RESUMO
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.
RESUMO
PURPOSE: The Alberta Stroke Program Early CT Score (ASPECTS) is regularly used to guide patient selection for mechanical thrombectomy (MT). Similarly, penumbral imaging based on computed tomography perfusion (CTP) may serve as neuroimaging tool to guide treatment. Yet, patients with a large ischemic core on CTP may show only minor ischemic changes resulting in a high ASPECTS. AIM: We hypothesized twofold: (1) the treatment effect of vessel recanalization in patients with core volume > 50 mL but ASPECTS ⩾ 6 is not different compared to high ASPECTS patients with core volume < 50 mL, and (2) recanalization is associated with core overestimation. METHODS: We conducted an observational study analyzing ischemic stroke patients consecutively treated with MT after triage by multimodal CT. Functional endpoint was the rate of functional independence at Day 90 defined as modified Rankin Scale (mRS) 0-2. Imaging endpoint was core overestimation, which was considered when CTP-derived core was larger than the final infarct volume assessed on follow-up imaging. Recanalization was evaluated with the extended Thrombolysis in Cerebral Infarction (eTICI) scale. Multivariable logistic regression analysis and propensity score matching (PSM) were used to assess the association of recanalization (eTICI ⩾ 2b) with functional outcome and core overestimation. RESULTS: Of 630 patients with ASPECTS ⩾ 6, 91 patients (14.4%) had a large ischemic core. Following 1:1 PSM, the treatment effect of recanalization was not different in patients with large core and ASPECTS ⩾ 6 (+ 25.8%, 95% CI: 16.3-35.4, p < 0.001) compared to patients with ASPECTS ⩾ 6 and core volume < 50 mL (+ 14.9%, 95% CI: 5.7-24.1, p = 0.002). Recanalization (aOR: 3.46, 95% CI: 1.85-6.47, p < 0.001) and higher core volume (aOR: 1.03, 95% CI: 1.02-1.04, p < 0.001) were significantly associated with core overestimation. CONCLUSION: In patients with ASPECTS ⩾ 6, core volumes did not significantly modify outcomes following recanalization. Reperfusion and higher core volume were significantly associated with core overestimation which may explain the treatment effect of MT for patients with a large ischemic core but minor ischemic changes on non-enhanced CT. DATA ACCESS STATEMENT: The data analyzed in this study will be available and shared on reasonable request from any qualified researcher for the purpose of replicating the results after clearance by the local ethics committee.
Assuntos
AVC Isquêmico , Trombectomia , Tomografia Computadorizada por Raios X , Humanos , Trombectomia/métodos , Masculino , Feminino , AVC Isquêmico/diagnóstico por imagem , AVC Isquêmico/cirurgia , AVC Isquêmico/terapia , Idoso , Tomografia Computadorizada por Raios X/métodos , Pessoa de Meia-Idade , Resultado do Tratamento , Idoso de 80 Anos ou mais , Isquemia Encefálica/diagnóstico por imagemRESUMO
BACKGROUND: Hematoma volume is a major pathophysiological hallmark of acute intracerebral hemorrhage (ICH). We investigated how the variance in functional outcome induced by the ICH volume is explained by neurological deficits at admission using a mediation model. METHODS: Patients with acute ICH treated in three tertiary stroke centers between January 2010 and April 2019 were retrospectively analyzed. Mediation analysis was performed to investigate the effect of ICH volume (0.8 ml (5% quantile) versus 130.6 ml (95% quantile)) on the risk of unfavorable functional outcome at discharge defined as modified Rankin Score (mRS) ≥ 3 with mediation through National Institutes of Health Stroke Scale (NIHSS) at admission. Multivariable regression was conducted to identify factors related to neurological improvement and deterioration. RESULTS: Three hundred thirty-eight patients were analyzed. One hundred twenty-one patients (36%) achieved mRS ≤ 3 at discharge. Mediation analysis showed that NIHSS on admission explained 30% [13%; 58%] of the ICH volume-induced variance in functional outcome at smaller ICH volume levels, and 14% [4%; 46%] at larger ICH volume levels. Higher ICH volume at admission and brainstem or intraventricular location of ICH were associated with neurological deterioration, while younger age, normotension, lower ICH volumes, and lobar location of ICH were predictors for neurological improvement. CONCLUSION: NIHSS at admission reflects 14% of the functional outcome at discharge for larger hematoma volumes and 30% for smaller hematoma volumes. These results underscore the importance of effects not reflected in NIHSS admission for the outcome of ICH patients such as secondary brain injury and early rehabilitation.
Assuntos
Hemorragia Cerebral , Humanos , Masculino , Feminino , Idoso , Pessoa de Meia-Idade , Hemorragia Cerebral/fisiopatologia , Hemorragia Cerebral/diagnóstico por imagem , Estudos Retrospectivos , Idoso de 80 Anos ou mais , Recuperação de Função Fisiológica/fisiologia , Avaliação de Resultados em Cuidados de Saúde , Admissão do Paciente , Índice de Gravidade de DoençaRESUMO
BACKGROUND: Long-term data showing the benefits of endovascular thrombectomy for stroke with large infarct are scarce. The TENSION trial showed the safety and efficacy of endovascular thrombectomy in patients with ischaemic stroke and large infarct at 90 days. We aimed to investigate the safety and efficacy at 12 months of endovascular thrombectomy in patients who were enrolled in the TENSION trial. METHODS: TENSION was an open-label, blinded endpoint, randomised trial done at 40 hospitals across Europe and one hospital in Canada. We included patients (aged ≥18 years) with acute ischaemic stroke due to large vessel occlusion in the anterior circulation and who had a large infarct, as indicated by an Alberta Stroke Program Early Computed Tomographic Score (ASPECTS) of 3-5 on standard-of-care stroke imaging. We randomly assigned patients (1:1) to receive either endovascular thrombectomy with medical treatment or medical treatment only up to 12 h from stroke onset. The primary outcome was functional outcome across the entire range of the modified Rankin Scale at 90 days. Here, we report the prespecified 12-month follow-up analyses for functional outcome (using the simplified modified Rankin Scale questionnaire), quality of life (using the Patient-Reported Outcomes Measurement Information System 10-item [PROMIS-10] and EQ-5D questionnaires), post-stroke anxiety and depression (using the Patient Health Questionnaire-4 [PHQ-4]), and overall survival. Outcomes (except survival) were assessed in the intention-to-treat population; the survival analysis was based on treatment received. This trial is registered with ClinicalTrials.gov, NCT03094715, and is completed. FINDINGS: We enrolled patients between July 17, 2018, and Feb 21, 2023, when the trial was stopped early for efficacy. 253 patients were randomly assigned, 125 (49%) to endovascular thrombectomy and 128 (51%) to medical treatment only. Median follow-up was 8·36 months (IQR 0·02-12·00). Endovascular thrombectomy was associated with a shift in the distribution of scores on the modified Rankin Scale towards better functional outcome at 12 months (adjusted common odds ratio 2·39 [95% CI 1·47-3·90]). Endovascular thrombectomy was also associated with a better quality of life compared with medical treatment only, as reflected by median scores on the EQ-5D questionnaire index (0·7 [IQR 0·4-0·9] vs 0·4 [0·2-0·7]), median scores for health status on the EQ-5D questionnaire visual analogue scale (50 [IQR 35-70] vs 30 [5-60]), and median global physical health scores on the PROMIS-10 questionnaire (T-score 39·8 [IQR 37·4-50·8] vs 37·4 [32·4-44·9]); although there was not enough evidence to suggest a difference between groups in global mental health scores on PROMIS-10 (41·1 [IQR 36·3-48·3] vs 38·8 [31·3-44·7]) or the numbers of patients reporting anxiety (13 [22%] of 58 vs 15 [42%] of 36) and depression (18 [31%] vs 18 [50%]) on PHQ-4. Overall survival was slightly better in the endovascular thrombectomy group compared with medical treatment only (adjusted hazard ratio 0·70 [95% CI 0·50-0·99]). INTERPRETATION: In patients with acute ischaemic stroke from large vessel occlusion with established large infarct, compared with medical treatment only, endovascular thrombectomy was associated at 12 months after stroke with better functional outcome, quality of life, and overall survival. These findings suggest that the benefits of endovascular thrombectomy in patients with an ischaemic stroke and a large infarct are sustained in the long term and support the use of endovascular thrombectomy in these patients. FUNDING: European Union Horizon 2020 Research and Innovation Programme.