Large vessel occlusion test device and method using eyeball deviation

Inventors

Kim, Dohyun • Song, Soohwa

Assignees

Heuron Co Ltd

Abstract

A large vessel occlusion (LVO) test device using eyeball deviation includes an image input unit configured to input non-contrast computed tomography (CT); a pre-processing unit; an image processing unit; and a determination unit. The objects include both eyes and the upper part of the brain corresponding to the entire cerebral cortex from the midbrain. The image processing unit configured to non-rigid register at least one atlas for the non-cis contrast CT images pre-processed from the pre-processing unit, normalize each cell of the non-contrast CT image to which the atlas is registered to have a value of 0 or 1, and extract a region of interest in a restored non-contrast CT image by combining each cell of the non-contrast CT image to which the atlas is registered through inverse transformation.

Core Innovation

The invention provides a large vessel occlusion test device that uses eyeball deviation from non-contrast computed tomography (CT) to perform an LVO test. The device inputs a sequence of consecutive non-contrast CT images including anatomical objects consisting of both eyes and the upper part of the brain corresponding to the entire cerebral cortex from the midbrain, extracts a region of interest in a restored non-contrast CT image, and identifies eyeball deviation from the extracted region of interest.

The device pre-processes the non-contrast CT images using rigid registration and affine registration. It non-rigid registers at least one atlas for the pre-processed images, normalizes each cell of the registered non-contrast CT image to a value of 0 or 1, and extracts a region of interest in the restored non-contrast CT image by combining each registered cell through inverse transformation. This generates atlas-registered/restored non-contrast CT image data from which eyeball deviation is identified.

The device determines the patient to be large vessel occlusion (LVO) positive or negative based on the eyeball deviation by performing the LVO test. It classifies LVO suspected cases of the patient determined to be LVO positive and provides a notification to a medical staff.

Claims Coverage

The independent claim set is centered on one independent claim (clm-00001). It contains four main inventive aspects: eyeball-deviation-based LVO testing from non-contrast CT input including eyes and the upper cerebral cortex, rigid and affine pre-processing, atlas-based non-rigid registration with cell-wise 0/1 normalization and inverse-transformation-based region of interest extraction, and determination of LVO-positive/negative with classification of LVO suspected cases followed by notification to medical staff.

Across the single independent claim, the claim coverage is defined by an eyeball deviation-based LVO test using non-contrast CT containing eyes and the upper cerebral cortex, rigid/affine pre-processing, atlas-based non-rigid registration with cell-wise 0/1 normalization and inverse-transformation ROI extraction, and a determination workflow that outputs LVO-positive/negative results, classifies LVO suspected cases, and notifies medical staff.

Stated Advantages

Documented Applications