Imaging Clot Characteristics in Stroke and its Possible Implication on Treatment

Safety and efficacy of stent retrievers plus contact aspiration in patients with acute ischaemic anterior circulation stroke and positive susceptibility vessel sign in France (VECTOR): a randomised, single-blind trial

BACKGROUND

Positive susceptibility vessel sign (SVS) in patients with acute ischaemic stroke has been associated with friable red blood cell-rich clots and more effective recanalisation using stent retrievers versus contact aspiration. We compared the safety and efficacy of stent retrievers plus contact aspiration (combined technique) versus contact aspiration alone as the first-line thrombectomy technique in patients with acute ischaemic anterior circulation stroke and SVS-positive occlusions.

METHODS

Adaptive Endovascular Strategy to the Clot MRI in Large Intracranial Vessel Occlusion (VECTOR) was a prospective, randomised, open-label study with blinded evaluation. Patients with SVS-positive anterior circulation occlusions on pretreatment MRI and arterial puncture within 24 h of symptom onset were enrolled from 22 centres in France. A centralised web-based method was used by interventional neuroradiologists for dynamic randomisation by minimisation. Patients were randomly assigned 1:1 to the combined technique or contact aspiration alone. The primary outcome was expanded Thrombolysis in Cerebral Infarction (eTICI) grade 2c or 3 reperfusion after three or fewer passes on post-treatment angiogram, adjudicated by a blinded independent central imaging core laboratory. The intention-to-treat population was used to assess the primary and secondary outcomes. This trial is registered with ClinicalTrials.gov (NCT04139486) and is complete.

FINDINGS

Between Nov 26, 2019, and Feb 14, 2022, 526 patients were enrolled, of whom 521 constituted the intention-to-treat population (combined technique, n=263; contact aspiration alone, n=258). The median age of participants was 74·9 years (IQR 64·4-83·3); 284 (55%) were female and 237 (45%) male. The primary outcome did not differ significantly between groups (152 [58%] of 263 patients for the combined technique vs 135 [52%] of 258 for contact aspiration; odds ratio [OR] 1·27; 95% CI 0·88-1·83; p=0·19). Procedure-related adverse events occurred in 32 (12%) of 263 patients in the combined technique group and 27 (11%) of 257 in the contact aspiration group (OR 1·14; 0·65-2·00; p=0·65). The most common adverse event was intracerebral haemorrhage (146 [56%] of 259 patients for the combined technique vs 123 [49%] of 251 for contact aspiration; OR 1·32; 0·91-1·90; p=0·13). All-cause mortality at 3 months occurred in 57 (23%) of 251 patients in the combined technique group and 48 (19%) of 247 in the contact aspiration group (OR 1·19; 0·76-1·86; p=0·45), none of which was treatment-related.

INTERPRETATION

The results of the VECTOR trial do not show superiority of the combined stent retriever plus contact aspiration technique over contact aspiration alone in patients with SVS-positive occlusion with respect to achieving eTICI 2c-3 within three passes. These findings support the use of either the combined technique or contact aspiration alone as the initial thrombectomy strategy in patients with acute anterior circulation stroke with SVS on pretreatment MRI.

FUNDING

Cerenovus.

Multimaterial decomposition in dual-energy CT for characterization of clots from acute ischemic stroke patients

BACKGROUND

Nowadays, there is no method to quantitatively characterize the material composition of acute ischemic stroke thrombi prior to intervention, but dual-energy CT (DE-CT) offers imaging-based multimaterial decomposition. We retrospectively investigated the material composition of thrombi ex vivo using DE-CT with histological analysis as a reference.

METHODS

Clots of 70 patients with acute ischemic stroke were extracted by mechanical thrombectomy and scanned ex vivo in formalin-filled tubes with DE-CT. Multimaterial decomposition in the three components, i.e., red blood cells (RBC), white blood cells (WBC), and fibrin/platelets (F/P), was performed and compared to histology (hematoxylin/eosin staining) as reference. Attenuation and effective Z values were assessed, and histological composition was compared to stroke etiology according to the Trial of ORG 10172 in Acute Stroke Treatment (TOAST) criteria.

RESULTS

Histological and imaging analysis showed the following correlation coefficients for RBC (r = 0.527, p < 0.001), WBC (r = 0.305, p = 0.020), and F/P (r = 0.525, p < 0.001). RBC-rich thrombi presented higher clot attenuation in Hounsfield units than F/P-rich thrombi (51 HU versus 42 HU, p < 0.01). In histological analysis, cardioembolic clots showed less RBC (40% versus 56%, p = 0.053) and more F/P (53% versus 36%, p = 0.024), similar to cryptogenic clots containing less RBC (34% versus 56%, p = 0.006) and more F/P (58% versus 36%, p = 0.003) than non-cardioembolic strokes. No difference was assessed for the mean WBC portions in all TOAST groups.

CONCLUSIONS

DE-CT has the potential to quantitatively characterize the material composition of ischemic stroke thrombi.

RELEVANCE STATEMENT

Using DE-CT, the composition of ischemic stroke thrombi can be determined. Knowledge of histological composition prior to intervention offers the opportunity to define personalized treatment strategies for each patient to accomplish faster recanalization and better clinical outcomes.

KEY POINTS

• Acute ischemic stroke clots present different recanalization success according to histological composition. • Currently, no method can determine clot composition prior to intervention. • DE-CT allows quantitative material decomposition of thrombi ex vivo in red blood cells, white blood cells, and fibrin/platelets. • Histological clot composition differs between stroke etiology. • Insights into the histological composition in situ offer personalized treatment strategies.

A propensity score-matched comparative study of balloon guide catheters versus conventional guide catheters for concurrent mechanical thrombectomy with carotid stenting in tandem strokes: comparison of first pass effect, symptomatic intracranial hemorrhage, and 90-day functional outcomes

BACKGROUND

Extensive clot burden in tandem strokes accounts for poor mechanical thrombectomy (MT) outcomes. Several studies have shown the benefit of balloon guide catheters (BGCs) in MT and carotid artery stenting.

OBJECTIVE

In view of this potential benefit, to investigate the safety and effectiveness of proximal flow arrest using a BGC during concurrent MT and carotid revascularization for tandem stroke treatment in a comparative, propensity score-matched (PSM) study.

METHODS

Patients with a tandem stroke identified from our endovascular database were dichotomized into groups treated with BGCs versus conventional guide catheters. One-to-one PSM adjustment for baseline demographics and treatment selection bias using nearest-neighbor matching was performed. Patient demographics, presentation characteristics, and procedural details were recorded. Outcomes assessed were final modified Thrombolysis in Cerebral Infarction (mTICI) grade, periprocedural symptomatic intracranial hemorrhage (sICH) rate, in-hospital mortality, and 90-day modified Rankin Scale (mRS) score. Mann-Whitney U test and multivariate logistic regression were performed to compare procedural parameters and clinical outcomes.

RESULTS

Concurrent carotid revascularization (stenting with/without angioplasty) and MT was performed in 125 cases (BGC: 85; no BGC: 40). After PSM (40 patients/group), the BGC group had a significantly shorter procedure duration (77.9 vs 61.5 min; OR=0.996; P=0.006), lower discharge National Institutes of Health Stroke Scale score (8.0 vs 11.0; OR=0.987; P=0.042), and higher odds of 90-day mRS 0-2 score (52.3% vs 27.5%; OR=0.34; P=0.040). On multivariate regression, the BGC group had a significantly higher first pass effect rate (mTICI 2b or 3)(OR=1.115, 95% CI 1.015 to 1.432; P=0.013) and lower periprocedural sICH rate (OR=0.615, 95% CI 0.406 to 0.932; P=0.025). No difference in in-hospital mortality was observed (OR=1.591, 95% CI 0.976 to 2.593; P=0.067).

CONCLUSION

BGCs used for concurrent MT-carotid revascularization with flow arrest were safe and resulted in superior clinical and angiographic outcomes in patients with a tandem stroke.

Quantification of clot spatial heterogeneity and its impact on thrombectomy

BACKGROUND

Compositional and structural features of retrieved clots by thrombectomy can provide insight into improving the endovascular treatment of ischemic stroke. Currently, histological analysis is limited to quantification of compositions and qualitative description of the clot structure. We hypothesized that heterogeneous clots would be prone to poorer recanalization rates and performed a quantitative analysis to test this hypothesis.

METHODS

We collected and did histology on clots retrieved by mechanical thrombectomy from 157 stroke cases (107 achieved first-pass effect (FPE) and 50 did not). Using an in-house algorithm, the scanned images were divided into grids (with sizes of 0.2, 0.3, 0.4, 0.5, and 0.6 mm) and the extent of non-uniformity of RBC distribution was computed using the proposed spatial heterogeneity index (SHI). Finally, we validated the clinical significance of clot heterogeneity using the Mann-Whitney test and an artificial neural network (ANN) model.

RESULTS

For cases with FPE, SHI values were smaller (0.033 vs 0.039 for grid size of 0.4 mm, P=0.028) compared with those without. In comparison, the clot composition was not statistically different between those two groups. From the ANN model, clot heterogeneity was the most important factor, followed by fibrin content, thrombectomy techniques, red blood cell content, clot area, platelet content, etiology, and admission of intravenous tissue plasminogen activator (IV-tPA). No statistical difference of clot heterogeneity was found for different etiologies, thrombectomy techniques, and IV-tPA administration.

CONCLUSIONS

Clot heterogeneity can affect the clot response to thrombectomy devices and is associated with lower FPE. SHI can be a useful metric to quantify clot heterogeneity.

Computed Tomography Embolus Texture Analysis as a Prognostic Marker of Acute Pulmonary Embolism

Texture analysis is a quantitative imaging analysis that provides novel biomarkers beyond conventional image reading. Our aim was to use texture analysis of pulmonary emboli derived from thoracic computed tomography for prediction of mortality and prognosis of acute pulmonary embolism (PE). Overall, 216 patients (116 female, 53.7%) were included in the analysis. Texture analysis was calculated on axial slices of the contrast enhanced pulmonary angiography of the proximal embolus. Clinical scores, serological parameters, need for intubation, intensive care unit (ICU) admission and mortality was assessed and correlated with the texture features. In the correlation analysis, there were several associations with mortality in days, the highest for the parameter S(0,5)SumVarnc (r = -0.43, P < 0.001). Another parameter, S(3,-3)AngScMom correlated with sepsis-related organ failure assessment score (SOFA)-score (r = 0.31, P < 0.001). Several texture features correlated with venous lactate and glucose levels. In discrimination analysis, there were significant differences in regard to texture features between survivors and non-survivors and between patients with and without the need for ICU admission (P = 0.02, respectively). These results highlight the potential clinical benefit of texture features in patients with acute PE as novel imaging biomarkers. Further studies are needed to validate these results.

Traumatic Brain Magnetic Resonance Imaging Feature Extraction Based on Variable Model Algorithm in Stroke Examination

The purpose of this study was to explore the diagnostic value of different sequence scanning of nonparametric variable model-based cranial magnetic resonance imaging (MRI) for ischemic stroke. A histogram analysis-based nonparametric variable model was proposed first, which was compared with the parametric deformation (PD) model and geometric deformation (GD) model. Then, 116 patients with acute ischemic stroke were selected as the research subjects. Routine MRI (T2WI, T1WI, FLAIR, DWI, SWI, and 3D TOF MRA) and MR SCALE-PWI were performed. The results showed that the nonparametric variable model algorithm was relatively complete in the actual segmentation results of MRI images, and the display clarity of lesions was better than PD and GD algorithms. The diagnostic sensitivity, specificity, and overall performance of the variable model algorithm were significantly higher than those of the other two algorithms (P < 0.05). According to ROC curve analysis, the AUC areas of DWI, SWI, 3D TOF MRA, and MR SCALE-PWI for the diagnosis of ischemic penumbra were 0.793, 0.825, 0.871, and 0.933, respectively. In summary, the segmentation results of MRI images by the nonparametric variable model based on histogram analysis were relatively complete, and the clarity of lesions was better than that of the traditional model. MRI images can effectively identify the occurrence of ischemic stroke. Moreover, MR SCALE-PWI had a good early identification effect on ischemic penumbra, which can reduce unnecessary treatment for patients.

Impedance-based sensors discriminate among different types of blood thrombi with very high specificity and sensitivity

BACKGROUND

Intracranial occlusion recanalization fails in 20% of endovascular thrombectomy procedures, and thrombus composition is likely to be an important factor. In this study, we demonstrate that the combination of electrical impedance spectroscopy (EIS) and machine learning constitutes a novel and highly accurate method for the identification of different human thrombus types.

METHODS

134 samples, subdivided into four categories, were analyzed by EIS: 29 'White', 26 'Mixed', 12 'Red' thrombi, and 67 liquid 'Blood' samples. Thrombi were generated in vitro using citrated human blood from five healthy volunteers. Histological analysis was performed to validate the thrombus categorization based on red blood cell content. A machine learning prediction model was trained on impedance data to differentiate blood samples from any type of thrombus and in between the four sample categories.

RESULTS

Histological analysis confirmed the similarity between the composition of in vitro generated thrombi and retrieved human thrombi. The prediction model yielded a sensitivity/specificity of 90%/99% for distinguishing blood samples from thrombi and a global accuracy of 88% for differentiating among the four sample categories.

CONCLUSIONS

Combining EIS measurements with machine learning provides a highly effective approach for discriminating among different thrombus types and liquid blood. These findings raise the possibility of developing a probe-like device (eg, a neurovascular guidewire) integrating an impedance-based sensor. This sensor, placed in the distal part of the smart device, would allow the characterization of the probed thrombus on contact. The information could help physicians identify optimal thrombectomy strategies to improve outcomes for stroke patients.

Prognostic capacity of hyperdense middle cerebral artery sign in anterior circulation acute ischaemic stroke patients receiving reperfusion therapy: a systematic review and meta-analysis

Pre-intervention CT imaging-based biomarkers, such as hyperdense middle cerebral artery sign (HMCAS) may have a role in acute ischaemic stroke prognostication. However, the clinical utility of HMCAS in settings of reperfusion therapy and the level of prognostic association is still unclear. This systematic review and meta-analysis investigated the association of HMCAS sign with clinical outcomes and its prognostic capacity in acute ischaemic stroke patients treated with reperfusion therapy. Prospective and retrospective studies from the following databases were retrieved from EMBASE, MEDLINE and Cochrane. Association of HMCAS with functional outcome, symptomatic intracerebral haemorrhage (sICH) and mortality were investigated. The random effect model was used to calculate the risk ratio (RR). Subgroup analyses were performed for subgroups of patients receiving thrombolysis (tPA), mechanical thrombectomy (EVT) and/or combined therapy (tPA + EVT). HMCAS significantly increased the rate of poor functional outcome by 1.43-fold in patients (RR 1.43; 95% CI 1.30-1.57; p < 0.0001) without any significant differences in sICH rates (RR 0.91; 95% CI 0.68-1.23; p = 0.546) and mortality (RR 1.34; 95% CI 0.72-2.51; p = 354) in patients with positive HMCAS as compared to negative HMCAS. In subgroup analyses, significant association between HMCAS and 90 days functional outcome was observed in patients receiving tPA (RR 1.53; 95% CI 1.40-1.67; p < 0.0001) or both therapies (RR 1.40; 95% CI 1.08-1.80; p = 0.010). This meta-analysis demonstrated that pre-treatment HMCAS increases risk of poor functional outcomes. However, its prognostic sensitivity and specificity in predicting long-term functional outcome, mortality and sICH after reperfusion therapy is poor.

Fully Automated Thrombus Segmentation on CT Images of Patients with Acute Ischemic Stroke

Thrombus imaging characteristics are associated with treatment success and functional outcomes in stroke patients. However, assessing these characteristics based on manual annotations is labor intensive and subject to observer bias. Therefore, we aimed to create an automated pipeline for consistent and fast full thrombus segmentation. We used multi-center, multi-scanner datasets of anterior circulation stroke patients with baseline NCCT and CTA for training (n = 228) and testing (n = 100). We first found the occlusion location using StrokeViewer LVO and created a bounding box around it. Subsequently, we trained dual modality U-Net based convolutional neural networks (CNNs) to segment the thrombus inside this bounding box. We experimented with: (1) U-Net with two input channels for NCCT and CTA, and U-Nets with two encoders where (2) concatenate, (3) add, and (4) weighted-sum operators were used for feature fusion. Furthermore, we proposed a dynamic bounding box algorithm to adjust the bounding box. The dynamic bounding box algorithm reduces the missed cases but does not improve Dice. The two-encoder U-Net with a weighted-sum feature fusion shows the best performance (surface Dice 0.78, Dice 0.62, and 4% missed cases). Final segmentation results have high spatial accuracies and can therefore be used to determine thrombus characteristics and potentially benefit radiologists in clinical practice.

Characterising acute ischaemic stroke thrombi: insights from histology, imaging and emerging impedance-based technologies

Treatment of acute ischaemic stroke (AIS) focuses on rapid recanalisation of the occluded artery. In recent years, advent of mechanical thrombectomy devices and new procedures have accelerated the analysis of thrombi retrieved during the endovascular thrombectomy procedure. Despite ongoing developments and progress in AIS imaging techniques, it is not yet possible to conclude definitively regarding thrombus characteristics that could advise on the probable efficacy of thrombolysis or thrombectomy in advance of treatment. Intraprocedural devices with dignostic capabilities or new clinical imaging approaches are needed for better treatment of AIS patients. In this review, what is known about the composition of the thrombi that cause strokes and the evidence that thrombus composition has an impact on success of acute stroke treatment has been examined. This review also discusses the evidence that AIS thrombus composition varies with aetiology, questioning if suspected aetiology could be a useful indicator to stroke physicians to help decide the best acute course of treatment. Furthermore, this review discusses the evidence that current widely used radiological imaging tools can predict thrombus composition. Further use of new emerging technologies based on bioimpedance, as imaging modalities for diagnosing AIS and new medical device tools for detecting thrombus composition in situ has been introduced. Whether bioimpedance would be beneficial for gaining new insights into in situ thrombus composition that could guide choice of optimum treatment approach is also reviewed.

Non contrast enhanced volumetric histology of blood clots through high resolution propagation-based X-ray microtomography

We have demonstrated the capability of laboratory propagation-based microtomography (miroCT) in non-destructive 3D virtual histopathology of human blood clots without any contrast agent. The volumetric information are valuable to understand the mechanical properties of clots which are crucial in selecting the most efficient mechanical thrombectomy method for clot extraction. Different clot types retrieved by mechanical thrombectomy from patient victims of acute ischemic stroke were evaluated through propagation-based microCT. The results were correlated with high-resolution scanning electron microscopy (SEM) images, confirming detected cellular and fibrillary structures. Calcifications appeared as glassy opacity areas with relatively intense signal on microCT images, also proved by energy-dispersive spectroscopy and X-ray diffraction. Hyperintense regions on the microCT corresponded to individual or compact aggregates of red blood cells, whereas fibrin dominated volumes appeared at consistently moderate to low normalized microCT values. Red blood cell shapes and sizes are consistent with the SEM observations. Together with other potential parameters, 3D porosity distribution and volume fraction of structures can be easily measured by microCT data. Further development of automated post-processing techniques for X-ray propagation-based micro/nanoCT, also based on machine learning algorithms, can enable high throughput analysis of blood clot composition and their 3D histological features on large sample cohorts.

A clinical perspective on endovascular stroke treatment biomechanics

Acute ischemic stroke (AIS) is caused by blockage of an arterial blood vessel in the brain by a thrombus, which interrupts oxygen supply to the brain parenchyma. The goal of endovascular stroke treatment (mechanical thrombectomy) is to restore blood flow as quickly and completely as possible. There are numerous factors that influence endovascular treatment success. They can be broadly grouped into a) factors related to blood vessels, b) factors related to the thrombus, c) factors related to endovascular treatment technique and tools and d) operator-related factors. While blood vessel and tgthro thrombus-related factors are mostly non-modifiable in the acute setting, operator and technique-related factors can be modified, and extensive research is currently being done to investigate the complex interplay of all these variables, and to optimize the modifiable factors to the maximum possible extent. In this review, we will describe these factors and how they interact with each other in detail, and outline some of their practical implications. We will conclude with a short summary and outlook on future directions for optimizing endovascular treatment success.

Diagnostic and prognostic utility of computed tomography perfusion imaging in posterior circulation acute ischemic stroke: A systematic review and meta-analysis

BACKGROUND

Computed tomography perfusion (CTP) imaging could be useful in the diagnosis of posterior circulation stroke (PCS) and in identifying patients who are likely to experience favorable outcomes following reperfusion therapy. The current study sought to investigate the diagnostic and prognostic capability of CTP in acute ischemic PCS by performing a systematic review and meta-analysis.

METHODS

Medline/PubMed and the Cochrane Library were searched using the terms: "posterior circulation", "CT perfusion", "acute stroke", and "reperfusion therapy". The following studies were included: (1) patients aged 18 years or above; (2) patients diagnosed with PCS; and (3) studies with good methodological design. Pooled sensitivity (SENS), specificity (SPEC), and area under the curve (AUC), computed using the summary receiver operating characteristic (SROC) curves, were used to determine diagnostic/prognostic capability.

RESULTS

Out of 14 studies included, a meta-analysis investigating diagnostic accuracy of CTP was performed on nine studies. Meta-analysis demonstrated comparable diagnostic accuracy of CTP to non-contrast computed tomography (NCCT) (AUC_CTP : 0.90 [95% CI 0.87-0.92] vs. AUC_NCCT : 0.96 [95% CI 0.94-0.97]); however, with higher pooled sensitivity (SENS_CTP : 72% [95% CI 57%-83%] vs. SENS_NCCT : 25% [95% CI 17%-35%]) and lower specificity (SPEC_CTP : 90% [95% CI 83%-94%] vs. SPEC_NCCT : 96% [95% CI 95%-98%]) than NCCT. Meta-analysis to determine prognostic capability of CTP could not be performed.

CONCLUSIONS

CTP has limited diagnostic utility in acute ischemic PCS, albeit with superior diagnostic sensitivity and inferior diagnostic specificity to NCCT. Further prospective trials are required to validate the prognostic capability of CTP-derived parameters in PCS.

Clot-based radiomics features predict first pass effect in acute ischemic stroke

PURPOSE

Our aim was to evaluate the performance of clot-based radiomics features (RFs) for predicting first pass effect (FPE) in patients with acute ischemic stroke (AIS). The secondary purpose was to search for any other variables associated with FPE.

MATERIALS AND METHODS

Patients who underwent mechanical thrombectomy (MT) for anterior circulation large vessel stroke in a single center were retrospectively reviewed. Patients were divided into two groups: FPE and non-FPE. Two observers extracted RFs from the clot on pretreatment noncontrast computed tomography (NCCT) images. Demographic, clinical, periprocedural, and RFs were compared between the groups and receiver operating characteristic (ROC) curves were constructed. Logistic regression analysis was used to determine the independent predictors of FPE.

RESULTS

Fifty-two patients (27 female, 25 male; mean age 64.50 ± 15.15) who were treated by stent retrievers as the first option were included in the study. FPE was achieved in 25 patients (25/52, 48.1%). Twelve RFs were significantly different between patients with FPE and non-FPE. The long-run low gray-level emphasis (odds ratio = 44.24, p = 0.003) and the zone percentage (odds ratio = 16.88, p = 0.017) were found as independent predictors of FPE. Female sex and a baseline ASPECT score of >8.5 were the other independent variables to predict FPE. The diagnostic accuracy to predict FPE was observed as 83% when using all independent predictors in our predictive model.

CONCLUSIONS

Clot-based RFs on NCCT may help to estimate the success of the intended outcome of MT in patients with AIS.

Endovascular treatment of acute ischemic stroke

Endovascular treatment of acute ischemic stroke has become the first choice of treatment in large cerebral vessel occlusions, with a very high efficacy in terms of revascularization and reducing disability of affected patients. Revolutionizing acute therapy, it induced important paradigm shifts in the concepts of time and salvageable brain. In this review we focus on the current concepts of patient selection, imaging, techniques and perspectives of endovascular stroke treatment.

Clot-Based Radiomics Predict a Mechanical Thrombectomy Strategy for Successful Recanalization in Acute Ischemic Stroke

Supplemental Digital Content is available in the text.

Background and Purpose:

Mechanical thrombectomy (MTB) is a reference treatment for acute ischemic stroke, with several endovascular strategies currently available. However, no quantitative methods are available for the selection of the best endovascular strategy or to predict the difficulty of clot removal. We aimed to investigate the predictive value of an endovascular strategy based on radiomic features extracted from the clot on preinterventional, noncontrast computed tomography to identify patients with first-attempt recanalization with thromboaspiration and to predict the overall number of passages needed with an MTB device for successful recanalization.

Methods:

We performed a study including 2 cohorts of patients admitted to our hospital: a retrospective training cohort (n=109) and a prospective validation cohort (n=47). Thrombi were segmented on noncontrast computed tomography, followed by the automatic computation of 1485 thrombus-related radiomic features. After selection of the relevant features, 2 machine learning models were developed on the training cohort to predict (1) first-attempt recanalization with thromboaspiration and (2) the overall number of passages with MTB devices for successful recanalization. The performance of the models was evaluated on the prospective validation cohort.

Results:

A small subset of radiomic features (n=9) was predictive of first-attempt recanalization with thromboaspiration (receiver operating characteristic curve–area under the curve, 0.88). The same subset also predicted the overall number of passages required for successful recanalization (explained variance, 0.70; mean squared error, 0.76; Pearson correlation coefficient, 0.73; P<0.05).

Conclusions:

Clot-based radiomics have the ability to predict an MTB strategy for successful recanalization in acute ischemic stroke, thus allowing a potentially better selection of the MTB strategy, as well as patients who are most likely to benefit from the intervention.