Dataset Information

Development and validation of intracranial thrombus segmentation on CT angiography in patients with acute ischemic stroke.

ABSTRACT:

Background and purpose

Thrombus characterization is increasingly considered important in predicting treatment success for patients with acute ischemic stroke. The lack of intensity contrast between thrombus and surrounding tissue in CT images makes manual delineation a difficult and time consuming task. Our aim was to develop an automated method for thrombus measurement on CT angiography and validate it against manual delineation.

Materials and methods

Automated thrombus segmentation was achieved using image intensity and a vascular shape prior derived from the segmentation of the contralateral artery. In 53 patients with acute ischemic stroke due to proximal intracranial arterial occlusion, automated length and volume measurements were performed. Accuracy was assessed by comparison with inter-observer variation of manual delineations using intraclass correlation coefficients and Bland-Altman analyses.

Results

The automated method successfully segmented the thrombus for all 53 patients. The intraclass correlation of automated and manual length and volume measurements were 0.89 and 0.84. Bland-Altman analyses yielded a bias (limits of agreement) of -0.4 (-8.8, 7.7) mm and 8 (-126, 141) mm3 for length and volume, respectively. This was comparable to the best interobserver agreement, with an intraclass correlation coefficients of 0.90 and 0.85 and a bias (limits of agreement) of -0.1 (-11.2, 10.9) mm and -17 (-216, 185) mm3.

Conclusions

The method facilitates automated thrombus segmentation for accurate length and volume measurements, is relatively fast and requires minimal user input, while being insensitive to high hematocrit levels and vascular calcifications. Furthermore, it has the potential to assess thrombus characteristics of low-density thrombi.

SUBMITTER: Santos EM

PROVIDER: S-EPMC4102487 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of intracranial thrombus segmentation on CT angiography in patients with acute ischemic stroke.

Santos Emilie M M EM Marquering Henk A HA Berkhemer Olvert A OA van Zwam Wim H WH van der Lugt Aad A Majoie Charles B CB Niessen Wiro J WJ

PloS one 20140717 7

<h4>Background and purpose</h4>Thrombus characterization is increasingly considered important in predicting treatment success for patients with acute ischemic stroke. The lack of intensity contrast between thrombus and surrounding tissue in CT images makes manual delineation a difficult and time consuming task. Our aim was to develop an automated method for thrombus measurement on CT angiography and validate it against manual delineation.<h4>Materials and methods</h4>Automated thrombus segmentat ...[more]

PMID: 25032691

Similar Datasets

Project description:Background and purposeIntracranial collaterals influence the prognosis of patients treated with intravenous tissue plasminogen activator in acute anterior circulation ischemic stroke. We compared the methods of scoring collaterals on pre-tPA brain CT angiography for predicting functional outcomes in acute anterior circulation ischemic stroke.Materials and methodsTwo hundred consecutive patients with acute anterior circulation ischemic stroke treated with IV-tPA during 2010-2012 were included. Two independent neuroradiologists evaluated intracranial collaterals by using the Miteff system, Maas system, the modified Tan scale, and the Alberta Stroke Program Early CT Score 20-point methodology. Good and extremely poor outcomes at 3 months were defined by modified Rankin Scale scores of 0-1 and 5-6 points, respectively.ResultsFactors associated with good outcome on univariable analysis were younger age, female sex, hypertension, diabetes mellitus, atrial fibrillation, small infarct core (ASPECTS ≥8), vessel recanalization, lower pre-tPA NIHSS scores, and good collaterals according to Tan methodology, ASPECTS methodology, and Miteff methodology. On multivariable logistic regression, only lower NIHSS scores (OR, 1.186 per point; 95% CI, 1.079-1.302; P = .001), recanalization (OR, 5.599; 95% CI, 1.560-20.010; P = .008), and good collaterals by the Miteff method (OR, 3.341; 95% CI, 1.203-5.099; P = .014) were independent predictors of good outcome. Poor collaterals by the Miteff system (OR, 2.592; 95% CI, 1.113-6.038; P = .027), Maas system (OR, 2.580; 95% CI, 1.075-6.187; P = .034), and ASPECTS method ≤5 points (OR, 2.685; 95% CI, 1.156-6.237; P = .022) were independent predictors of extremely poor outcomes.ConclusionsOnly the Miteff scoring system for intracranial collaterals is reliable for predicting favorable outcome in thrombolyzed acute anterior circulation ischemic stroke. However, poor outcomes can be predicted by most of the existing methods of scoring intracranial collaterals.

Project description:BackgroundTo evaluate the predictive value of radiomics features extracted from the thrombus on preoperative computed tomography images to identify successful recanalization after stent retrieve (SR) treatment in patients with acute ischemic stroke (AIS).MethodsTwo hundred fifty-six patients newly diagnosed AIS between March 2017 and September 2020 from two institutes, including the first affiliated hospital of Soochow university (institute I) and Northern Jiangsu People's hospital (institute II), were enrolled continuously and retrospectively. Patients with unsatisfactory image quality were excluded. The remaining patients of institute I were randomly divided into the training and internal validation cohorts at a ratio of 7 to 3, and patients of institute II were collected as the external validation cohort. After extraction and selection of the optimal radiomics features from training cohort, six machine learning (ML) classifiers including naïve Bayes (NB), random forest (RF), logistic regression (LR), linear support vector machine (L.SVM), radial SVM (R.SVM), and an artificial neural network (ANN) were developed to predict successful recanalization with SR treatment and compared. A combined model based on the optimal ML classifier was constructed using the optimal radiomics model and clinical-radiological risk variables. Finally, the performance of the model was selected based on the Matthews correlation coefficient (MCC) and the area under the receiver operating (AUC) and independently evaluated on the internal validation and external validation cohorts.ResultsWe automatically extracted 1,130 radiomics features from the voxel of interest (VOI) using PyRadiomics. The eight most relevant radiomics features were identified using Intraclass coefficient, single-factor logistic regression analysis, and least absolute shrinkage and selection operator algorithm in the training cohort. Among the six ML classifiers, the ANN classifier using thrombus radiomics features achieved the best prediction of early recanalization under SR with MCCs of 0.913, 0.693 and 0.505 in training, internal and external validation cohorts, respectively. Moreover, receiver operating characteristic curves showed that the combined model [AUC =0.860, 95% confidence interval (CI): 0.731-0.936; AUC =0.849, 95% CI: 0.759-0.831] was not significantly better than radiomics model based on the ANN classifier alone (AUC =0.873, 95% CI: 0.803-0.891; AUC =0.805, 95% CI: 0.864-0.971) (P>0.05, Delong test) in internal and external validation cohorts.ConclusionsA radiomics model based on the ANN classifier has the ability to predict successful recanalization after SR in patients with AIS, thus allowing a potentially better selection of mechanical thrombectomy treatment.

Project description:PurposeTo test whether the relationship between acute ischemic infarct size on concurrent computed tomographic (CT) angiography source images and diffusion-weighted (DW) magnetic resonance images is dependent on the parameters of CT angiography acquisition protocols.Materials and methodsThis retrospective study had institutional review board approval, and all records were HIPAA compliant. Data in 100 patients with anterior-circulation acute ischemic stroke and large vessel occlusion who underwent concurrent CT angiography and DW imaging within 9 hours of symptom onset were analyzed. Measured areas of hyperintensity at acute DW imaging were used as the standard of reference for infarct size. Information regarding lesion volumes and CT angiography protocol parameters was collected for each patient. For analysis, patients were divided into two groups on the basis of CT angiography protocol differences (patients in group 1 were imaged with the older, slower protocol). Intermethod agreement for infarct size was evaluated by using the Wilcoxon signed rank test, as well as by using Spearman correlation and Bland-Altman analysis. Multivariate analysis was performed to identify predictors of marked (?20%) overestimation of infarct size on CT angiography source images.ResultsIn group 1 (n=35), median hypoattenuation volumes on CT angiography source images were slightly underestimated compared with DW imaging hyperintensity volumes (33.0 vs 41.6 mL, P=.01; ratio=0.83), with high correlation (?=0.91). In group 2 (n=65), median volume on CT angiography source images was much larger than that on DW images (94.8 vs 17.8 mL, P<.0001; ratio=3.5), with poor correlation (?=0.49). This overestimation on CT angiography source images would have inappropriately excluded from reperfusion therapy 44.4% or 90.3% of patients eligible according to DW imaging criteria on the basis of a 100-mL absolute threshold or a 20% or greater mismatch threshold, respectively. Atrial fibrillation and shorter time from contrast material injection to image acquisition were independent predictors of marked (?20%) infarct size overestimation on CT angiography source images.ConclusionCT angiography protocol changes designed to speed imaging and optimize arterial opacification are associated with significant overestimation of infarct size on CT angiography source images.

Project description:Importance:Recanalization of intracranial thrombus is associated with improved clinical outcome in patients with acute ischemic stroke. The association of intravenous alteplase treatment and thrombus characteristics with recanalization over time is important for stroke triage and future trial design. Objective:To examine recanalization over time across a range of intracranial thrombus occlusion sites and clinical and imaging characteristics in patients with ischemic stroke treated with intravenous alteplase or not treated with alteplase. Design, Setting, and Participants:Multicenter prospective cohort study of 575 patients from 12 centers (in Canada, Spain, South Korea, the Czech Republic, and Turkey) with acute ischemic stroke and intracranial arterial occlusion demonstrated on computed tomographic angiography (CTA). Exposures:Demographics, clinical characteristics, time from alteplase to recanalization, and intracranial thrombus characteristics (location and permeability) defined on CTA. Main Outcomes and Measures:Recanalization on repeat CTA or on first angiographic acquisition of affected intracranial circulation obtained within 6 hours of baseline CTA, defined using the revised arterial occlusion scale (rAOL) (scores from 0 [primary occlusive lesion remains the same] to 3 [complete revascularization of primary occlusion]). Results:Among 575 patients (median age, 72 years [IQR, 63-80]; 51.5% men; median time from patient last known well to baseline CTA of 114 minutes [IQR, 74-180]), 275 patients (47.8%) received intravenous alteplase only, 195 (33.9%) received intravenous alteplase plus endovascular thrombectomy, 48 (8.3%) received endovascular thrombectomy alone, and 57 (9.9%) received conservative treatment. Median time from baseline CTA to recanalization assessment was 158 minutes (IQR, 79-268); median time from intravenous alteplase start to recanalization assessment was 132.5 minutes (IQR, 62-238). Successful recanalization occurred at an unadjusted rate of 27.3% (157/575) overall, including in 30.4% (143/470) of patients who received intravenous alteplase and 13.3% (14/105) who did not (difference, 17.1% [95% CI, 10.2%-25.8%]). Among patients receiving alteplase, the following factors were associated with recanalization: time from treatment start to recanalization assessment (OR, 1.28 for every 30-minute increase in time [95% CI, 1.18-1.38]), more distal thrombus location, eg, distal M1 middle cerebral artery (39/84 [46.4%]) vs internal carotid artery (10/92 [10.9%]) (OR, 5.61 [95% CI, 2.38-13.26]), and higher residual flow (thrombus permeability) grade, eg, hairline streak (30/45 [66.7%]) vs none (91/377 [24.1%]) (OR, 7.03 [95% CI, 3.32-14.87]). Conclusions and Relevance:In patients with acute ischemic stroke, more distal thrombus location, greater thrombus permeability, and longer time to recanalization assessment were associated with recanalization of arterial occlusion after administration of intravenous alteplase; among patients who did not receive alteplase, rates of arterial recanalization were low. These findings may help inform treatment and triage decisions in patients with acute ischemic stroke.

Project description:Background and Purpose- The location of the thrombus as observed on first digital subtraction angiography during endovascular treatment may differ from the initial observation on initial noninvasive imaging. We studied the incidence of thrombus dynamics, its impact on patient outcomes, and its association with intravenous thrombolytics. Methods- We included patients from the MR CLEAN registry (Multicenter Randomized Clinical Trial of Endovascular Treatment of Acute Ischemic Stroke) with an initial target occlusion on computed tomography angiography located in the intracranial internal carotid artery, M1, or M2. The conventional angiography target occlusion was defined during endovascular treatment. Thrombus dynamics were classified as growth, stability, migration, and resolution. The primary outcome was functional outcome at 90 days (modified Rankin Scale). The secondary outcomes were successful and complete reperfusion (extended treatment in cerebral infarction scores of 2b-3 and 3, respectively). Results- The analysis included 1349 patients. Thrombus migration occurred in 302 (22%) patients, thrombus growth in 87 (6%), and thrombus resolution in 39 (3%). Intravenous treatment with alteplase was associated with more thrombus migration (adjusted odds ratio, 2.01; CI, 1.29-3.11) and thrombus resolution (adjusted odds ratio, 1.85; CI, 1.22-2.80). Thrombus migration was associated with a lower chance of complete reperfusion (adjusted odds ratio, 0.57; CI, 0.42-0.78) and successful reperfusion (adjusted odds ratio, 0.74; CI, 0.55-0.99). In the subgroup of patients with M1 initial target occlusion, thrombus migration was associated with better functional outcome (adjusted common odds ratio, 1.49; CI, 1.02-2.17), and there was a trend towards better functional outcome in patients with thrombus resolution (adjusted common odds ratio, 2.23; CI, 0.93-5.37). Conclusions- In patients with acute ischemic stroke, thrombus location regularly changes between computed tomography angiography and digital subtraction angiography. Administration of intravenous alteplase increases the chance of thrombus migration and resolution. Thrombus migration is associated with better functional outcome but reduces the rate of complete reperfusion.

Project description:PurposeReperfusion therapies for acute ischemic stroke due to large-vessel occlusion (AIS-LVO) are highly time-dependent, and large infarction is related to poor outcomes and risk of symptomatic hemorrhage. It is of significance to investigate and optimize the screening means and selection criteria for reperfusion therapies to identify more appropriate patients with better outcomes. This study aimed to compare the performance of attenuation changes vs. automated Alberta Stroke Program Early CT Score (ASPECTS) and using CT angiography (CTA) source images vs. non-contrast CT (NCCT) in distinguishing the infarction extent of ischemic core volumes ≥ 70 ml within different time windows.MethodsA total of 73 patients with AIS-LVO who received multimodal CT were analyzed. The automated software was used to calculate ASPECTS. Attenuation change was defined as the sum of products of relative Hounsfield unit (rHU) values times weighting factors of all 10 ASPECTS regions. rHU value of each region was the HU of the ischemic side over that of the contralateral. The corresponding weighting factors were the regression coefficients derived from a multivariable linear regression model which was used to correlate regional rHU with ischemic core volumes, because each region in the ASPECTS template is weighted disproportionally in the ASPECTS system. Automated ASPECTS and attenuation changes were both calculated using CTA and NCCT, respectively.ResultsAttenuation changes were correlated with ischemic core volumes within different time windows (Rho ranging from 0.439 to 0.637). In classification of the ischemic core ≥ 70 ml, the performances of attenuation changes were comparable with ASPECTS (area under the curve [AUC] ranging from 0.799 to 0.891), with DeLong's test (P = 0.079, P = 0.373); using CTA (AUC = 0.842) was not different from NCCT (AUC = 0.838).ConclusionAttenuation changes in ASPECTS regions were correlated with ischemic core volumes. In the classification of infarction volumes, attenuation changes had a high diagnostic ability comparable with automated ASPECTS. Measurement of attenuation changes is not involved in complicated scoring algorithms. This measurement can be used as an available, rapid, reliable, and accurate means to evaluate infarction extent within different time windows. The usefulness of infarction volumes measured by attenuation changes to identify more appropriate patients for reperfusion therapies can be validated in future clinical trials.

Dataset Information

Development and validation of intracranial thrombus segmentation on CT angiography in patients with acute ischemic stroke.

Background and purpose

Materials and methods

Results

Conclusions

Publications

Development and validation of intracranial thrombus segmentation on CT angiography in patients with acute ischemic stroke.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets