scholarly journals Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning

Stroke ◽  
2018 ◽  
Vol 49 (6) ◽  
pp. 1394-1401 ◽  
Author(s):  
Anne Nielsen ◽  
Mikkel Bo Hansen ◽  
Anna Tietze ◽  
Kim Mouridsen
Keyword(s):  
Ischemic Stroke ◽  
Deep Learning ◽  
Acute Ischemic Stroke ◽  
Treatment Effect

Abstract P343: Relationship of Infarct Volume to Inflammation and Prognostic Significance in Patients With Acute Ischemic Stroke

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Lingling Ding ◽  
Zixiao Li ◽  
Yongjun Wang
Keyword(s):  
Ischemic Stroke ◽  
Deep Learning ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Acute Inflammation ◽  
Infarct Volume ◽  
Prognostic Significance ◽  
Stroke Recurrence ◽  
Vascular Events ◽  
Poor Functional Outcome

Background and Purpose: The diffusion weighted imaging (DWI) lesion volumes in acute ischemic stroke (AIS) can be automatically measured using deep learning-based segmentation algorithms. We aim to explore the prognostic significance of artificial intelligence-predicted infarct volume, and the association of markers of acute inflammation with the infarct volume. Methods: 12,598 AIS/TIA patients were included in this analysis. Intarct volume was automatically measured using a U-Net model for acute ischemic stroke lesion segmentation on DWI. Participants were divided into 5 subgroups according to infarct volume. Spearman’s correlations were employed to study the association between infarct volume and markers of acute inflammation. Multivariable logistic regression and Cox proportional hazards model were performed to explore the relationship between infarct volume and the incidence of poor functional outcome (modified Rankin scale score 3-6), stroke recurrence or combined vascular events at 3 months. Results: The U-Net model prediction correlated and agreed well with manual annotation ground truth for infarct volume (r=0.96; P<0.001). There were positive correlations between the infarct volume and markers of acute inflammation (neutrophil [r=0.175; P<0.001], hs-CRP [r=0.180; P<0.001], and IL-6 [r=0.225; P<0.001]). Compared with those without DWI lesions, patients with the largest infarct volume (4th Quartile) were nearly five times more likely to have poor functional outcome (mRS 3-6) (adjusted odds ratio, 4.70; 95% confidence intervals [CI], 3.29-6.72; P for trend<0.001) after adjustment for confounding factors and markers of acute inflammation. The infarct volume category was significantly associated with stroke recurrence (adjusted hazard ratios [HRs], 1.0, 1.43[0.95,2.17], 2.22[1.49,3.29], 2.06[1.40,3.05], 2.26[1.52,3.36]; P for trend<0.001) and combined vascular events(adjusted HRs, 1.0, 1.38[0.92,2.09], 2.25[1.53,3.32], 2.03[1.38,2.98], 2.28[1.54,3.36]; P for trend<0.001). Conclusions: Infarct volume measured automatically by deep learning-based tool was a strong predictor of poor functional outcome as well as stroke recurrence, with the potential for widespread adoption in both research and clinical settings.

Abstract TP83: Predicting Clinical Outcomes of Acute Ischemic Stroke Due to Large Vessel Occlusion: The Approach to Utilize High-dimensional Neuroimaging Data With Deep Learning

Stroke ◽  
2019 ◽  
Vol 50 (Suppl_1) ◽  
Author(s):  
Hidehisa Nishi ◽  
Naoya Oishi ◽  
Akira Ishii ◽  
Hideo Chihara ◽  
Takenori Ogura ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Deep Learning ◽  
Acute Ischemic Stroke ◽  
Clinical Outcomes ◽  
Large Vessel ◽  
High Dimensional ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Neuroimaging Data

scholarly journals Current Smoking Does Not Modify the Treatment Effect of Intravenous Thrombolysis in Acute Ischemic Stroke Patients—A Post-hoc Analysis of the WAKE-UP Trial

2019 ◽  
Vol 10 ◽  
Author(s):  
Ludwig Schlemm ◽  
Anna Kufner ◽  
Florent Boutitie ◽  
Alexander Heinrich Nave ◽  
Christian Gerloff ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Treatment Effect ◽  
Intravenous Thrombolysis ◽  
Stroke Patients ◽  
Current Smoking ◽  
Post Hoc Analysis ◽  
Post Hoc

Abstract TMP66: Intravenous Thrombolysis is Associated with Lower Risk of Severe Disability and Death among SPAN-100 Positive Acute Ischemic Stroke Patients

Stroke ◽  
2013 ◽  
Vol 44 (suppl_1) ◽  
Author(s):  
Bruce Ovbiagele ◽  
Mat Reeves ◽  
S. C Johnston ◽  
Philip Bath ◽  
Gustavo Saposnik ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Treatment Effect ◽  
Lower Risk ◽  
Intravenous Thrombolysis ◽  
Severe Disability ◽  
Neurological Deficits ◽  
Stroke Severity ◽  
Low Probability

BACKGROUND: Clinicians are cautious about administering intravenous thrombolysis (tPA) to acute ischemic stroke (AIS) patients who are very elderly and/or have severe neurological deficits. The Stroke Prognostication using Age and NIHSS (SPAN) index combines age plus stroke severity (NIHSS) to create a binary measure (≥ 100 vs. < 100) to predict clinical outcome. We evaluated the effectiveness of tPA by SPAN-100 index status among a large sample of AIS patients. METHODS: Data on 7140 AIS participants in the Virtual International Stroke Trials Archive (VISTA) collaboration. Outcome measures included severe disability or death at 3 months (defined as modified Rankin Scale {mRS} 4-6) and death alone. Effect of tPA on outcomes was assessed using multivariable logistic regression adjusting for SPAN-100 status. RESULTS: Among all patients, 743 (10.5%) were SPAN-100 positive (≥ 100), and 2731 (38.2%) received tPA treatment. Of those treated with tPA, SPAN-100 positive patients were more likely to experience severe disability or death (73.2% vs. 36.3%; p<0.0001) or death alone (33.6% vs. 11.4%; p<0.0001) than SPAN-100 negative patients. However, among SPAN-100 positive patients, tPA was associated with a significantly lower risk of severe disability and death, and tPA had a significantly greater treatment effect among SPAN-100 positive vs. SPAN-100 negative patients (Table). Logistic regression analyses showed significant interactions between SPAN-100 status and tPA (mRS of 4-6 <0.001; death 0.029) confirming that tPA had a greater treatment effect among SPAN-100 positive vs. SPAN-100 negative patients, even after adjustment for age and NIHSS. CONCLUSIONS: Despite the low probability of a favorable outcome, tPA reduces the risk of severe disability and death among SPAN-100 positive AIS patients. SPAN-100 index can be readily used in emergency care settings to identify high risk AIS patients who may be less prone to catastrophic outcomes after tPA treatment.

Abstract WMP19: Prediction of Subacute Infarction in Acute Ischemic Stroke Using Baseline Multi-modal MRI and Deep Learning

Stroke ◽  
2019 ◽  
Vol 50 (Suppl_1) ◽  
Author(s):  
Yannan Yu ◽  
Yuan Xie ◽  
Thoralf Thamm ◽  
Kevin T Chen ◽  
Enhao Gong ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Deep Learning ◽  
Acute Ischemic Stroke

Does prior antiplatelet treatment improve functional outcome after intra-arterial treatment for acute ischemic stroke?

2016 ◽  
Vol 12 (4) ◽  
pp. 368-376 ◽  
Author(s):  
Maxim JHL Mulder ◽  
Olvert A Berkhemer ◽  
Puck SS Fransen ◽  
Lucie A van den Berg ◽  
Hester F Lingsma ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Confidence Interval ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Treatment Effect ◽  
Absolute Risk ◽  
Antiplatelet Agents ◽  
Antiplatelet Treatment ◽  
Vessel Occlusion ◽  
Ordinal Logistic Regression Analysis

Background and purpose In patients with acute ischemic stroke who receive antiplatelet treatment, uncertainty exists about the effect and safety of intra-arterial treatment. Our aim was to study whether intra-arterial treatment in patients with prior antiplatelet treatment is safe and whether prior antiplatelet treatment modifies treatment effect. Methods All 500 MR CLEAN patients were included. We estimated the effect of intra-arterial treatment with ordinal logistic regression analysis, and tested for interaction of antiplatelet treatment with intra-arterial treatment on outcome. Furthermore, safety parameters and serious adverse events were analyzed. Results The 144 patients (29%) on antiplatelet treatment were older, more often male, and had more vascular comorbidity. Intra-arterial treatment effect size after adjustments in antiplatelet treatment patients was 1.7 (95% confidence interval 0.9–3.2), and in no antiplatelet treatment patients 1.8 (95% confidence interval: 1.2–2.6). There was no statistically or clinically significant interaction between prior antiplatelet treatment and the relative effect of intra-arterial treatment ( p = 0.78). However, in patients on antiplatelet treatment, the effect of successful reperfusion on functional outcome in the intervention arm of the trial was doubled: the absolute risk difference for favorable outcome after successful reperfusion in patients on prior antiplatelet treatment was 39% versus 18% in patients not on prior antiplatelet treatment (Pinteraction = 0.025). Patients on antiplatelet treatment more frequently had a symptomatic intracranial hemorrhage (15%) compared to patients without antiplatelet treatment (4%), without differences between the control and intervention arm. Conclusions Prior treatment with antiplatelet agents did not modify the effect of intra-arterial treatment in patients with acute ischemic stroke presenting with an intracranial large vessel occlusion. There were no safety concerns. In patients with reperfusion, antiplatelet agents may improve functional outcome.

scholarly journals Clot Burden Score on Baseline Computerized Tomographic Angiography and Intra-Arterial Treatment Effect in Acute Ischemic Stroke

Stroke ◽  
2016 ◽  
Vol 47 (12) ◽  
pp. 2972-2978 ◽  
Author(s):  
Kilian M. Treurniet ◽  
Albert J. Yoo ◽  
Olvert A. Berkhemer ◽  
Hester F. Lingsma ◽  
Anna M.M. Boers ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Treatment Effect ◽  
Clot Burden ◽  
Tomographic Angiography

Abstract P494: Automatically Predicting Modified Treatment in Cerebral Ischemia Scores From Patient Digital Subtraction Angiography Using Deep Learning

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Ayush Lall ◽  
Fabien Scalzo ◽  
Henrik Ullman ◽  
David S Liebeskind ◽  
Aichi Chien
Keyword(s):  
Neural Networks ◽  
Ischemic Stroke ◽  
Deep Learning ◽  
Cerebral Ischemia ◽  
Acute Ischemic Stroke ◽  
Digital Subtraction Angiography ◽  
Endovascular Therapy ◽  
Imaging Biomarker ◽  
Digital Subtraction ◽  
Neural Network Models

Introduction: We propose a new method for quantifying the effect of endovascular therapy for acute ischemic stroke. Currently, an mTICI (modified treatment in cerebral ischemia) score is assigned manually to document the success of endovascular revascularization therapy. The mTICI score based on Digital Subtraction Angiography (DSA), due to visual assignment, has limitations in settings where standardization is pertinent. Methods: We hypothesize that mTICI scores can be classified successfully by deep learning and thus be used as a standardized imaging biomarker. We aim to develop a regression framework using classification models that can assign continuous score to patients depending on the success of therapy, resulting in a score that is more granular than the mTICI. We use deep learning and 3D Convolutional Neural Networks (CNN) to classify frontal post-intervention DSA 2D time series into the mTICI score categories of 0, 1, 2a, 2b, and 3. An mTICI score of 0 represents no perfusion and a score of 3 represents full perfusion. The DSA series serve as features where the time dimension is the third dimension for the CNN. For our preliminary research we have condensed our groupings into binary {0,1} (0 refers to mTICI of 0, 1, 2a while 1 refers to mTICI of 2b, 3) of frontal DSA to see if Deep Learning models can categorize between the different mTICI classes. Results: We reduced our original data size of 181 patients to 93 patients in binary group 0 and 88 patients in group 1. Using a train/test split of 0.2, we have achieved a test classification accuracy of 73%, and F1-Score of 72.2% on the binary dataset. This is a good statistical indication that neural networks are able to classify between DSA. Conclusion: Neural network models show promise as a method of distinguishing between DSA to be used as an automatic standardized scoring method for acute ischemic stroke procedures. We aim to expand this research to frontal and lateral DSA images to get more vascular information to improve model accuracies. We propose using the softmax score of the classifier as a new score which will be a standardized measurement for endovascular therapy success.

scholarly journals Time to Reperfusion and Treatment Effect for Acute Ischemic Stroke

2016 ◽  
Vol 73 (2) ◽  
pp. 190 ◽  
Author(s):  
Puck S. S. Fransen ◽  
Olvert A. Berkhemer ◽  
Hester F. Lingsma ◽  
Debbie Beumer ◽  
Lucie A. van den Berg ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Treatment Effect
Sign in / Sign up

Export Citation Format

Share Document