16-month follow-up was 53.4% (95% CI: 28.1 to 85.0). Multivariate Cox regression indicated that the predictors of mortality were old age, MAP above 95 mmHg, low GCS, complications such as infection, spasticity, wound dehiscence, CSF leaks, having GOS < 3, QoLIBRI < 50, SDH, contusion, and EIH.

CONCLUSION

EIH is common in Uganda following RTA with an occurrence of 59.3% and a 16-month higher mortality rate. An increased age above 39 years, smoking, having severe systemic disease, and the presence of swirl sign are independent risk factors. Old age, MAP above 95 mmHg, low GCS, complications such as infection, spasticity, wound dehiscence, CSF leaks, having a GOS < 3, QoLIBRI < 50, ASDH, and contusion are predictors of mortality. These findings imply that all patients with intracranial hematomas (IH) need to be monitored closely and a repeat CT scan to be done within a specific period following their initial CT scan. We recommend the development of a protocol for specific surgical and medical interventions that can be implemented for patients at moderate and severe risk for EIH.

The relationship between hematoma morphology and intraventricular hemorrhage in supratentorial deep intracerebral hemorrhage

Background

Intraventricular hemorrhage (IVH) after intracerebral hemorrhage (ICH) is a strong independent predictor of poor outcomes. Although the location and volume of ICH are associated with IVH, our knowledge concerning the mechanism of IVH after ICH is still limited. This study aimed to investigate the relationship between hematoma morphology and IVH in patients with supratentorial deep ICH.

Methods

We retrospectively analyzed adult patients (aged ≥18 years) with spontaneous supratentorial deep ICH who underwent computed tomography (CT) within 48 h after ICH symptom onset in Peking University First Hospital between January 2017 and August 2022. We collected the clinical and imaging data of the patients and assessed hematoma morphology using several quantitative radiological parameters including hematoma volume, sphericity index, A/B ratio (A: the largest area of hematoma; B: the largest diameter 90° to A on the same slice), and our newly proposed largest diameter-midline angle (LMA). Multivariable logistic regression analysis was used to analyze the relationship between these parameters and the presence of IVH on the initial CT scan.

Results

Among 114 patients with spontaneous supratentorial deep ICH, 41 (36.0%) had IVH. In patients with IVH, the sphericity index was lower than that in individuals without IVH, while the LMA was larger. Multivariate logistic regression analysis showed that sphericity index [0.1-unit odds ratio (OR) =0.252; 95% CI: 0.089-0.709; P=0.009] and the LMA (10-unit OR =1.281; 95% CI: 1.007-1.630; P=0.04) were independently associated with the presence of IVH in patients with supratentorial deep ICH. Univariate analyses showed that hematoma volume, A/B ratio, sphericity index, and the LMA were significantly associated with poor outcomes at discharge.

Conclusions

Two quantitative parameters of hematoma morphology, sphericity index and the LMA, were significantly associated with the presence of IVH in patients with supratentorial deep ICH. Further prospective studies with larger sample sizes are needed to validate our results.

Intensive Blood Pressure Reduction is Associated with Reduced Hematoma Growth in Fast Bleeding Intracerebral Hemorrhage

OBJECTIVE

Patients with spontaneous intracerebral hemorrhage (ICH) at the highest risk of hematoma growth are those with the most potential to benefit from anti-expansion treatment. Large clinical trials have not definitively shown a clear benefit of blood pressure (BP) reduction. We aim to determine whether intensive blood pressure reduction could benefit patients with fast bleeding ICH.

METHODS

An exploratory analysis of data from the Antihypertensive Treatment of Acute Cerebral Hemorrhage 2 (ATACH-2) randomized controlled trial was performed. In order to capture not just early bleeding (even if a small amount), but the rate of bleeding (ml/hour), we restricted the study to "Fast bleeding ICH," defined as an ICH volume/onset to computed tomography (CT) time >5 ml/hr. Hematoma growth, as defined as an increase of hematoma volume > 33% between baseline and 24 hours.

RESULTS

A total of 940 patients were included (mean age = 62.1 years, 61.5% men), of whom 214 (22.8%) experienced hematoma expansion. Of these, 567 (60.3%) met the definition of "fast bleeding" with baseline ICH volume/time to presentation of at least 5 ml/hr. Intensive BP reduction was associated with a significantly lower rate of hematoma growth in fast bleeding patients (20.6% vs 31.0%, p = 0.005). In a subgroup of 266 (46.9%) fast-bleeding patients who received treatment within 2 hours after symptom onset, intensive BP lowering was associated with improved functional independence (odds ratio [OR] = 1.98, 95% confidence interval [CI] = 1.06-3.69, p = 0.031).

INTERPRETATION

Our results suggest that early use of intensive BP reduction may reduce hematoma growth and improve outcome in fast bleeding patients. ANN NEUROL 2023.

Using Radiomics and Convolutional Neural Networks for the Prediction of Hematoma Expansion After Intracerebral Hemorrhage

Background

Hematoma enlargement (HE) is a common complication following acute intracerebral hemorrhage (ICH) and is associated with early deterioration and unfavorable clinical outcomes. This study aimed to evaluate the predictive performance of a computed tomography (CT) based model that utilizes deep learning features in identifying HE.

Methods

A total of 408 patients were retrospectively enrolled between January 2015 and December 2020 from our institution. We designed an automatic model that could mask the hematoma area and fusion features of radiomics, clinical data, and convolutional neural network (CNN) in a hybrid model. We assessed the model's performance by using confusion matrix metrics (CM), the area under the receiver operating characteristics curve (AUC), and other statistical indicators.

Results

After automated masking, 408 patients were randomly divided into two cohorts with 204 patients in the training set and 204 patients in the validation set. The first cohort trained the CNN model, from which we then extracted radiomics, clinical data, and CNN features for the second validation cohort. After feature selection by K-highest score, a support vector machines (SVM) model classification was used to predict HE. Our hybrid model exhibited a high AUC of 0.949, and 0.95 of precision, 0.83 of recall, and 0.94 of average precision (AP). The CM found that only 5 cases were misidentified by the model.

Conclusion

The automatic hybrid model we developed is an end-to-end method and can assist in clinical decision-making, thereby facilitating personalized treatment for patients with ICH.

NCCT Markers of Intracerebral Hemorrhage Expansion Using Revised Criteria: An External Validation of Their Predictive Accuracy

BACKGROUND AND PURPOSE

Several NCCT expansion markers have been proposed to improve the prediction of hematoma expansion. We retrospectively evaluated the predictive accuracy of 9 expansion markers.

MATERIALS AND METHODS

Patients admitted for intracerebral hemorrhage within 24 hours of last seen well were retrospectively included from April 2016 to April 2020. The primary outcome was revised hematoma expansion, defined as any of a ≥6-mL or ≥33% increase in intracerebral hemorrhage volume, a ≥ 1-mL increase in intraventricular hemorrhage volume, or de novo intraventricular hemorrhage. We assessed the predictive accuracy of expansion markers and determined their association with revised hematoma expansion.

RESULTS

We included 124 patients, of whom 51 (41%) developed revised hematoma expansion. The sensitivity of each marker for the prediction of revised hematoma expansion ranged from 4% to 78%; the specificity, 37%-97%; the positive likelihood ratio, 0.41-7.16; and the negative likelihood ratio, 0.49-1.06. By means of univariable logistic regressions, 5 markers were significantly associated with revised hematoma expansion: black hole (OR = 8.66; 95% CI, 2.15-58.14; P = .007), hypodensity (OR = 3.18; 95% CI, 1.49-6.93; P = .003), blend (OR = 2.90; 95% CI, 1.08-8.38; P = .04), satellite (OR = 2.84; 95% CI, 1.29-6.61; P = .01), and Barras shape (OR = 2.41, 95% CI; 1.17-5.10; P = .02). In multivariable models, only the black hole marker remained independently associated with revised hematoma expansion (adjusted OR = 5.62; 95% CI, 1.23-40.23; P = .03).

CONCLUSIONS

No single NCCT expansion marker had both high sensitivity and specificity for the prediction of revised hematoma expansion. Improved image-based analysis is needed to tackle limitations associated with current NCCT-based expansion markers.

Comparison of different noncontrast computed tomographic markers for predicting early perihematomal edema expansion in patients with intracerebral hemorrhage

OBJECTIVES

Noncontrast computed tomography (NCCT) imaging markers are associated with early perihematomal edema (PHE) growth. The aim of this study was to compare the predictive value of different NCCT markers in predicting early PHE expansion.

METHODS

ICH patients who underwent baseline CT scan within 6 h of symptoms onset and follow-up CT scan within 36 h between July 2011 and March 2017 were included in this study. The predictive value of hypodensity, satellite sign, heterogeneous density, irregular shape, blend sign, black hole sign, island sign and expansion-prone hematoma for early perihematomal edema expansion were assessed, separately.

RESULTS

214 patients were included in our final analysis. After adjusting for ICH characteristics, hypodensity, blend sign, island sign and expansion-prone hematoma are still predictors of early perihematomal edema expansion in multivariable logistics regression analysis (all P < 0.05). The area under the receiver operating characteristic (ROC) curve of expansion-prone hematoma was significantly larger than the area under the ROC curve of hypodensity, blend sign and island sign in predicting PHE expansion (P = 0.003, P < 0.001 and P = 0.002, respectively).

CONCLUSION

Compared with single NCCT imaging markers, expansion-prone hematoma seems to be optimal predictor for early PHE expansion than any single NCCT imaging marker.

Difference of mean Hounsfield units (dHU) between follow-up and initial noncontrast CT scan predicts 90-day poor outcome in spontaneous supratentorial acute intracerebral hemorrhage with deep convolutional neural networks

OBJECTIVES

This study aimed to investigate the usefulness of a new non-contrast CT scan (NCCT) sign called the dHU, which represented the difference in mean Hounsfield unit values between follow-up and the initial NCCT for predicting 90-day poor functional outcomes in acute supratentorial spontaneous intracerebral hemorrhage(sICH) using deep convolutional neural networks.

METHODS

A total of 377 consecutive patients with sICH from center 1 and 91 patients from center 2 (external validation set) were included. A receiver operating characteristic (ROC) analysis was performed to determine the critical value of dHU for predicting poor outcome at 90 days. Modified Rankin score (mRS) >3 or >2 was defined as the primary and secondary poor outcome, respectively. Two multivariate models were developed to test whether dHU was an independent predictor of the two unfavorable functional outcomes.

RESULTS

The ROC analysis showed that a dHU >2.5 was a critical value to predict the poor outcomes (mRS >3) in sICH. The sensitivity, specificity, and accuracy of dHU >2.5 for poor outcome prediction were 37.5%, 86.0%, and 70.6%, respectively. In multivariate models developed after adjusting for all elements of the ICH score and hematoma expansion, dHU >2.5 was an independent predictor of both primary and secondary poor outcomes (OR = 2.61, 95% CI [1.32,5.13], P = 0.006; OR = 2.63, 95% CI [1.36,5.10], P = 0.004, respectively). After adjustment for all possible significant predictors (p < 0.05) by univariate analysis, dHU >2.5 had a positive association with primary and secondary poor outcomes (OR = 3.25, 95% CI [1.52,6.98], P = 0.002; OR = 3.42, 95% CI [1.64,7.15], P = 0.001).

CONCLUSIONS

The dHU of hematoma based on serial CT scans is independently associated with poor outcomes after acute sICH, which may help predict clinical evolution and guide therapy for sICH patients.

A Clinical-Radiomics Based Nomogram to Predict Progressive Intraparenchymal Hemorrhage in Mild to Moderate Traumatic Injury Patients

PURPOSE

To develop a non-contrast computed tomography(NCCT)based radiomics model for predicting intraparenchymal hemorrhage progression in patients with mild to moderate traumatic brain injury(TBI).

METHODS

We retrospectively analyzed 166 mild to moderate TBI patients with intraparenchymal hemorrhage from January 2018 to December 2021. The enrolled patients were divided into training cohort and test cohort with a ratio of 6:4. Uni- and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), the calibration curve, the decision curve analysis, sensitivity, and specificity.

RESULTS

Eleven radiomics features, presence with SDH, and D-dimer > 5 mg/l were selected to construct the combined clinical-radiomic model for the prediction of TICH in mild to moderate TBI patients. The AUC of the combined model was 0.81(95% confidence interval (CI), 0.72 to 0.90) in the training cohort and 0.88 (95% CI 0.79 to 0.96) in the test cohort, which were superior to the clinical model alone (AUC_training = 0.72, AUC_test = 0.74). The calibration curve demonstrated that the radiomics nomogram had a good agreement between prediction and observation. Decision curve analysis confirmed clinically useful.

CONCLUSIONS

The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors can serve as a reliable and powerful tool for Predicting intraparenchymal hemorrhage progression for patients with mild to moderate TBI.

Intracerebral haemorrhage expansion: definitions, predictors, and prevention

Haematoma expansion affects a fifth of patients within 24 h of the onset of acute intracerebral haemorrhage and is associated with death and disability, which makes it an appealing therapeutic target. The time in which active intervention can be done is short as expansion occurs mostly within the first 3 h after onset. Baseline haemorrhage volume, antithrombotic treatment, and CT angiography spot signs are each associated with increased risk of haematoma expansion. Non-contrast CT features are promising predictors of haematoma expansion, but their potential contribution to current models is under investigation. Blood pressure lowering and haemostatic treatment minimise haematoma expansion but have not led to improved functional outcomes in randomised clinical trials. Ultra-early enrolment and selection of participants on the basis of non-contrast CT imaging markers could focus future clinical trials to show clinical benefit in people at high risk of expansion or investigate heterogeneity of treatment effects in clinical trials with broad inclusion criteria.

The "SALPARE study" of spontaneous intracerebral haemorrhage-part 2-early CT predictors of outcome in ICH: keeping it simple

BACKGROUND

The aim of this study was to investigate the prognostic role of hematoma characteristics and hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (ICH).

METHODS

This multicenter prospective cohort study enrolled consecutive adult patients with non-traumatic ICH admitted to three Italian academic hospitals (Salerno, Padova, Reggio Emilia) over a 2-year period. Early noncontrast CT (NCCT) features of the hematoma, including markers of HE, and 3-month outcome were recorded. Multivariable logistic regression analysis was performed to identify predictors of poor outcome.

RESULTS

A total of 682 patients were included in the study [mean age: 73 ± 14 years; 316 (46.3%) females]. Pontine and massive hemorrhage, intraventricular bleeding, baseline hematoma volume > 15 mL, blend sign, swirl sign, margin irregularity ≥ 4, density heterogeneity ≥ 3, hypodensity ≥ 1, island sign, satellite sign, and black hole sign were associated with a higher risk of mortality and disability. However, at multivariate analysis only initial hematoma volume (OR 29.71) proved to be an independent predictor of poor functional outcome at 3 months.

CONCLUSION

Simple hematoma volume measured on baseline CT best identifies patients with a worse outcome, while early NCCT markers of HE do not seem to add any clinically significant information.

Added value of non-contrast CT and CT perfusion markers for prediction of intracerebral hemorrhage expansion and outcome

OBJECTIVES

To test the hypothesis that the combined analysis of non-contrast CT (NCCT) and CT perfusion (CTP) imaging markers improves prediction of hematoma expansion (HE) and outcome in intracerebral hemorrhage (ICH).

METHODS

Retrospective, single-center analysis of patients with primary ICH undergoing NCCT and CTP within 6 h from onset. NCCT images were assessed for the presence of intrahematomal hypodensity and shape irregularity. Perihematomal cerebral blood volume and spot sign were assessed on CTP. The main outcomes of the analysis were HE (growth > 6 mL and/or > 33%) and poor functional prognosis (90 days modified Rankin Scale 3-6). Predictors of HE and outcome were explored with logistic regression.

RESULTS

A total of 150 subjects were included (median age 68, 47.1% males) of whom 54 (36%) had HE and 52 (34.7%) had poor outcome. The number of imaging markers on baseline imaging was independently associated with HE (odds ratio 2.66, 95% confidence interval 1.70-4.17, p < 0.001) and outcome (odds ratio 1.64, 95% CI 1.06-2.56, p = 0.027). Patients with the simultaneous presence of all the four markers had the highest risk of HE and unfavorable prognosis (mean predicted probability of 91% and 79% respectively). The combined-markers analysis outperformed the sensitivity of the single markers analyzed separately. In particular, the presence of at least one marker identified patients with HE and poor outcome with 91% and 87% sensitivity respectively.

CONCLUSION

NCCT and CTP markers provide additional yield in the prediction of HE and ICH outcome.

KEY POINTS

• Perihematomal hypoperfusion is associated with hematoma expansion and poor outcome in acute intracerebral hemorrhage. • Non-contrast CT and CT perfusion markers improve prediction of hematoma expansion and unfavorable prognosis. • A multimodal CT protocol including CT perfusion will help the identification of patients at high risk of clinical deterioration and poor outcome.

A non-contrast computed tomography-based radiomics nomogram for the prediction of hematoma expansion in patients with deep ganglionic intracerebral hemorrhage

Background and purpose

Hematoma expansion (HE) is a critical event following acute intracerebral hemorrhage (ICH). We aimed to construct a non-contrast computed tomography (NCCT) model combining clinical characteristics, radiological signs, and radiomics features to predict HE in patients with spontaneous ICH and to develop a nomogram to assess the risk of early HE.

Materials and methods

We retrospectively reviewed 388 patients with ICH who underwent initial NCCT within 6 h after onset and follow-up CT within 24 h after initial NCCT, between January 2015 and December 2021. Using the LASSO algorithm or stepwise logistic regression analysis, five models (clinical model, radiological model, clinical-radiological model, radiomics model, and combined model) were developed to predict HE in the training cohort (n = 235) and independently verified in the test cohort (n = 153). The Akaike information criterion (AIC) and the likelihood ratio test (LRT) were used for comparing the goodness of fit of the five models, and the AUC was used to evaluate their ability in discriminating HE. A nomogram was developed based on the model with the best performance.

Results

The combined model (AIC = 202.599, χ2 = 80.6) was the best fitting model with the lowest AIC and the highest LRT chi-square value compared to the clinical model (AIC = 232.263, χ2 = 46.940), radiological model (AIC = 227.932, χ2 = 51.270), clinical-radiological model (AIC = 212.711, χ2 = 55.490) or radiomics model (AIC = 217.647, χ2 = 57.550). In both cohorts, the nomogram derived from the combined model showed satisfactory discrimination and calibration for predicting HE (AUC = 0.900, sensitivity = 83.87%; AUC = 0.850, sensitivity = 80.10%, respectively).

Conclusion

The NCCT-based model combining clinical characteristics, radiological signs, and radiomics features could efficiently discriminate early HE, and the nomogram derived from the combined model, as a non-invasive tool, exhibited satisfactory performance in stratifying HE risks.

Association between leukocyte subpopulations and hematoma expansion after spontaneous intracerebral hemorrhage: A retrospective cohort study

Aims

To verify the association between leukocyte subpopulations and hematoma expansion (HE) determined by two definitions in Chinese individuals who experienced spontaneous intracerebral hemorrhage.

Methods

We enrolled 471 patients. The 1/2ABC formula was used to gauge hematoma volume. The outcome was whether HE appeared within 72 h. We used Definition 1 (volume increase ≥6 mL or 33%) and Definition 2 (volume increase ≥12.5 mL or 33%) to define HE, respectively. Binary logistic regression analysis was used to assess the association between leukocyte subpopulations and HE. For statistically significant leukocyte subpopulations, we also performed subgroup analyses to assess differences between subgroups.

Results

Among 471 patients, 131 (27.81%) and 116 (24.63%) patients experienced HE based on Definition 1 and Definition 2, respectively. After adjusting for confounding factors, elevated monocyte count was associated with a higher risk of HE-Definition 1 [adjusted odds ratio (aOR) 2.45, 95% confidence interval (CI) 1.02–5.88, P = 0.0450] and HE-Definition 2 (aOR 2.54, 95% CI 1.04–6.20, P = 0.0399). Additionally, we compared the results before and after adjusting for coagulation parameters. Monocyte count was significantly correlated with HE only after adjusting for coagulation parameters. Increased neutrophil count was associated with a lower risk of HE-Definition 1 (aOR 0.91, 95% CI 0.84–1.00, P = 0.0463). No correlations were observed between lymphocyte and leukocyte counts and HE (P > 0.05), and no subgroup interactions were observed (interaction P > 0.05).

Conclusion

A higher monocyte count is associated with a higher HE risk regardless of the two definitions, after excluding the influence of the coagulation parameters, which facilitates risk stratification. Moreover, an increased neutrophil count is associated with a decreased risk of HE in the context of HE-Definition 1, which reflects the importance of standardizing the definition of HE.

Deep Learning-Based Prediction of Hematoma Expansion Using a Single Brain Computed Tomographic Slice in Patients With Spontaneous Intracerebral Hemorrhages

OBJECTIVES

We aimed to predict hematoma expansion in intracerebral hemorrhage (ICH) patients by using the deep learning technique.

METHODS

We retrospectively collected data from ICH patients treated between May 2015 and May 2019. Head computed tomography (CT) scans were performed at admission, and 6 hours, 24 hours, and 72 hours after admission. CT scans were mandatory when neurologic deficits occurred. Univariate and multivariate analyses were conducted to illustrate the association between clinical variables and hematoma expansion. Convolutional neural network (CNN) was adopted to predict hematoma expansion based on brain CT slices. In addition, 5 machine learning methods, including support vector machine, multi-layer perceptron, naive Bayes, decision tree, and random forest, were also performed to predict hematoma expansion based on clinical variables for comparisons.

RESULTS

A total of 223 patients were included. It was revealed that patients' older age (odds ratio [95% confidence interval]: 1.783 [1.417-1.924]), cerebral hemorrhage and breaking into the ventricle (2.524 [1.291-1.778]), coagulopathy (2.341 [1.677-3.454]), and baseline National Institutes of Health Stroke Scale (1.545 [1.132-3.203]) and Glasgow Coma Scale scores (0.782 [0.432-0.918]) independently associated with hematoma expanding. After 4-5 epochs, the CNN framework was well trained. The average sensitivity, specificity, and accuracy of CNN prediction are 0.9197, 0.8837, and 0.9058, respectively. Compared with 5 machine learning methods based on clinical variables, CNN can also achieve better performance.

CONCLUSIONS

More than 90% of hematomas with or without expansion can be precisely classified by deep learning technology within this study, which is better than other methods based on clinical variables only. Deep learning technology could favorably predict hematoma expansion from non-contrast CT scan images.

Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage

To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods.

Initial investigation of predicting hematoma expansion for intracerebral hemorrhage using imaging biomarkers and machine learning

PURPOSE

Intracerebral Hemorrhage (ICH) is one of the most devastating types of strokes with mortality and morbidity rates ranging from about 51%-65% one year after diagnosis. Early hematoma expansion (HE) is a known cause of worsening neurological status of ICH patients. The goal of this study was to investigate whether non-contrast computed tomography imaging biomarkers (NCCT-IB) acquired at initial presentation can predict ICH growth in the acute stage.

MATERIALS AND METHODS

We retrospectively collected NCCT data from 200 patients with acute (<6 hours) ICH. Four NCCT-IBs (blending region, dark hole, island, and edema) were identified for each hematoma, respectively. HE status was recorded based on the clinical observation reported in the patient chart. Supervised machine learning models were developed, trained, and tested for 15 different input combinations of the NCCT-IBs to predict HE. Model performance was assessed using area under the receiver operating characteristic curve and probability for accurate diagnosis (PAD) was calculated. A 20-fold Monte-Carlo cross validation was implemented to ensure model reliability on a limited sample size of data, by running a myriad of random training/testing splits.

RESULTS

The developed algorithm was able to predict expansion utilizing all four inputs with an accuracy of 70.17%. Further testing of all biomarker combinations yielded P _AD ranging from 0.57, to 0.70.

CONCLUSION

Specific attributes of ICHs may influence the likelihood of HE and can be evaluated via a machine learning algorithm. However, certain parameters may differ in importance to reach accurate conclusions about potential expansion.

A predictive nomogram for intracerebral hematoma expansion based on non-contrast computed tomography and clinical features

PURPOSE

To develop and validate a new nomogram utilizing non-contrast computed tomography (NCCT) signs and clinical factors for predicting hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (ICH).

METHODS

HE was defined as > 6 mL or 33% increase in baseline hematoma volume. Multivariable logistic regression analysis was performed to identify the predictors of HE. The discriminatory performance of the proposed model was evaluated via receiver operation characteristic (ROC) analysis, and the predictive accuracy was assessed by a calibration curve. The nomogram was established by R programming language. The decision curve analysis and clinical impact curve were drawn according to the related risk factors.

RESULTS

A total of 506 patients with spontaneous ICH were recruited in the development cohort, and 103 patients were registered as the external validation cohort. Among the development cohort, 132 (26.09%) experienced HE. Glasgow coma scale (GCS) (P < 0.001), neutrophil to lymphocyte ratio (NLR) (P < 0.001), blend sign (P < 0.001), swirl sign (P < 0.001), and hypodensities (P = 0.003) were significant predictors of HE, by which were used to establish the nomogram. The model demonstrated good performance with high area under the curve both in the development (AUC = 0.908; 95% confidence interval, 0.880-0.936) and the external validation (AUC = 0.844; 95% confidence interval, 0.760-0.908) cohort. The calibration curve illustrated a high accuracy for HE prediction.

CONCLUSION

The nomogram derived from NCCT markers and clinical factors outperformed the NCCT signs-only model in predicting HE for patients with ICH, thus providing an effective and noninvasive tool for the risk stratification of HE.

Different Effects of Hematoma Expansion on Short-Term Functional Outcome in Basal Ganglia and Thalamic Hemorrhages

Purpose

To investigate the impact of hematoma expansion (HE) on short-term functional outcome of patients with thalamic and basal ganglia intracerebral hemorrhage.

Methods

Data of 420 patients with deep intracerebral hemorrhage (ICH) that received a baseline CT scan within 6 hours from symptom onset and a follow-up CT scan within 72 hours were retrospectively analyzed. The poor functional outcome was defined as modified Rankin score (mRS) > 3 at 30 days. Receiver operating characteristic (ROC) curves for relative and absolute growth of HE were generated and compared. Multivariable logistic regression models were used to analyze the impact of HE on the functional outcome in basal ganglia and thalamic hemorrhages. The predictive values for different thresholds of HE were calculated, and correlation coefficient matrices were used to explore the correlation between the covariables.

Results

Basal ganglia ICH showed a higher possibility of absolute hematoma growth than thalamic ICH. The area under the curve (AUC) for absolute and relative growth of thalamic hemorrhage was lower than that of basal ganglia hemorrhage (AUC 0.71 and 0.67, respectively) in discriminating short-term poor outcome with an AUC of 0.59 and 0.60, respectively. Each threshold of HE independently predicted poor outcome in basal ganglia ICH (P < 0.001), with HE > 3 ml and > 6 ml showing higher positive predictive values and accuracy compared to HE > 33%. In contrast, thalamic ICH had a smaller baseline volume (BV, 9.55 ± 6.85 ml) and was more likely to initially involve the posterior limb of internal capsule (PLIC) (85/153, 57.82%), and the risk of HE was lower without PLIC involvement (4.76%, P = 0.009). Therefore, in multivariate analysis, the effect of thalamic HE on poor prognosis was largely replaced by BV and the involvement of PLIC, and the adjusted odds ratios (ORs) of HE was not significant (P > 0.05).

Conclusion

Though HE is a high-risk factor for short-term poor functional outcome, it is not an independent risk factor in thalamic ICH, and absolute growth is more predictive of poor outcome than relative growth for basal ganglia ICH.

Machine learning-based modified BAT score in predicting hematoma enlargement after spontaneous intracerebral hemorrhage

OBJECTIVE

The BAT score is an easy-to-use prediction tool to detect hematoma enlargement after spontaneous intracerebral hemorrhage. Machine learning technique has potential predictive gains in accuracy over regression models. We sought to use machine learning technique to improve the BAT score for the prediction of hematoma enlargement.

METHODS

Totally 232 patients with spontaneous intracerebral hemorrhage were enrolled from our hospital between 2015 and 2020. The BAT score was calculated to identify high-risk patients with hematoma enlargement. Using the same variables of the original BAT score and 5 common machine learning algorithms, the modified BAT scores were constructed in the training subset (n = 162) and validated in the testing subset (n = 70). Receiver operating characteristic curves were performed to evaluate the discriminative ability of all BAT scores.

RESULTS

Among 5 modified BAT scores, the modified BAT score based on Naive Bayes algorithm performed best, with the area under the receiver operating characteristic curve (AUC) of 0.83 in the training subset and 0.77 in the testing subset. The DeLong test showed that the performances of the modified BAT score based on Naive Bayes algorithm were significantly better than that of the BAT score (AUC = 0.57) in the training and testing subsets (both P < 0.001).

CONCLUSIONS

Machine learning technique could improve the identification performance of the original BAT score using the same variables. The modified BAT score based on Naive Bayes algorithm could be used as an effective prediction tool for identifying high-risk patients with hematoma enlargement.

Aspirin does not affect hematoma growth in severe spontaneous intracranial hematoma

Hematoma growth (HG) affects the prognosis of patients with spontaneous intracranial hematoma (ICH), but there is still a lack of evidence about the effects of aspirin (acetylsalicylic acid, ASA) on HG in patients with severe ICH. This study retrospectively analyzed patients with severe ICH who met the inclusion and exclusion criteria in Beijing Tiantan Hospital, Capital Medical University, between January 1, 2015, and July 31, 2019. Severe ICH patients were divided into ASA group and nASA groups according to ASA usage, and the incidence of HG between the groups was compared. Univariate analysis was performed by the Mann-Whitney U test, chi-square test, or Fisher exact test. Multivariate logistic regression analysis was used to analyze the impact of ASA on HG and to screen for risk factors of HG. In total, 221 patients with severe ICH were consecutively enrolled in this study. There were 72 (32.6%) patients in the ASA group and 149 patients in the nASA group. Although the incidence of HG in the nASA group was higher than that in the ASA group (34.9% VS 22.2%, p = 0.056), ASA did not significantly affect the occurrence of HG (p = 0.285) after adjusting for initial hematoma volume, high blood pressure at admission, coronary heart disease, and GCS at admission. In addition, we found that high blood pressure at admission was a risk factor for HG. Prior ASA does not increase the incidence of HG in severe ICH patients, and high blood pressure at admission is a risk factor for HG.

Intraventricular Hemorrhage Growth: Definition, Prevalence and Association with Hematoma Expansion and Prognosis

BACKGROUND/OBJECTIVES

The objective of this study is to propose a definition of intraventricular hemorrhage (IVH) growth and to investigate whether IVH growth is associated with ICH expansion and functional outcome.

METHODS

We performed a prospective observational study of ICH patients between July 2011 and March 2017 in a tertiary hospital. Patients were included if they had a baseline CT scan within 6 h after onset of symptoms and a follow-up CT within 36 h. IVH growth was defined as either any newly occurring intraventricular bleeding on follow-up CT scan in patients without baseline IVH or an increase in IVH volume ≥ 1 mL on follow-up CT scan in patients with initial IVH. Poor outcome was defined as modified Rankin Scale score of 3-6 at 90 days. The association between IVH growth and functional outcome was assessed by using multivariable logistic regression analysis.

RESULTS

IVH growth was observed in 59 (19.5%) of 303 patients. Patients with IVH growth had larger baseline hematoma volume, higher NIHSS score and lower GCS score than those without. Of 44 patients who had concurrent IVH growth and hematoma growth, 41 (93.2%) had poor functional outcome at 3-month follow-up. IVH growth (adjusted OR 4.15, 95% CI 1.31-13.20; P = 0.016) was an independent predictor of poor functional outcome (mRS 3-6) at 3 months in multivariable analysis.

CONCLUSION

IVH growth is not uncommon and independently predicts poor outcome in ICH patients. It may serve as a promising therapeutic target for intervention.

Validation and Comparison of Noncontrast CT Scores to Predict Intracerebral Hemorrhage Expansion

BACKGROUND AND PURPOSE

The BAT, BRAIN, and HEP scores have been proposed to predict hematoma expansion (HE) with noncontrast computed tomography (NCCT). We sought to validate these tools and compare their diagnostic performance.

METHODS

We retrospectively analyzed two cohorts of patients with primary intracerebral hemorrhage. HE expansion was defined as volume growth > 33% or > 6 mL. Two raters analyzed NCCT scans and calculated the scores, blinded to clinical and imaging data. The inter-rater reliability was assessed with the interclass correlation statistic. Discrimination and calibration were calculated with area under the curve (AUC) and Hosmer-Lemeshow χ² statistic, respectively. AUC comparison between different scores was explored with DeLong test. We also calculated the sensitivity, specificity, positive, and negative predictive values of the dichotomized scores with cutoffs identified with the Youden's index.

RESULTS

A total of 230 subjects were included, of whom 86 (37.4%) experienced HE. The observed AUC for HE were 0.696 for BAT, 0.700 for BRAIN, and 0.648 for HEP. None of the scores had a significantly superior AUC compared with the others (all p > 0.4). All the scores had good calibration (all p > 0.3) and good-to-excellent inter-rater reliability (interclass correlation > 0.8). BAT ≥ 3 showed the highest specificity (0.81), whereas BRAIN ≥ 6 had the highest sensitivity (0.76).

CONCLUSIONS

The BAT, BRAIN, and HEP scores can predict HE with acceptable discrimination and require just a baseline NCCT scan. These tools may be used to stratify the risk of HE in clinical practice or randomized controlled trials.

Tranexamic acid for acute intracerebral haemorrhage growth based on imaging assessment (TRAIGE): a multicentre, randomised, placebo-controlled trial

BACKGROUND

Studies show tranexamic acid can reduce the risk of death and early neurological deterioration after intracranial haemorrhage. We aimed to assess whether tranexamic acid reduces haematoma expansion and improves outcome in intracerebral haemorrhage patients susceptible to haemorrhage expansion.

METHODS

We did a prospective, double-blind, randomised, placebo-controlled trial at 10 stroke centres in China. Acute supratentorial intracerebral haemorrhage patients were eligible if they had indication of haemorrhage expansion on admission imaging (eg, spot sign, black hole sign or blend sign), and were treatable within 8 hours of symptom onset. Patients were randomly assigned (1:1) to receive either tranexamic acid or a matching placebo. The primary outcome was intracerebral haematoma growth (>33% relative or >6 mL absolute) at 24 hours. Clinical outcomes were assessed at 90 days.

RESULTS

Of the 171 included patients, 124 (72.5%) were male, and the mean age was 55.9±11.6 years. 89 patients received tranexamic acid and 82 received placebo. The primary outcome did not differ significantly between the groups: 36 (40.4%) patients in the tranexamic acid group and 34 (41.5%) patients in the placebo group had intracranial haemorrhage growth (OR 0.96, 95% CI 0.52 to 1.77, p=0.89). The proportion of death was lower in the tranexamic acid treatment group than placebo group (8.1% vs 10.0%), but there were no significant differences in secondary outcomes including absolute intracranial haemorrhage growth, death and dependency.

CONCLUSIONS

Among patients susceptible to haemorrhage expansion treated within 8 hours of stroke onset, tranexamic acid did not significantly prevent intracerebral haemorrhage growth. Larger studies are needed to assess safety and efficacy of tranexamic acid in intracerebral haemorrhage patients.

New Prediction Models of Functional Outcome in Acute Intracerebral Hemorrhage: The dICH Score and uICH Score

Objectives: The original intracerebral hemorrhage (oICH) score is the severity score most commonly used in clinical intracerebral hemorrhage (ICH) research but may be influenced by hematoma expansion or intraventricular hemorrhage (IVH) growth in acute ICH. Here, we aimed to develop new clinical scores to improve the prediction of functional outcomes in patients with ICH.

Methods: Patients admitted to the First Affiliated Hospital of Chongqing Medical University with primary ICH were prospectively enrolled in this study. Hematoma volume was measured using a semiautomated, computer-assisted technique. The dynamic ICH (dICH) score was developed by incorporating hematoma expansion and IVH growth into the oICH score. The ultra-early ICH (uICH) score was developed by adding the independent non-contrast CT markers to the oICH score. Receiver operating characteristic curve analysis was used to compare performance among the oICH score, dICH score, and uICH score.

Results: There were 310 patients in this study which included 72 patients (23.2%) with hematoma expansion and 58 patients (18.7%) with IVH growth. Of 31 patients with two or more non-contrast computed tomography markers, 61.3% died, and 96.8% had poor outcomes at 90 days. After adjustment for potential confounding variables, we found that age, baseline Glasgow Coma Scale score, presence of IVH on initial CT, baseline ICH volume, infratentorial hemorrhage, hematoma expansion, IVH growth, blend sign, black hole sign, and island sign could independently predict poor outcomes in multivariate analysis. In comparison with the oICH score, the dICH score and uICH score exhibited better performance in the prediction of poor functional outcomes.

Conclusions: The dICH score and uICH score were useful clinical assessment tools that could be used for risk stratification concerning functional outcomes and provide guidance in clinical decision-making in acute ICH.

The 'swirl sign' as a marker for haematoma expansion and outcome in intra-cranial haemorrhage: A meta-analysis

The 'swirl sign' is a CT imaging finding associated with haematoma expansion and poor prognosis. We performed a systematic review and meta-analysis to determine its prognostic value. PubMed/MEDLINE and EMBASE were searched until 16/12/2020 for related articles. Articles detailing the relationship between the swirl sign and any of haematoma expansion (HE), neurological outcome in the form of Glasgow Outcome Score (GOS) or mortality were included. A meta-analysis was performed and the pooled sensitivity, specificity, positive likelihood ratio (PLR) and negative likelihood ratio (NLR) were calculated for each of HE, GOS and mortality. 15 papers were assessed. Nine papers related to HE, for which the pooled sensitivity was 50% (95% CI 30-71), specificity was 77% (95%CI 67-85) and PLR was 2.16 (95%CI 1.89-2.42). There was significant heterogeneity (I² = 70%, Q = 26.9). Three papers related to GOS, for which the pooled sensitivity was 45% (95%CI 20-74), specificity was 78.3% (95%CI 40-95.2) and PLR was 1.77 (95%CI 1.04-2.62). Three papers related to mortality, for which the pooled sensitivity was 65% (95% CI 32-88), specificity was 75% (95%CI 42-92) and pooled PLR was 2.64 (95%CI 1.60-4.13). Our findings indicated that the swirl sign is a useful prognostic marker in the radiological evaluation of intracranial haemorrhage. However, more research is needed to assess its independence from other risk factors for haematoma expansion.

Can perihaematomal radiomics features predict haematoma expansion?

AIM

To evaluate the association between perihaematomal radiomics features and haematoma expansion (HE).

MATERIALS AND METHODS

Clinical and radiological data were collected retrospectively. The 1:1 propensity score matching (PSM) method was used to balance the difference of baseline characteristics between patients with and without HE. Radiomics features were extracted from the intra- and perihaematomal regions. Top HE-associated features were selected using the minimum redundancy, maximum relevancy algorithm. Support vector machine models were used to predict HE. Predictive performance of radiomics features from different regions was evaluated by receiver operating characteristic curve and confusion matrix-derived metrics.

RESULTS

A total of 1,062 patients were enrolled. After PSM analysis, the propensity score-matched cohort (PSM cohort) included 314 patients (HE: n=157; non-HE: n=157). The PSM cohort was distributed into the training (n=218) and the validation cohorts (n=96). The predictive performance of intra- and perihaematomal features were comparable in the training (area under the receiver operating characteristic curve [AUC], 0.751 versus 0.757; p=0.867) and the validation cohorts (AUC, 0.724 versus 0.671; p=0.454). By incorporating intra- and perihaematomal features, the combined model outperformed the single intrahaematomal model in the training cohort (AUC, 0.872 versus 0.751; p<0.001). Decision curve analysis (DCA) further confirmed the clinical usefulness of the combined model.

CONCLUSION

Perihaematomal radiomics features can predict HE. The integration of intra- and perihaematomal signatures may provide additional benefit to the prediction of HE.

Hematoma Expansion in Intracerebral Hemorrhage With Unclear Onset

OBJECTIVE

To investigate the prevalence, predictors, and prognostic effect of hematoma expansion (HE) in patients with intracerebral hemorrhage (ICH) with unclear symptom onset (USO).

METHODS

We performed a retrospective analysis of patients with primary spontaneous ICH admitted at 5 academic medical centers in the United States and Italy. HE (volume increase >6 mL or >33% from baseline to follow-up noncontrast CT [NCCT]) and mortality at 30 days were the outcomes of interest. Baseline NCCT was also analyzed for presence of hypodensities (any hypodense region within the hematoma margins). Predictors of HE and mortality were explored with multivariable logistic regression.

RESULTS

We enrolled 2,165 participants, 1,022 in the development cohort and 1,143 in the replication cohort, of whom 352 (34.4%) and 407 (35.6%) had ICH with USO, respectively. When compared with participants having a clear symptom onset, patients with USO had a similar frequency of HE (25.0% vs 21.9%, p = 0.269 and 29.9% vs 31.5%, p = 0.423). Among patients with USO, HE was independently associated with mortality after adjustment for confounders (odds ratio [OR] 2.64, 95% confidence interval [CI] 1.43-4.89, p = 0.002). This finding was similar in the replication cohort (OR 3.46, 95% CI 1.86-6.44, p < 0.001). The presence of NCCT hypodensities in patients with USO was an independent predictor of HE in the development (OR 2.59, 95% CI 1.27-5.28, p = 0.009) and replication (OR 2.43, 95% CI 1.42-4.17, p = 0.001) population.

CONCLUSION

HE is common in patients with USO and independently associated with worse outcome. These findings suggest that patients with USO may be enrolled in clinical trials of medical treatments targeting HE.

Computed Tomography Imaging Predictors of Intracerebral Hemorrhage Expansion

PURPOSE OF REVIEW

Hematoma expansion (HE) is strongly associated with poor clinical outcome and is a compelling target for improving outcome after intracerebral hemorrhage (ICH). Non-contrast computed tomography (NCCT) is widely used in clinical practice due to its faster acquisition at the presence of acute stroke. Recently, imaging markers on NCCT are increasingly used for predicting HE. We comprehensively review the current evidence on HE prediction using NCCT and provide a summary for assessment of these markers in future research studies.

RECENT FINDINGS

Predictors of HE on NCCT have been described in reports of several studies. The proposed markers, including swirl sign, blend sign, black hole sign, island sign, satellite sign, and subarachnoid extension, were all significantly associated with HE and poor outcome in their small sample studies after ICH. In summary, the optimal management of ICH remains a therapeutic dilemma. Therefore, using NCCT markers to select patients at high risk of HE is urgently needed. These markers may allow rapid identification and provide potential targets for anti-HE treatments in patients with acute ICH.

Radiomics for intracerebral hemorrhage: are all small hematomas benign?

OBJECTIVES

We hypothesized that not all small hematomas are benign and that radiomics could predict hematoma expansion (HE) and short-term outcomes in small hematomas.

METHODS

We analyzed 313 patients with small (<10 ml) intracerebral hemorrhage (ICH) who underwent baseline non-contrast CT within 6 h of symptom onset between September 2013 and February 2019. Poor outcome was defined as a Glasgow Outcome Scale score ≤3. A radiomic model and a clinical model were built using least absolute shrinkageand selection operator algorithm or multivariate analysis. A combined model that incorporated the developed radiomic score and clinical factors was then constructed. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of these models.

RESULTS

The addition of radiomics to clinical factors significantly improved the prediction performance of HE compared with the clinical model alone in both the training {AUC, 0.762 [95% CI (0.665-0.859)] versus AUC, 0.651 [95% CI (0.556-0.745)], p = 0.007} and test {AUC, 0.776 [95% CI (0.655-0.897) versus AUC, 0.631 [95% CI (0.451-0.810)], p = 0.001} cohorts. Moreover, the radiomic-based model achieved good discrimination ability of poor outcomes in the 3-10 ml group (AUCs 0.720 and 0.701).

CONCLUSION

Compared with clinical information alone, combined model had greater potential for discriminating between benign and malignant course in patients with small ICH, particularly 3-10 ml hematomas.

ADVANCES IN KNOWLEDGE

Radiomics can be used as a supplement to conventional medical imaging, improving clinical decision-making and facilitating personalized treatment in small ICH.

Clinical-radiomics Nomogram for Risk Estimation of Early Hematoma Expansion after Acute Intracerebral Hemorrhage

RATIONALE AND OBJECTIVES

Noncontrast CT-based radiomics signature has shown ability for detecting hematoma expansion (HE) in spontaneous intracerebral hemorrhage (ICH). We sought to compare its predictive performance with clinical risk factors and develop a clinical-radiomics nomogram to assess the risk of early HE.

MATERIALS AND METHODS

In total, 1153 patients with ICH who underwent baseline cranial CT within 6 hours and follow-up scans within 72 hours of stroke onset were enrolled, of whom 864 (75%) were assigned to the derivation cohort and 289 (25%) to the validation cohort. Based on LASSO algorithm or stepwise logistic regression analysis, three models (clinical model, radiomics model, and hybrid model) were constructed to predict HE. The Akaike information criterion (AIC) and likelihood ratio test (LRT) were used for comparing the goodness of fit of the three models, and the AUC was used to evaluate their discrimination ability for HE.

RESULTS

The hybrid model (AIC = 681.426; χ²= 128.779) was the optimal model with the lowest AIC and highest chi-square values compared to the radiomics model (AIC = 767.979; χ² = 110.234) or the clinical model (AIC = 753.757; χ² = 56.448). The radiomics model was superior in the prediction of HE to the clinical model in both derivation (p = 0.009) and validation (p = 0.022) cohorts. In both datasets, the clinical-radiomics nomogram showed satisfactory discrimination and calibration for detecting HE (AUC = 0.771, Sensitivity = 87.0%; AUC = 0.820, Sensitivity = 88.1%; respectively).

CONCLUSION

Among patients with acute ICH, noncontrast CT-based radiomics model outperformed the clinical-only model in the prediction of HE, and the established clinical-radiomics nomogram with favorable performance can offer a noninvasive tool for the risk stratification of HE.

Noncontrast Computed Tomography Markers as Predictors of Revised Hematoma Expansion in Acute Intracerebral Hemorrhage

Background Noncontrast computed tomography (NCCT) markers are the emerging predictors of hematoma expansion in intracerebral hemorrhage. However, the relationship between NCCT markers and the dynamic change of hematoma in parenchymal tissues and the ventricular system remains unclear. Methods and Results We included 314 consecutive patients with intracerebral hemorrhage admitted to our hospital from July 2011 to May 2017. The intracerebral hemorrhage volumes and intraventricular hemorrhage (IVH) volumes were measured using a semiautomated, computer-assisted technique. Revised hematoma expansion (RHE) was defined by incorporating the original definition of hematoma expansion into IVH growth. Receiver operating characteristic curve analysis was used to compare the performance of the NCCT markers in predicting the IVH growth and RHE. Of 314 patients in our study, 61 (19.4%) had IVH growth and 93 (23.9%) had RHE. After adjustment for potential confounding variables, blend sign, black hole sign, island sign, and expansion-prone hematoma could independently predict IVH growth and RHE in the multivariate logistic regression analysis. Expansion-prone hematoma had a higher predictive performance of RHE than any single marker. The diagnostic accuracy of RHE in predicting poor prognosis was significantly higher than that of hematoma expansion. Conclusions The NCCT markers are independently associated with IVH growth and RHE. Furthermore, the expansion-prone hematoma has a higher predictive accuracy for prediction of RHE and poor outcome than any single NCCT marker. These findings may assist in risk stratification of NCCT signs for predicting active bleeding.

Deep learning for automatically predicting early haematoma expansion in Chinese patients

Background and purpose

Early haematoma expansion is determinative in predicting outcome of intracerebral haemorrhage (ICH) patients. The aims of this study are to develop a novel prediction model for haematoma expansion by applying deep learning model and validate its prediction accuracy.

Methods

Data of this study were obtained from a prospectively enrolled cohort of patients with primary supratentorial ICH from our centre. We developed a deep learning model to predict haematoma expansion and compared its performance with conventional non-contrast CT (NCCT) markers. To evaluate the predictability of this model, it was also compared with a logistic regression model based on haematoma volume or the BAT score.

Results

A total of 266 patients were finally included for analysis, and 74 (27.8%) of them experienced early haematoma expansion. The deep learning model exhibited highest C statistic as 0.80, compared with 0.64, 0.65, 0.51, 0.58 and 0.55 for hypodensities, black hole sign, blend sign, fluid level and irregular shape, respectively. While the C statistics for swirl sign (0.70; p=0.211) and heterogenous density (0.70; p=0.141) were not significantly higher than that of the deep learning model. Moreover, the predictive value for the deep learning model was significantly superior to that of the logistic model of haematoma volume (0.62; p=0.042) and the BAT score (0.65; p=0.042).

Conclusions

Compared with the conventional NCCT markers and BAT predictive model, the deep learning algorithm showed superiority for predicting early haematoma expansion in ICH patients.

Radiomics in Stroke Neuroimaging: Techniques, Applications, and Challenges

Stroke is a leading cause of disability and mortality worldwide, resulting in substantial economic costs for post-stroke care each year. Neuroimaging, such as cranial computed tomography or magnetic resonance imaging, is the backbone of stroke management strategies, which can guide treatment decision-making (thrombolysis or hemostasis) at an early stage. With advances in computational technologies, particularly in machine learning, visual image information can now be converted into numerous quantitative features in an objective, repeatable, and high-throughput manner, in a process known as radiomics. Radiomics is mainly used in the field of oncology, which remains an area of active research. Over the past few years, investigators have attempted to apply radiomics to stroke in the hope of gaining benefits similar to those obtained in cancer management, i.e., in promoting the development of personalized precision medicine. Currently, radiomic analysis has shown promise for a variety of applications in stroke, including the diagnosis of stroke lesions, early prediction of outcomes, and evaluation for long-term prognosis. In this article, we elaborate the contributions of radiomics to stroke, as well as the subprocesses and techniques involved in radiomics studies. We also discuss the potential challenges facing its widespread implementation in routine practice and the directions for future research.

Comparison of Black Hole Sign, Satellite Sign, and Iodine Sign to Predict Hematoma Expansion in Patients with Spontaneous Intracerebral Hemorrhage

PURPOSE

To discretely and collectively compare black hole sign (BHS) and satellite sign (SS) with recently introduced gemstone spectral imaging-based iodine sign (IS) for predicting hematoma expansion (HE) in spontaneous intracerebral hemorrhage (SICH).

METHODS

This retrospective study includes 90 patients from 2017 to 2019 who underwent both spectral computed tomography angiography (CTA) as well as noncontrast computed tomography (NCCT) within 6 hours of SICH onset along with subsequent follow-up NCCT scanned within 24 hours. We named the presence of any of BHS or SS as any NCCT sign. Two independent reviewers analyzed all the HE predicting signs. Receiver-operator characteristic curve analysis and logistic regression were performed to compare the predictive performance of HE.

RESULTS

A total of 61 patients had HE, out of which IS was seen in 78.7% (48/61) while BHS and SS were seen in 47.5% (29/61) and 41% (25/61), respectively. The area under the curve for BHS, SS, and IS was 63.4%, 67%, and 82.4%, respectively, while for any NCCT sign was 71.5%. There was no significant difference between IS and any NCCT sign (P = 0.108). Multivariate analysis showed IS (odds ratio 68.24; 95% CI 11.76-396.00; P < 0.001) and any NCCT sign (odds ratio 19.49; 95% CI 3.99-95.25; P < 0.001) were independent predictors of HE whereas BHS (odds ratio 0.34; 95% CI 0.01-38.50; P = 0.534) and SS (odds ratio 4.54; 95% CI 0.54-38.50; P = 0.165) had no significance.

CONCLUSION

The predictive accuracy of any NCCT sign was better than that of sole BHS and SS. Both any NCCT sign and IS were independent predictors of HE. Although IS had higher predictive accuracy, any NCCT sign may still be regarded as a fair predictor of HE when CTA is not available.

Development and external validation of a novel multihematoma fuzzy sign on computed tomography for predicting traumatic intraparenchymal hematoma expansion

Acute traumatic intraparenchymal hematoma (tICH) expansion is a devastating neurological complication that is associated with poor outcome after cerebral contusion. This study aimed to develop and validate a novel noncontrast computed tomography (CT) (NCCT) multihematoma fuzzy sign to predict acute tICH expansion. In this multicenter, prospective cohort study, multihematoma fuzzy signs on baseline CT were found in 212 (43.89%) of total 482 patients. Patients with the multihematoma fuzzy sign had a higher frequency of tICH expansion than those without (90.79% (138) vs. 46.71% (71)). The presence of multihematoma fuzzy sign was associated with increased risk for acute tICH expansion in entire cohort (odds ratio [OR]: 16.15; 95% confidence interval (CI) 8.85-29.47; P < 0.001) and in the cohort after propensity-score matching (OR: 9.37; 95% CI 4.52-19.43; P < 0.001). Receiver operating characteristic analysis indicated a better discriminative ability of the presence of multihematoma fuzzy sign for acute tICH expansion (AUC = 0.79; 95% CI 0.76-0.83), as was also observed in an external validation cohort (AUC = 0.76; 95% CI 0.67-0.84). The novel NCCT marker of multihematoma fuzzy sign could be easily identified on baseline CT and is an easy-to-use predictive tool for tICH expansion in the early stage of cerebral contusion.

Smoking Status Affects the Association Between Hematoma Heterogeneity and Hematoma Expansion

Objective

The purpose of this study was to verify the relationship between hematoma heterogeneity and hematoma expansion and explore any effect modifiers through subgroup analyses.

Methods

Clinical records of 357 patients with spontaneous cerebral hemorrhage at Shenzhen Second People’s Hospital from March 2016 to October 2018 were included in the study. Hematoma heterogeneity was measured on the first noncontrast computed tomography image according to the Barras scale. Hematoma expansion was defined as an absolute hematoma volume increase of 6 mL, or a 33% increase. We performed univariate and multivariate logistic regression analyses, as well as subgroup analyses, to assess the relationship between the presence of heterogeneity on noncontrast computed tomography and hematoma expansion.

Results

Hematoma expansion occurred in 79 (22.13%) of the 357 patients with intracerebral hemorrhage (ICH). Among the patients with ICH, there were 83 smokers, accounting for 23.24%. The average patient age was 56.21 ± 13.75 years, and 74.51% were male. Compared with the absence of heterogeneity, the risk of hematoma expansion increased by 1.06 times (odds ratio, 2.06; 95% confidence interval, 1.10–3.86). Based on the subgroup analysis, smoking status was found to modify the association between heterogeneity and hematoma expansion; the association was stronger in smokers than in nonsmokers (odds ratio, 10.23; 95% confidence interval, 2.15–48.65).

Conclusions

Heterogeneity independently predicts hematoma expansion, especially in smoking patients.

Noncontrast CT markers of intracerebral hemorrhage expansion and poor outcome: A meta-analysis

OBJECTIVE

To provide precise estimates of the association between noncontrast CT (NCCT) markers, hematoma expansion (HE), and functional outcome in patients presenting with intracerebral hemorrhage (ICH) through a systematic review and meta-analysis.

METHODS

We searched PubMed for English-written observational studies or randomized controlled trials reporting data on NCCT markers of HE and outcome in spontaneous ICH including at least 50 subjects. The outcomes of interest were HE (hematoma growth >33%, >33% and/or >6 mL, >33% and/or >12.5 mL), poor functional outcome (modified Rankin Scale 3-6 or 4-6) at discharge or at 90 days, and mortality. We pooled data in random-effects models and extracted cumulative odds ratio (OR) for each NCCT marker.

RESULTS

We included 25 eligible studies (n = 10,650). The following markers were associated with increased risk of HE and poor outcome, respectively: black hole sign (OR = 3.70, 95% confidence interval [CI] = 1.42-9.64 and OR = 5.26, 95% CI = 1.75-15.76), swirl sign (OR = 3.33, 95% CI = 2.42-4.60 and OR = 3.70; 95% CI = 2.47-5.55), heterogeneous density (OR = 2.74; 95% CI = 1.71-4.39 and OR = 2.80; 95% CI = 1.78-4.39), blend sign (OR = 3.49; 95% CI = 2.20-5.55 and OR = 2.21; 95% CI 1.16-4.18), hypodensities (OR = 3.47; 95% CI = 2.18-5.50 and OR = 2.94; 95% CI = 2.28-3.78), irregular shape (OR = 2.01, 95% CI = 1.27-3.19 and OR = 3.43; 95% CI = 2.33-5.03), and island sign (OR = 7.87, 95% CI = 2.17-28.47 and OR = 6.05, 95% CI = 4.44-8.24).

CONCLUSION

Our results suggest that multiple NCCT ICH shape and density features, with different effect size, are important markers for HE and clinical outcome and may provide useful information for future randomized controlled trials.

Benign Intracerebral Hemorrhage: A Population at Low Risk for Hematoma Growth and Poor Outcome

Background

To define benign intracerebral hemorrhage (ICH) and to investigate the association between benign ICH, hematoma expansion, and functional outcome.

Methods and Results

We analyzed a prospectively collected cohort of patients with ICH, who presented within 6 hours of symptom onset between July 2011 and February 2017 to a tertiary teaching hospital. Follow‐up computed tomographic scanning was performed within 36 hours after initial computed tomographic scanning. Benign ICH was operationally defined as homogeneous and regularly shaped small ICH. The presence of benign ICH was judged by 2 independent reviewers (Q.L., W.Y.) on the basis of the admission computed tomographic scan. Functional independence was defined as a modified Rankin Scale score of 0 to 2 at 3 months. The associations between benign ICH, hematoma expansion, and functional outcome were assessed by using multivariable logistic regression analyses. A total of 288 patients with ICH were included. Benign ICH was found in 48 patients (16.7%). None of the patients with benign ICH had early hematoma expansion. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of benign ICH for predicting functional independence at 3 months were 30.7%, 96.6%, 90.0%, 60.0%, and 0.637, respectively.

Conclusions

Patients with benign ICH are at low risk of hematoma expansion and poor outcome. These patients may be safe for less intensive monitoring and are unlikely to benefit from therapies aimed at preventing ICH expansion.

Hematoma Expansion in Intracerebral Hemorrhage: An Update on Prediction and Treatment

Intracerebral hemorrhage (ICH) is the most lethal type of stroke, but there is no specific treatment. After years of effort, neurologists have found that hematoma expansion (HE) is a vital predictor of poor prognosis in ICH patients, with a not uncommon incidence ranging widely from 13 to 38%. Herein, the progress of studies on HE after ICH in recent years is updated, and the topics of definition, prevalence, risk factors, prediction score models, mechanisms, treatment, and prospects of HE are covered in this review. The risk factors and prediction score models, including clinical, imaging, and laboratory characteristics, are elaborated in detail, but limited by sensitivity, specificity, and inconvenience to clinical practice. The management of HE is also discussed from bench work to bed practice. However, the upmost problem at present is that there is no treatment for HE proven to definitely improve clinical outcomes. Further studies are needed to identify more accurate predictors and effective treatment to reduce HE.

The NAG scale can screen for hematoma expansion in acute intracerebral hemorrhage-a multi-institutional validation

BACKGROUND

Early hematoma expansion (HE) is seen in approximately 30% of patients with intracerebral hemorrhage (ICH), but detecting patients with a high HE risk is challenging.

AIMS

The NAG scale is a simple predictive scale for HE in acute ICH patients. Multi-institutional validation of the usefulness of this scale was the aim of this study.

METHODS

We retrospectively reviewed 142 consecutive primary ICH patients admitted to our hospital between September 2016 and December 2018. The NAG scale consists of three factors: National Institutes of Health Stroke Scale (NIHSS) score ≥ 10, anticoagulant use, and glucose ≥133 mg/dl (1 point each). Patients underwent non-contrast computed tomography (CT) within 24 h of symptom onset and follow-up CT 6 h, 24 h, and 7 days after admission. We defined HE as increased hemorrhage volume > 33% or an absolute increase of >6 mL on follow-up CT. Poor prognosis was defined as a modified Rankin scale score of 4-6 at discharge. We performed logistic regression analysis and created receiver operating characteristic curves to determine the discrimination ability of the NAG score.

RESULTS

Patients constituted 96 men and 46 women (median age: 64 years; median NIHSS: 11), and HE was observed in 38/142 patients (27%). Higher NAG sores were associated with HE (P < .001), poor prognosis (P < .001), and in-hospital death (P < .001). The C statistic was 0.72 (95% confidence interval [CI]: 0.63-0.82) for HE, 0.67 (95% CI: 0.58-0.76) for poor prognosis, and 0.85 (95% CI: 0.74-0.95) for in-hospital death. Multivariate logistic regression analysis with known risk factors showed that NAG scale score was an independent risk factor for HE (odds ratio: 2.95; 95% CI: 1.57-5.52; P = .001).

CONCLUSION

The NAG scale showed good discrimination in our multi-institutional validation.