Correlation of Tmax volumes with clinical outcome in anterior circulation stroke

Magnetic Resonance Perfusion-Weighted Imaging in Predicting Hemorrhagic Transformation of Acute Ischemic Stroke: A Retrospective Study

Hemorrhagic transformation (HT) is one of the common complications in patients with acute ischemic stroke (AIS). This study aims to investigate the value of different thresholds of Tmax generated from perfusion-weighted MR imaging (PWI) and the apparent diffusion coefficient (ADC) value in the prediction of HT in AIS. A total of 156 AIS patients were enrolled in this study, with 55 patients in the HT group and 101 patients in non-HT group. The clinical baseline data and multi-parametric MRI findings were compared between HT and non-HT groups to identify indicators related to HT. The optimal parameters for predicting HT and the corresponding cutoff values were obtained using the receiver operating characteristic curve analysis of the volumes of ADC < 620 × 10-6 mm2/s and Tmax > 6 s, 8 s, and 10 s. The results showed that the volumes of ADC < 620 × 10-6 mm2/s and Tmax > 6 s, 8 s, and 10 s in the HT group were all significantly larger than that in the non-HT group and were all independent risk factors for HT. Early measurement of the volume of Tmax > 10 s had the highest value, with a cutoff lesion volume of 10.5 mL.

Development of machine learning models for predicting outcome in patients with distal medium vessel occlusions: a retrospective study

Background

While numerous prognostic factors have been reported for large vessel occlusion (LVO)-acute ischemic stroke (AIS) patients, the same cannot be said for distal medium vessel occlusions (DMVOs). We used machine learning (ML) algorithms to develop a model predicting the short-term outcome of AIS patients with DMVOs using demographic, clinical, and laboratory variables and baseline computed tomography (CT) perfusion (CTP) postprocessing quantitative parameters.

Methods

In this retrospective cohort study, consecutive patients with AIS admitted to two comprehensive stroke centers between January 1, 2017, and September 1, 2022, were screened. Demographic, clinical, and radiological data were extracted from electronic medical records. The clinical outcome was divided into two categories, with a cut-off defined by the median National Institutes of Health Stroke Scale (NIHSS) shift score. Data preprocessing involved addressing missing values through imputation, scaling with a robust scaler, normalization using min-max normalization, and encoding of categorical variables. The data were split into training and test sets (70:30), and recursive feature elimination (RFE) was employed for feature selection. For ML analyses, XGBoost, LightGBM, CatBoost, multi-layer perceptron, random forest, and logistic regression algorithms were utilized. Performance evaluation involved the receiver operating characteristic (ROC) curve, precision-recall curve (PRC), the area under these curves, accuracy, precision, recall, and Matthews correlation coefficient (MCC). The relative weights of predictor variables were examined using Shapley additive explanations (SHAP).

Results

Sixty-nine patients were included and divided into two groups: 35 patients with favorable outcomes and 34 patients with unfavorable outcomes. Utilizing ten selected features, the XGBoost algorithm achieved the best performance in predicting unfavorable outcomes, with an area under the ROC curve (AUROC) of 0.894 and an area under the PRC curve (AUPRC) of 0.756. The SHAP analysis ranked the following features in order of importance for the XGBoost model: mismatch volume, time-to-maximum of the tissue residue function (Tmax) >6 s, diffusion-weighted imaging (DWI) volume, neutrophil-to-platelet ratio (NPR), mean corpuscular volume (MCV), Tmax >10 s, hemoglobin, potassium, hypoperfusion index (HI), and Tmax >8 s.

Conclusions

Our ML models, trained on baseline quantitative laboratory and CT parameters, accurately predicted the short-term outcome in patients with DMVOs. These findings may aid clinicians in predicting prognosis and may be helpful for future research.

Using Deep-Learning-Based Artificial Intelligence Technique to Automatically Evaluate the Collateral Status of Multiphase CTA in Acute Ischemic Stroke

BACKGROUND

Collateral status is an important predictor for the outcome of acute ischemic stroke with large vessel occlusion. Multiphase computed-tomography angiography (mCTA) is useful to evaluate the collateral status, but visual evaluation of this examination is time-consuming. This study aims to use an artificial intelligence (AI) technique to develop an automatic AI prediction model for the collateral status of mCTA.

METHODS

This retrospective study enrolled subjects with acute ischemic stroke receiving endovascular thrombectomy between January 2015 and June 2020 in a tertiary referral hospital. The demographic data and images of mCTA were collected. The collateral status of all mCTA was visually evaluated. Images at the basal ganglion and supraganglion levels of mCTA were selected to produce AI models using the convolutional neural network (CNN) technique to automatically predict the collateral status of mCTA.

RESULTS

A total of 82 subjects were enrolled. There were 57 cases randomly selected for the training group and 25 cases for the validation group. In the training group, there were 40 cases with a positive collateral result (good or intermediate) and 17 cases with a negative collateral result (poor). In the validation group, there were 21 cases with a positive collateral result and 4 cases with a negative collateral result. During training for the CNN prediction model, the accuracy of the training group could reach 0.999 ± 0.015, whereas the prediction model had a performance of 0.746 ± 0.008 accuracy on the validation group. The area under the ROC curve was 0.7.

CONCLUSIONS

This study suggests that the application of the AI model derived from mCTA images to automatically evaluate the collateral status is feasible.

RAPID CT Perfusion-Based Relative CBF Identifies Good Collateral Status Better Than Hypoperfusion Intensity Ratio, CBV-Index, and Time-to-Maximum in Anterior Circulation Stroke

BACKGROUND AND PURPOSE

Information of collateral flow may help to determine eligibility for thrombectomy. Our aim was to identify CT perfusion-based surrogate parameters of good collateral status in acute anterior circulation ischemic stroke.

MATERIALS AND METHODS

In this retrospective study, we assessed the collateral status of 214 patients who presented with acute ischemic stroke due to occlusion of the MCA M1 segment or the carotid terminus. Collaterals were assessed on dynamic CTA images analogous to the multiphase CTA score by Menon et al. CT perfusion parameters (time-to-maximum, relative CBF, hypoperfusion intensity ratio, and CBV-index) were assessed with RAPID software. The Spearman rank correlation and receiver operating characteristic analyses were performed to identify the parameters that correlate with collateral scores and good collateral supply (defined as a collateral score of ≥4).

RESULTS

The Spearman rank correlation was highest for a relative CBF < 38% volume (ρ = -0.66, P < .001), followed by the hypoperfusion intensity ratio (ρ = -0.49, P < .001), CBV-index (ρ = 0.51, P < .001), and time-to-maximum > 8 seconds (ρ = -0.54, P < .001). Good collateral status was better identified by a relative CBF < 38% at a lesion size <27 mL (sensitivity of 75%, specificity of 80%) compared with a hypoperfusion intensity ratio of <0.4 (sensitivity of 75%, specificity of 62%), CBV-index of >0.8 (sensitivity of 60%, specificity of 78%), and time-to-maximum > 8 seconds (sensitivity of 68%, specificity of 76%).

CONCLUSIONS

Automated CT perfusion analysis allows accurate identification of collateral status in acute ischemic stroke. A relative CBF < 38% may be a better perfusion-based indicator of good collateral supply compared with time-to-maximum, the hypoperfusion intensity ratio, and the CBV-index.

Tissue outcome prediction in hyperacute ischemic stroke: Comparison of machine learning models

Machine Learning (ML) has been proposed for tissue fate prediction after acute ischemic stroke (AIS), with the aim to help treatment decision and patient management. We compared three different ML models to the clinical method based on diffusion-perfusion thresholding for the voxel-based prediction of final infarct, using a large MRI dataset obtained in a cohort of AIS patients prior to recanalization treatment. Baseline MRI (MRI₀), including diffusion-weighted sequence (DWI) and Tmax maps from perfusion-weighted sequence, and 24-hr follow-up MRI (MRI_24h) were retrospectively collected in consecutive 394 patients AIS patients (median age = 70 years; final infarct volume = 28mL). Manually segmented DWI_24h lesion was considered the final infarct. Gradient Boosting, Random Forests and U-Net were trained using DWI, apparent diffusion coefficient (ADC) and Tmax maps on MRI₀ as inputs to predict final infarct. Tissue outcome predictions were compared to final infarct using Dice score. Gradient Boosting had significantly better predictive performance (median [IQR] Dice Score as for median age, maybe you can replace the comma with an equal sign for consistency 0.53 [0.29-0.68]) than U-Net (0.48 [0.18-0.68]), Random Forests (0.51 [0.27-0.66]), and clinical thresholding method (0.45 [0.25-0.62]) (P < 0.001). In this benchmark of ML models for tissue outcome prediction in AIS, Gradient Boosting outperformed other ML models and clinical thresholding method and is thus promising for future decision-making.

Safety of Mechanical Thrombectomy with Combined Intravenous Thrombolysis in Stroke Treatment 4.5 to 9 Hours from Symptom Onset

BACKGROUND

An extended time window for intravenous thrombolysis (IVT) for acute stroke patients up to 9 hours from symptom onset has been established in recent trials, excluding patients who received mechanical thrombectomy (MT). We therefore investigated whether combined therapy with IVT and MT (IVT+MT) is safe in patients with ischemic stroke and large vessel occlusion (LVO) in an extended time window.

METHODS

We retrospectively analyzed patients with anterior circulation ischemic stroke and LVO who were treated within 4.5 to 9 hours after symptom onset using MT with or without IVT. Primary endpoint was the occurrence of any intracranial hemorrhage (ICH). Multivariable logistic regression was used to adjust for potential confounders.

RESULTS

In total, 168 patients were included in the study, 44 (26%) were treated with IVT+ MT. 133 (79%) patients had a M1-/distal carotid artery occlusion. Median ASPECT-Score was 8 (IQR 7-10) and complete reperfusion (mTICI 2b-3) was achieved in 132 (79%) patients. 18 (41%) of the patients in the IVT+MT group developed any ICH vs. 45 (36%) patients in the direct MT group (p=0.587). Symptomatic ICH occurred in 5 (11%) patients with IVT+MT vs. 8 (6%) patients receiving direct MT (p=0.295). In multivariable analysis, IVT+MT was not an independent predictor of ICH (adjusted for NIHSS, degree of reperfusion, symptom-onset-to-treatment time and therapy with tirofiban; OR 0.95 [95% CI 0.43-2.08], p=0.896).

CONCLUSION

Mechanical thrombectomy in stroke patients seems to be safe with combined intravenous thrombolysis within 4.5 to 9 hours after onset as it did not significantly increase the risk for intracranial hemorrhage.

Detection of ischemic changes on baseline multimodal computed tomography: expert reading vs. Brainomix and RAPID software

PURPOSE

The aim of the study was to compare the assessment of ischemic changes by expert reading and available automated software for non-contrast CT (NCCT) and CT perfusion on baseline multimodal imaging and demonstrate the accuracy for the final infarct prediction.

METHODS

Early ischemic changes were measured by ASPECTS on the baseline neuroimaging of consecutive patients with anterior circulation ischemic stroke. The presence of early ischemic changes was assessed a) on NCCT by two experienced raters, b) on NCCT by e-ASPECTS, and c) visually on derived CT perfusion maps (CBF<30%, Tmax>10s). Accuracy was calculated by comparing presence of final ischemic changes on 24-hour follow-up for each ASPECTS region and expressed as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The subanalysis for patients with successful recanalization was conducted.

RESULTS

Of 263 patients, 81 fulfilled inclusion criteria. Median baseline ASPECTS was 9 for all tested modalities. Accuracy was 0.76 for e-ASPECTS, 0.79 for consensus, 0.82 for CBF<30%, 0.80 for Tmax>10s. e-ASPECTS, consensus, CBF<30%, and Tmax>10s had sensitivity 0.41, 0.46, 0.49, 0.57, respectively; specificity 0.91, 0.93, 0.95, 0.91, respectively; PPV 0.66, 0.75, 0.82, 0.73, respectively; NPV 0.78, 0.80, 0.82, 0.83, respectively. Results did not differ in patients with and without successful recanalization.

CONCLUSION

This study demonstrated high accuracy for the assessment of ischemic changes by different CT modalities with the best accuracy for CBF<30% and Tmax>10s. The use of automated software has a potential to improve the detection of ischemic changes.

Comparison of Accuracy of Arrival-Time-Insensitive and Arrival-Time-Sensitive CTP Algorithms for Prediction of Infarct Tissue Volumes

The purpose of this study was to compare the performance of arrival-time-insensitive (ATI) and arrival-time-sensitive (ATS) computed tomography perfusion (CTP) algorithms in Philips IntelliSpace Portal (v9, ISP) and to investigate optimal thresholds for ATI regarding the prediction of final infarct volume (FIV). Retrospective, single-center study with 54 patients (mean 67.0 ± 13.1 years, 68.5% male) who received Stroke-CT/CTP-imaging between 2010 and 2018 with occlusion of the middle cerebral artery in the M1-/proximal M2-segment or terminal internal carotid artery. FIV was determined on short-term follow-up imaging in two patient groups: A) not attempted or failed mechanical thrombectomy (MT) and B) successful MT. ATS (default settings) and ATI (full-range of threshold settings regarding FIV prediction) maps were coregistered in 3D with FIV using voxel-wise overlap measurement. Based on an average imaging follow-up of 2.6 ± 2.1 days, the estimation regarding penumbra (group A, ATI: r = 0.63/0.69, ATS: r = 0.64) and infarct core (group B, ATI: r = 0.60/0.68, ATS: r = 0.63) was slightly higher in ATI but the effect was not significant (p > 0.05). Regarding ATI, Tmax (AUC 0.9) was the best estimator of the penumbra (group A), CBF relative to the contralateral hemisphere (AUC 0.80) showed the best estimation of the infarct core (group B). There was a broad range of thresholds of optimal ATI settings in both groups. Prediction of FIV with ATI was slightly better compared to ATS. However, this difference was not significant. Since ATI showed a broad range of optimal thresholds, exact thresholds regarding the ATI algorithm should be evaluated in further prospective, clinical studies.

Collateral Scores in Acute Ischemic Stroke : A retrospective study assessing the suitability of collateral scores as standalone predictors of clinical outcome

BACKGROUND AND PURPOSE

Several collateral scores have been published for stroke in the middle cerebral artery territory, each considering different aspects of cerebral collateralization. Currently, there is no gold standard in CT-based collateral assessment. The aim of this retrospective study was to compare five collateral scores and determine whether they are able to predict clinical outcome after thrombectomy as standalone parameters.

METHODS

Inclusion criteria were M1 occlusion, premorbid modified Rankin scale (mRS) of 0-3, treatment with endovascular thrombectomy and groin puncture within 12 h after stroke onset. The Maas et al., Miteff et al., Tan et al., ASITN/SIR and mCTA collateral scores were retrospectively assessed in multiphase CTA images and correlated with 90-day mRS (90d-mRS) scores. Good outcome was defined as 90d-mRS 0-2 or unchanged to premorbid mRS.

RESULTS

In total, 108 patients were included of which 39.8% achieved a good outcome. The area under the curve (AUC) values of receiver operating characteristic (ROC) curve analysis for Maas et al., Miteff et al., Tan et al., ASITN/SIR and mCTA scores were 0.60 (0.51-0.70), 0.60 (0.52-0.68), 0.61 (0.51-0.70), 0.59 (0.49-0.70) and 0.61 (0.50-0.71), respectively. The correlation between 90d-mRS and Maas (r = -0.16, P = 0.091), Miteff (r = -0.25, P = 0.009), Tan (r = -0.26, P = 0.007), ASITN/SIR (r = -0.21, P = 0.030) and mCTA (r = -0.22, P = 0.021) scores was poor.

CONCLUSION

Although collaterals are known to correlate with clinical outcome, none of the analyzed collateral scores sufficiently predicted outcome as a standalone parameter.

"Code-Stroke" CT Perfusion; Challenges and Pitfalls

RATIONALE AND OBJECTIVES

Regarding the most recent ischemic stroke treatment guideline, perfusion imaging has been recommended up to 24 hours after initial symptoms of brain infarction. Patients with a significant amount of salvageable peri-infarct ischemia and no contraindications benefit from delayed thrombolysis and intra-arterial thrombectomy. This approach causes increasingly more CT perfusion to be done in the subacute phase of ischemic stroke. CT perfusion findings in this "subacute phase" are slightly different from "hyper-acute" ischemic stroke. The interpreting radiologist must be confident in reporting the CT perfusion study in an urgent setting since these studies are under the umbrella of "code-stroke" and should be read in minutes. In addition, results of the CT perfusion have a critical effect on the patient's outcome and misinterpretation can be fatal in that underestimation of the salvageable ischemia excludes the patient from potential effective treatment. Underestimation of infarct volume may cause unnecessary thrombolysis/thrombectomy and potentially fatal intracranial hemorrhage.

MATERIALS AND METHODS

In this review, we are trying to explain the basic concept of "code-stroke" CT perfusion, typical findings, and pitfalls in a practical way.

History of Hypertension Is Associated With MR Hypoperfusion in Chinese Inpatients With DWI-Negative TIA

Objectives: The present study aimed to examine the prevalence of and risk factors for magnetic resonance (MR) perfusion abnormality in a Chinese population with transient ischemic attack (TIA) and normal diffusion-weighted imaging (DWI) findings.

Methods: Patients with TIA admitted to our stroke center between January 2015 and October 2017 were recruited to the present study. MRI, including both DWI and perfusion-weighted imaging (PWI), was performed within 7 days of symptom onset. Time to maximum of the residue function (T_max) maps were evaluated using the RAPID software (Ischemaview USA, Version 4.9) to determine hypoperfusion. Multivariate analysis was used to assess perfusion findings, clinical variables, medical history, cardio-metabolic, and the ABCD2 scores (age, blood pressure, clinical features, symptom duration, and diabetes).

Results: Fifty-nine patients met the inclusion criteria. The prevalence of MR perfusion T_max ≥ 4 s ≥ 0 ml and ≥ 10 mL were 72.9% (43/59) and 42.4% (25/59), respectively. Multivariate analyses revealed that history of hypertension is an independent factor associated with MR perfusion abnormality (T_max ≥ 4 s ≥ 10 mL) for Chinese patients with TIA (P = 0.033, adjusted OR = 4.11, 95% CI = 1.12–15.11). Proximal artery stenosis (>50%) tended to lead to a larger PW lesion on MRI (p = 0.067, adjusted OR = 3.60, 95% CI = 0.91–14.20).

Conclusion: Our results suggest that the prevalence of perfusion abnormality is high as assessed by RAPID using the parametric T_max ≥ 4 s. History of hypertension is a strong predictor of focal perfusion abnormality as calculated by RAPID on T_max map of TIA patients with negative DWI findings.

[Imaging in acute ischemic stroke using automated postprocessing algorithms]

There are several automated analytical methods to detect thromboembolic vascular occlusions, the infarct core and the potential infarct-endangered tissue (tissue at risk) by means of multimodal computed tomography (CT) and magnetic resonance imaging (MRI). The infarct core is more reliably visualized by diffusion-weighted imaging (DWI) MRI or CT perfusion than by native CT. The extent of tissue at risk and endangerment can only be estimated; however, it seems essential whether "tissue at risk" actually exists. To ensure consistent patient care, uniform imaging protocols should be acquired in the referring hospital and thrombectomy center and the collected data should be standardized and automatically evaluated and presented. Whether patients with a large infarct core and with or without tissue at risk or patients with large vessel occlusion (LVO) but low NIHSS benefit from thrombectomy has to be evaluated in controlled clinical trials using standardized imaging protocols. A promising, potentially time-saving approach is also native CT and CT angiography using a flat-panel detector angiography system for assessment of vessel occlusion and leptomeningeal collaterals.

Correlation of Tmax volumes with clinical outcome in anterior circulation stroke

BACKGROUND AND PURPOSE

The recent thrombectomy trials have shown that perfusion imaging is helpful in proper patient selection in thromboembolic stroke. In this study, we analyzed the correlation of pretreatment T_max volumes in MR and CT perfusion with clinical outcome after thrombectomy.

METHODS

Forty-one consecutive patients with middle cerebral artery occlusion (MCA) or carotid T occlusion treated with thrombectomy were included. T_max volumes at delays of >4, 6, 8, and 10 s as well as infarct core and mismatch ratio were automatically estimated in preinterventional MRI or CT perfusion using RAPID software. These perfusion parameters were correlated with clinical outcome. Outcome was assessed using modified Rankin scale at 90 days.

RESULTS

In patients with successful recanalization of MCA occlusion, T_max > 8 and 10 s showed the best linear correlation with clinical outcome (r = 0.75; p = .0139 and r = 0.73; p = .0139), better than infarct core (r = 0.43; p = .2592). In terminal internal carotid artery occlusions, none of the perfusion parameters showed a significant correlation with clinical outcome.

CONCLUSIONS

T_max at delays of >8 and 10 s is a good predictor for clinical outcome in MCA occlusions. In carotid T occlusion, however, T_max volumes do not correlate with outcome.