NICO.LAB at ISC 2021

Incase you missed it, here is the abstract of the poster from the International Stroke Conference last week.

This study in the US included CTAs from 297 patients, using our LVO Detection and Location algorithms. StrokeViewer notified experts of the AI findings in just approximately 3 minutes of the image being uploaded. The sensitivity of the LVO detection algorithm was 92% including distal M2 occlusions which are typically smaller and more difficult to detect.

Abstract P544: Automated Artificial Intelligence Based Detection and Location Specification of Large Vessel Occlusion on CT Angiography in Stroke

Originally published

Introduction: Fast and accurate detection of large vessel occlusions (LVOs) is crucial in selection of patients for endovascular treatment. We assessed the diagnostic performance and speed of an Artifical Intelligence algorithm for automated LVO detection with a novel feature that specifies the exact level of occlusion.

Methods: All Computed Tomography Angiography (CTA) imaging data were analyzed by an automated algorithm for anterior circulation LVOs (internal carotid artery (ICA), M1 or M2 segments of the middle cerebral artery) (StrokeViewer, Nico.lab). Ground truth was established by consensus of two independent neuroradiologist readings. Diagnostic performance was assessed by calculating sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Performance of the LVO localization feature was assessed by calculating interrater agreement (Cohen’s Kappa) between the algorithm and the expert panel.

Results: CTAs from 297 patients referred or directly admitted to a comprehensive stroke center in the United States (mean age 67 years, SD 15; 145 males) were analyzed. One-hundred and fifty-six patients had an anterior circulation LVO. Location of the occlusions was ICA (n=43 [28%]), M1 (n=79 [51%]) and M2 (n=34 [22%]). Sensitivity and specificity for LVO detection were respectively 92% (95% CI, 86.2%-95.5%) and 85% (95% CI, 78.1%-90.5%). NPV and PPV were 90% and 87% respectively. Interrater agreement between the algorithm and the expert observers for LVO location was 0.92 (95% CI, 0.86-0.98). Median upload-to-notification time for all cases was 3 minutes, 34 seconds (minimal 2:28 minutes; maximal 5:03 minutes).

Conclusions: Anterior circulation LVOs can be rapidly and accurately detected by an automated LVO detection algorithm with reliable localization of the involved vessel segment. Therefore, the algorithm presented in this study is a suitable screening tool to support diagnosis of LVOs.

Our cloud-based solution enables physicians to provide every stroke patient with the right treatment in time.

With Medicare Reimbursement, ICD-10-PCS code, we can help your hospital to improve patient outcome while reducing hospital costs

StrokeViewer helps to reduce undetected LVOs

Artificial intelligence detects occlusions up to distal M2 on CTA
User immediately notified of findings via App/email
Automated PDF reports

“I think it works brilliantly as a screening tool to alert the team that there is high suspicion of LVO. The communication gets everyone coordinated in a parallel fashion...”

Dr. Albert Yoo, MD

Medical Director at Texas Stroke Institute

Want to schedule a meeting with Merel, our CEO or one of our Country Managers?

Get in touch!



    StrokeViewer Features

    Mobile miniPACS

    This mobile miniPACS is an extension to the familiar hospital PACS , enabling stroke experts to access analyzed patient scans within minutes, anywhere on their device.

    Seamless image sharing

    Rapid image exchange allows stroke experts to forward patient scans to the nearest intervention center with the click of a button, physicians can then plan for patient arrival.

    Certified Diagnostic Viewer

    The certified diagnostic viewer is a unique feature to StrokeViewer. This allows physicians to diagnose patients from their mobile device.

    3D Treatment Planning

    This feature is included in StrokeViewer LVO. It helps neurologists and radiologists visualize the brain vasculature and blood clot.

    Interventional neuroradiologists in particular have reported their use of the 3D Treatment Planning feature for selecting the micro catheters to use prior to patient arrival.

    “It can be really helpful in detecting distal occlusions, because the 3D Treatment Planning can make an occlusion more obvious especially when a vessel goes into another slice or in a different direction. It prevents you from mistaking an occlusion for a loop in the vessel”

    Dr. Bart Emmer, Ph.D.

    Interventional Neuroradiologist, Amsterdam UMC, Netherlands