Ischemic stroke detection and classification method based on medical image, apparatus and system
Inventors
Kim, Dohyun • Song, Soohwa • Jung, Sumin • Lee, Jin Soo • Lee, Seong Joon • KOH, Seung Yon
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11602322-B2
Publication Date
2023-03-14
Expiration Date
Abstract
The present disclosure relates to a method, an apparatus, and a system for detecting and classifying an ischemic stroke based on a medical image. A medical image based ischemic stroke detecting and type classifying apparatus according to an aspect of the present disclosure includes an acquiring unit which collects images related to a brain of at least one patient; a detecting unit which determines whether the at least one patient is a large vessel occlusion patient, based on the collected image; a determining unit which determines whether a type of the large vessel occlusion is embolism or intracranial atherosclerosis (ICAS), when the at least one patient is a large vessel occlusion patient; and a diagnosing unit which provides treatment direction information which is applied differently according to the determined type of the large vessel occlusion.
Core Innovation
The invention provides a medical image-based ischemic stroke detecting, classifying, and treatment method. The method collects images of a brain of a patient using an acquiring unit, determines that the patient has a large vessel occlusion based on the collected images using a detecting unit, and determines whether the large vessel occlusion is embolism or intracranial atherosclerosis (ICAS) using a determining unit.
A spatially normalized region of interest is extracted from the collected images in the large vessel occlusion detection process, and presence or absence of large vessel occlusion is determined using the extracted region of interest. The embolism versus ICAS classification is refined by additional determinations including whether a position of the large vessel occlusion corresponds to posterior circulation (PC) or anterior circulation (AC), and whether the large vessel occlusion is branching-site occlusion (BSO) or truncal-type occlusion (TTO).
The disclosed framework provides treatment direction information based on the determined type and then provides a treatment selected from multiple treatment options. The approach includes additional determination paths that relate perfusion and diffusion information to ICAS-related collateral-circulation formation conditions, and that further tailor treatment direction to embolism severity and ICAS treatment direction options.
Claims Coverage
Independent claim clm-00001 sets out a medical image-based ischemic stroke detecting, classifying, and treatment method with a five-step pipeline. It includes inventive features spanning occlusion detection with spatial alignment and region-of-interest extraction, embolism versus ICAS classification, circulation position and occlusion-type determinations, treatment-direction information provision, and subsequent treatment selection from a defined set of options.
Medical image-based ischemic stroke pipeline for detecting, classifying, and directing treatment
A medical image-based ischemic stroke detecting, classifying, and treatment method comprising collecting brain images with an acquiring unit, determining large vessel occlusion with a detecting unit, determining whether the large vessel occlusion is embolism or intracranial atherosclerosis (ICAS) with a determining unit, providing treatment direction information based on the determined type with a diagnosing unit, and providing a treatment selected from angioplasty, antiplatelet agent treatment, thrombolytic agent treatment, thrombectomy, treatments using a drug other than the antiplatelet agent, treatments using a stent, treatments using insertion of a balloon, counterpulsation treatment, or combinations thereof.
Large vessel occlusion detection with spatial alignment and region of interest extraction
The method where the large vessel occlusion detection includes performing spatial alignment of collected brain images for spatial normalization and extracting a region of interest from the spatial normalized images by an image processing unit, receiving the region of interest and determining the presence or absence of large vessel occlusion by a large vessel occlusion detecting unit.
Embolism vs ICAS classification using posterior/anterior position and BSO/TTO occlusion type
The method where the embolism versus ICAS classification includes determining whether a position of the large vessel occlusion corresponds to posterior circulation (PC) or anterior circulation (AC), determining whether a type of the large vessel occlusion is branching-site occlusion (BSO) or truncal-type occlusion (TTO), and determining a type of the large vessel occlusion based on a first determination for PC or AC and a second determination of BSO or TTO.
The claim coverage is anchored by clm-00001’s integrated workflow: image collection, large vessel occlusion detection using spatial normalization and region-of-interest extraction, embolism versus ICAS classification, refinement through posterior/anterior circulation position and BSO/TTO type logic, followed by treatment-direction information provision and selection of a treatment from a defined set.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?