ISP-Net: Fusing Features to Predict Ischemic Stroke Infarct Core on CT Perfusion Maps

2022 ◽  
pp. 106630
Author(s):  
Haichen Zhu ◽  
Yang Chen ◽  
Tianyu Tang ◽  
Gao Ma ◽  
Jiaying Zhou ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Ct Perfusion ◽  
Infarct Core ◽  
Perfusion Maps

scholarly journals Neural Network-derived perfusion maps: a Model-free approach to computed tomography perfusion in patients with acute ischemic stroke

2021 ◽  
Author(s):  
Umberto A. Gava ◽  
Federico D’Agata ◽  
Enzo Tartaglione ◽  
Marco Grangetto ◽  
Francesca Bertolino ◽  
...  
Keyword(s):  
Neural Network ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
State Of The Art ◽  
Ct Perfusion ◽  
Pearson Correlation ◽  
Ground Truth ◽  
Infarct Core ◽  
Model Free ◽  
Perfusion Maps

AbstractPurposeIn this study we investigate whether a Convolutional Neural Network (CNN) can generate clinically relevant parametric maps from CT perfusion data in a clinical setting of patients with acute ischemic stroke.MethodsTraining of the CNN was done on a subset of 100 perfusion data, while 15 samples were used as validation. All the data used for the training/validation of the network and to generate ground truth (GT) maps, using a state-of-the-art deconvolution-algorithm, were previously pre-processed using a standard pipeline. Validation was carried out through manual segmentation of infarct core and penumbra on both CNN-derived maps and GT maps. Concordance among segmented lesions was assessed using the Dice and the Pearson correlation coefficients across lesion volumes.ResultsMean Dice scores from two different raters and the GT maps were > 0.70 (good-matching). Inter-rater concordance was also high and strong correlation was found between lesion volumes of CNN maps and GT maps (0.99, 0.98).ConclusionOur CNN-based approach generated clinically relevant perfusion maps that are comparable to state-of-the-art perfusion analysis methods based on deconvolution of the data. Moreover, the proposed technique requires less information to estimate the ischemic core and thus might allow the development of novel perfusion protocols with lower radiation dose.

Predictive value of time-variant color-coded multiphase CT angiography (mCTA) regarding clinical outcome of acute ischemic stroke: in comparison with conventional mCTA and CT perfusion

2020 ◽  
pp. 028418512098177
Author(s):  
Yu Lin ◽  
Nannan Kang ◽  
Jianghe Kang ◽  
Shaomao Lv ◽  
Jinan Wang
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Predictive Value ◽  
Ct Perfusion ◽  
Roc Curves ◽  
Multivariate Logistic Regression Model ◽  
Infarct Core ◽  
Predictive Values ◽  
Significant Difference ◽  
Core Volume

Background Color-coded multiphase computed tomography angiography (mCTA) can provide time-variant blood flow information of collateral circulation for acute ischemic stroke (AIS). Purpose To compare the predictive values of color-coded mCTA, conventional mCTA, and CT perfusion (CTP) for the clinical outcomes of patients with AIS. Material and Methods Consecutive patients with anterior circulation AIS were retrospectively reviewed at our center. Baseline collateral scores of color-coded mCTA and conventional mCTA were assessed by a 6-point scale. The reliabilities between junior and senior observers were assessed by weighted Kappa coefficients. Receiver operating characteristic (ROC) curves and multivariate logistic regression model were applied to evaluate the predictive capabilities of color-coded mCTA and conventional mCTA scores, and CTP parameters (hypoperfusion and infarct core volume) for a favorable outcome of AIS. Results A total of 138 patients (including 70 cases of good outcomes) were included in our study. Patients with favorable prognoses were correlated with better collateral circulations on both color-coded and conventional mCTA, and smaller hypoperfusion and infarct core volume (all P < 0.05) on CTP. ROC curves revealed no significant difference between the predictive capability of color-coded and conventional mCTA ( P = 0.427). The predictive value of CTP parameters tended to be inferior to that of color-coded mCTA score (all P < 0.001). Both junior and senior observers had consistently excellent performances (κ = 0.89) when analyzing color-coded mCTA maps. Conclusion Color-coded mCTA provides prognostic information of patients with AIS equivalent to or better than that of conventional mCTA and CTP. Junior radiologists can reach high diagnostic accuracy when interpreting color-coded mCTA images.

Abstract 3200: Comparison of CT Perfusion Mismatch with Perfusion-Diffusion MRI in Ischemic Stroke - a Reliable Alternative?

Stroke ◽  
2012 ◽  
Vol 43 (suppl_1) ◽  
Author(s):  
Bruce C Campbell ◽  
Søren Christensen ◽  
Christopher R Levi ◽  
Patricia M Desmond ◽  
Geoffrey A Donnan ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Diffusion Mri ◽  
Roc Analysis ◽  
Ct Perfusion ◽  
Residue Function ◽  
Infarct Core ◽  
Widespread Application ◽  
Time To Peak ◽  
Value Decomposition

Background and purpose: CT-perfusion (CTP) is widely and rapidly accessible for imaging acute ischemic stroke. However, there has been limited validation of CTP parameters against the more intensively studied MRI perfusion-diffusion mismatch paradigm. We tested the correspondence of CTP with contemporaneous perfusion-diffusion MRI. Methods: Acute ischemic stroke patients <6hr after onset had CTP and perfusion-diffusion MRI within 1hr, before reperfusion therapies. Relative cerebral blood flow (relCBF) and time-to-peak of the deconvolved tissue-residue-function (Tmax) were calculated (standard singular value decomposition deconvolution). The diffusion lesion was registered to the CTP slabs and manually outlined to its maximal visual extent. CT-infarct core was defined as relCBF<31% contralateral mean as previously published using this software. The volumetric accuracy of relCBF core compared to the diffusion lesion was tested in isolation, but also when restricted to pixels with relative time-to-peak (TTP) >4sec, to reduce artifactual false positive low CBF (eg in leukoaraiosis). The MR Tmax>6sec perfusion lesion (previously validated to define penumbral tissue at risk of infarction) was automatically segmented and registered to the CTP slabs. Receiver operating characteristic (ROC) analysis determined the optimal CT-Tmax threshold to match MR-Tmax>6sec, confidence intervals generated by bootstrapping. Agreement of these CT parameters with MR perfusion-diffusion mismatch on co-registered slabs was assessed (mismatch ratio >1.2, absolute mismatch>10mL, infarct core<70mL). Results: In analysis of 98 CTP slabs (54 patients, median onset to CT 190min, median CT to MR 30min), volumetric agreement with the diffusion lesion was substantially improved by constraining relCBF<31% within the automated TTP perfusion lesion ROI (median magnitude of volume difference 9.0mL vs unconstrained 13.9mL, p<0.001). ROC analysis demonstrated the best CT-Tmax threshold to match MR-Tmax>6sec was 6.2sec (95% confidence interval 5.6-7.3sec, ie not significantly different to 6sec), sensitivity 91%, specificity 70%, AUC 0.87. Using CT-Tmax>6s “penumbra” and relCBF<31% (restricted to TTP>4s) “core”, volumetric agreement was sufficient for 90% concordance between CT and MRI-based mismatch status (kappa 0.80). Conclusions: Automated CTP mismatch classification using relCBF and Tmax is similar to perfusion-diffusion MRI. CTP may allow more widespread application of the “mismatch” paradigm in clinical practice and trials.

What is the impact of head movement on automated CT perfusion mismatch evaluation in acute ischemic stroke?

2021 ◽  
pp. neurintsurg-2021-017510
Author(s):  
Arne Potreck ◽  
Fatih Seker ◽  
Matthias Anthony Mutke ◽  
Charlotte Sabine Weyland ◽  
Christian Herweh ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Head Movement ◽  
Ct Perfusion ◽  
Treatment Decision ◽  
Brain Perfusion ◽  
Left Middle Cerebral Artery ◽  
Ct Scanner ◽  
Infarct Core ◽  
The Impact

ObjectivesAutomated CT perfusion mismatch assessment is an established treatment decision tool in acute ischemic stroke. However, the reliability of this method in patients with head motion is unclear. We therefore sought to evaluate the influence of head movement on automated CT perfusion mismatch evaluation.MethodsUsing a realistic CT brain-perfusion-phantom, 7 perfusion mismatch scenarios were simulated within the left middle cerebral artery territory. Real CT noise and artificial head movement were added. Thereafter, ischemic core, penumbra volumes and mismatch ratios were evaluated using an automated mismatch analysis software (RAPID, iSchemaView) and compared with ground truth simulated values.ResultsWhile CT scanner noise alone had only a minor impact on mismatch evaluation, a tendency towards smaller infarct core estimates (mean difference of −5.3 (−14 to 3.5) mL for subtle head movement and −7.0 (−14.7 to 0.7) mL for strong head movement), larger penumbral estimates (+9.9 (−25 to 44) mL and +35 (−14 to 85) mL, respectively) and consequently larger mismatch ratios (+0.8 (−1.5 to 3.0) for subtle head movement and +1.9 (−1.3 to 5.1) for strong head movement) were noted in dependence of patient head movement.ConclusionsMotion during CT perfusion acquisition influences automated mismatch evaluation. Potentially treatment-relevant changes in mismatch classifications in dependence of head movement were observed and occurred in favor of mechanical thrombectomy.

Abstract WP45: Comparison of Automated Whole Brain CT Perfusion Analysis with Perfusion-Diffusion MRI in Ischemic Stroke

Stroke ◽  
2013 ◽  
Vol 44 (suppl_1) ◽  
Author(s):  
Bruce C Campbell ◽  
Søren Christensen ◽  
Nawaf Yassi ◽  
Gagan Sharma ◽  
Andrew Bivard ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Diffusion Mri ◽  
Ct Perfusion ◽  
Diffusion Imaging ◽  
Residue Function ◽  
Accurate Estimate ◽  
Mr Perfusion ◽  
Infarct Core ◽  
Whole Brain ◽  
Brain Ct

Background and purpose: CT perfusion (CTP) provides rapid and accessible imaging of ischemic stroke pathophysiology. Studies with limited brain coverage CTP have suggested that relative cerebral blood flow (relCBF) is the optimal CTP parameter to define irreversible infarction. We analyzed patients with whole brain CT perfusion and contemporaneous MR perfusion-diffusion imaging to confirm the optimal CTP parameter for infarct core and compare mismatch classification between MR and CT. Methods: Acute ischemic stroke patients <6hr after onset had whole brain CTP (320slice) closely followed by perfusion-diffusion MRI. Maps of CBF, CBV and time-to-peak of the deconvolved tissue residue function (Tmax) were generated by RAPID automated perfusion analysis software (Stanford University) using delay insensitive deconvolution. The optimal CTP map to identify infarct core was selected by maximizing the average Dice co-efficient across the same threshold range for all patients using co-registered diffusion lesion (manually outlined to its maximal visual extent) as reference region. Mismatch classification agreement between CT and MRI was then assessed using 2 definitions: mismatch ratio a) >1.2 or b) >1.8, absolute mismatch a) >10mL or b) >15mL, infarct core<70mL. Results: In 28 patients imaged <6hr from stroke onset (median age 69, median onset to CT 180min, median CT to MR 69min), relCBF provided the most accurate estimate for infarct core, significantly better than absolute or relative CBV (both p<0.001). Using relCBF to generate acute CTP infarct core volumes, the median magnitude of volume difference versus diffusion MR was 6.9mL, interquartile range 1.6-27.4mL. CTP mismatch between relCBF core and Tmax>6sec perfusion lesion was assessed in 25 patients (3/28 had no MR perfusion). CTP and MR perfusion-diffusion mismatch classification agreed in 23/25 (92%) patients (kappa 0.84) using either definition. Conclusions: This study using whole brain CTP confirms the greater accuracy of CBF over CBV for estimation of the infarct core. The >90% agreement in mismatch classification between CTP and MRI supports the concept that both modalities can identify similar patient populations for clinical trials of reperfusion therapies.

Topographic correlation of infarct area on CT perfusion with functional outcome in acute ischemic stroke

2020 ◽  
Vol 132 (1) ◽  
pp. 33-41 ◽  
Author(s):  
Neil Haranhalli ◽  
Nnenna Mbabuike ◽  
Sanjeet S. Grewal ◽  
Tasneem F. Hasan ◽  
Michael G. Heckman ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Ct Perfusion ◽  
Multivariable Analysis ◽  
Reperfusion Therapy ◽  
Infarct Core ◽  
Anterior Circulation ◽  
Logistic Regression Models ◽  
Confounding Variables

OBJECTIVEThe role of CT perfusion (CTP) in the management of patients with acute ischemic stroke (AIS) remains a matter of debate. The primary aim of this study was to evaluate the correlation between the areas of infarction and penumbra on CTP scans and functional outcome in patients with AIS.METHODSThis was a retrospective review of 100 consecutively treated patients with acute anterior circulation ischemic stroke who underwent CT angiography (CTA) and CTP at admission between February 2011 and October 2014. On CTP, the volume of ischemic core and penumbra was measured using the Alberta Stroke Program Early CT Score (ASPECTS). CTA findings were also noted, including the site of occlusion and regional leptomeningeal collateral (rLMC) score. Functional outcome was defined by modified Rankin Scale (mRS) score obtained at discharge. Associations of CTP and CTA parameters with mRS scores at discharge were assessed using multivariable proportional odds logistic regression models.RESULTSThe median age was 67 years (range 19–95 years), and the median NIH Stroke Scale score was 16 (range 2–35). In a multivariable analysis adjusting for potential confounding variables, having an infarct on CTP scans in the following regions was associated with a worse mRS score at discharge: insula ribbon (p = 0.043), perisylvian fissure (p < 0.001), motor strip (p = 0.007), M2 (p < 0.001), and M5 (p = 0.023). A worse mRS score at discharge was more common in patients with a greater volume of infarct core (p = 0.024) and less common in patients with a greater rLMC score (p = 0.004).CONCLUSIONSThe results of this study provide evidence that several CTP parameters are independent predictors of functional outcome in patients with AIS and have potential to identify those patients most likely to benefit from reperfusion therapy in the treatment of AIS.

Abstract 38: Brain CT Perfusion is Superior to Non-contrast CT Aspects in the Evaluation of Hyperacute Infarct Volume

Stroke ◽  
2017 ◽  
Vol 48 (suppl_1) ◽  
Author(s):  
Jelle Demeestere ◽  
Carlos Garcia-Esperon ◽  
Pablo Garcia-Bermejo ◽  
Fouke Ombelet ◽  
Patrick McElduff ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ischemic Stroke ◽  
Ct Perfusion ◽  
Infarct Volume ◽  
Lesion Volume ◽  
Infarct Core ◽  
Anterior Circulation ◽  
C Statistic ◽  
Contrast Ct ◽  
Core Volume

Objective: To compare the predictive capacity to detect established infarct in acute anterior circulation stroke between the Alberta Stroke Program Early Computed Tomography Score (ASPECTS) on non-contrast computed tomography (CT) and CT perfusion. Methods: Fifty-nine acute anterior circulation ischemic stroke patients received brain non-contrast CT, CT perfusion and hyperacute magnetic resonance imaging (MRI) within 100 minutes from CT imaging. ASPECTS scores were calculated by 4 independent vascular neurologists, blinded from CT perfusion and MRI data. CT perfusion infarct core volumes were calculated by MIStar software. The accuracy of commonly used ASPECTS cut-off scores and a CT perfusion core volume of ≥ 70 mL to detect a hyperacute MRI diffusion lesion of ≥ 70 ml was evaluated. Results: Median ASPECTS score was 9 (IQR 7-10). Median CT perfusion core volume was 22 ml (IQR 10.4-71.9). Median MRI diffusion lesion volume was 24,5 ml (IQR 10-63.9). ASPECTS score of < 6 had a sensitivity of 0.37, specificity of 0.95 and c-statistic of 0.66 to predict an acute MRI lesion ≥ 70 ml. In comparison, a CT perfusion core lesion of ≥ 70 ml had a sensitivity of 0.76, specificity of 0.98 and c-statistic of 0.92. The CT perfusion core lesion covered a median of 100% of the acute MRI lesion volume (IQR 86-100%). Conclusions: CT perfusion is superior to ASPECTS to predict hyperacute MRI lesion volume in ischemic stroke.

Sign in / Sign up

Export Citation Format

Share Document