Noncontrast Computed Tomography versus Computed Tomography Angiography Source Images for Predicting Final Infarct Size in Anterior Circulation Acute Ischemic Stroke: a Prospective Cohort Study

Automated detection of early signs of irreversible ischemic change on CTA source images in patients with large vessel occlusion

PURPOSE

To create and validate an automated pipeline for detection of early signs of irreversible ischemic change from admission CTA in patients with large vessel occlusion (LVO) stroke.

METHODS

We retrospectively included 368 patients for training and 143 for external validation. All patients had anterior circulation LVO stroke, endovascular therapy with successful reperfusion, and follow-up diffusion-weighted imaging (DWI). We devised a pipeline to automatically segment Alberta Stroke Program Early CT Score (ASPECTS) regions and extracted their relative Hounsfield unit (rHU) values. We determined the optimal rHU cut points for prediction of final infarction in each ASPECT region, performed 10-fold cross-validation in the training set, and measured the performance via external validation in patients from another institute. We compared the model with an expert neuroradiologist for prediction of final infarct volume and poor functional outcome.

RESULTS

We achieved a mean area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of 0.69±0.13, 0.69±0.09, 0.61±0.23, and 0.72±0.11 across all regions and folds in cross-validation. In the external validation cohort, we achieved a median [interquartile] AUC, accuracy, sensitivity, and specificity of 0.71 [0.68-0.72], 0.70 [0.68-0.73], 0.55 [0.50-0.63], and 0.74 [0.73-0.77], respectively. The rHU-based ASPECTS showed significant correlation with DWI-based ASPECTS (rS = 0.39, p<0.001) and final infarct volume (rS = -0.36, p<0.001). The AUC for predicting poor functional outcome was 0.66 (95%CI: 0.57-0.75). The predictive capabilities of rHU-based ASPECTS were not significantly different from the neuroradiologist's visual ASPECTS for either final infarct volume or functional outcome.

CONCLUSIONS

Our study demonstrates the feasibility of an automated pipeline and predictive model based on relative HU attenuation of ASPECTS regions on baseline CTA and its non-inferior performance in predicting final infarction on post-stroke DWI compared to an expert human reader.

Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission

Introduction

In acute ischemic stroke, prediction of the tissue outcome after reperfusion can be used to identify patients that might benefit from mechanical thrombectomy (MT). The aim of this work was to develop a deep learning model that can predict the follow-up infarct location and extent exclusively based on acute single-phase computed tomography angiography (CTA) datasets. In comparison to CT perfusion (CTP), CTA imaging is more widely available, less prone to artifacts, and the established standard of care in acute stroke imaging protocols. Furthermore, recent RCTs have shown that also patients with large established infarctions benefit from MT, which might not have been selected for MT based on CTP core/penumbra mismatch analysis.

Methods

All patients with acute large vessel occlusion of the anterior circulation treated at our institution between 12/2015 and 12/2020 were screened (N = 404) and 238 patients undergoing MT with successful reperfusion were included for final analysis. Ground truth infarct lesions were segmented on 24 h follow-up CT scans. Pre-processed CTA images were used as input for a U-Net-based convolutional neural network trained for lesion prediction, enhanced with a spatial and channel-wise squeeze-and-excitation block. Post-processing was applied to remove small predicted lesion components. The model was evaluated using a 5-fold cross-validation and a separate test set with Dice similarity coefficient (DSC) as the primary metric and average volume error as the secondary metric.

Results

The mean ± standard deviation test set DSC over all folds after post-processing was 0.35 ± 0.2 and the mean test set average volume error was 11.5 mL. The performance was relatively uniform across models with the best model according to the DSC achieved a score of 0.37 ± 0.2 after post-processing and the best model in terms of average volume error yielded 3.9 mL.

Conclusion

24 h follow-up infarct prediction using acute CTA imaging exclusively is feasible with DSC measures comparable to results of CTP-based algorithms reported in other studies. The proposed method might pave the way to a wider acceptance, feasibility, and applicability of follow-up infarct prediction based on artificial intelligence.

Factors influencing the reliability of a CT angiography-based deep learning method for infarct volume estimation

Objectives

CT angiography (CTA)-based machine learning methods for infarct volume estimation have shown a tendency to overestimate infarct core and final infarct volumes (FIV). Our aim was to assess factors influencing the reliability of these methods.

Methods

The effect of collateral circulation on the correlation between convolutional neural network (CNN) estimations and FIV was assessed based on the Miteff system and hypoperfusion intensity ratio (HIR) in 121 patients with anterior circulation acute ischaemic stroke using Pearson correlation coefficients and median volumes. Correlation was also assessed between successful and futile thrombectomies. The timing of individual CTAs in relation to CTP studies was analysed.

Results

The strength of correlation between CNN estimated volumes and FIV did not change significantly depending on collateral status as assessed with the Miteff system or HIR, being poor to moderate (r = 0.09-0.50). The strongest correlation was found in patients with futile thrombectomies (r = 0.61). Median CNN estimates showed a trend for overestimation compared to FIVs. CTA was acquired in the mid arterial phase in virtually all patients (120/121).

Conclusions

This study showed no effect of collateral status on the reliability of the CNN and best correlation was found in patients with futile thrombectomies. CTA timing in the mid arterial phase in virtually all patients can explain infarct volume overestimation.

Advances in knowledge

CTA timing seems to be the most important factor influencing the reliability of current CTA-based machine learning methods, emphasizing the need for CTA protocol optimization for infarct core estimation.

Proposed Protocols for Artificial Intelligence Imaging Database in Acute Stroke Imaging

PURPOSE

To propose standardized and feasible imaging protocols for constructing artificial intelligence (AI) database in acute stroke by assessing the current practice at tertiary hospitals in South Korea and reviewing evolving AI models.

MATERIALS AND METHODS

A nationwide survey on acute stroke imaging protocols was conducted using an electronic questionnaire sent to 43 registered tertiary hospitals between April and May 2021. Imaging protocols for endovascular thrombectomy (EVT) in the early and late time windows and during follow-up were assessed. Clinical applications of AI techniques in stroke imaging and required sequences for developing AI models were reviewed. Standardized and feasible imaging protocols for data curation in acute stroke were proposed.

RESULTS

There was considerable heterogeneity in the imaging protocols for EVT candidates in the early and late time windows and posterior circulation stroke. Computed tomography (CT)-based protocols were adopted by 70% (30/43), and acquisition of noncontrast CT, CT angiography and CT perfusion in a single session was most commonly performed (47%, 14/30) with the preference of multiphase (70%, 21/30) over single phase CT angiography. More hospitals performed magnetic resonance imaging (MRI)-based protocols or additional MRI sequences in a late time window and posterior circulation stroke. Diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) were most commonly performed MRI sequences with considerable variation in performing other MRI sequences. AI models for diagnostic purposes required noncontrast CT, CT angiography and DWI while FLAIR, dynamic susceptibility contrast perfusion, and T1-weighted imaging (T1WI) were additionally required for prognostic AI models.

CONCLUSION

Given considerable heterogeneity in acute stroke imaging protocols at tertiary hospitals in South Korea, standardized and feasible imaging protocols are required for constructing AI database in acute stroke. The essential sequences may be noncontrast CT, DWI, CT/MR angiography and CT/MR perfusion while FLAIR and T1WI may be additionally required.

Identifying 'fast progressors' likely to benefit from mechanical thrombectomy

OBJECTIVES

Although the effect of mechanical thrombectomy in large vessel occlusions has been clearly demonstrated, there are different opinions about the treatment of patients with low ASPECT scores. We conducted this research to explore the utility of mechanical thrombectomy for the fast progressor patients.

METHODS

We evaluated 394 patients with large vessel occlusion (LVO) who applied to our center between 2012 and 2020 retrospectively. Patients with posterior system stroke and who admitted 6 h after the onset of symptoms, were not included in the study. The remaining 256 patients were divided into two groups as computed tomography angiography source image Alberta stroke program early computer tomography score (CTA-SI ASPECT) ≤ 6 and > 6. Modified rankin scale (mRS) 0-2 defined as good clinical outcome. Thrombolysis in cerebral infarction (TICI) score 2c-3 was accepted as successful recanalization.

RESULTS

The mean age of the patients in the fast-progressive group (23.4%; n = 60) was 66.3 ± 11.6 years, whereas the mean age of the CTA-SI ASPECTS > 6 group (76.6%; n = 196) was 62.4 ± 12.8 years (p = 0.034) A statistically significant difference was found between the groups regarding 90-day mRS (p < 0.001). Whereas 61.7% of the patients with a CTA-SI ASPECTS > 6 had a 90-day mRS 0-2, this rate was 28.3% for patients with a CTA-SI ASPECTS ≤ 6.

CONCLUSION

According to our study, approximately 1/3 of patients with ASPECTS ≤ 6 benefit from mechanical thrombectomy. In this patient group, age emerged as a determinant of good clinical outcome.

Computed tomography angiography-based deep learning method for treatment selection and infarct volume prediction in anterior cerebral circulation large vessel occlusion

Background

Computed tomography perfusion (CTP) is the mainstay to determine possible eligibility for endovascular thrombectomy (EVT), but there is still a need for alternative methods in patient triage.

Purpose

To study the ability of a computed tomography angiography (CTA)-based convolutional neural network (CNN) method in predicting final infarct volume in patients with large vessel occlusion successfully treated with endovascular therapy.

Materials and Methods

The accuracy of the CTA source image-based CNN in final infarct volume prediction was evaluated against follow-up CT or MR imaging in 89 patients with anterior circulation ischemic stroke successfully treated with EVT as defined by Thrombolysis in Cerebral Infarction category 2b or 3 using Pearson correlation coefficients and intraclass correlation coefficients. Convolutional neural network performance was also compared to a commercially available CTP-based software (RAPID, iSchemaView).

Results

A correlation with final infarct volumes was found for both CNN and CTP-RAPID in patients presenting 6–24 h from symptom onset or last known well, with r = 0.67 (p < 0.001) and r = 0.82 (p < 0.001), respectively. Correlations with final infarct volumes in the early time window (0–6 h) were r = 0.43 (p = 0.002) for the CNN and r = 0.58 (p < 0.001) for CTP-RAPID. Compared to CTP-RAPID predictions, CNN estimated eligibility for thrombectomy according to ischemic core size in the late time window with a sensitivity of 0.38 and specificity of 0.89.

Conclusion

A CTA-based CNN method had moderate correlation with final infarct volumes in the late time window in patients successfully treated with EVT.

Relationship of electrocardiographic changes and severity of acute cerebral ischemic stroke in old patients: A clinical observational study

There was a controversy for the electrocardiogram (ECG) changes and their relationship with disease severity in old patients with acute cerebral ischemic stroke (CIS). This study was aim to provide referential data for this topic.Totally 200 old patients with acute CIS in our hospital from January 2017 to December 2019 were included into this study. According to the ST-T segment changes in ECG, these patients were divided into 3 groups: persistent ischemic group (n = 38), transient ischemic group (n = 106) and non-ischemic group (n = 56). The characteristics and incidence of abnormal ECG and their relationship with disease severity, infarct size and prognosis were respectively analyzed under the severe, moderate and mild type of disease.The ECG changes of patients were mainly characterized by myocardial ischemic ST-T segment changes with a abnormal ECG incidence of 72.00%, the arrhythmia with a abnormal ECG incidence of 9.50%, which were the second most common in clinical features. There were statistically significant differences of myocardial ischemic ST-T segment changes among different disease severity, infarct size and prognosis of acute CIS patients (P < .05). The ischemic ST-T segment changes of ECG reflected that the disease severity, and more ECG abnormalities indicated more severe pathological conditions in CIS patients.The characteristics of ischemic ST-T segment changes have important reference value in the evaluation of severity and prognosis of acute CIS in old patients.

Evaluation of a CTA-based convolutional neural network for infarct volume prediction in anterior cerebral circulation ischaemic stroke

BACKGROUND

Computed tomography angiography (CTA) imaging is needed in current guideline-based stroke diagnosis, and infarct core size is one factor in guiding treatment decisions. We studied the efficacy of a convolutional neural network (CNN) in final infarct volume prediction from CTA and compared the results to a CT perfusion (CTP)-based commercially available software (RAPID, iSchemaView).

METHODS

We retrospectively selected 83 consecutive stroke cases treated with thrombolytic therapy or receiving supportive care that presented to Helsinki University Hospital between January 2018 and July 2019. We compared CNN-derived ischaemic lesion volumes to final infarct volumes that were manually segmented from follow-up CT and to CTP-RAPID ischaemic core volumes.

RESULTS

An overall correlation of r = 0.83 was found between CNN outputs and final infarct volumes. The strongest correlation was found in a subgroup of patients that presented more than 9 h of symptom onset (r = 0.90). A good correlation was found between the CNN outputs and CTP-RAPID ischaemic core volumes (r = 0.89) and the CNN was able to classify patients for thrombolytic therapy or supportive care with a 1.00 sensitivity and 0.94 specificity.

CONCLUSIONS

A CTA-based CNN software can provide good infarct core volume estimates as observed in follow-up imaging studies. CNN-derived infarct volumes had a good correlation to CTP-RAPID ischaemic core volumes.

Brain Computed Tomography Angiography Maximum Intensity Projection Images for ASPECTS Derivation and Detection of Large Infarct Volumes: Preliminary Study

PURPOSE

Non-contrast CT ASPECTS (NCCT_asp) has an established role in determining eligibility for mechanical thrombectomy in centers without ready access to perfusion or DWI. Moreover, it has been suggested that CTA source ASPECTS (CTA_asp) may be superior to NCCT_asp in predicting final infarct volume (FIV). In this study, we hypothesized that CTA maximum intensity projection ASPECTS (MIPS_asp) would be superior compared to both NCCT_asp and CTA_asp in predicting FIV as measured by DWI.

MATERIALS AND METHODS

In 41 consecutive patients with MCA territory infarcts, NCCT_asp, CTA_asp and MIPS_asp were visually assessed by 2 neuroradiologists. Disagreements were adjudicated by a third neuroradiologist, and the reconciled data used for all further analysis. MR-DWI was used as the standard for FIV determination. Receiver operating characteristic curve analysis was used to compare the area under the curve for all three CT-based methods in predicting FIV ≥70 ml.

RESULTS

MIPS_asp (AUC: 0.98, CI: 0.88-1.00) were statistically better than NCCT_asp (AUC: 0.87, 95% CI: 0.72-0.95; p=0.01) in predicting FIV ≥70 ml. MIPS_asp were also superior to CTA_asp (AUC: 0.9, CI: 0.79-.98; p˂0.05). Optimal test performance for predicting FIV ≥70 ml for MIPS_asp was ≤6 (sensitivity=100%, specificity=91.4%; Youden's J=0.98).

CONCLUSION

Our preliminary study suggests that a novel CTA-MIPS derived ASPECTS better predicts large MCA territory infarcts compared to CTA source and non-contrast ASPECTS. Thus, MIPS_asp may be a promising technique for future studies aimed at improving ischemic stroke treatment in centers using ASPECTS for stroke management.

Performance of Automated Attenuation Measurements at Identifying Large Vessel Occlusion Stroke on CT Angiography

PURPOSE

Computed tomography angiography (CTA) is routinely used to detect large-vessel occlusion (LVO) in patients with suspected acute ischemic stroke; however, visual analysis is time consuming and prone to error. To evaluate solutions to support imaging triage, we tested performance of automated analysis of CTA source images (CTASI) at identifying patients with LVO.

METHODS

Stroke patients with LVO were selected from a prospectively acquired cohort. A control group was selected from consecutive patients with clinically suspected stroke without signs of ischemia on CT perfusion (CTP) or infarct on follow-up. Software-based automated segmentation and Hounsfield unit (HU) measurements were performed on CTASI for all regions of the Alberta Stroke Program Early CT score (ASPECTS). We derived different parameters from raw measurements and analyzed their performance to identify patients with LVO using receiver operating characteristic curve analysis.

RESULTS

The retrospective analysis included 145 patients, 79 patients with LVO stroke and 66 patients without stroke. The parameters hemispheric asymmetry ratio (AR), ratio between highest and lowest regional AR and M2-territory AR produced area under the curve (AUC) values from 0.95-0.97 (all p < 0.001) for detecting presence of LVO in the total population. Resulting sensitivity (sens)/specificity (spec) defined by the Youden index were 0.87/0.97-0.99. Maximum sens/spec defined by the specificity threshold ≥0.70 were 0.91-0.96/0.77-0.83. Performance in a small number of patients with isolated M2 occlusion was lower (AUC: 0.72-0.85).

CONCLUSION

Automated attenuation measurements on CTASI identify proximal LVO stroke patients with high sensitivity and specificity. This technique can aid in accurate and timely patient selection for thrombectomy, especially in primary stroke centers without CTP capacity.

Cerebral attenuation on single-phase CT angiography source images: Automated ischemia detection and morphologic outcome prediction after thrombectomy in patients with ischemic stroke

Objectives

Stroke triage using CT perfusion (CTP) or MRI gained importance after successful application in recent trials on late-window thrombectomy but is often unavailable and time-consuming. We tested the clinical value of software-based analysis of cerebral attenuation on Single-phase CT angiography source images (CTASI) as CTP surrogate in stroke patients.

Methods

Software-based automated segmentation and Hounsfield unit (HU) measurements for all regions of the Alberta Stroke Program Early CT Score (ASPECTS) on CTASI were performed in patients with large vessel occlusion stroke who underwent thrombectomy. To normalize values, we calculated relative HU (rHU) as ratio of affected to unaffected hemisphere. Ischemic regions, regional ischemic core and final infarction were determined on simultaneously acquired CTP and follow-up imaging as ground truth. Receiver operating characteristics analysis was performed to calculate the area-under-the-curve (AUC). Resulting cut-off values were used for comparison with visual analysis and to calculate an 11-point automated CTASI ASPECTS.

Results

Seventy-nine patients were included. rHU values enabled significant classification of ischemic involvement on CTP in all ten regions of the ASPECTS (each p<0.001, except M4-cortex p = 0.002). Classification of ischemic core and prediction of final infarction had best results in subcortical regions but produced lower AUC values with significant classification for all regions except M1, M3 and M5. Relative total hemispheric attenuation provided strong linear correlation with CTP total ischemic volume. Automated classification of regional ischemia on CTASI was significantly more accurate in most regions and provided better agreement with CTP cerebral blood flow ASPECTS than visual assessment.

Conclusions

Automated attenuation measurements on CTASI provide excellent performance in detecting acute ischemia as identified on CTP with improved accuracy compared to visual analysis. However, value for the approximation of ischemic core and morphologic outcome in large vessel occlusion stroke after thrombectomy was regionally dependent and limited. This technique has the potential to facilitate stroke imaging as sensitive surrogate for CTP-based ischemia.

Preliminary study of time maximum intensity projection computed tomography imaging for the detection of early ischemic change in patient with acute ischemic stroke

Noncontrast computed tomography (NCCT) has been used for the detection of early ischemic change (EIC); however, correct interpretation of NCCT findings requires much clinical experience. This study aimed to assess the accuracy of time maximum intensity projection computed tomography technique (tMIP), which reflects the maximum value for the time phase direction from the dynamic volume data for each projected plane, for detection of EIC, against that of NCCT.Retrospective review of NCCT, cerebral blood volume in CT perfusion (CTP-CBV), and tMIP of 186 lesions from 280 regions evaluated by Alberta Stroke Program Early CT Score (ASPECTS) in 14 patients with acute middle cerebral artery stroke who had undergone whole-brain CTP using 320-row area detector CT was performed. Four radiologists reviewed EIC on NCCT, CTP-CBV, and tMIP in each ASPECTS region at onset using the continuous certainty factor method. Receiver operating characteristic analysis was performed to compare the relative performance for detection of EIC. The correlations were evaluated.tMIP-color showed the best discriminative value for detection of EIC. There were significant differences in the area under the curve for NCCT and tMIP-color, CTP-CBV (P < .05). Scatter plots of ASPECTS showed a positive significant correlation between NCCT, tMIP-gray, tMIP-color, and the follow-up study (NCCT, r = 0.32, P = .0166; tMIP-gray, r = 0.44, P = .0007; tMIP-color, r = 0.34, P = .0104).Because tMIP provides a high contrast parenchymal image with anatomical and vascular information in 1 sequential scan, it showed greater accuracy for detection of EIC and predicted the final infarct extent more accurately than NCCT based on ASPECTS.