Predicting Hematoma Expansion Research Articles

Advances in computed tomography-based prognostic methods for intracerebral hemorrhage.

Spontaneous intracerebral hemorrhage (ICH) has high morbidity and mortality. Computed tomography (CT) plays an important role in the diagnosis, treatment, and research of cerebrovascular diseases. Non-contrast CT is widely used in the clinical diagnosis of ICH because of its high imaging speed and high sensitivity and specificity in the detection of stroke. Many markers-based CT imaging, quantitative parameters, and artificial intelligence (AI) methods based on CT are increasingly used for the prediction of hematoma expansion (HE), prognosis of ICH, and the evaluation of perihematomal edema (PHE). Therefore, we performed a comprehensive review of studies, focusing on current research evidence related to CT use for the prediction of HE and prognostic. This review discusses recent insights into, outlines current limitations, and puts forward suggestions for the challenges and directions of future research. Although at present the prognosis for ICH is not optimistic, the treatment methods remain controversial. However, identifying imaging markers that can evaluate and predict existing possible existing therapeutic targets could help to provide individualized advice for patients and achieve patient risk stratification, which is a key step in improving treatment outcomes.

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

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). HE was defined as > 6mL 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. 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. 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.

Establishment of a Scale for Predicting Early Hematoma Enlargement of Spontaneous Intracerebral Hemorrhage Based on Non-Contrast CT Signs.

This study aimed to optimize the Spontaneous intracerebral hemorrhage (sICH) early hematoma expansion prediction scoring table based on the clinical data of sICH patients to adopt appropriate clinical treatment plans and improve the prognosis of sICH patients. A total of 150 patients with sICH were enrolled, and 44 had early hematoma expansion. According to the selection and exclusion criteria, the study subjects were screened, their NCCT characteristic signs and clinical data were analyzed statistically, and the prediction score table was established. The established prediction score was applied to the follow-up study cohort to conduct a pilot study, and the t-test and ROC curve were used to evaluate its predictive ability. Statistical analysis found that initial hematoma volume, GCS score, and NCCT special signs were independent risk factors for early hematoma expansion after sICH (P 0.05). Thus, a score table was established. Subjects with ≥10 were divided into high-risk group, 6-8 comprised the medium-risk group, and ≤4 were divided into low-risk group. Among 17 patients with acute sICH, 7 developed early hematoma enlargement. The prediction accuracy was 92.41% in the low-risk group, 98.06% in the medium-risk group, and 84.61% in the high-risk group. It shows the high prediction accuracy of the prediction rating table. This study established a sICH early hematoma expansion prediction score table based on the special signs of NCCT. This table has highly sensitive and accurate.

Establishment and evaluation of a nomogram model for predicting hematoma expansion in hypertensive intracerebral hemorrhage based on clinical factors and plain CT scan signs

Hematoma expansion (HE) is an important risk factor for poor prognosis in patients with hypertensive intracerebral hemorrhage. This study aimed to establish a nomogram model for predicting HE, and evaluate the model. The clinical data and plain computed tomography (CT) scan signs of 341 patients with hypertensive intracerebral hemorrhage were retrospectively analyzed. According to the development of HE, the patients were divided into an HE group (100 cases) and a non-HE group (241 cases). The clinical data and CT scan signs of the patients in these two groups were compared. Variables that had statistically significant differences were included in the multivariate logistic regression analysis to screen for independent predictors of HE and establish a nomogram model. The discrimination, calibration, and clinical practicability of this model were evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and a decision curve analysis (DCA), respectively. Finally, the internal validation of this model was performed using the bootstrap method. The time interval from disease onset to the first CT [odds ratio (OR) =0.807, 95% confidence interval (CI): 0.665-0.979], volume of the hematoma at the first CT (OR =1.017, 95% CI: 1.001-1.033), irregular shape of the hematoma (OR =2.458, 95% CI: 1.355-4.456), swirl sign (OR =2.308, 95% CI: 1.239-4.298), and blend sign (OR =2.509, 95% CI: 1.304-4.830) were independent predictors of HE (all P<0.05). These factors were used to establish a nomogram model. The area under the ROC curve of the model was 0.762 (95% CI: 0.703-0.821). The results of the Hosmer-Lemeshow test and calibration curves showed that the predictive probabilities of the model fit the actual probabilities well. The DCA results showed that the domain probability range of the model was wide. The internal validation results showed that the C-index was 0.751, and the model's discrimination was good. The nomogram model established in this study had good discrimination, calibration, and clinical practicability. The model could serve as an intuitive and reliable guiding tool for the clinical identification of HE risk of hypertensive intracerebral hemorrhage.

Prediction of Hematoma Expansion in Patients With Intracerebral Hemorrhage Using Thromboelastography With Platelet Mapping: A Prospective Observational Study

Background and Purpose: The purpose of the study was to evaluate the usefulness of thromboelastography with platelet mapping (TEG-PM) for predicting hematoma expansion (HE) and poor functional outcome in patients with intracerebral hemorrhage (ICH).Methods: Patients with primary ICH who underwent baseline computed tomography (CT) and TEG-PM within 6 h after symptom onset were enrolled in the observational cohort study. We performed univariate and multivariate logistic regression models to assess the association of admission platelet function with HE and functional outcome. In addition, a receiver operating characteristic (ROC) curve analysis investigated the accuracy of platelet function in predicting HE. A mediation analysis was undertaken to determine causal associations among platelet function, HE, and outcome.Results: Of 142 patients, 37 (26.1%) suffered HE. Multivariate logistic regression identified arachidonic acid (AA) and adenosine diphosphate (ADP) inhibition as significant independent predictors of HE. The area under the ROC curves was 0.727 for AA inhibition and 0.721 for ADP inhibition. Optimal threshold for AA inhibition was 41.75% (75.7% sensitivity; 67.6% specificity) and ADP inhibition was 65.8% (73.0% sensitivity; 66.7% specificity). AA and ADP inhibition were also associated with worse 3-month outcomes after adjusting for age, admission Glasgow Coma Scale score, intraventricular hemorrhage, baseline hematoma volume, and hemoglobin. The mediation analysis showed that the effect of higher platelet inhibition with poor outcomes was mediated through HE.Conclusions: These findings suggest that the reduced platelet response to ADP and AA independently predict HE and poor outcome in patients with ICH. Platelet function may represent a modifiable target of ICH treatment.

Establishment of a nomogram model for predicting hematoma expansion in intracerebral hemorrhage and its multidimensional evaluation

Objective: To establish a nomogram model for hematoma expansion (HE) prediction after intracerebral hemorrhage (ICH) and evaluate its performance in a multidimensionally way. Methods: A total of 348 ICH patients who were firstly diagnosed and hospitalized in the Second Affiliated Hospital of Soochow University from January 2017 to December 2019 were collected retrospectively. There were 236 males and 112 females, and their age ranged from 18 to 94 (62.0±14.6) years. All patients were divided into HE group (n=121) or non-HE group (n=227) according to the presence or absence of HE. The clinical and imaging features were compared between the two groups. Multivariate logistic regression analysis was performed for determining the independent predicting factors for HE prediction and a Nomogram model was established by using these factors. Receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the prediction effectiveness, accuracy and clinical practicability of the model, respectively. Bootstrap method was used for internal validation. Results: There were significant differences in onset time, swirl sign, history of anticoagulants administrations, systolic blood pressure when admission, Glasgow coma scale (GCS) scores and RBC distribution width between the two groups[(1.77(1.0, 2.5) h vs 2(1, 3) h, 72 cases (59.5%) vs 94 cases (41.4%), 17 cases (14.0%) vs 15 cases (6.6%), (170.69±29.19) mmHg(1 mmHg=0.133 kPa) vs (163.84±26.07) mmHg, 11(8, 14) scores vs 14(10, 15) scores, 44.3% (41.2%, 46.8%) vs 42.4% (40.1%, 45.3%);respectively, all P<0.05]. Multivariate logistic regression analysis demonstrated that onset time (OR=0.809, 95%CI: 0.682-1.961, P=0.015), swirl sign (OR=0.562, 95%CI:0.349-0.905, P=0.018), history of anticoagulants administrations (OR=0.394, 95%CI: 0.180-1.861, P=0.020), and GCS (OR=0.881, 95%CI: 0.815-1.952, P=0.001) were the predicting factors for HE. The area under the curve (AUC) of the Nomogram model was 0.735(95%CI: 0.687-0.805), which demonstrated that the model has an ideal prediction effectiveness. The calibration curve showed that the prediction probability of HE of the model fits well with the actual probability, and with high calibration. DCA showed relatively wide range of optional threshold probability of the model (ranging from 14% to 72%), the clinical practicability of this model was high. The internal validation results showed a C-index of 0.703, indicated a good discrimination power. Conclusion: The established Nomogram model can predict the HE of ICH with good prediction effectiveness, discrimination power and with good clinical practicability, which can be capable of providing an intuitive and visual guidance tool for timely identifying ICH patients who may have HE.

A prediction of hematoma expansion in hemorrhagic patients using a novel dual-modal machine learning strategy

Objective. Hematoma expansion is closely associated with adverse functional outcomes in patients with intracerebral hemorrhage (ICH). Prediction of hematoma expansion would therefore be of great clinical significance. We therefore attempted to predict hematoma expansion using a dual-modal machine learning (ML) strategy which combines information from non-contrast computed tomography (NCCT) images and multiple clinical variables. Approach. We retrospectively identified 140 ICH patients (57 with hematoma expansion) with 5616 NCCT images of hematoma (2635 with hematoma expansion) and 10 clinical variables. The dual-modal ML strategy consists of two steps. The first step is to derive a mono-modal predictor from a deep convolutional neural network using solely NCCT images. The second step is to achieve a dual-modal predictor by combining the mono-modal predictor with 10 clinical variables to predict hematoma growth using a multi-layer perception network. Main results. For the mono-modal predictor, the best performance was merely 69.5% in accuracy with solely the NCCT images, whereas the dual-modal predictor could boost the accuracy greatly to be 86.5% by combining clinical variables. Significance. To our knowledge, this is the best performance from using ML to predict hematoma expansion. It could be potentially useful as a screening tool for high-risk patients with ICH, though further clinical tests would be necessary to show its performance on a larger cohort of patients.

Comparison of Radiomic Models Based on Different Machine Learning Methods for Predicting Intracerebral Hemorrhage Expansion.

The objective of this study was to predict hematoma expansion (HE) by radiomic models based on different machine learning methods and determine the best radiomic model through the comparison. A total of 108 patients with intracerebral hemorrhage were retrospectively evaluated. Images of baseline non-contrast computed tomography (NCCT) and follow-up NCCT scan within 24 h were retrospectively reviewed. An HE was defined as avolume increase of more than 33% or an increase greater than 12.5 mL from the volume of the baseline NCCT. Texture parameters of the baseline NCCT images were selected by the least absolute shrinkage and selection operator (LASSO) regression. We used support vector machine (SVM), decision tree (DT), conditional inference trees (CIT), random forest (RF), k‑nearest neighbors (KNN), back-propagation neural network (BPNet) and Bayes to build models. Receiver operating characteristic (ROC) analysis and decision curve analysis (DCA) was performed and compared among models. Every model had arelatively high AUC (all > 0.75), SVM and KNN had the highest AUC of 0.91. There were significant differences between SVM and CIT (Z > 2.266, p = 0.02345), KNN and CIT (Z = 2.4834, p = 0.01301), RF and CIT (Z = 2.6956, p = 0.007027), KNN and BPNet (Z = 2.0122, p = 0.0442), RF and BPNet (Z = 1.9793, p = 0.04778). There was no significant difference among SVM, DT, RF, KNN and Bayes (p> 0.05). The SVM obtained the largest net benefit when the threshold probability was less than 0.33, while KNN obtained the largest net benefit when the threshold probability was greater than 0.33. Combined with ROC and DCA, SVM and KNN performed better in all the models for predicting HE. Radiomic models based on different machine learning methods can be used to predict HE and the models generated by SVM and KNN performed best.

Are computed-tomography-based hematoma radiomics features reproducible and predictive of intracerebral hemorrhage expansion? an in vitro experiment and clinical study.

To identify reproducible hematoma radiomics features (RFs) for use in predicting hematoma expansion (HE) in patients with acute intracerebral hemorrhage (ICH). For test-retest analysis, three syringes with different volumes of blood collected at the same time (to mimic homogeneous hematoma) and a phantom (FT/HK 2000; Huake, Szechwan, China) containing three cylindrical inserts were scanned seven times within 6 h on the same CT scanner. Three additional syringes with mixed blood collected at different time points (to mimic heterogeneous hematoma) were tied together with the first three syringes as well as the phantom were scanned using modified CT acquisition parameters for intra CT analysis. A coefficient of variation below 10% served as the cutoff value for reproducibility. Finally, reproducible and potentially useful RFs were used to predict HE in 144 acute ICH patients, with the area under the receiver operating characteristic curves (AUC) used to evaluate their diagnostic performance. A total of 630 RFs including 18 first-order, 24 gray-level co-occurrence matrix (GLCM), 16 gray-level run length matrix (GLRLM), five neighborhood gray-tone difference matrix (NGTDM), 63 Laplacian of Gaussian (LoG), and 504 Wavelet features were evaluated. In the test-retest analysis, the percentages of reproducible RFs ranged from 42.54% (268/630) to 45.4% (286/630) for the three homogeneous hematoma samples and 79.05% (498/630) to 81.43% (513/630) for the phantom. In the intra-CT analysis, the percentages varied from 31.43% (198/630) to 42.38% (267/630) for the six hematoma samples and 48.89% (308/630) to 53.97% (340/630) for the phantom. In the in vitro experiment, 148 RFs were reproducible for all hematoma samples in both the test-retest and intra-CT analyses; however, only 80 were statistically different between homogeneous and heterogeneous hematoma samples. Finally, HE occurred in 25% (growth >6 ml, 36/144) to 31.94% (growth >3 ml or 33%, 46/144) of the patients. The AUCs in predicting HE ranged from 0.625 to 0.703. Only a few CT-based RFs from the in vitro hematoma were reproducible and can distinguish between homogeneous and heterogeneous hematomas. The use of RFs alone to predict HE in acute ICH showed only a moderate performance. Using an in vitro experiment and clinical validation, this study demonstrated for the first time that CT-based hematoma RFs can be used to predict HE in acute ICH; nonetheless, only a few RFs are reproducible and can be used for prediction.

Feasibility of a combined swirl and blending sign on non-contrast computed tomography for predicting early hematoma expansion after spontaneous intracerebral hemorrhage.

For predicting the hematoma expansion of spontaneous intracerebral hemorrhage, spot and swirl signs have been investigated. However, the clinical effectiveness of these signs remains debatable. These signs do not consider the peripheral hypodense lesions, which may imply a greater chance of ongoing bleedings. We proposed a new combined swirl and blending sign and evaluated its clinical usefulness in predicting hematoma expansion in non-contrast computed tomography settings. A total of 201 patients who were diagnosed with spontaneous intracerebral hemorrhage were enrolled. Their clinical and radiologic data were retrospectively reviewed. Patients were classified into hematoma expansion (N.=51) and nonexpansion groups (N.=150), and multivariable logistic regression analyses were performed to identify the factors associated with hematoma expansion. In the hematoma expansion group, an average of 20 mL of volume increase was noted. In multivariate analyses, several factors, including higher systolic blood pressure (P=0.026), larger initial hematoma volume (0.002), spot sign (0.019) and combined swirl and blending sign (<0.001), were identified as reliable predictors of hematoma expansion. A swirl (P=0.396) or blending sign (P=0.124) alone was not identified as a significant predictor of hematoma growth. The sensitivity, specificity, and positive and negative predictive values of the combined swirl and blending sign were 31%, 97%, 80%, and 81%, respectively. A newly defined "combined swirl and blending sign" on non-contrast computed tomography was positively associated with an increased risk of hematoma expansion of spontaneous intracerebral hemorrhage and could be regarded as a reliable predictor in non-contrast computed tomography settings.

Early spot sign is associated with functional outcomes in primary intracerebral hemorrhage survivors

BackgroundThe computed tomography angiography (CTA) spot sign is a validated predictor of hematoma expansion and 30-day mortality in intracerebral hemorrhage (ICH). However, whether the spot sign predicts worse functional outcomes among ICH survivors remains unclear. This study investigated the frequency of the spot sign and its association with functional outcomes and length of hospital stay among ICH survivors.MethodsThis was a retrospective analysis of consecutive patients with primary ICH who received CTA within 24 h from presentation to admission to the emergency department of a single medical center between January 2007 and December 2017. Patients who died before discharge and those referred from other hospitals were excluded. CTAs with motion artifacts were excluded from the analysis. The presence of a spot sign was examined by an experienced neuroradiologist. Functional outcomes were determined based on the modified Rankin Scale (mRS) score and Barthel Index (BI). Severe dependency in activities of daily living (ADL) was defined as BI of ≤60 and severe disability as an mRS score of ≥4. Odds ratio (OR) and multiple linear regression were used as measures of association.ResultsIn total, 66 patients met the inclusion criteria, of whom 9 (13.64%) were positive for a spot sign. No significant differences were observed in baseline characteristics between patients with and without a spot sign. Patients with a spot sign tended to be severely dependent in ADL at discharge (66.67% vs 41.07%; OR = 2.87; p = 0.15) and were more likely to require ICH-related surgery (66.67% vs 24.56%; OR = 6.14; p = 0.01). In multiple linear regression, patients with a higher spot sign score had a significantly longer hospital stay (coefficient = 9.57; 95% CI = 2.11–17.03; p = 0.013).ConclusionsThe presence of a spot sign is a common finding and is associated with longer hospital stay and possibly worse functional outcomes in ICH survivors.

Abstract P427: Use of Machine Learning to Determine Predictors of Intracerebral Hemorrhage Expansion

Background: Intracerebral hemorrhage (ICH) constitutes upto 40% mortality in first 30 days. Early identification of predictors of hematoma expansion (HE) may improve efforts to prevent its occurrence and improve clinical outcome. Methods: We identified patients with ICH and follow-up imaging. HE was defined as a combination of absolute volume increase of 6cc, new IVH, or proportional increase of 33% in our dataset on 72h follow up scan. Presence of IVH was also included in hematoma expansion. We evaluated the predictive ability of 3 machine learning classifiers, Random Forest, Support Vector Machine (with RBF kernel) and Logistic regression (with L1 regularization). The evaluation was done using a K-fold stratified cross validation to avoid overfitting. K was selected to be the number of subjects with HE. The features employed by classifiers were entirely based on the baseline imaging: Hematoma volume, Systolic BP, Diastolic BP, Black hole signs, Island signs, Blend signs, Fluid level, Swirl signs, Spot signs. Results: Our dataset comprised of 91 patients (n=21 HE, n=70 no HE). According to the area under the ROC (AUC), the two top performing classifiers were Support Vector Machine (AUC=0.66 CI 0.50-0.79) and Logistic Regression (AUC=0.64 CI 0.49-0.80). The statistical significance of the prediction is confirmed by the Mann-Whitney U test, p=0.01 and p=0.04 respectively. Random Forest did not reach statistical significance. Finally, we evaluated what were the highest and lowest weighted features across the cross-validation with Logistic Regression. The 3 top features were: presence of black hole and island signs and the systolic blood pressure. The 3 least useful features were: presence of spot and swirl signs and hematoma volume. Conclusion: Using our cohort, we developed a machine learning algorithm that predicts hematoma expansion using imaging features and blood pressure. MBL provided better sensitivity of these imaging markers compared with previous studies.

Radiomics for intracerebral hemorrhage: are all small hematomas benign?

We hypothesized that not all small hematomas are benign and that radiomics could predict hematoma expansion (HE) and short-term outcomes in small hematomas. 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. 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). 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. Radiomics can be used as a supplement to conventional medical imaging, improving clinical decision-making and facilitating personalized treatment in small ICH.

Prediction of hematoma expansion in spontaneous intracerebral hemorrhage: Our institutional experience

BackgroundSpontaneous intracerebral hemorrhage (sICH) is a disease process with high morbidity and mortality. In particular, hematoma expansion (HE) is a feared complication of sICH. With 15–40% of patients experiencing HE, it has become increasingly important to predict which sICH will remain stable and which will expand. ObjectiveWith new treatment options being developed, it is becoming increasingly important to be able to predict which hemorrhages are at high versus low risk for expansion. The authors of this study hope to reexamine variables associated with hematoma expansion in hopes of generating newer data on risk factors for expansion. MethodsA retrospective analysis identified 334 patients who presented with sICH. The primary outcome was HE on follow up head CT. HE was defined as a greater than 33% increase or an absolute increase in 6 mL or more in overall volume between the two sets of CT images. Analysis was performed using unpaired t-test, Chi-square, and Fisher’s exact tests, as appropriate. ResultsOf the 334 patients, 247 (74.0%) did not experience an expansion of their ICH while 87 (26.0%) did. Multivariable logistic regression was performed demonstrating ICH score of 3 or greater (4.76 (95% CI 2.60–8.72, p < 0.001) , cortical location of the sICH (1.77 (95% CI 1.03–3.04, p = 0.038), and presence of a fluid level (6.46 (95% CI 2.28–18.3, p < 0.001) as significant predictors of HE. ConclusionsOur study found that fluid–fluid levels on non-contrast CT, an ICH score 3 or greater, and lobar sICH were all more likely to expand.

Different criteria for defining "spot sign" in intracerebral hemorrhage show different abilities to predict hematoma expansion and clinical outcomes: a systematic review and meta-analysis.

The "spot sign" is a well-known radiological marker used for predicting hematoma expansion and clinical outcomes in patients with intracerebral hemorrhage (ICH). We performed a meta-analysis to assess the predictive accuracy of spot sign, depending on the criteria used to identify them.We conducted a systematic review of clinical studies that clearly stated their definition of spot sign and that were indexed in the Cochrane Library, MEDLINE, EMBASE, and the China National Knowledge Infrastructure databases. We collected data on computed tomography (CT) parameters, spot sign diagnostic criteria, hematoma expansion, and clinical outcomes.Based on the eligibility criteria, we included 17 studies in this systematic review. CT imaging modality, type, time from symptom onset to CT, time from contrast infusion to scan, slice thickness, tube current, and tube electric discharge showed variation across studies. Three different definitions of the spot sign were applied: (1) a hyperdense spot within the hematoma; (2) one or more focal areas/regions of contrast pooling of any size and morphology that occurred within a hemorrhage, were discontinuous from the normal or abnormal vasculature adjacent to the hemorrhage, and showed an attenuation rate ≥ 120 UH; or (3) serpiginous or spot-like contrast density on CTA images that occurred within the hematoma margin, showed twice the density of the hematoma background, and did not contact vessels outside the hematoma. Three definitions for the spot sign were identified, all of which were associated with hematoma expansion, mortality, and unfavorable functional outcome. Subgroup analyses based on these definitions showed that spot sign identified using the second definition were more likely to be associated with hematoma expansion (OR 18.31, 95% CI 9.11-36.8) and unfavorable functional outcomes (OR 8.78, 95% CI 3.24-23.79), while those identified using the third definition were associated with increased risk of mortality (OR 6.88, 95% CI 1.43-33.13).Clinical studies identify spot sign using different CT protocols and criteria. These differences affect the ability of spot sign to predict hematoma expansion and clinical outcomes in ICH patients.

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.

Dual-Energy CT Angiography Improves Accuracy of Spot Sign for Predicting Hematoma Expansion in Intracerebral Hemorrhage.

Background and Purpose Spot sign (SS) on computed tomography angiography (CTA) is associated with hematoma expansion (HE) and poor outcome after intracerebral hemorrhage (ICH). However, its predictive performance varies across studies, possibly because differentiating hyperdense hemorrhage from contrast media is difficult. We investigated whether dual-energy-CTA (DE-CTA), which can separate hemorrhage from iodinated contrast, improves the diagnostic accuracy of SS for predicting HE. Methods Primary ICH patients undergoing DE-CTA (both arterial as well as delayed venous phase) and follow-up computed tomography were prospectively included between 2014 and 2019. SS was assessed on both arterial and delayed phase images of the different DE-CTA datasets, i.e., conventional-like mixed images, iodine images, and fusion images. Diagnostic accuracy of SS for prediction of HE was determined on all datasets. The association between SS and HE, and between SS and poor outcome (modified Rankin Scale at 3 months ≥3) was assessed with multivariable logistic regression, using the dataset with highest diagnostic accuracy. Results Of 139 included patients, 47 showed HE (33.8%). Sensitivity of SS for HE was 32% (accuracy 0.72) on conventional-like mixed arterial images which increased to 76% (accuracy 0.80) on delayed fusion images. Presence of SS on delayed fusion images was independently associated with HE (odds ratio [OR], 17.5; 95% confidence interval [CI], 6.14 to 49.82) and poor outcome (OR, 3.84; 95% CI, 1.16 to 12.73). Conclusions Presence of SS on DE-CTA, in particular on delayed phase fusion images, demonstrates higher diagnostic performance in predicting HE compared to conventional-like mixed imaging, and it is associated with poor outcome.

In spontaneous intracerebral hematoma patients, prediction of the hematoma expansion risk and mortality risk using radiological and clinical markers and a newly developed scale

ABSTRACT Objective: In patients with spontaneous intracerebral hematoma (ICH), early-stage hematoma expansion has been associated with poor prognosis in literature. This study aimed to develop predictive parameter(s) as well as a new scale to define hematoma expansion and short-term prognosis in patients with ICH. Methods: In 46 patients with ICH, Glasgow Coma Scale (GCS) scores, non-contrast CT (NCCT) markers (hematoma volume on admission and follow-up, hypodensity, intraventricular hemorrhage, blend and island sign, BAT score), and modified Rankin Scale scores were evaluated for predicting the hematoma expansion risk and mortality risk. Furthermore, a newly developed scale called the ‘HEMRICH scale’ was constituted using the GCS score, hematoma volumes, and some NCCT markers. Results: Roc-Curve and Logistic Regression test results revealed that GCS score, initial hematoma volume value, hypodensity, intraventricular haemorrhage, BAT score, and HEMRICH scale score could be the best markers in predicting hematoma expansion risk whereas GCS score, intraventricular haemorrhage, BAT score, hematoma expansion, and HEMRICH scale score could be the best markers in predicting mortality risk (p = 0.01). Moreover, Factor analysis and Reliability test results showed that HEMRICH scale score could predict both hematoma expansion and mortality risks validly (Kaiser-Meyer-Olkin test value = 0.729) and reliably (Cronbach’s alpha = 0.564). Conclusion: It was concluded that the GCS score, intraventricular haemorrhage, and BAT score could predict both hematoma expansion risk and mortality risk in the early stage in patients with ICH. Furthermore, it was suggested that the newly produced HEMRICH scale could be a valid and reliable scale for predicting both hematoma expansion and mortality risk.

Hypodensities within Hematoma is Time-Dependent and Predicts Outcome after Spontaneous Intracerebral Hemorrhage.

Non-contrast CT (NCCT) brain imaging biomarkers of hematoma expansion in intracerebral hemorrhage (ICH) has gained relevance in recent times. Though intra-hematoma hypodensities (IHH) can predict hematoma expansion and outcome, it is postulated to be time-dependent. To assess the differential prevalence of IHH in spontaneous ICH over time and assess its predictive valve in early hematoma expansion and functional outcome at 3 months. Patients with ICH within 48 h of stroke onset were included. Baseline clinical and demographic data were collected. Baseline NCCT brain was analyzed for hematoma volume, characterization of IHH, with 24-hours follow-up NCCT hematoma volume calculated for identification of hematoma expansion. Poor functional outcome was defined as mRS ≥3. Around 92 subjects were included in the study. IHH was found in 40%. Prevalence of IHH was higher in those with baseline NCCT performed within 3 h of symptom onset compared to those beyond 3 h (71% vs 29%, P = 0.002). The hematoma expansion was more common in patients with IHH compared to those without (54% vs 29%; P = 0.02). Multivariate analysis revealed the presence of IHH (rather than pattern or number) to be strongly associated with poor functional outcome at 3 months (OR 3.86; 95% CI: 1.11-13.42, P = 0.03). There is a decreasing prevalence of IHH as the time from symptom onset to NCCT increases. Nevertheless, its presence is significantly associated with hematoma expansion and predicted poor short-term functional outcomes in spontaneous ICH.

Intracerebral Hemorrhage Hematoma Expansion Prediction with Deep Learning

Background: Hematoma expansion (HE) is associated with poor clinical outcomes following intracerebral hemorrhage (IcH). Existing predictors of HE from non-contrast computed tomography (NCCT) have low sensitivity and high inter-observer variability. Availability of an objective, standardized method to predict HE remains an unmet need. Methods: This multicenter observational cohort study analyzed a retrospective dataset of 2350 patients (December 2011 to June 2018, NCCT only, 86 centers), and a prospective dataset of 460 patients (March 2018 to February 2019, NCCT plus clinical data, 28 centers) with acute IcH . Prediction of HE, defined as a hematoma growth of > 6ml within 48 hours was the primary outcome of the study. A deep learning system (DLS) was developed and validated to autonomously predict HE based on the NCCT images using retrospectively collected data. A multivariate logistic regression model and a five-point score based on clinical variables and DLS prediction score were then developed using prospectively collected data. Findings: The DLS, using only NCCT, achieved HE prediction AUC of 0·783 (95% CI, 0·693-0·871) on the prospective validation dataset. Multivariate analysis of clinical variables indicated a higher risk of HE in patients with higher baseline NIHSS (OR: 4·37(1·56-12·25)), shorter onset-to-NCCT time (OR: 2·92(1·13-7·56)), and lack of antihypertensive therapy history (OR: 2·61 (1·05-6·53)) . Inclusion of these clinical variables along with DLS prediction, further improved the HE prediction accuracy, achieving an AUC of 0·812 (0·732-0·891) which was higher than all the previous methods. Finally, an easy-to-use five-point score was developed, which achieved an AUC of 0·789 (0·707-0·871). Interpretation: Deep learning systems could provide an automated, objective, multicenter generalizable, and observer bias-free solution for HE prediction from NCCT images. Inclusion of clinical factors may further improve the prediction accuracy and the system can be used to identify patients at risk of HE leading to a personalized treatment planning. Funding: Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences, Beijing Municipal Committee of Science and Technology, Ministry of Science and Technology of the People’s Republic of China, National Natural Science Foundation of China, and Beijing Nova Program. Declaration of Interest: None to declare. Ethical Approval: This study was approved by the Institutional Review Board of Beijing TianTan hospital which covers all the hospitals contributing data to this study as part of the Chinese Stroke Center Alliance