Background: and Purpose Multiphase computed tomographic angiography (mCTA) provides time variant images of pial vasculature supplying brain in patients with acute ischemic stroke (AIS). To develop a machine learning (ML) technique to predict tissue perfusion and infarction from mCTA source images. Methods: 284 patients with AIS were included from the Precise and Rapid assessment of collaterals using multi-phase CTA in the triage of patients with acute ischemic stroke for Intra-artery Therapy (Prove-IT) study. All patients had non-contrast computed tomography, mCTA, and computed tomographic perfusion (CTP) at baseline and follow-up magnetic resonance imagingon-contrast-enhanced computed tomography. Of the 284 patient images, 140 patient images were randomly selected to train and validate three ML models to predict a pre-defined Tmax thresholded perfusion abnormality, core and penumbra on CTP. The remaining 144 patient images were used to test the ML models. The predicted perfusion, core and penumbra lesions from ML models were compared to CTP perfusion lesion and to follow-up infarct using Bland-Altman plots, concordance correlation coefficient (CCC), intra-class correlation coefficient (ICC), and Dice similarity coefficient. Results: Mean difference between the mCTA predicted perfusion volume and CTP perfusion volume was 4.6 mL (limit of agreement [LoA], –53 to 62.1 mL; P=0.56; CCC 0.63 [95% confidence interval [CI], 0.53 to 0.71; P<0.01], ICC 0.68 [95% CI, 0.58 to 0.78; P<0.001]). Mean difference between the mCTA predicted infarct and follow-up infarct in the 100 patients with acute reperfusion (modified thrombolysis in cerebral infarction [mTICI] 2b/2c/3) was 21.7 mL, while it was 3.4 mL in the 44 patients not achieving reperfusion (mTICI 0/1). Amongst reperfused subjects, CCC was 0.4 (95% CI, 0.15 to 0.55; P<0.01) and ICC was 0.42 (95% CI, 0.18 to 0.50; P<0.01); in non-reperfused subjects CCC was 0.52 (95% CI, 0.20 to 0.60; P<0.001) and ICC was 0.60 (95% CI, 0.37 to 0.76; P<0.001). No difference was observed between the mCTA and CTP predicted infarct volume in the test cohort (P=0.67). Conclusions A ML based mCTA model is able to predict brain tissue perfusion abnormality and follow-up infarction, comparable to CTP.

Background: and Purpose Multiphase computed tomographic angiography (mCTA) provides time variant images of pial vasculature supplying brain in patients with acute ischemic stroke (AIS). To develop a machine learning (ML) technique to predict tissue perfusion and infarction from mCTA source images. Methods: 284 patients with AIS were included from the Precise and Rapid assessment of collaterals using multi-phase CTA in the triage of patients with acute ischemic stroke for Intra-artery Therapy (Prove-IT) study. All patients had non-contrast computed tomography, mCTA, and computed tomographic perfusion (CTP) at baseline and follow-up magnetic resonance imagingon-contrast-enhanced computed tomography. Of the 284 patient images, 140 patient images were randomly selected to train and validate three ML models to predict a pre-defined Tmax thresholded perfusion abnormality, core and penumbra on CTP. The remaining 144 patient images were used to test the ML models. The predicted perfusion, core and penumbra lesions from ML models were compared to CTP perfusion lesion and to follow-up infarct using Bland-Altman plots, concordance correlation coefficient (CCC), intra-class correlation coefficient (ICC), and Dice similarity coefficient. Results: Mean difference between the mCTA predicted perfusion volume and CTP perfusion volume was 4.6 mL (limit of agreement [LoA], –53 to 62.1 mL; P=0.56; CCC 0.63 [95% confidence interval [CI], 0.53 to 0.71; P<0.01], ICC 0.68 [95% CI, 0.58 to 0.78; P<0.001]). Mean difference between the mCTA predicted infarct and follow-up infarct in the 100 patients with acute reperfusion (modified thrombolysis in cerebral infarction [mTICI] 2b/2c/3) was 21.7 mL, while it was 3.4 mL in the 44 patients not achieving reperfusion (mTICI 0/1). Amongst reperfused subjects, CCC was 0.4 (95% CI, 0.15 to 0.55; P<0.01) and ICC was 0.42 (95% CI, 0.18 to 0.50; P<0.01); in non-reperfused subjects CCC was 0.52 (95% CI, 0.20 to 0.60; P<0.001) and ICC was 0.60 (95% CI, 0.37 to 0.76; P<0.001). No difference was observed between the mCTA and CTP predicted infarct volume in the test cohort (P=0.67). Conclusions A ML based mCTA model is able to predict brain tissue perfusion abnormality and follow-up infarction, comparable to CTP.

Background: and Purpose Various imaging paradigms are used for endovascular treatment (EVT) decision-making and outcome estimation in acute ischemic stroke (AIS). We aim to compare how these imaging paradigms perform for EVT patient selection and outcome estimation. Methods: Prospective multi-center cohort study of patients with AIS symptoms with multi-phase computed tomography angiography (mCTA) and computed tomography perfusion (CTP) baseline imaging. mCTA-based EVT-eligibility was defined as presence of large vessel occlusion (LVO) and moderate-to-good collaterals on mCTA. CTP-based eligibility was defined as presence of LVO, ischemic core (defined on relative cerebral blood flow, absolute cerebral blood flow, and cerebral blood volume maps) <70 mL, mismatch-ratio >1.8, absolute mismatch >15 mL. EVT-eligibility and adjusted rates of good outcome (modified Rankin Scale 0–2) based on these imaging paradigms were compared. Results: Of 289/464 patients with LVO, 263 (91%) were EVT-eligible by mCTA-criteria versus 63 (22%), 19 (7%) and 103 (36%) by rCBF, aCBF, and CBV-CTP-criteria. CTP and mCTA-criteria were discordant in 40% to 53%. Estimated outcomes were best in patients who met both mCTA and CTP eligibility-criteria and were treated with EVT (62% to 87% good outcome). Patients eligible for EVT by mCTA-criteria and not by CTP-criteria receiving EVT achieved good outcome rates of 53% to 57%. Few patients met CTP-criteria and not mCTA-criteria for EVT. Conclusions Simpler imaging selection criteria that rely on little else than detection of the occluded blood vessel may be more sensitive and less specific, thus resulting in more patients being offered EVT and arguably benefiting from it.

Background: and Purpose Various imaging paradigms are used for endovascular treatment (EVT) decision-making and outcome estimation in acute ischemic stroke (AIS). We aim to compare how these imaging paradigms perform for EVT patient selection and outcome estimation. Methods: Prospective multi-center cohort study of patients with AIS symptoms with multi-phase computed tomography angiography (mCTA) and computed tomography perfusion (CTP) baseline imaging. mCTA-based EVT-eligibility was defined as presence of large vessel occlusion (LVO) and moderate-to-good collaterals on mCTA. CTP-based eligibility was defined as presence of LVO, ischemic core (defined on relative cerebral blood flow, absolute cerebral blood flow, and cerebral blood volume maps) <70 mL, mismatch-ratio >1.8, absolute mismatch >15 mL. EVT-eligibility and adjusted rates of good outcome (modified Rankin Scale 0–2) based on these imaging paradigms were compared. Results: Of 289/464 patients with LVO, 263 (91%) were EVT-eligible by mCTA-criteria versus 63 (22%), 19 (7%) and 103 (36%) by rCBF, aCBF, and CBV-CTP-criteria. CTP and mCTA-criteria were discordant in 40% to 53%. Estimated outcomes were best in patients who met both mCTA and CTP eligibility-criteria and were treated with EVT (62% to 87% good outcome). Patients eligible for EVT by mCTA-criteria and not by CTP-criteria receiving EVT achieved good outcome rates of 53% to 57%. Few patients met CTP-criteria and not mCTA-criteria for EVT. Conclusions Simpler imaging selection criteria that rely on little else than detection of the occluded blood vessel may be more sensitive and less specific, thus resulting in more patients being offered EVT and arguably benefiting from it.

Background: and Purpose Infarcts in acute ischemic stroke (AIS) patients may continue to grow even after reperfusion, due to mechanisms such as microvascular obstruction and reperfusion injury. We investigated whether and how much infarcts grow in AIS patients after near-complete (expanded Thrombolysis in Cerebral Infarction [eTICI] 2c/3) reperfusion following endovascular treatment (EVT), and to assess the association of post-reperfusion infarct growth with clinical outcomes. Methods: Data are from a single-center retrospective observational cohort study that included AIS patients undergoing EVT with near-complete reperfusion who received diffusion-weighted magnetic resonance imaging (MRI) within 2 hours post-EVT and 24 hours after EVT. Association of infarct growth between 2 and 24 hours post-EVT and 24-hour National Institutes of Health Stroke Scale (NIHSS) as well as 90-day modified Rankin Scale score was assessed using multivariable logistic regression. Results: Ninety-four of 155 (60.6%) patients achieved eTICI 2c/3 and were included in the analysis. Eighty of these 94 (85.1%) patients showed infarct growth between 2 and 24 hours post-reperfusion. Infarct growth ≥5 mL was seen in 39/94 (41.5%) patients, and infarct growth ≥10 mL was seen in 20/94 (21.3%) patients. Median infarct growth between 2 and 24 hours post-reperfusion was 4.5 mL (interquartile range: 0.4–9.2 mL). Post-reperfusion infarct growth was associated with the 24-hour NIHSS in multivariable analysis (odds ratio: 1.16 [95% confidence interval 1.09–1.24], P<0.01). Conclusion Infarcts continue to grow after EVT, even if near-complete reperfusion is achieved. Investigating the underlying mechanisms may inform future therapeutic approaches for mitigating the process and help improve patient outcome.

Background: and Purpose Infarct volume and other imaging markers are increasingly used as surrogate measures for clinical outcome in acute ischemic stroke research, but how improvements in these imaging surrogates translate into better clinical outcomes is currently unclear. We investigated how changes in infarct volume at 24 hours alter the probability of achieving good clinical outcome (modified Rankin Scale [mRS] 0–2). Methods: Data are from endovascular thrombectomy patients from the randomized controlled ESCAPE-NA1 (Efficacy and Safety of Nerinetide for the Treatment of Acute Ischaemic Stroke) trial. Infarct volume at 24 hours was manually segmented on non-contrast computed tomography or diffusion-weighted magnetic resonance imaging. Probabilities of achieving good outcome based on infarct volume were obtained from a multivariable logistic regression model. The probability of good outcome was plotted against infarct volume using linear spline regression. Results: A total of 1,099 patients were included in the analysis (median final infarct volume 24.9 mL [interquartile range: 6.6–92.2]). The relationship between total infarct volume and good outcome probability was nearly linear for infarct volumes between 0 mL and 250 mL. In this range, a 10% increase in the probability of achieving mRS 0–2 required a decrease in infarct volume of approximately 34.0 mL (95% confidence interval: -32.5 to -35.6). At infarct volumes above 250 mL, the probability of achieving mRS 0–2 probability was near zero. The relationships of tissue-specific infarct volumes and parenchymal hemorrhage volume generally showed similar patterns, although variability was high. Conclusion There seems to be a near-linear association between total infarct volume and probability of achieving good outcome for infarcts up to 250 mL, whereas patients with infarct volumes greater than 250 mL are highly unlikely to have a favorable outcome.