Publication
Deep Learning Enabled Acute Ischemic Stroke Lesion Segmentation for Smart Healthcare Systems
Jan 1, 2024 · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany
OpenAlex citations: 0Open
Public profile
Dias Tashev
Connected with DSML. This person's Telegram account has been confirmed through DSML Kazakhstan.@diassio
ML | Cerebra AI, Ltd. · Research | Harvard University
My DS/ML interests center on the intersection of healthcare and machine learning—specifically how AI can support doctors in real clinical settings.
Boston, United StatesHarvard University
Featured
A few things that best show this member's work and contribution.
About
As an MD and ML engineer, I've spent around four years building deep learning models for medical imaging, from stroke and hemorrhage detection to 3D segmentation on CT. My work spans the full pipeline: dataset construction, model training, and deploying validated models to production, including FDA-grade validation with clinical partners.
Research and publications
A compact preview of this member's public research layer.
My research sits at the intersection of machine learning and clinical medicine, focused on how AI can support doctors in real clinical environments
Computer vison in Radiology