Search

Computed tomography perfusion (CTP) is frequently used in the triage of ischemic stroke patients for endovascular thrombectomy (EVT). We aimed to quantify the volumetric and spatial agreement of the CTP ischemic core estimated with different thresholds and follow-up MRI infarct volume on diffusion-weighted imaging (DWI). Patients treated with EVT between November 2017 and September 2020 with available baseline CTP and follow-up DWI were included. Data were processed with Philips IntelliSpace Portal using four different thresholds. Follow-up infarct volume was segmented on DWI. In 55 patients, the median DWI volume was 10 mL, and median estimated CTP ischemic core volumes ranged from 10–42 mL. In patients with complete reperfusion, the intraclass correlation coefficient (ICC) showed moderate-good volumetric agreement (range 0.55–0.76). A poor agreement was found for all methods in patients with successful reperfusion (ICC range 0.36–0.45). Spatial agreement (median Dice) was low for all four methods (range 0.17–0.19). Severe core overestimation was most frequently (27%) seen in Method 3 and patients with carotid-T occlusion. Our study shows moderate–good volumetric agreement between ischemic core estimates for four different thresholds and subsequent infarct volume on DWI in EVT-treated patients with complete reperfusion. The spatial agreement was similar to other commercially available software packages.

Background and objective Computed tomography perfusion (CTP) is widely used in the evaluation of acute ischemic stroke patients for endovascular thrombectomy (EVT). The stability of CTP core estimation is suboptimal and varies between software packages. We aimed to quantify the volumetric and spatial agreement between the CTP ischemic core and follow-up infarct for four ischemic core estimation approaches using syngo.via. Methods We included successfully reperfused, EVT-treated patients with baseline CTP and 24h follow-up diffusion weighted magnetic resonance imaging (DWI) (November 2017–September 2020). Data were processed with syngo.via VB40 using four core estimation approaches based on: cerebral blood volume (CBV) Results In 59 patients, median estimated CTP core volumes for four core estimation approaches ranged from 12–39 mL. Median 24h follow-up DWI infarct volume was 11 mL. The intraclass correlation coefficient (ICC) showed moderate–good volumetric agreement for all approaches (range 0.61–0.76). Median Dice was low for all approaches (range 0.16–0.21). CTP core overestimation >10mL occurred least frequent (14/59 [24%] patients) using the CBV-based core estimation approach with smoothing filter. Conclusions In successfully reperfused patients who underwent EVT, syngo.via CTP ischemic core estimation showed moderate volumetric and spatial agreement with the follow-up infarct on DWI. In patients with complete reperfusion after EVT, the volumetric agreement was excellent. A CTP core estimation approach based on CBV

Background and purposeCT perfusion (CTP) might support decision making in patients with acute ischemic stroke by providing perfusion maps of ischemic tissue. Currently, the reliability of CTP is hampered by varying results between different post-processing software packages. The purpose of this study is to compare ischemic core volumes estimated by IntelliSpace Portal (ISP) and syngo.via with core volumes as estimated by RAPID.MethodsThirty-five CTP datasets from patients in the MR CLEAN trial were post-processed. Core volumes were estimated with ISP using default settings and with syngo.via using three different settings: default settings (method A); additional smoothing filter (method B); and adjusted settings (method C). The results were compared with RAPID. Agreement between methods was assessed using Bland–Altman analysis and intraclass correlation coefficient (ICC). Accuracy for detecting volumes up to 25 mL, 50 mL, and 70 mL was assessed. Final infarct volumes were determined on follow-up non-contrast CT.ResultsMedian core volume was 50 mL with ISP, 41 mL with syngo.via method A, 20 mL with method B, 36 mL with method C, and 11 mL with RAPID. Agreement ranged from poor (ISP: ICC 0.41; method A: ICC 0.23) to good (method B: ICC 0.83; method C: ICC 0.85). The bias (1.8 mL) and limits of agreement (−27, 31 mL) were the smallest with syngo.via with additional smoothing (method B). Agreement for detecting core volumes ≤25 mL with ISP was 54% and 57%, 85% and 74% for syngo.via methods A, B, and C, respectively.ConclusionBest agreement with RAPID software is provided by syngo.via default settings with additional smoothing. Moreover, this method has the highest agreement in categorizing patients with small core volumes.

BackgroundThrombus radiomics (TR) describe complex shape and textural thrombus imaging features. We aimed to study the relationship of TR extracted from non-contrast CT with procedural and functional outcome in endovascular-treated patients with acute ischemic stroke.MethodsThrombi were segmented on thin-slice non-contrast CT (≤1 mm) from 699 patients included in the MR CLEAN Registry. In a pilot study, we selected 51 TR with consistent values across two raters’ segmentations (ICC >0.75). Random forest models using TR in addition or as a substitute to baseline clinical variables (CV) and manual thrombus measurements (MTM) were trained with 499 patients and evaluated on 200 patients for predicting successful reperfusion (extended Thrombolysis in Cerebral Ischemia (eTICI) ≥2B), first attempt reperfusion, reperfusion within three attempts, and functional independence (modified Rankin Scale (mRS) ≤2). Three texture and shape features were selected based on feature importance and related to eTICI ≥2B, number of attempts to eTICI ≥2B, and 90-day mRS with ordinal logistic regression.ResultsRandom forest models using TR, CV or MTM had comparable predictive performance. Thrombus texture (inverse difference moment normalized) was independently associated with reperfusion (adjusted common OR (acOR) 0.85, 95% CI 0.72 to 0.99). Thrombus volume and texture were also independently associated with the number of attempts to successful reperfusion (acOR 1.36, 95% CI 1.03 to 1.88 and acOR 1.24, 95% CI 1.04 to 1.49).ConclusionsTR describing thrombus volume and texture were associated with more attempts to successful reperfusion. Compared with models using CV and MTM, TR had no added value for predicting procedural and functional outcome.

Introduction: Fast and accurate detection of large vessel occlusions (LVOs) is crucial in selection of patients for endovascular treatment. We assessed the diagnostic performance and speed of an Artifical Intelligence algorithm for automated LVO detection with a novel feature that specifies the exact level of occlusion. Methods: All Computed Tomography Angiography (CTA) imaging data were analyzed by an automated algorithm for anterior circulation LVOs (internal carotid artery (ICA), M1 or M2 segments of the middle cerebral artery) (StrokeViewer, Nico.lab). Ground truth was established by consensus of two independent neuroradiologist readings. Diagnostic performance was assessed by calculating sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Performance of the LVO localization feature was assessed by calculating interrater agreement (Cohen’s Kappa) between the algorithm and the expert panel. Results: CTAs from 297 patients referred or directly admitted to a comprehensive stroke center in the United States (mean age 67 years, SD 15; 145 males) were analyzed. One-hundred and fifty-six patients had an anterior circulation LVO. Location of the occlusions was ICA (n=43 [28%]), M1 (n=79 [51%]) and M2 (n=34 [22%]). Sensitivity and specificity for LVO detection were respectively 92% (95% CI, 86.2%-95.5%) and 85% (95% CI, 78.1%-90.5%). NPV and PPV were 90% and 87% respectively. Interrater agreement between the algorithm and the expert observers for LVO location was 0.92 (95% CI, 0.86-0.98). Median upload-to-notification time for all cases was 3 minutes, 34 seconds (minimal 2:28 minutes; maximal 5:03 minutes). Conclusions: Anterior circulation LVOs can be rapidly and accurately detected by an automated LVO detection algorithm with reliable localization of the involved vessel segment. Therefore, the algorithm presented in this study is a suitable screening tool to support diagnosis of LVOs.

The aim of this study was to develop a convolutional neural network (CNN) that automatically detects and segments intra-arterial thrombi on baseline non-contrast computed tomography (NCCT) scans. We retrospectively collected computed tomography (CT)-scans of patients with an anterior circulation large vessel occlusion (LVO) from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands trial, both for training (n = 86) and validation (n = 43). For testing we included patients with (n = 58) and without (n = 45) an LVO from our comprehensive stroke center. Ground truth was established by consensus between two experts using both CT angiography and NCCT. We evaluated the CNN for correct identification of a thrombus, its location and thrombus segmentation and compared these with the results of a neurologist in training and expert neuroradiologist. Sensitivity of the CNN thrombus detection was 0.86, vs. 0.95 and 0.79 for the neuroradiologists. Specificity was 0.65 for the network vs. 0.58 and 0.82 for the neuroradiologists. The CNN correctly identified the location of the thrombus in 79% of the cases, compared to 81% and 77% for the neuroradiologists. The sensitivity and specificity for thrombus identification and the rate for correct thrombus location assessment by the CNN were similar to those of expert neuroradiologists.

Late endovascular treatment of acute ischemic stroke Endovascular treatment (EVT) has become the standard of care for patients with acute ischemic stroke (AIS) due to large-vessel occlusion of the anterior circulation within 6 hours after the onset of symptoms. The recently published DAWN and DEFUSE 3 trials have shown that EVT is also effective beyond 6 hours after the onset of symptoms in patients who have been selected on the basis of CT perfusion imaging. We describe three cases of patients in whom we considered 'late' EVT on the basis of the results of these trials. Two female patients, 56 and 66 years old, both with large hemispheric AIS, were treated with EVT, respectively 8 and 15 hours after the onset of symptoms. Both patients had good clinical outcomes. In the third patient, a 79-year-old male, we decided to refrain from treatment with EVT on the basis of CT perfusion imaging. We describe our considerations with respect to these treatment decisions, our interpretation of the results of the DAWN and DEFUSE 3 trials and the implications of these results for the organization of stroke logistics in the Netherlands.

Introduction: Rapid detection of a large vessel occlusion (LVO) in acute ischemic stroke is beneficial as it may accelerate therapeutic management. The hyperdense artery sign (HAS) on non-contrast CT (NCCT) is result of an acute thrombolytic occlusion and is known as the earliest radiological marker to identify LVO. However, HAS is not apparent for all LVOs and detection by a less-trained eye can be sub-optimal. Artificial intelligence (AI) may support the non-trained radiologist in swift and accurate LVO detection. We evaluated the LVO detection accuracy of AI, and compared this to human expert performance. Materials and Methods: We used a convolutional neural network (CNN) developed by Nico.lab (www.nico-lab.com) that automatically detects and segments thrombi on NCCT using a patch-based approach. The CNN was trained using thrombus and non-thrombus patches, combined with the contralateral side. In a retrospective analysis of thin-slice NCCTs, obtained from Amsterdam UMC patients, with (ICA-T, M1, or M2) and without occlusions (stroke mimics), the CNN and two observers (>15y and >4y of experience) assessed LVO-presence and location. Ground truth was established by consensus between two different experts with >5y of experience, using both CTA and NCCT. Thrombus segmentations were considered accurate if segmentations overlapped with the ground truth. Sensitivity and specificity of the LVO detection were assessed. Results: We included 107 patients, of which 59 had proven LVOs. Nico.lab CNN showed a thrombus segmentation accuracy of 81%, vs. 81% and 77% of human experts. Sensitivity of LVO detection by CNN was 0.86, vs. 0.95 and 0.79 for human observers. Specificity was 0.65 for the CNN vs. 0.58 and 0.82 for human experts respectively. Conclusion: AI-based LVO detection on NCCT showed comparable results to expert observers. This supportive tool could lead to earlier detection of LVO in acute stroke situations. Fig 1A. HAS; B. CNN output (red); C. clot on CTA (blue arrow)