NEUROGUIDE AI
Year: 2025
Type: article
Abstract: NeuroGuide AI is a cutting-edge, full-stack open-source platform designed to assist interventional neuroradiologists by transforming conventional imaging workstations into intelligent, learning-enabled neuro-intervention cockpits. It addresses the major cognitive and technical challenges in navigating catheters through the brain’s vascular system by offering real-time AI-driven support. Its key capabilities include automatic vessel segmentation using advanced MONAI-based models, optimized catheter path planning with 3D A*/RRT algorithms, in-situ augmented reality overlays for surgical navigation, and integration with robotic systems via ROS 2 for semi-automated catheter control. The system features a modular microservice architecture, scalable deployment options from single GPU workstations to Kubernetes clusters, and end-to-end observability using Prometheus and Grafana. Additional features include a federated learning engine for privacy-preserving model updates across institutions, automated regulatory documentation generation compliant with IEC 62304 and EU MDR, and a vision-language auto-labeler using BLIP-2 for generating structured clinical findings from CTA/MRA scans. NeuroGuide AI is built with clinical alignment, CI/CD best practices, and open licensing (Apache 2.0), making it a robust and future-ready platform for revolutionizing neurovascular interventions.
Authors: Tariq, Hassan, Alishba, Zainab
Institution: Punjab Medical College
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W6930833975
FWCI:
Cites:
Cited by:
Related to: