Accuracy of imaging markers on noncontrast computed tomography in predicting intracerebral hemorrhage expansion

Hematoma expansion prediction in intracerebral hemorrhage patients by using synthesized CT images in an end-to-end deep learning framework

Spontaneous intracerebral hemorrhage (ICH) is a type of stroke less prevalent than ischemic stroke but associated with high mortality rates. Hematoma expansion (HE) is an increase in the bleeding that affects 30%-38% of hemorrhagic stroke patients. It is observed within 24 h of onset and associated with patient worsening. Clinically it is relevant to detect the patients that will develop HE from their initial computed tomography (CT) scans which could improve patient management and treatment decisions. However, this is a significant challenge due to the predictive nature of the task and its low prevalence, which hinders the availability of large datasets with the required longitudinal information. In this work, we present an end-to-end deep learning framework capable of predicting which cases will exhibit HE using only the initial basal image. We introduce a deep learning framework based on the 2D EfficientNet B0 model to predict the occurrence of HE using initial non-contrasted CT scans and their corresponding lesion annotation as priors. We used an in-house acquired dataset of 122 ICH patients, including 35 HE cases, containing longitudinal CT scans with manual lesion annotations in both basal and follow-up (obtained within 24 h after the basal scan). Experiments were conducted using a 5-fold cross-validation strategy. We addressed the limited data problem by incorporating synthetic images into the training process. To the best of our knowledge, our approach is novel in the field of HE prediction, being the first to use image synthesis to enhance results. We studied different scenarios such as training only with the original scans, using standard image augmentation techniques, and using synthetic image generation. The best performance was achieved by adding five generated versions of each image, along with standard data augmentation, during the training process. This significantly improved (p=0.0003) the performance obtained with our baseline model using directly the original CT scans from an Accuracy of 0.56 to 0.84, F1-Score of 0.53 to 0.82, Sensitivity of 0.51 to 0.77, and Specificity of 0.60 to 0.91, respectively. The proposed approach shows promising results in predicting HE, especially with the inclusion of synthetically generated images. The obtained results highlight the significance of this research direction, which has the potential to improve the clinical management of patients with hemorrhagic stroke. The code is available at: https://github.com/NIC-VICOROB/HE-prediction-SynthCT.

Combining Non-Contrast CT Signs With Onset-to-Imaging Time to Predict the Evolution of Intracerebral Hemorrhage

OBJECTIVE

This study aimed to determine the predictive performance of non-contrast CT (NCCT) signs for hemorrhagic growth after intracerebral hemorrhage (ICH) when stratified by onset-to-imaging time (OIT).

MATERIALS AND METHODS

1488 supratentorial ICH within 6 h of onset were consecutively recruited from six centers between January 2018 and August 2022. NCCT signs were classified according to density (hypodensities, swirl sign, black hole sign, blend sign, fluid level, and heterogeneous density) and shape (island sign, satellite sign, and irregular shape) features. Multivariable logistic regression was used to evaluate the association between NCCT signs and three types of hemorrhagic growth: hematoma expansion (HE), intraventricular hemorrhage growth (IVHG), and revised HE (RHE). The performance of the NCCT signs was evaluated using the positive predictive value (PPV) stratified by OIT.

RESULTS

Multivariable analysis showed that hypodensities were an independent predictor of HE (adjusted odds ratio [95% confidence interval] of 7.99 [4.87-13.40]), IVHG (3.64 [2.15-6.24]), and RHE (7.90 [4.93-12.90]). Similarly, OIT (for a 1-h increase) was an independent inverse predictor of HE (0.59 [0.52-0.66]), IVHG (0.72 [0.64-0.81]), and RHE (0.61 [0.54-0.67]). Blend and island signs were independently associated with HE and RHE (10.60 [7.36-15.30] and 10.10 [7.10-14.60], respectively, for the blend sign and 2.75 [1.64-4.67] and 2.62 [1.60-4.30], respectively, for the island sign). Hypodensities demonstrated low PPVs of 0.41 (110/269) or lower for IVHG when stratified by OIT. When OIT was ≤ 2 h, the PPVs of hypodensities, blend sign, and island sign for RHE were 0.80 (215/269), 0.90 (142/157), and 0.83 (103/124), respectively.

CONCLUSION

Hypodensities, blend sign, and island sign were the best NCCT predictors of RHE when OIT was ≤ 2 h. NCCT signs may assist in earlier recognition of the risk of hemorrhagic growth and guide early intervention to prevent neurological deterioration resulting from hemorrhagic growth.

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

AIM

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

MATERIALS AND METHODS

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

RESULTS

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

CONCLUSION

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

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

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

Computed tomography and clinical parameters predict intracerebral hemorrhage expansion

This study aimed to evaluate the association of imaging signs, and to establish a predictive model through selecting highly relevant imaging signs in combination with clinical parameters for hematoma expansion.Intracerebral Hemorrhage (ICH) patients who received 2 consecutive noncontrast computed tomography scans were examined and recruited through January 2014 to December 2020. Demographic information and clinical characteristics were collected. Two experienced radiologists reviewed baseline noncontrast computed tomography images to assess the imaging characteristics. Correlation analysis was analyzed with Pearson and Spearman correlation tests. The association between clinical and imaging predictors with hematoma expansion was evaluated in multivariate models. Receiver operating characteristic (ROC) curve analysis was adopted to evaluate predictive performance.A total of 232 ICH patients, with mean age of 59.73 years, and 31% of female were included, among which, 32 patients occurred with hematoma expansion. For sex, ICH density, low density in hematoma, the midline shift, and Glasgow Coma Scale score, liquid level, H-tra, edema Cor, H Volume, time from onset to examination, there were significant differences between the 2 groups. As for imaging signs, only blend sign showed a significant difference, that patients with blend sign had a higher incidence of ICH expansion. The logistic analysis found that radiation attenuation, liquid level, the midline shift, Glasgow Coma Scale score, history of ischemic stroke, and smoking could predict the occurrence of ICH expansion.In summary, the model combined radiological characteristics with clinical indicators showed considerable predictive performance. Further validation is needed to verify the findings and help transfer to clinical practice.

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.

Noncontrast Computed Tomography Markers of Cerebral Hemorrhage Expansion: Diagnostic Accuracy Meta-Analysis

BACKGROUND AND PURPOSE

Assess the diagnostic accuracy of noncontrast computed tomography (NCCT) markers of hematoma expansion in patients with primary intracerebral hemorrhage.

METHODS

We performed a meta-analysis of observational studies and randomized controlled trials with available data for calculation of sensitivity and specificity of NCCT markers for hematoma expansion (absolute growth >6 or 12.5 mL and/or relative growth >33%). The following NCCT markers were analyzed: irregular shape, island sign (shape-related features); hypodensity, heterogeneous density, blend sign, black hole sign, and swirl sign (density-related features). Pooled accuracy values for each marker were derived from hierarchical logistic regression models.

RESULTS

A total of 10,363 subjects from 23 eligible studies were included. Significant risk of bias of included studies was noted. Hematoma expansion frequency ranged from 7% to 40%, mean intracerebral hemorrhage volume from 9 to 27.8 ml, presence of NCCT markers from 9% (island sign) to 82% (irregular shape). Among shape features, sensitivity ranged from 0.32 (95%CI = 0.20-0.47) for island sign to 0.68 (95%CI = 0.57-0.77) for irregular shape, specificity ranged from 0.47 (95%CI = 0.36-0.59) for irregular shape to 0.92 (95%CI = 0.85-0.96) for island sign; among density features sensitivity ranged from 0.28 (95%CI = 0.21-0.35) for black hole sign to 0.63 (95%CI = 0.44-0.78) for hypodensity, specificity ranged from 0.65 (95%CI = 0.56-0.73) for heterogeneous density to 0.89 (95%CI = 0.85-0.92) for blend sign.

CONCLUSION

Diagnostic accuracy of NCCT markers remains suboptimal for implementation in clinical trials although density features performed better than shape-related features. This analysis may help in better tailoring patients' selection for hematoma expansion targeted trials.

Size-Related Differences in Computed Tomography Markers of Hematoma Expansion in Acute Intracerebral Hemorrhage

BACKGROUND

Noncontrast computed tomography (NCCT) markers for hematoma expansion (HE) in intracerebral hemorrhage (ICH) are difficult to be found in small ICHs, of which can also expand. We aimed to investigate whether there were size-related differences in the prevalence of NCCT markers and their association with HE.

METHODS

This retrospective analysis of prospectively collected stroke registry included 267 consecutive patients with ICH who underwent baseline NCCT within 12 h of onset. Qualitative NCCT markers, including heterogeneous density and irregular shape, were assessed. Hematoma density, defined as mean Hounsfield unit of hematoma, and hematoma volume were measured by semiautomated planimetry. Hematoma volume was categorized as small (≤ 10 ml) and large (> 10 ml). Associations of NCCT markers with HE were analyzed using multivariable logistic regression analyses. The model performances of NCCT markers and hematoma density were compared using receiver operating characteristic curves.

RESULTS

Hematoma expansion occurred in 29.9% of small ICHs and 35.5% of large ICHs. Qualitative NCCT markers were less frequently observed in small ICHs. Heterogeneous density, irregular shape, and hematoma density were associated with HE in small ICH (adjusted odds ratios [95% confidence interval] 3.94 [1.50-10.81], 4.23 [1.73-10.81], and 0.72 [0.60-0.84], respectively), and hematoma density was also related to HE in large ICH (0.84 [0.73-0.97). The model performance was significantly improved in small ICHs when hematoma density was added to the baseline model (DeLong's test, p = 0.02).

CONCLUSIONS

The prevalence of NCCT markers and their association with HE differed according to hematoma volume. Quantitative hematoma density was associated with HE, regardless of hematoma size.

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.

IL-33 as a Novel Serum Prognostic Marker of Intracerebral Hemorrhage

Objective

Interleukin 33 (IL-33) is a key cytokine involved in inflammation and oxidative stress. The significance of serum IL-33 levels on the prognosis of patients with intracerebral hemorrhage (ICH) has not been well studied. The purpose of this study is to determine whether there is a relationship between the serum IL-33 level and the prognosis of patients with ICH upon admission.

Methods

A total of 402 patients with confirmed ICH were included in this study. Their demographic data, medical history, laboratory data, imaging data, and clinical scores on admission were collected. At the same time, enzyme-linked immunoassay (ELISA) was used to detect the serum IL-33 levels of patients. The prognosis of patients was evaluated by mRS scale after 3 months, and mRS > 2 was defined as poor prognosis.

Results

Among 402 patients with ICH, the number of patients with good prognosis and poor prognosis after 3 months was 148 and 254, respectively. Compared with the ICH group with poor prognosis, the ICH group with good prognosis had lower baseline NHISS scores (p = 0.039) and hematoma volume (p = 0.025) and higher GCS scores (p < 0.001) and serum IL-33 levels (p < 0.001). The results of linear correlation analysis showed that serum IL-33 levels were significantly negatively correlated with baseline NHISS scores (r = −0.224, p = 0.033) and hematoma volume (r = −0.253, p = 0.046) but were significantly positively correlated with baseline GCS scores (r = 0.296, p = 0.020). The receiver operating characteristic curve (ROC) analysis showed that the sensitivity and specificity of serum IL-33 level in evaluating the prognosis of ICH were 72.1% and 74.3%, respectively. A cut-off value of serum IL-33 level < 109.3 pg/mL may indicate a poor prognosis for ICH.

Conclusions

Serum IL-33 level on admission may be a prognostic indicator of ICH, and its underlying mechanism needs further study.

Is the CT Blend Sign Composed of Two Parts of Blood with Different Age?

BACKGROUND

Blend sign on initial computed tomography (CT) is associated with poor outcome in patients with intracerebral hemorrhage (ICH). However, the mechanisms underlying the blend sign formation are poorly understood. The present study aimed to explore the possible mechanism of the CT blend sign in patients with ICH.

METHODS

Seventy healthy rabbits were selected to prepare an ICH model. The animals were assigned to a whole blood group + whole blood group (ww group, 50 rabbits), a whole blood + plasma group (wp group, 10 rabbits) or a whole blood + serum group (ws group, 10 rabbits). The animals of the ww group were allocated to five subgroups based on the interval between the first infusion of blood and the second one. The subgroups included ww 1 h group (with an interval of 1 h), ww 2 h group, ww 3 h group, ww 4 h group and ww 5 h group. The rabbits from each group received first infusion of 0.3 mL of whole blood into the basal ganglia area to form a hematoma. Then, they received a second infusion of the same amount of whole blood, plasma or serum into the brain to form another hematoma adjacent to the first one.

RESULTS

A hematoma with two densities on brain CT could be formed in each group after a second infusion of blood into the brain. A significant difference in CT attenuation values was observed between the hyperattenuation and the hypoattenuation in all the groups. However, only the morphological features of the hematoma in the ww group was in accordance with the CT blend sign observed in humans. The CT attenuation values in the hypodensity area of the ww 4 h group or the ww 5 h group were decreased compared with the ww 1 h group to the ww 3 h group.

CONCLUSIONS

The CT blend sign observed in humans might be composed of two parts of blood with different ages. The hypodense area might be blood with older age and the hyperdense area might be new bleeding.

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

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.