# US 10,478,069 B2 · Method for estimating time of occurrence of infarct on basis of brain image > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,478,069 B2 - Document ID: US10478069B2 - Status: Granted - Kind: B2 - Application number: 15/557,423 - Filed: 2015-03-12 - Published: 2018-09-27 - Granted: 2019-11-19 - Earliest claimed: 2015-03-12 - Assignees: The Asan Foundation - Applicants: The Asan Foundation - Inventors: Nam Kug Kim; Dong Wha Kang - Web page: https://patentgrep.com/patent/US10478069B2 ## CPC - A61B 5/0042: {for the brain} - G06T 7/0012: {Biomedical image inspection} - A61B 5/00: Measuring for diagnostic purposes (radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00); Identification of persons - A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging - G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)} - G01R 33/56341: {Diffusion imaging} - G01R 33/56366: {Perfusion imaging} - G06T 7/0014: {using an image reference approach} - G06T 7/30: Determination of transform parameters for the alignment of images, i.e. image registration - G06T 2207/10088: Magnetic resonance imaging [MRI] - G06T 2207/30016: Brain - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) ## 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 ### Claim 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. ### Claim 2 (depends on 1) 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. ### Claim 3 (depends on 2) 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. ### Claim 4 (depends on 1) 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. ### Claim 5 (depends on 4) 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. ### Claim 6 (depends on 1) 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. ### Claim 7 (depends on 6) 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. ### Claim 8 (depends on 7) 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 VI, an infarct location VIL, a penumbra volume VP, a penumbra position VPL, 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. ### Claim 9 (depends on 1) 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.