System and method for estimating acute cerebral infarction onset time

1. A method for estimating an onset time of acute cerebral infarction, the method comprising:

receiving, by a processor, from an external device, a first image and a second image of a first patient whose acute cerebral infarction onset time is not identified, the first image is a fluid-attenuated inversion recovery image, and the second image is a diffusion-weighted image;

extracting, by the processor, an infarction region image from the second image;

aligning, by the processor, the second image with the first image;

defining, by the processor, an infarction region in the first image, based on a result of the alignment of the second image with the first image;

extracting, by the processor, feature information of the first patient, from the infarction region in the first image;

comparing, by the processor, the extracted feature information with reference data;

calculating, by the processor, an amount of time that has elapsed since the acute cerebral infarction onset time, based on a result of the comparison of the extracted feature information with the reference data;

comparing, by the processor, the infarction region with a symmetric region located in a brain of the first patient and being symmetrical to the infarction region;

extracting, by the processor, a relative signal amount of the infarction region, based on a result of the comparison of the infarction region with the symmetric region; and

generating, by the processor, a third image that shows a ratio map of a pixel comparison of pixels of the symmetric region with corresponding pixels of the infarction region,

wherein the feature information includes:

first feature information extracted from the infarction region in the first image; and

second feature information extracted from an infarction region in the third image.

2. The method of claim 1 , wherein the reference data includes:

feature information of at least one second patient, contained in an infarction region of a first image of the at least one second patient, the second patient is a patient whose acute cerebral infarction onset time is identified; and

information on an amount of time that has elapsed since an acute cerebral infarction onset time of the at least one second patient.

3. The method of claim 2 , further comprising:

generating, by the processor, the reference data as a support vector machine, based on first and second images of a plurality of second patients,

wherein the generating of the reference data comprises:

classifying the plurality of second patients into a training group, a validating group, and a testing group;

extracting feature information of each of second patients classified into the training group, from a first image of the each of the second patients classified into the training group, by performing an alignment of the first image of the each of the second patients classified into the training group with a second image of the each of the second patients classified into the training group;

training the support vector machine by using the feature information of the second patients classified into the training group;

determining a type of the support vector machine by using the validating group; and

applying the testing group to the determined support vector machine type to determine whether the type of the support vector machine is to be defined as the reference data.

4. The method of claim 2 , wherein the reference data is classified into detailed groups according to gender or age information of second patients, and

wherein the calculating of the elapsed amount of time comprises defining detailed groups to be compared with the feature information of the first patient, based on age information or gender information of the first patient.

5. The method of claim 1 , wherein the extracting of the infarction region image from the second image comprises:

normalizing an intensity of an apparent diffusion coefficient map of the second image; and

extracting the infarction region image via an absolute reference value search in the normalized apparent diffusion coefficient map.

6. The method of claim 1 , further comprising:

determining, by the processor, whether the elapsed amount of time is within a reference duration; and

outputting, by the processor, a signal for notifying the determination result.

7. The method of claim 1 , wherein the aligning of the second image with the first image comprises

aligning of the second image with the first image by applying at least one of an enlargement, a shrinkage, a symmetrical movement, and a rotation, to the first image or the second image, based on a skeleton position in the first image or the second image.

8. The method of claim 1 , wherein the extracting of the feature information comprises

extracting the feature information by applying at least one of a gray level co-occurrence matrix, a run-length matrix and a local binary pattern, to signal intensity and gradient of the infarction region.

9. A non-transitory computer readable recording medium storing a computer program coupled to a computer device including a processor to execute the method for estimating an onset time of acute cerebral infarction, according to claim 1 .

10. A system for estimation of an acute cerebral infarction onset time, the system comprising:

an image storage that stores a first image and a second image of a first patient whose acute cerebral infarction onset time is not identified, the first image is a fluid-attenuated inversion recovery image, and the second image is a diffusion-weighted image;

an infarction region image extractor that extracts an infarction region image from the second image;

an image aligner that aligns the second image with the first image;

an infarction region definer that defines an infarction region in the first image, based on a result of the alignment of the second image with the first image;

a feature information extractor that extracts feature information of the first patient, from the infarction region of the first image;

an elapsed amount of time calculator that compares the extracted feature information with reference data, and calculates an amount of time that has elapsed since the acute cerebral infarction onset time, based on a result of the comparison of the extracted feature information with reference data; and

a ratio map generator configured to:

compare the infarction region with a symmetric region located in a brain of the first patient and being symmetrical to the infarction region;

extract a relative signal amount of the infarction region, based on a result of the comparison of the infarction region with the symmetric region; and

generate a third image that shows a ratio map of a pixel comparison of pixels of the symmetric region with corresponding pixels of the infarction region,

wherein the feature information includes:

first feature information extracted from the infarction region in the first image; and

second feature information extracted from an infarction region in third image.

11. The system of claim 10 , wherein the reference data includes:

feature information of at least one second patient, contained in an infarction region of a first image of the at least one second patient, the second patient is a patient whose acute cerebral infarction onset time is identified; and

information on an amount of time that has elapsed since an acute cerebral infarction onset time of the at least one second patient.

12. The system of claim 10 , further comprising:

a reference data generator that generates the reference data as a support vector machine, based on first and second images of a plurality of second patients,

wherein the reference data generator is configured to:

classify the plurality of second patients into a training group, a validating group, and a testing group;

extracts feature information of each of second patients classified into the training group, from a first image of the each of the second patients classified into the training group, by performing an alignment of the first image of the each of the second patients classified into the training group with a second image of the each of the second patients classified into the training group;

train the support vector machine by using the feature information of the second patients classified into the training group;

determine a type of the support vector machine by using the validating group; and

apply the testing group to the determined support vector machine type to determine whether the determined support vector machine type is to be defined as the reference data.