An interview with Prof. Marc Ribo, MD, PhD, Assistant Professor at the Stroke Unit/Department of Neurology at the Hospital Vall d’Hebron, Barcelona, Spain.
Interviewed by Dr. Vera Sharashidze, MD, Vascular Neurology Fellow, University of Miami.
They will be discussing the article “Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography,” published in the October 2020 issue of Stroke.
Dr. Sharashidze: First of all, thank you for taking time to discuss this very interesting article. What led you to become interested in this topic?
Prof. Ribo: My first interest in AI analysis of acute stroke imaging began when I met by coincidence with an expert engineer who wanted to use his skills to help stroke patients.
Dr. Sharashidze: How do you think Methinks software could change management of LVO patients?
Prof. Ribo: Many stroke patients are still first transferred to centers in which contrast imaging is not available, leading to diagnostic delays and negative impact on outcome.
Dr. Sharashidze: What changes and systems of care do you think would need to be implemented if Methinks software is used widely?
Prof. Ribo: For most centers, installing Methinks technology that allows instant AI interpretation and eventual alert to the corresponding stroke team represents minimal one-time effort, much simpler than training local teams to perform acute contrast imaging 24/7.
Dr. Sharashidze: Do you foresee Methinks replacing vessel imaging?
Prof. Ribo: That would be a very reasonable option, especially in primary stroke centers or developing countries. This would help reducing the gap with most advanced large comprehensive stroke centers.
Dr. Sharashidze: What are the next steps with future studies?
Prof. Ribo: Validation of the present findings in a prospective study within a stroke network will allow to confirm the accuracy of the algorithm and quantify time savings on workflows, thrombectomies, and clinical outcome.
Dr. Sharashidze: What do you think would be the next thing replaced by AI in stroke care?
Prof. Ribo: Future developments in the field are oriented to extract the most information from non-contrast CT imaging such as identification of infarct core and penumbra or clot characterization. I believe in the midterm, AI will offer valuable information, comparable or even superior to what is currently obtained using contrast with faster and simpler acquisition protocols.
Dr. Sharashidze: Thank you so much, Dr. Ribo, for taking time out from your busy schedule to talk to us.