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

Nielsen A, Hansen MB, Tietze A, Mouridsen K. Stroke. 2018;49(6):1394-1401.

Abstract

Background and purpose

Treatment options for patients with acute ischemic stroke depend on the volume of salvageable tissue. This volume assessment is currently based on fixed thresholds and single imagine modalities, limiting accuracy. We wish to develop and validate a predictive model capable of automatically identifying and combining acute imaging features to accurately predict final lesion volume using deep convolutional neural networks.

Conclusion

The considerable prediction improvement accuracy over the current state of the art increases the potential for automated decision support in providing recommendations for personalized treatment plans.

Get access to the full article doi:10.1161/STROKEAHA.117.019740

Ready to Transform Your Diagnostic Capabilities?

Join Us in Advancing Brain Health with Cutting-Edge Microvascular Modeling.
Contact Us Today to Learn More!
Contact us
Cercare Medical A/S
Inge Lehmanns Gade 10
8000 Aarhus C
Denmark

Solutions
Cercare Perfusion Neuro & Oncology Stroke Modules
Support
Assistance Instructions for Use
Company
Board Members Investors About News Privacy Policy Regulatory & Compliance
© 2025 Cercare Medical. All rights reserved.
TRY US

CLINICAL USE CASES AND TECHNICAL HIGHLIGHTS


CLINICAL USE CASES
  • Assess outcomes post-intervention: detect missed stenoses, distal occlusions, or microvascular disturbances.
  • Guide complementary therapies on the spot based on perfusion status.
  • May detect the no-reflow phenomenon — providing insight into cases where recovery may fail despite successful thrombectomy.
  • Potentially enables direct-to-angio workflows.

TECHNICAL HIGHLIGHTS
  • Full set of perfusion markers: CBF, CBV, MTT.
  • Advanced oxygen metabolism imaging: OEF, CMRO₂.
  • Reliable results with as few as 5 CBCT acquisitions (bolus injection timing protocol very important).
  • Integrated with Siemens and Philips systems; GE/Canon under evaluation.

CBCT Imaging

Side-by-side comparison: The left-hand side is the raw CBCT data, while the right-hand side panel is the pre-processed data.
Using CMN software in the angio suite delivers results comparable to conventional CT/MR perfusion.

Explore CMN!

Fast. Reliable. Personalized.

Discover how Cercare Medical Neurosuite (CMN) enhances post-processing images and provides actionable insights from advanced biomarkers - tailored to your workflow.

Fill-out the form below, and a representative will contact you.

Thank you for uploading your DICOM files.

Your submission has been received successfully.

Next steps:

  • Our team will analyze the uploaded data.
  • A Cercare Medical representative will reach out to you once the analysis is complete.
  • Rest assured that all files will be deleted immediately after use, in line with our data protection policies.
Perfusion Summit 2026
Date: 26 March 2026, Thursday
Time: 10:15 - 17:40 (CET)
Venue: Concorde Hall, Hilton Paris Hotel, CDG
Participation is Optional

Hands-On Workshops
Date: 27 March 2026

Workshop selection is optional and does not confirm registration. Confirmation and further details will be provided in January 2026. Please note that seating is limited.
By participating in this event, you consent to the use of your image, voice, and likeness in photographs, and videos for promotional purposes, in accordance with GDPR regulations.

Sign up for the upcoming Perfusion & Metabolic Imaging Community (PMIC)

Request a demo

Let us give you a tour around our solution.

Fill in your credentials, and a member of the Cercare Medical team will contact you with a date and time proposal that fits your schedule.
})