Cerebral apoplexy diagnosis device and method based on artificial intelligence

A technology of artificial intelligence and diagnostic devices, which is applied to radiological diagnostic instruments, diagnostics, computerized tomography scanners, etc., and can solve problems such as differences, differences in diagnostic results, and high probability of errors

Active Publication Date: 2020-11-10
HEURON CO LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] On the other hand, when the severity of cerebral infarction is scored based on the plain computerized tomography images of the brain, the early computerized tomography score of the Alberta Stroke Project, etc., the regional judgment and interpretation of the clinician Differences in diagnostic results occur, and therefore, there is a problem that it is difficult to maintain an inertia of diagnostic results
[0019] In addition, in the conventional brain disease analysis device, a method of normalizing only brain lesions is detected in medical images such as computerized tomography scans and brain magnetic resonance imaging acquired from diagnostic objects. , has the problem that the areas extracted from the medical images of each patient are inconsistent and different from each other, and when scoring the severity, the probability of error occurrence is high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cerebral apoplexy diagnosis device and method based on artificial intelligence
  • Cerebral apoplexy diagnosis device and method based on artificial intelligence
  • Cerebral apoplexy diagnosis device and method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0279] Figure 13 To illustrate it can be Figure 5 A flowchart of an embodiment of screening patients with sudden large vessel occlusion based on the artificial intelligence algorithm in the process described in .

[0280] refer to Figure 13 Then, the mechanical thrombectomy judging unit 45 executes the step of constructing a regression-structure artificial intelligence model based on multi-numeric data (step S111 ).

[0281] Afterwards, in the case of a patient whose dense arterial sign is detected at the subganglionic level, the mechanical thrombectomy judging unit 45 can perform an emergency large vessel occlusion (ELVO, Emergent large vessel occlusion) based on an artificial intelligence model. Step (step S90 ), the output of the ischemia classification step (step S70 ), and the Alberta stroke project early electronic computed tomography evaluation judged by step S100 to distinguish whether to operate or not (step S112 ).

[0282] That is, when the estimated early com...

no. 2 example

[0284] Figure 14 To illustrate it can be Figure 5 A flow chart of yet another embodiment of screening patients with sudden large vessel occlusion based on the artificial intelligence algorithm in the process described in .

[0285] refer to Figure 14 The mechanical thrombectomy judging unit 45 may execute the step of detecting the volume of the lesion (early ischemic signal, obvious hypodensity) caused by sudden large vessel occlusion by artificial intelligence (step S113 ).

[0286] Afterwards, the mechanical thrombectomy judging unit 45 may machine learning-logistic regression the volume of the detected lesion (step S114 ).

[0287] In addition, the mechanical thrombectomy judging unit 45 judges whether to perform mechanical thrombectomy based on the model of machine learning and the Alberta Stroke Program early computerized tomography score (step S115 ).

[0288] That is, it is possible to determine whether the at least one patient is a patient applicable to mechanica...

no. 3 example

[0290] Figure 15 To illustrate it can be Figure 5A flow chart of another embodiment of screening patients with sudden large vessel occlusion based on the artificial intelligence algorithm in the process described in .

[0291] refer to Figure 15 , the mechanical thrombectomy judging unit 45 executes the step of collecting the absolute time, early ischemic signal, and obviously low-density volume of plain-scan electronic computed tomography after the occurrence of large vessel occlusion (LVO, large vesselocclusion) (step S116) .

[0292] Thereafter, the mechanical thrombectomy judging unit 45 calculates a tissue clock based on the collected information (step S117).

[0293] Furthermore, the mechanical thrombectomy judging unit 45 judges whether to perform mechanical thrombectomy and the available time based on the tissue clock and the Alberta Stroke Program early computerized tomography score (step S118 ).

[0294] As described above, if it is identified as a patient sui...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses a cerebral apoplexy diagnosis device based on artificial intelligence, and the device comprises an image acquisition unit for acquiring a flat-scan computed tomography image related to the brain of at least one patient; a preprocessing unit that preprocesses the flat-scan computed tomography image and determines whether the at least one patient is in a non-bleeding state or a bleeding state on the basis of the preprocessed image; an image processing unit that normalizes the preprocessed image and divides and extracts a region of interest by using a preset standard mask template; and a determination unit for determining whether or not there is an abnormality in the cerebral great vessels of the at least one patient by using the divided and extractedregion of interest.

Description

technical field [0001] The invention relates to a device and method for diagnosing cerebral apoplexy based on artificial intelligence. In more detail, it relates to a device and method for diagnosing cerebral apoplexy using an artificial intelligence algorithm. The above-mentioned artificial intelligence algorithm classifies stroke patients and screens patients with sudden large vessel occlusion based on unenhanced computerized tomography images. Background technique [0002] Brain diseases, that is, cerebrovascular diseases include cerebral hemorrhage in which cerebral blood vessels rupture, cerebral infarction in which cerebral blood vessels are blocked by thrombus, etc., and cerebral aneurysms in which cerebral blood vessels are abnormally dilated. Cerebral hemorrhage and cerebral infarction are collectively referred to as "stroke". [0003] For diagnosing brain diseases as described above, non-invasive techniques such as ultrasound diagnosis, brain computed tomography (C...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61B6/03G06K9/32G06T3/60G06T5/00G06T7/00G06T7/38
CPCA61B6/032G06T7/0012G06T5/002G06T3/608G06T7/38A61B6/4411A61B6/501A61B6/5211A61B6/5258A61B6/5217G06T2207/10081G06T2207/30016G06T2207/30101G06T2207/20081G06T2207/20084G06V10/25G06V2201/03A61B6/504G16H50/20G16H30/40G06T7/11G06T7/174A61B6/507A61B6/5294
Inventor 金到炫宋洙和郑秀玟李真守李圣濬
Owner HEURON CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap