scholarly journals Response by Olivé Gadea and Ribo to Letter Regarding Article, “Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography”

Stroke ◽  
2021 ◽  
Vol 52 (2) ◽  
Author(s):  
Marta Olivé Gadea ◽  
Marc Ribo
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Noncontrast Computed Tomography

scholarly journals Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography

Stroke ◽  
2020 ◽  
Vol 51 (10) ◽  
pp. 3133-3137
Author(s):  
Marta Olive-Gadea ◽  
Carlos Crespo ◽  
Cristina Granes ◽  
Maria Hernandez-Perez ◽  
Natalia Pérez de la Ossa ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Positive Predictive Value ◽  
Acute Stroke ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Learning Algorithm ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Noncontrast Computed Tomography

Background and Purpose: Reliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT. Methods: Patients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included. Software detection of LVO (MethinksLVO) on NCCT was tested against the CTA readings of 2 experienced radiologists (NR-CTA). We used a deep learning algorithm to identify clot signs on NCCT. The software image output trained a binary classifier to determine LVO on NCCT. We studied software accuracy when adding National Institutes of Health Stroke Scale and time from onset to the model (MethinksLVO+). Results: From 1453 patients, 823 (57%) had LVO by NR-CTA. The area under the curve for the identification of LVO with MethinksLVO was 0.87 (sensitivity: 83%, specificity: 71%, positive predictive value: 79%, negative predictive value: 76%) and improved to 0.91 with MethinksLVO+ (sensitivity: 83%, specificity: 85%, positive predictive value: 88%, negative predictive value: 79%). Conclusions: In patients with suspected acute stroke, MethinksLVO software can rapidly and reliably predict LVO. MethinksLVO could reduce the need to perform CTA, generate alarms, and increase the efficiency of patient transfers in stroke networks.

scholarly journals Role of Favorable Perfusion Imaging in Predicting the Outcome of Patients with Acute Ischemic Stroke due to Large Vessel Occlusion Undergoing Effective Thrombectomy: A Single-Center Study

2021 ◽  
pp. 1-8
Author(s):  
Riccardo Di Iorio ◽  
Fabio Pilato ◽  
Iacopo Valente ◽  
Andrea Laurienzo ◽  
Simona Gaudino ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Large Vessel ◽  
Controlled Study ◽  
Ischemic Penumbra ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Single Center Study

<b><i>Introduction:</i></b> We sought to verify the predicting role of a favorable profile on computed tomography perfusion (CTP) in the outcome of patients with acute ischemic stroke (AIS) due to large vessel occlusion (LVO) undergoing effective mechanical thrombectomy (MT). <b><i>Methods:</i></b> We retrospectively enrolled 25 patients with AIS due to LVO and with a CTP study showing the presence of ischemic penumbra who underwent effective MT, regardless of the time of onset. The controls were 25 AIS patients with overlapping demographics and clinical and computed tomography angiography features at admission who had undergone successful MT within 6 h from onset and without a previous CTP study. The outcome measure was the modified Rankin Scale (mRS) score at 90 days. <b><i>Results:</i></b> Sixty-four percent of the study patients had an mRS score of 0–1 at 90 days versus 12% of the control patients (<i>p</i> &#x3c; 0.001). Patients of the study group had a more favorable distribution of disability scores (median mRS [IQR] score of 0 [0–2] vs. 2 [2–3]). Multivariate analysis showed that the selection of patients based on a favorable CTP study was strongly associated (<i>p</i> &#x3c; 0.001) with a better neurological outcome. <b><i>Conclusions:</i></b> In our small-sized and retrospective study, the presence of ischemic penumbra was associated with a better clinical outcome in patients with AIS due to LVO after MT. In the future, a larger and controlled study with similar criteria of enrollment is needed to further validate the role of CTP in patient selection for MT, regardless of the time from the onset of symptoms.

scholarly journals Electroencephalography Might Improve Diagnosis of Acute Stroke and Large Vessel Occlusion

Stroke ◽  
2020 ◽  
Vol 51 (11) ◽  
pp. 3361-3365 ◽  
Author(s):  
Fareshte Erani ◽  
Nadezhda Zolotova ◽  
Benjamin Vanderschelden ◽  
Nima Khoshab ◽  
Hagop Sarian ◽  
...  
Keyword(s):  
Neural Network ◽  
Emergency Department ◽  
Deep Learning ◽  
Acute Stroke ◽  
Clinical Data ◽  
Area Under The Curve ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Deep Learning Neural Network

Background and Purpose: Clinical methods have incomplete diagnostic value for early diagnosis of acute stroke and large vessel occlusion (LVO). Electroencephalography is rapidly sensitive to brain ischemia. This study examined the diagnostic utility of electroencephalography for acute stroke/transient ischemic attack (TIA) and for LVO. Methods: Patients (n=100) with suspected acute stroke in an emergency department underwent clinical exam then electroencephalography using a dry-electrode system. Four models classified patients, first as acute stroke/TIA or not, then as acute stroke with LVO or not: (1) clinical data, (2) electroencephalography data, (3) clinical+electroencephalography data using logistic regression, and (4) clinical+electroencephalography data using a deep learning neural network. Each model used a training set of 60 randomly selected patients, then was validated in an independent cohort of 40 new patients. Results: Of 100 patients, 63 had a stroke (43 ischemic/7 hemorrhagic) or TIA (13). For classifying patients as stroke/TIA or not, the clinical data model had area under the curve=62.3, whereas clinical+electroencephalography using deep learning neural network model had area under the curve=87.8. Results were comparable for classifying patients as stroke with LVO or not. Conclusions: Adding electroencephalography data to clinical measures improves diagnosis of acute stroke/TIA and of acute stroke with LVO. Rapid acquisition of dry-lead electroencephalography is feasible in the emergency department and merits prehospital evaluation.

Association of Computed Tomography Ischemic Lesion Location With Functional Outcome in Acute Large Vessel Occlusion Ischemic Stroke

Stroke ◽  
2017 ◽  
Vol 48 (9) ◽  
pp. 2426-2433 ◽  
Author(s):  
Marielle Ernst ◽  
Anna M.M. Boers ◽  
Annette Aigner ◽  
Olvert A. Berkhemer ◽  
Albert J. Yoo ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ischemic Stroke ◽  
Functional Outcome ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Ischemic Lesion ◽  
Lesion Location

scholarly journals Validation of a Deep Learning Tool in the Detection of Intracranial Hemorrhage and Large Vessel Occlusion

2021 ◽  
Vol 12 ◽  
Author(s):  
Joel McLouth ◽  
Sebastian Elstrott ◽  
Yasmina Chaibi ◽  
Sarah Quenet ◽  
Peter D. Chang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Middle Cerebral Artery ◽  
Intracranial Hemorrhage ◽  
Cerebral Artery ◽  
The United States ◽  
Large Vessel ◽  
True Positive ◽  
Large Vessel Occlusion ◽  
Learning Tool ◽  
Vessel Occlusion

Purpose: Recently developed machine-learning algorithms have demonstrated strong performance in the detection of intracranial hemorrhage (ICH) and large vessel occlusion (LVO). However, their generalizability is often limited by geographic bias of studies. The aim of this study was to validate a commercially available deep learning-based tool in the detection of both ICH and LVO across multiple hospital sites and vendors throughout the U.S.Materials and Methods: This was a retrospective and multicenter study using anonymized data from two institutions. Eight hundred fourteen non-contrast CT cases and 378 CT angiography cases were analyzed to evaluate ICH and LVO, respectively. The tool's ability to detect and quantify ICH, LVO, and their various subtypes was assessed among multiple CT vendors and hospitals across the United States. Ground truth was based off imaging interpretations from two board-certified neuroradiologists.Results: There were 255 positive and 559 negative ICH cases. Accuracy was 95.6%, sensitivity was 91.4%, and specificity was 97.5% for the ICH tool. ICH was further stratified into the following subtypes: intraparenchymal, intraventricular, epidural/subdural, and subarachnoid with true positive rates of 92.9, 100, 94.3, and 89.9%, respectively. ICH true positive rates by volume [small (&lt;5 mL), medium (5–25 mL), and large (&gt;25 mL)] were 71.8, 100, and 100%, respectively. There were 156 positive and 222 negative LVO cases. The LVO tool demonstrated an accuracy of 98.1%, sensitivity of 98.1%, and specificity of 98.2%. A subset of 55 randomly selected cases were also assessed for LVO detection at various sites, including the distal internal carotid artery, middle cerebral artery M1 segment, proximal middle cerebral artery M2 segment, and distal middle cerebral artery M2 segment with an accuracy of 97.0%, sensitivity of 94.3%, and specificity of 97.4%.Conclusion: Deep learning tools can be effective in the detection of both ICH and LVO across a wide variety of hospital systems. While some limitations were identified, specifically in the detection of small ICH and distal M2 occlusion, this study highlights a deep learning tool that can assist radiologists in the detection of emergent findings in a variety of practice settings.

Sign in / Sign up

Export Citation Format

Share Document