Combination of Intra-Hematomal Hypodensity on CT and BRAIN Scoring Improves Prediction of Hemorrhage Expansion in ICH

VanDerWerf, Joshua D.; Kurowski, Donna; Siegler, James E.; Ganguly, Taneeta M.; Cucchiara, Brett

doi:10.1007/s12028-018-0507-y

Cited by 14 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HE prediction scores may combine multiple NCCT predictors and risk factors of HE for a relatively accurate assessment of HE. Regardless of the Hematoma Expansion Prediction score [24], the clinical prediction algorithm (BRAIN) [25] or BAT score [7], HE risk grading scores are mainly based on NCCT markers as predictors, and currently, there is lack of consistent criteria and consensus regarding the optimal grading of each variable.…”

Section: Discussionmentioning

confidence: 99%

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

Cai

Zhu

Yang

et al. 2020

Neurological Research

View full text Add to dashboard Cite

Objectives: Hematoma expansion (HE) is an important factor of unfavorable outcome in patients with intracerebral hemorrhage (ICH). Imaging markers on noncontrast computed tomography (NCCT) provide increasing value in the prediction of HE due to fast and easy-touse advantages; however, the accuracy of NCCT-based prediction of intracerebral HE remains unclear. We aimed to investigate the predictive accuracy of NCCT markers for the evaluation of HE using a well-characterized ICH cohort. Methods: We retrospectively analyzed 414 patients with spontaneous ICH, who underwent baseline CT within 6 h after symptom onset and follow-up CT within 24 h after ICH. Hematoma volumes were measured on baseline and follow-up CT images, and imaging features that predicted HE were analyzed. The test characteristics for the NCCT predictors were calculated. Results: Of the 414 patients investigated, 63 presented blend sign, 45 showed black hole sign, 36 had island sign and 34 had swirl sign. In the 414 patients, 88 presented HE, the incidence was 21.26%. Of the 88 patients with HE, 22 presented blend sign, 11 showed black hole sign, 8 had swirl sign and 7 had island sign. The blend sign showed highest sensitivity (25.00%) and swirl sign showed the highest specificity (92.02%) among the four predictors. We noted excellent interobserver agreement for the identification of HE. Conclusion:The four NCCT markers can predict HE with limited sensitivity, high specificity and good accuracy. This may be useful for prompt identification of patients at high risk of active bleeding, and prevention of over-treatment associated with HE.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Cai

Zhu

Yang

et al. 2020

Neurological Research

View full text Add to dashboard Cite

show abstract

“… 12 These features, due to the differences in cell structure, are shown as the spatial relationship and density differences between CT image pixels. 12 , 13 Imagomics converts the observable and unobservable image information into deep level features for quantitative analysis to achieve repeatability and stability. 11 , 13 The AUC in the training group was 0.89 (0.82-0.96), and that in the validation group was 0.82 (0.80-0.97).…”

Section: Discussionmentioning

confidence: 99%

“… 12 , 13 Imagomics converts the observable and unobservable image information into deep level features for quantitative analysis to achieve repeatability and stability. 11 , 13 The AUC in the training group was 0.89 (0.82-0.96), and that in the validation group was 0.82 (0.80-0.97). Similar to the prediction efficiency of only drawing the hematoma ROI, our method can also accurately predict the occurrence of HE, solving the problem of assessing an irregular hematoma, which is difficult to draw.…”

Section: Discussionmentioning

confidence: 99%

“…15 , 16 Although CTA spot sign and leakage sign are of high value in predicting the occurrence of E in patients with primary cerebral hemorrhage, they have shortcomings such as excessive radiation dose, high cost, and risk of allergic reaction. 13 , 17 Therefore, they cannot be used as the first choice for examination, while the blend sign is convenient and suitable for general use. 9 , 11 , 12 Hematoma density is affected by its components, specifically, hemoglobin is an important factor that determines the hematoma density on a CT scan.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Hematoma Expansion in Hypertensive Intracerebral Hemorrhage by a Radiomics Nomogram

Dai¹,

Liú²,

Li³

et al. 2023

Pak J Med Sci

View full text Add to dashboard Cite

Objective: To develop and validate a radiomics-based nomogram model which aimed to predict hematoma expansion (HE) in hypertensive intracerebral hemorrhage (HICH). Methods: Patients with HICH (n=187) were included from October 2017 to March 2022 in the Yongchuan Affiliated Hospital of Chongqing Medical University. Patients were randomly divided into a training set (n=130) and a validation set (n=57) in a ratio of 7:3. The radiomic features were extracted from the regions of interest (including main hematoma, the surrounding small hematoma(s) and perihematomal edema) in the first CT scan images. The variance threshold, SelectKBest and LASSO (least absolute shrinkage and selection operator), features were selected and the radiomics signature was built. Multivariate logistic regression was used to establish a nomogram based on clinical risk factors and the Rad-score. A receiver operating characteristic (ROC) curve was used to evaluate the generalization of the models’ performance.The calibration curve and the Hosmer-Lemeshow test were used to assess the calibration of the predictive nomogram. And decision curve analysis (DCA) was used to evaluate the prediction model. Results: Thirteen radiomics features were selected to construct the radiomics signature, which has a robust association with HE. The radiomics model found that blend sign was a predictive factor of HE. The radiomics model ROC in the training set was 0.89 (95%CI 0.82-0.96) and was 0.82 (95%CI 0.60-0.93) in the validation set. The nomogram model was built using the combined prediction model based on radiomics and blend sign, and worked well in both the training set (ROC: 0.90[95%CI 0.83-0.96]) and the validation set (ROC: 0.88[95%CI 0.71-0.93]). Conclusion: The radiomic signature based on CT of HICH has high accuracy for predicting HE. The combined prediction model of radiomics and blend sign improves the prediction performance. doi: https://doi.org/10.12669/pjms.39.4.7724 How to cite this: Dai J, Liu D, Li X, Liu Y, Wang F, Yang Q. Prediction of Hematoma Expansion in Hypertensive Intracerebral Hemorrhage by a Radiomics Nomogram. Pak J Med Sci. 2023;39(4):1149-1155. doi: https://doi.org/10.12669/pjms.39.4.7724 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Although spontaneous ICH comprises only 10% to 20% of all strokes, its mortality rates approach 30% to 40% at 1 month, and up to 75% of patients suffer significant disability or mortality at 1 year. [19][20][21][22][23] Currently, the management of spontaneous ICH patients includes primarily supportive therapies, [24] such as airway management, hemodynamic monitoring, and control of intracranial pressure, [25] with no treatment options demonstrating significant efficacy. [26] However, preventing secondary expansion of hemorrhage after initial ICH highlights opportunities for therapeutic intervention.…”

Section: Discussionmentioning

confidence: 99%

The comprehensive comparison of imaging sign from CT angiography and noncontrast CT for predicting intracranial hemorrhage expansion: A comparative study

et al. 2022

View full text Add to dashboard Cite

Expansion of intracranial hemorrhage (ICH) is an important predictor of poor clinical outcomes. Various imaging markers on non-contrast computed tomography (NCCT) or computed tomographic angiography (CTA) have been reported as predictors of ICH expansion. We aimed to compare the associations between various CT imaging markers and ICH expansion. Patients with spontaneous ICH who underwent initial NCCT, CTA, and subsequent NCCT between January 2016 and December 2019 were retrospectively identified. ICH expansion was defined as a volume increase of > 33% or > 6 mL. We analyzed the presence of imaging markers such as the black hole sign, blend sign, island sign, or swirl sign on initial NCCT or spot sign on CTA. An alternative free-response receiver operating characteristic curve analysis was performed using a 4-point scoring system based on the consensus of the reviewers. The predictive value of each marker was assessed using univariate and multivariate logistic regression analyses. A total of 250 patients, including 60 (24.0%) with ICH expansion, qualified for the analysis. Among the patients with spontaneous ICH, 118 (47.2%) presented with a black hole sign, 52 (20.8%) with a blend sign, 93 (37.2%) with an island sign, 79 (31.6%) with a swirl sign, and 56 (22.4%) with a spot sign. In univariate logistic regression, the initial ICH volume (P = .038), initial intraventricular hemorrhage (IVH) presence (P < .001), swirl sign (P < .001), and spot sign (P < .001) were associated with ICH expansion. Multivariate analysis confirmed that the presence of initial IVH (odds ratio, 4.111; P = .002) and spot sign (odds ratio, 109.5; P < .001) were independent predictors of ICH expansion. Initial ICH volume, IVH, swirl sign, and spot sign are associated with ICH expansion. The presence of spot signs and IVH were independent predictors of ICH expansion.

show abstract

Combination of Intra-Hematomal Hypodensity on CT and BRAIN Scoring Improves Prediction of Hemorrhage Expansion in ICH

Abstract: Combining IHH on non-contrast CT and a simple clinical BRAIN score is a potentially powerful way to predict those patients at very high and very low risk of HE.

Cited by 14 publications

References 26 publications

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

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

Prediction of Hematoma Expansion in Hypertensive Intracerebral Hemorrhage by a Radiomics Nomogram

The comprehensive comparison of imaging sign from CT angiography and noncontrast CT for predicting intracranial hemorrhage expansion: A comparative study

Contact Info

Product

Resources

About