Dataset Information

Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging.

ABSTRACT:

Background

In ischaemic stroke patients undergoing reperfusion therapy, the amount of salvageable tissue, that is, extent of the ischaemic penumbra, predicts the clinical outcomes. CT perfusion (CTP) enables quantification of penumbral tissues to guide decision making, and current programmes have automated its analysis. More advanced machine learning techniques utilising the CTP maps may improve prediction beyond the ischaemic volume measures.

Method

We determined whether applying convolutional neural networks (CNN), a key machine learning technique in modelling image-label relationships, to post-processed CTP maps improved prediction of outcome, assessed by 3 months modified Rankin scale (mRS). Patients who underwent thrombolysis but not thrombectomy were included. CTP maps of a retrospective cohort of 230 patients with middle cerebral artery stroke were used to develop the model, which was validated in an independent cohort of 129 patients.

Results

We constructed a CNN model that predicted a favourable post-thrombolysis outcome (mRS 0-2 at 3 months) with an area under receiver-operator characteristics curve (AUC) of 0.792 (95% CI, 0.707-0.877). This model outperformed a currently clinically used MISTAR software using previously validated thresholds (AUC = 0.583, 95% CI, 0.480-0.686) and a model modified using thresholds from the derivation cohort (AUC = 0.670, 95% CI, 0.571-0.769). By combining CNN-derived features and baseline demographic features, the prediction AUC was improved to 0.865 (95% CI, 0.794-0.936).

Conclusion

CNN improved prediction of post-thrombolysis outcome, and may be useful in selecting which patients benefit from thrombolysis.

SUBMITTER: Chen Y

PROVIDER: S-EPMC10472959 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging.

Chen Yutong Y Tozer Daniel J DJ Liu Weiran W Peake Edward J EJ Markus Hugh S HS

European stroke journal 20230623 3

<h4>Background</h4>In ischaemic stroke patients undergoing reperfusion therapy, the amount of salvageable tissue, that is, extent of the ischaemic penumbra, predicts the clinical outcomes. CT perfusion (CTP) enables quantification of penumbral tissues to guide decision making, and current programmes have automated its analysis. More advanced machine learning techniques utilising the CTP maps may improve prediction beyond the ischaemic volume measures.<h4>Method</h4>We determined whether applying ...[more]

PMID: 37350512

Similar Datasets

Project description:ObjectiveIn this study, we investigate whether a Convolutional Neural Network (CNN) can generate informative parametric maps from the pre-processed CT perfusion data in patients with acute ischemic stroke in a clinical setting.MethodsThe CNN training was performed on a subset of 100 pre-processed perfusion CT dataset, while 15 samples were kept for testing. All the data used for the training/testing of the network and for generating ground truth (GT) maps, using a state-of-the-art deconvolution algorithm, were previously pre-processed using a pipeline for motion correction and filtering. Threefold cross validation had been used to estimate the performance of the model on unseen data, reporting Mean Squared Error (MSE). Maps accuracy had been checked through manual segmentation of infarct core and total hypo-perfused regions on both CNN-derived and GT maps. Concordance among segmented lesions was assessed using the Dice Similarity Coefficient (DSC). Correlation and agreement among different perfusion analysis methods were evaluated using mean absolute volume differences, Pearson correlation coefficients, Bland-Altman analysis, and coefficient of repeatability across lesion volumes.ResultsThe MSE was very low for two out of three maps, and low in the remaining map, showing good generalizability. Mean Dice scores from two different raters and the GT maps ranged from 0.80 to 0.87. Inter-rater concordance was high, and a strong correlation was found between lesion volumes of CNN maps and GT maps (0.99, 0.98, respectively).ConclusionThe agreement between our CNN-based perfusion maps and the state-of-the-art deconvolution-algorithm perfusion analysis maps, highlights the potential of machine learning methods applied to perfusion analysis. CNN approaches can reduce the volume of data required by deconvolution algorithms to estimate the ischemic core, and thus might allow the development of novel perfusion protocols with lower radiation dose deployed to the patient.

Project description:See Saver (doi:10.1093/awx020) for a scientific commentary on this article.Stroke shortens an individual's disability-free life. We aimed to assess the relative prognostic influence of pre- and post-treatment perfusion computed tomography imaging variables (e.g. ischaemic core and penumbral volumes) compared to standard clinical predictors (such as onset-to-treatment time) on long-term stroke disability in patients undergoing thrombolysis. We used data from a prospectively collected international, multicentre, observational registry of acute ischaemic stroke patients who had perfusion computed tomography and computed tomography angiography before treatment with intravenous alteplase. Baseline perfusion computed tomography and follow-up magnetic resonance imaging were analysed to derive the baseline penumbra volume, baseline ischaemic core volume, and penumbra salvaged from infarction. The primary outcome measure was the effect of imaging and clinical variables on Disability-Adjusted Life Year. Clinical variables were age, sex, National Institutes of Health Stroke Scale score, and onset-to-treatment time. Age, sex, country, and 3-month modified Rankin Scale were extracted from the registry to calculate disability-adjusted life-year due to stroke, such that 1 year of disability-adjusted life-year equates to 1 year of healthy life lost due to stroke. There were 772 patients receiving alteplase therapy. The number of disability-adjusted life-year days lost per 1 ml of baseline ischaemic core volume was 17.5 (95% confidence interval, 13.2-21.9 days, P < 0.001). For every millilitre of penumbra salvaged, 7.2 days of disability-adjusted life-year days were saved (β = -7.2, 95% confidence interval, -10.4 to -4.1 days, P < 0.001). Each minute of earlier onset-to-treatment time resulted in a saving of 4.4 disability-free days after stroke (1.3-7.5 days, P = 0.006). However, after adjustment for imaging variables, onset-to-treatment time was not significantly associated with savings in disability-adjusted life-year days. Pretreatment perfusion computed tomography can (independently of clinical variables) predict significant gains, or loss, of disability-free life in patients undergoing reperfusion therapy for stroke. The effect of earlier treatment on disability-free life appears explained by salvage of penumbra, particularly when the ischaemic core is not too large.

Project description:PurposeTo perform a proof-of-concept study to investigate the clinical utility of perfusion maps derived from convolutional neural networks (CNNs) for the workup of patients with acute ischemic stroke presenting with a large vessel occlusion.Materials and methodsData on endovascularly treated patients with acute ischemic stroke (n = 151; median age, 68 years [interquartile range, 59-75 years]; 82 of 151 [54.3%] women) were retrospectively extracted from a single-center institutional prospective registry (between January 2011 and December 2015). Dynamic susceptibility perfusion imaging data were processed by applying a commercially available reference method and in parallel by a recently proposed CNN method to automatically infer time to maximum of the tissue residue function (Tmax) perfusion maps. The outputs were compared by using quantitative markers of tissue at risk derived from manual segmentations of perfusion lesions from two expert raters.ResultsStrong correlations of lesion volumes (Tmax > 4 seconds, > 6 seconds, and > 8 seconds; R = 0.865-0.914; P < .001) and good spatial overlap of respective lesion segmentations (Dice coefficients, 0.70-0.85) between the CNN method and reference output were observed. Eligibility for late-window reperfusion treatment was feasible with use of the CNN method, with complete interrater agreement for the CNN method (Cohen κ = 1; P < .001), although slight discrepancies compared with the reference-based output were observed (Cohen κ = 0.609-0.64; P < .001). The CNN method tended to underestimate smaller lesion volumes, leading to a disagreement between the CNN and reference method in five of 45 patients (9%).ConclusionCompared with standard deconvolution-based processing of raw perfusion data, automatic CNN-derived Tmax perfusion maps can be applied to patients who have acute ischemic large vessel occlusion stroke, with similar clinical utility.© RSNA, 2019Supplemental material is available for this article.

Project description:ObjectivesWe aimed to evaluate the real-world variation in CT perfusion (CTP) imaging protocols among stroke centers and to explore the potential for standardizing vendor software to harmonize CTP images.MethodsStroke centers participating in a nationwide multicenter healthcare evaluation were requested to share their CTP scan and processing protocol. The impact of these protocols on CTP imaging was assessed by analyzing data from an anthropomorphic phantom with center-specific vendor software with default settings from one of three vendors (A-C): IntelliSpace Portal, syngoVIA, and Vitrea. Additionally, standardized infarct maps were obtained using a logistic model.ResultsEighteen scan protocols were studied, all varying in acquisition settings. Of these protocols, seven, eight, and three were analyzed with center-specific vendor software A, B, and C respectively. The perfusion maps were visually dissimilar between the vendor software but were relatively unaffected by the acquisition settings. The median error [interquartile range] of the infarct core volumes (mL) estimated by the vendor software was - 2.5 [6.5] (A)/ - 18.2 [1.2] (B)/ - 8.0 [1.4] (C) when compared to the ground truth of the phantom (where a positive error indicates overestimation). Taken together, the median error [interquartile range] of the infarct core volumes (mL) was - 8.2 [14.6] before standardization and - 3.1 [2.5] after standardization.ConclusionsCTP imaging protocols varied substantially across different stroke centers, with the perfusion software being the primary source of differences in CTP images. Standardizing the estimation of ischemic regions harmonized these CTP images to a degree.Clinical relevance statementThe center that a stroke patient is admitted to can influence the patient's diagnosis extensively. Standardizing vendor software for CT perfusion imaging can improve the consistency and accuracy of results, enabling a more reliable diagnosis and treatment decision.Key points• CT perfusion imaging is widely used for stroke evaluation, but variation in the acquisition and processing protocols between centers could cause varying patient diagnoses. • Variation in CT perfusion imaging mainly arises from differences in vendor software rather than acquisition settings, but these differences can be reconciled by standardizing the estimation of ischemic regions. • Standardizing the estimation of ischemic regions can improve CT perfusion imaging for stroke evaluation by facilitating reliable evaluations independent of the admission center.

Project description:Background and purposeComputed tomography perfusion imaging allows estimation of tissue status in patients with acute ischemic stroke. We aimed to improve prediction of the final infarct and individual infarct growth rates using a deep learning approach.MethodsWe trained a deep neural network to predict the final infarct volume in patients with acute stroke presenting with large vessel occlusions based on the native computed tomography perfusion images, time to reperfusion and reperfusion status in a derivation cohort (MR CLEAN trial [Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands]). The model was internally validated in a 5-fold cross-validation and externally in an independent dataset (CRISP study [CT Perfusion to Predict Response to Recanalization in Ischemic Stroke Project]). We calculated the mean absolute difference between the predictions of the deep learning model and the final infarct volume versus the mean absolute difference between computed tomography perfusion imaging processing by RAPID software (iSchemaView, Menlo Park, CA) and the final infarct volume. Next, we determined infarct growth rates for every patient.ResultsWe included 127 patients from the MR CLEAN (derivation) and 101 patients of the CRISP study (validation). The deep learning model improved final infarct volume prediction compared with the RAPID software in both the derivation, mean absolute difference 34.5 versus 52.4 mL, and validation cohort, 41.2 versus 52.4 mL (P<0.01). We obtained individual infarct growth rates enabling the estimation of final infarct volume based on time and grade of reperfusion.ConclusionsWe validated a deep learning-based method which improved final infarct volume estimations compared with classic computed tomography perfusion imaging processing. In addition, the deep learning model predicted individual infarct growth rates which could enable the introduction of tissue clocks during the management of acute stroke.

Dataset Information

Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging.

Background

Method

Results

Conclusion

Publications

Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets