Computed Tomographic Black Hole Sign Predicts Postoperative Rehemorrhage in Patients with Spontaneous Intracranial Hemorrhage Following Stereotactic Minimally Invasive Surgery

Predicting postoperative rehemorrhage in hypertensive intracerebral hemorrhage using noncontrast CT radiomics and clinical data with an interpretable machine learning approach

In hypertensive intracerebral hemorrhage (HICH) patients, while emergency surgeries effectively reduce intracranial pressure and hematoma volume, their significant risk of causing postoperative rehemorrhage necessitates early detection and management to improve patient prognosis. This study sought to develop and validate machine learning (ML) models leveraging clinical data and noncontrast CT radiomics to pinpoint patients at risk of postoperative rehemorrhage, equipping clinicians with an early detection tool for prompt intervention. The study conducted a retrospective analysis on 609 HICH patients, dividing them into training and external verification cohorts. These patients were categorized into groups with and without postoperative rehemorrhage. Radiomics features from noncontrast CT images were extracted, standardized, and employed to create several ML models. These models underwent internal validation using both radiomics and clinical data, with the best model's feature significance assessed via the Shapley additive explanations (SHAP) method, then externally validated. In the study of 609 patients, postoperative rehemorrhage rates were similar in the training (18.8%, 80/426) and external verification (17.5%, 32/183) cohorts. Six significant noncontrast CT radiomics features were identified, with the support vector machine (SVM) model outperforming others in both internal and external validations. SHAP analysis highlighted five critical predictors of postoperative rehemorrhage risk, encompassing three radiomics features from noncontrast CT and two clinical data indicators. This study highlights the effectiveness of an SVM model combining radiomics features from noncontrast CT and clinical parameters in predicting postoperative rehemorrhage among HICH patients. This approach enables timely and effective interventions, thereby improving patient outcomes.

Research advances in imaging markers for predicting hematoma expansion in intracerebral hemorrhage: a narrative review

Introduction

Stroke is a major global health concern and is ranked as the second leading cause of death worldwide, with the third highest incidence of disability. Intracerebral hemorrhage (ICH) is a devastating form of stroke that is responsible for a significant proportion of stroke-related morbidity and mortality worldwide. Hematoma expansion (HE), which occurs in up to one-third of ICH patients, is a strong predictor of poor prognosis and can be potentially preventable if high-risk patients are identified early. In this review, we provide a comprehensive summary of previous research in this area and highlight the potential use of imaging markers for future research studies.

Recent advances

Imaging markers have been developed in recent years to aid in the early detection of HE and guide clinical decision-making. These markers have been found to be effective in predicting HE in ICH patients and include specific manifestations on Computed Tomography (CT) and CT Angiography (CTA), such as the spot sign, leakage sign, spot-tail sign, island sign, satellite sign, iodine sign, blend sign, swirl sign, black hole sign, and hypodensities. The use of imaging markers holds great promise for improving the management and outcomes of ICH patients.

Conclusion

The management of ICH presents a significant challenge, and identifying high-risk patients for HE is crucial to improving outcomes. The use of imaging markers for HE prediction can aid in the rapid identification of such patients and may serve as potential targets for anti-HE therapies in the acute phase of ICH. Therefore, further research is needed to establish the reliability and validity of these markers in identifying high-risk patients and guiding appropriate treatment decisions.

Irregular-Shaped Hematoma Predicts Postoperative Rehemorrhage After Stereotactic Minimally Invasive Surgery for Intracerebral Hemorrhage

Background and Purpose

Minimally invasive surgery (MIS) is performed to treat patients with intracerebral hemorrhage (ICH) with favorable results. However, postoperative rehemorrhage is a significant risk. The present study retrospectively analyzed the association of irregular-shaped hematoma with postoperative rehemorrhage following stereotactic MIS (sMIS).

Methods

We enrolled 548 patients with spontaneous ICH who underwent sMIS. Based on the hematoma shape, the patients were assigned to the regular-shaped hematoma group (RSH group; 300 patients) or irregular-shaped hematoma group (ISH group; 248 patients). Logistic regression analysis was performed to identify the predictors of postoperative rehemorrhage after sMIS for ICH evacuation. The functional outcome was assessed using the modified ranking scale (mRS) score at discharge. A receiver operating characteristic (ROC) curve was used to confirm the results.

Results

Among 548 patients with ICH who underwent sMIS, 116 developed postoperative rehemorrhage. Postoperative rehemorrhage occurred in 30.65% of patients with ISH and 13.30% with RSH (P < 0.01), with a significant difference between the ISH and RSH groups. Among 116 patients with postoperative rehemorrhage, 76 (65.52%) showed ISH on CT scan. In 432 patients without postoperative rehemorrhage, only 39.81% displayed ISH. The logistic regression analysis demonstrated that ISH could independently predict postoperative rehemorrhage. The sensitivity, specificity, positive predictive value, and negative predicative value were 0.655, 0.398, 0.655, and 0.602, respectively. The ROC analysis confirmed the value of ISH in predicting postoperative rehemorrhage with an area under the curve of 0.629.

Conclusions

Irregular-shaped hematoma was an independent predictor of postoperative rehemorrhage after sMIS.

Association of Satellite Sign with Postoperative Rebleeding in Patients Undergoing Stereotactic Minimally Invasive Surgery for Hypertensive Intracerebral Haemorrhage

There are few studies regarding imaging markers for predicting postoperative rebleeding after stereotactic minimally invasive surgery (MIS) for hypertensive intracerebral haemorrhage (ICH), and little is known about the relationship between satellite sign on computed tomography (CT) scans and postoperative rebleeding after MIS. This study aimed to determine the value of the CT satellite sign in predicting postoperative rebleeding in patients with hypertensive ICH who undergo stereotactic MIS. We retrospectively examined and analysed 105 patients with hypertensive ICH who underwent standard stereotactic MIS for hematoma evacuation within 72 h following admission. Postoperative rebleeding occurred in 14 of 65 (21.5%) patients with the satellite sign on baseline CT, and in 5 of the 40 (12.5%) patients without the satellite sign. This difference was statistically significant. Positive and negative values of the satellite sign for predicting postoperative rebleeding were 21.5% and 87.5%, respectively. Multivariate logistic regression analysis verified that baseline ICH volume and intraventricular rupture were independent predictors of postoperative rebleeding. In conclusion, the satellite sign on baseline CT scans may not predict postoperative rebleeding following stereotactic MIS for hypertensive ICH.

The Effect of Preoperative Antiplatelet Therapy on Early Postoperative Rehemorrhage and Outcomes in Patients With Spontaneous Intracranial Hematoma

Background and Purpose

The effect of antiplatelet therapy (APT) on early postoperative rehemorrhage and outcomes of patients with spontaneous intracerebral hemorrhage (ICH) is still unclear. This study is to evaluate the effect of preoperative APT on early postoperative rehemorrhage and outcomes in ICH patients.

Methods

This was a multicenter cohort study. ICH patients undergoing surgery were divided into APT group and no antiplatelet therapy (nAPT) group according to whether patients received APT or not. Chi-square test, t-test, and Mann–Whitney U test were used to compare the differences in variables, postoperative rehematoma, and outcomes between groups. Multivariate logistics regression analysis was used to correct for confounding variables, which were different in group comparison.

Results

One hundred fifty ICH patients undergoing surgical treatment were consecutively included in this study. Thirty five (23.33%) people were included in the APT group, while 115 (76.67%) people were included in the nAPT group. The incidence of early postoperative rehemorrhage in the APT group was significantly higher than that in the nAPT group (25.7% VS 10.4%, p = 0.047 < 0.05). After adjustment for age, ischemic stroke history, and ventricular hematoma, preoperative APT had no significant effect on early postoperative rehemorrhage (p = 0.067). There was no statistical difference between the two groups in early poorer outcomes (p = 0.222) at 14 days after surgery. After adjustment for age, ischemic stroke history, and ventricular hematoma, preoperative APT also had no significant effect on early poorer modified Rankin Scale (mRS) (p = 0.072).

Conclusion

In conclusion, preoperative APT appears to be safe and have no significant effect on early postoperative rehematoma and outcomes in ICH patients.

The initial CT blend sign is not associated with poor patient outcomes after stereotactic minimally invasive surgery

Background

The initial CT blend sign is an imaging marker that has been used to predict haematoma expansion and poor outcomes in patients with small-volume intracerebral haemorrhage (ICH). However, the association of the blend sign with the outcomes of patients undergoing surgery remains unclear. The present study aimed to retrospectively evaluate the influence of the initial CT blend sign on short-term outcomes in patients with hypertensive ICH after stereotactic minimally invasive surgery (sMIS).

Methods

We enrolled 242 patients with spontaneous ICH. The patients were assigned to the blend sign group (91 patients) or non-blend sign (control) group (151 patients) based on the initial CT features. The NIHSS, GCS and mRS were used to assess the effects of sMIS. The rates of severe pulmonary infection and cardiac complications were also compared between the two groups.

Results

Statistically significant differences in the NIHSS and GCS scores were not observed between the blend sign group and the control group. No significant differences in the proportion of patients with good outcomes during the follow-up period were observed between the two groups. A higher rate of re-haemorrhage was noted in the blend sign group. Significant differences in the rates of severe pulmonary infection and cardiac complications were not observed between the two groups.

Conclusions

The initial CT blend sign is not associated with poor outcomes in patients with hypertensive ICH after sMIS. ICH patients with the CT blend sign should undergo sMIS if they are suitable candidates for surgery.

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.

Regular-Shaped Hematomas Predict a Favorable Outcome in Patients with Hypertensive Intracerebral Hemorrhage Following Stereotactic Minimally Invasive Surgery

BACKGROUND

Stereotactic minimally invasive surgery (sMIS) has been used in the treatment of intracerebral hemorrhage (ICH) in recent years and has obtained promising results. However, the outcomes of patients are associated with many factors. The aim of the present study was to retrospectively observe the relationship between hematoma shape features and the outcome of patients with spontaneous ICH following sMIS.

METHODS

One hundred eighty-three patients with hypertensive ICH who underwent sMIS were enrolled. Based on hematoma shape features, the patients were assigned to a regular-shaped hematoma group (RSH group, including 121 patients) or an irregular-shaped hematoma group (ISH group, including 62 patients). The Glasgow Coma Scale (GCS) score and the National Institutes of Health Stroke Scale (NIHSS) score were assessed on admission and at 1 week and 2 weeks after surgery. The rates of severe pulmonary infection, cardiac complications, and postoperative rebleeding during the hospital stay were also recorded for comparison. The functional outcome assessed by using the modified Rankin scale score was determined at discharge. A multivariate logistic regression analysis was performed for predictors of good outcome in patients with ICH who underwent sMIS. A receiver operating characteristic curve was also used to confirm the results.

RESULTS

Compared to the ISH group, the RSH group showed increased median GCS scores at one week and two weeks after surgery. The RSH group showed significantly decreased NIHSS scores at one week and two weeks after surgery compared with the ISH group at the same time point. Significant differences in the GCS score and the NIHSS score at 1 week (P < 0.05) and 2 weeks (P < 0.05) after surgery were observed between the RSH group and the ISH group. The RSH group showed lower rates of severe pulmonary infection, heart failure, and postoperative rehemorrhage than the ISH group (P < 0.05). Of the total patients with good outcomes, the RSH group accounted for 84.6%, and just 15.4% were from the ISH group. The multivariate logistic regression analysis demonstrated that regular-shaped hematoma (P < 0.0001) was an independent predictor of good outcome. The postoperative residual hematoma volume (P < 0.05) predicted a poor outcome. The sensitivity, specificity, and positive and negative predictive values of regular-shaped hematomas for the prediction of a favorable outcome in patients were 0.667, 0.846, 0.917, and 0.542, respectively. Additionally, the Youden index was 0.513.

CONCLUSIONS

Patients with regular-shaped hematomas exhibited more favorable outcomes. Irregular-shaped hematomas and postoperative residual hematoma volume predicted a poor outcome in patients with ICH following sMIS.

Blend Sign Is a Strong Predictor of the Extent of Early Hematoma Expansion in Spontaneous Intracerebral Hemorrhage

Background and Purpose: It is unclear which imaging marker is optimal for predicting the extent of hematoma expansion (EHE). We aimed to compare the usefulness of the blend sign (BS) with that of other non-contrast computed tomography (NCCT) markers for predicting the EHE in patients with spontaneous intracerebral hemorrhage (sICH). Methods: Patients with sICH admitted to our Neurology Emergency Department between September 2013 and January 2019 were enrolled. The EHE was calculated as the absolute increase in hematoma volume between baseline and follow-up CT (within 72 h). The EHE was categorized into four groups: "no growth," "minimal change" (≤5.1 ml), "moderate change" (5.1-12.5 ml), and "massive change" (>12.5 ml). Univariate and multivariate analyses were performed to investigate the relationship between the NCCT markers [BS, black hole sign (BHS), satellite sign, and island sign] and the EHE. Results: A total of 1,111 sICH patients were included (median age: 60 years; 66.5% males). Multiple linear regression analysis showed that the presence of the BS and BHS was independently associated with the EHE, after adjusting for confounders (P < 0.001 and P = 0.003, respectively). The presence of the BS and BHS was positively correlated with growth category (r = 0.285 and r = 0.199, both Ps < 0.001). The BS demonstrated a better predictive performance for the EHE than did the BHS [area under the curve (AUC): 0.67 vs. 0.57; both Ps < 0.001]. Conclusions: In patients with acute sICH, the BS showed a better performance in predicting the EHE compared with other NCCT markers. This imaging marker may help identify patients at a high risk of significant hematoma expansion and may facilitate its early management.

Analysis of different hematoma expansion shapes caused by different risk factors in patients with hypertensive intracerebral hemorrhage

OBJECTIVE

To elucidate the relationship between the risk factors and hematoma expansion(HE)shapes.

PATIENTS AND METHODS

From February 2013 to November 2018, 60 patients diagnosed as basal ganglia ICH were divided into the filled type hematoma expansion group (FTE group) and the expanded type hematoma expansion group (ETE group). we performed follow-up CT and three-dimensional reconstruction for the patients and compared the hematoma before and after the expansion of size and extent.

RESULTS

The regression analysis showed that the irregular sign (odds ratio, 3.64; 95 % CI, 1.46-9.12), black hole sign (odds ratio, 3.85; 95 % CI, 1.40-10.60), blend sign (odds ratio, 2.86; 95 % CI, 1.03-7.95), and early use of dehydration (odds ratio, 4.59; 95 % CI, 1.59-13.19) were possible risk factors for the ETE group, while the high systolic blood pressure (odds ratio, 1.51; 95 % CI, 1.04-2.30), early use of dehydration (odds ratio, 3.27; 95 % CI, 1.10-9.69) and low density low-density band (odds ratio, 4.52; 95 % CI, 1.54-13.28) were possible risk factors for the FTE group.

CONCLUSIONS

The irregular sign, black hole sign, blend sign and early use of dehydration may be the main risk factors for ETE, whereas early use of dehydration, high systolic blood pressure, and low density low-density band may be the main risk factors for FTE.

Does Noncontrast Computed Tomography Scan Predict Rebleeding After Endoscopic Surgery for Spontaneous Intracerebral Hemorrhage?

BACKGROUND

The relationship between noncontrast computed tomography (CT) markers, which predict the expansion of spontaneous intracerebral hemorrhage (sICH) under conservative treatment, and postoperative rebleeding (PR) after treatment by directly removing the sICH is unknown. This study investigated the relationship between noncontrast CT markers and PR in patients with sICH treated by endoscopic surgery.

METHODS

The study population included 92 patients with available data who underwent endoscopic surgery for sICH at our institution from January 2010 to September 2018. The correlations between PR and preoperative noncontrast CT markers, including the blend sign, hypodensities, black hole sign, heterogeneous density, and island signs, were retrospectively evaluated.

RESULTS

In 5 of the 18 patients (27.8%) with the blend sign, PR developed, whereas only 5 of 74 patients (6.8%) without the blend sign developed PR. In the univariate regression analyses, manifestation of hydrocephalus (odds ratio [OR], 8.75; 95% confidence interval [CI], 2.15-35.68; P = 0.002), presence of the blend sign (OR, 5.31; 95% CI, 1.34-20.97; P = 0.02), and insertion of external ventricular drainage (OR, 13.88; 95% CI, 3.22-59.77; P < 0.001) were significant risk factors. The other radiographic markers were not associated with PR. In a multivariate analysis, the presence of the blend sign (OR, 22.07; 95% CI, 2.18-223.60; P = 0.009) was the only independent predictor of PR.

CONCLUSIONS

The blend sign is likely to be a strong predictor for PR in patients who undergo endoscopic surgery for sICH. To improve the prognosis of patients with sICH, further studies are needed to establish new treatment strategies and surgical procedures.