MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641025134 A) filed by Dayananda Sagar University, Bengaluru, Karnataka, on March 3, for 'system and method for generating and immersive visualization of the 3d perfusion maps for ischemic stroke assessment using artificial intelligence and augmented/virtual reality.'
Inventor(s) include Dr. Revathi V; Dr. Renukadevi M N; Dr. Naresh Nikhil; Dr. Roopa H N; Syed Fuzail Rubbani; Suhaib Yasir Bhosge; Sunil Kumar Chavhan; Tavva Tejaswini Reddy; and Dr. Santosh Kumar J.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The invention discloses a computer-implemented system and a method for enhanced ischemic stroke assessment that predicts volumetric perfusion parameter maps-specifically cerebral blood flow (CBF), cerebral blood volume (CBV), and mean transit time (MTT)-directly from non-contrast structural biomedical images, such as non-contrast computed tomography (NCCT), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. A custom 3D U-Net deep learning architecture, featuring 3 3 3 convolutions, Instance Normalization, Leaky Re LU activations, skip connections, and strided down sampling, processes the input volumes to generate the high-fidelity, multi-channel perfusion predictions without requiring contrast-enhanced dynamic scanning. The predicted volumetric maps undergo post-processing, including thresholding for infarct core (e.g., CBF 30% contralateral mean) and penumbra identification via CBF-ADC mismatch criteria, followed by mesh generation using marching cubes and smoothing for a renderable 3D geometry. These models are seamlessly integrated into an immersive augmented reality (AR) and virtual reality (VR) environment built with Unity 3D and the XR Interaction Toolkit, supporting real-time six-degrees-of-freedom interaction, arbitrary plane slicing, parameter-specific colour overlays, and dynamic visualization of hemodynamic patterns."
Disclaimer: Curated by HT Syndication.
