Stroke monitoring

Inventors

ABBOSH, Amin • AFSARI, Arman

Assignees

Emvision Medical Devices Ltd

Abstract

A computer-implemented process for continuous monitoring of a brain stroke during a critical rehabilitation period, the process including the steps of: (i) accessing initial image data representing an initial image of a subjects brain containing a stroke region; (ii) accessing scattering parameter data representing microwaves scattered by the subjects brain and originating from a plurality of antennas disposed around the subjects brain; and (iii) processing the scattering parameter data and the initial image data using a gradient-free optimisation method to generate estimates of spatial dimensions of the stroke region within the subjects brain, wherein the initial image of the subjects brain is used as a priori information to improve the accuracy of the generated estimates, and the spatial dimensions of the stroke region are generated as global parameters of the gradient-free optimisation method.

Core Innovation

The invention provides a computer-implemented process for continuous monitoring of a brain stroke during a critical rehabilitation period. The process involves accessing initial image data representing an initial image of a subject's brain containing a stroke region, accessing scattering parameter data representing microwaves scattered by the subject's brain and originating from antennas disposed around the brain, and processing these data using a gradient-free optimization method to generate estimates of spatial dimensions of the stroke region. The initial image is used as a priori information to improve the accuracy of these estimates, with the spatial dimensions generated as global parameters of the gradient-free optimization method.

The problem being solved relates to the lack of an efficient stroke monitoring tool to continuously measure the geometrical size of a stroke and its response to treatment during the critical rehabilitation period, typically the first six hours after symptom onset. Current imaging modalities such as MRI and X-rays are unsuitable for continuous monitoring during this period due to limitations like bulky equipment, ionizing radiation, genotoxic effects, high cost, and prohibitively long computational times. Electromagnetic tomography (EMT) offers a potential solution due to portability and safety but suffers from inaccuracies and high computational demands, especially when using gradient-based optimizations that calculate variables at every pixel.

The innovation overcomes these limitations by using an initial high-resolution image (from MRI, X-ray, or EMT) as a priori information to define the initial shape and dielectric properties of the stroke region. Instead of pixel-based optimizations, the process treats the shape, dimensions, and dielectric properties as global parameters optimized by a gradient-free method, specifically the Nelder-Mead method. This reduces unknowns from thousands of pixel variables to a few global parameters, greatly reducing computational time while improving accuracy, thus enabling efficient and continuous monitoring of stroke growth or shrinkage during the critical rehabilitation period.

Claims Coverage

The patent includes three independent claims covering the process, apparatus, and computer-readable storage medium for continuous brain stroke monitoring using initial image data, scattering parameter data, and gradient-free optimization methods. The coverage focuses on the main inventive features of spatial dimension estimation, a priori image use, and optimization techniques.

The claims collectively cover a novel stroke monitoring process and system that use initial brain imaging data combined with microwave scattering measurements processed by a Nelder-Mead gradient-free optimisation to efficiently estimate and track global spatial dimensions of the stroke region, enabling continuous monitoring during the critical rehabilitation period.

Stated Advantages

Documented Applications