IP Library › Granted Patent US 10,478,069
Granted Patent B2
US 10,478,069 · App. 15/557,423 · Granted Nov 19, 2019

Method for estimating time of occurrence of infarct on basis of brain image

Inventors: Nam Kug Kim (Seoul, KR); Dong Wha Kang (Seoul, KR)
Assignee: THE ASAN FOUNDATION
A61B5/0042A61B5/055G01R33/5608G01R33/56341G01R33/56366G06T7/0014G06T7/30G06T2207/10088G06T2207/30016
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,478,069
App. No.
15/557,423
Granted
Nov 19, 2019
Kind
B2
Abstract

Disclosed is a method for estimating an onset time of an infarct region based on brain images, the method including: obtaining brain images; extracting from the infarct region included in the brain images a set of quantitative values that vary according to the onset time of the infarct region; and having the set of quantitative values correspond to the onset time of the infarct region by applying a corresponding relation prepared therefor.

Claims (27)

1. A method for estimating an onset time of an infarct region based on brain images, the method comprising:

obtaining brain images;

extracting from the infarct region included in the brain images a set of quantitative values that vary according to the onset time of the infarct region; and

having the set of quantitative values correspond to the onset time of the infarct region by applying a corresponding relation prepared therefor,

wherein the corresponding relation is prepared using a classifier that classifies the set of quantitative values by the onset time of the infarct region.

2. The method according to claim 1 , further comprising:

after obtaining the brain images and before extracting the set of quantitative values, segmenting the infarct region using at least one of the obtained brain images;

segmenting a penumbra region of the infarct region using at least one of the obtained brain images; and

registering the brain images including the at least one brain images having a segmented infarct or penumbra region.

3. The method according to claim 2 , wherein extracting the set of quantitative values comprises:

extracting from the registered brain images at least one information selected from the group consisting of size, location and intensity of the penumbra or infarct region.

4. The method according to claim 1 , wherein the corresponding relation is prepared using the classifier to have a set of accumulated quantitative values acquired from brain images whose onset times of the infarct region are known correspond to the onset time of the infarct region, with the classifier comprising at least one of the following: uni-variate regression, multi-variate regression, robust regression, support vector regression, a decision tree, a Bayesian classifier and curve fitting.

5. The method according to claim 4 , wherein having the set of quantitative values correspond to the onset time of the infarct region comprises:

having the set of quantitative values extracted from brain images with an unknown onset time of the infarct region correspond to the onset time of the infarct region by applying the corresponding relation, and

revising the corresponding relation using data accumulated by having the set of quantitative values with the unknown onset time of the infarct region correspond to the onset time of the infarct region.

6. The method according to claim 1 , wherein obtaining the brain images comprises:

generating at least two images selected from the group consisting of an MRI-based DWI image, an ADC image, a PWI image, a FLAIR image, a T1 image, a T2 image and a GRE image.

7. The method according to claim 6 , further comprising:

after obtaining the brain images and before extracting the set of quantitative values, segmenting the infarct region using the DWI or ADC image;

segmenting a penumbra region of the infarct region using the PWI image; and

registering the brain images that include the DWI or ADC image with the segmented infarct region or the PWI image with the segmented penumbra region.

8. The method according to claim 7 , wherein extracting the set of quantitative values comprises:

acquiring from the registered brain images two or more quantitative values selected from the group consisting of an infarct volume V I , an infarct location V IL , a penumbra volume V P , a penumbra position V PL , mismatch M between the infarct region and the penumbra region, an average intensity of the infarct region in a respective brain image, and an average intensity of the penumbra region in the respective brain image.

9. The method according to claim 1 , wherein having the set of quantitative values correspond to the onset time of the infarct region comprises:

a process in which the onset time of the infarct region corresponds to a first zone for one quantitative value included in the set of the quantitative values;

a process in which in which the onset time of the infarct region corresponds to a second zone for another quantitative value included in the set of the quantitative values; and

a process in which an intersection of the first and second zones is obtained to narrow down a corresponding zone at the onset time of the infarct region.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 3, 2025
From: THE ASAN FOUNDATION
To: NUNAPS INC.
Reel/Frame 070718/0561 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 11, 2017
From: KIM, NAM KUG; KANG, DONG WHA
To: THE ASAN FOUNDATION
Reel/Frame 043548/0840 →
Continuity (1)
Related Publication 20180271373A1 · Sep 27, 2018