KR102045435B1 - Apparatus and method for making diagnosis using densitometry analysis in computed tomography, and computer readable medium thereof - Google Patents

Abstract

The present invention relates to a diagnostic apparatus, a method and a recording medium recording the same by analyzing density of a computed tomography image. The diagnostic method through the density analysis of the computed tomography image image according to the present invention is a method for diagnosing ischemic damage through the density analysis of the computed tomography image image Hounsfield unit of the pixel value of the computed tomography image of the brain section Converting to a HU: Hounsfield Unit (HU) value, extracting a region corresponding to brain tissue from the image, extracting a density distribution curve of a hounsfield unit value of a region corresponding to the extracted brain tissue, Dividing the density distribution curve area of the Hounsfield unit value into quadrants to calculate the interval length of the quartered Hounsfield unit value as a parameter, and diagnosing ischemic injury using the calculated parameters. It includes.

Description

TECHNICAL FIELD, METHOD FOR MAKING DIAGNOSIS USING DENSITOMETRY ANALYSIS IN COMPUTED TOMOGRAPHY, AND COMPUTER READABLE MEDIUM THEREOF}

The present invention relates to a diagnostic apparatus, a diagnostic method, and a recording medium recording the same by analyzing density of a computed tomography image.

Most types of brain injury are exacerbated by secondary ischemic or edema seizures that occur within a few hours after the primary injury occurs. Acquired Brain Injury (ABI), which appears as a trauma or stroke, can minimize secondary brain damage as soon as the extent of the injury is quickly determined during the acute phase.

Currently, in order to prevent such acquired brain damage, the acquired brain injury is diagnosed by image reading after CT scan. However, such a method involves not only the volatility between the readers, but also the objective and quantitative evaluation because the subjective judgment of the subject is involved.

In order to solve this problem, studies are being conducted to quantify brain density by introducing Hounsfield Unit (HU) values of computed tomography images and to use them to improve the accuracy of diagnosis and prognostic prediction. However, the HU value is pre-processed or post-processed to correct the error of the HU value because the variability of the value occurs due to the difference in value depending on the computed tomography device and the shooting conditions (tube-voltage, tube-current, etc.). Processing is needed.

There is a need for a method capable of real-time detection of tissue damage such as acquired brain injury in a quantitative value that can solve the above problems.

Patent No. 10-1530015, Name of the invention: Method for density analysis of computed tomography images US Patent US8218835, titled: Method for assisting in diagnosis of cerebral diseases and apparatus

The present invention quantitatively detects tissue damage in real time using a density distribution curve obtained by converting a hounsfield value of brain tissue and lesions into a ratio of the total number of pixels, and uses the value to diagnose a related disease. An object of the present invention is to provide a diagnostic apparatus, a diagnostic method, and a recording medium recording the same by analyzing density of a computed tomography image.

In order to achieve the above object, an ischemic injury diagnosis method through density analysis of a computed tomography image image in accordance with an embodiment of the present invention is performed by calculating a pixel value of a computed tomography image of a brain cross-section using a hounsfield unit (HU). Converting a Hounsfield Unit) value, extracting a region corresponding to brain tissue from the image, extracting a density distribution curve of Hounsfield unit values of a region corresponding to the extracted brain tissue, and Dividing the density distribution curve area of the Sfield unit value into quadrants to calculate the interval length of the quartered Hounsfield unit value as a parameter, and diagnosing ischemic injury using the calculated parameter. do.

Here, the step of extracting an area corresponding to the brain tissue may include dividing each pixel of the computed tomography image into an effective pixel and an invalid pixel, and setting a reference point so that an upper direction, a lower direction, a left direction, and The region corresponding to the brain tissue may be extracted by selecting an effective pixel in a range in which the hounsfield unit value is set in the right direction.

In the extracting of the density distribution curve of the hounsfield unit values, the number of pixels having the hounsfield unit values of which the sum of 0 and 79 or less is 100 is respectively counted, and the hounsfield units of each pixel are counted. The density distribution curve of the hounsfield unit value may be extracted by dividing the value by the counted total number of pixels.

In the extracting of the density distribution curve, the density distribution curve of the hounsfield unit value may be extracted by adding the number of pixels having the hounsfield unit value in each slice unit for each 3D tomography image. have.

The calculating of the parameter may include calculating a total area of the density distribution curve in a direction in which the hounsfield value increases from a point where the hounsfield value is 0, 25%, 50 of the total area. Dividing the regions which are%, 75%, and 100%, determining the hounsfield values P1, P2, P3, and P4 to each of the divided regions, and the determined hounsfield values P1 and P2. , P3 and P4 may be substituted into the following equation to calculate the parameters L1, L2, L3, and L4.

In addition, diagnosing the ischemic injury may diagnose the ischemic injury using morphological parameters.

Here, when the sum of the parameter L2 and the parameter L3 is defined as IQR (InterQuartile Range), the morphological parameter may be expressed as a result obtained by multiplying the IQR by skewness or kurtosis.

The skewness and kurtosis are calculated by the following equation.

,

,

Where λ _P is the Hounsfield value, m is the mean, and σ is the standard deviation.

According to another embodiment of the present invention, a computer-readable recording medium having recorded thereon a program for executing the method for diagnosing ischemic injury through density analysis of the computed tomography image image may be provided.

In addition, according to another embodiment of the present invention, a method for diagnosing damage to a tissue by analyzing density of a computed tomography image image may include calculating a pixel value of a computed tomography image of a cross section of a tissue by a Hounsfield unit (HU). A step of extracting a region corresponding to the tissue in the image, extracting a density distribution curve of a hounsfield unit value of the region corresponding to the extracted tissue, and extracting the region of the hounsfield unit value. Dividing the area of the density distribution curve into N sections in a set percentage unit, calculating a section length of the Hounsfield unit values of the N sections as a parameter, and using the calculated parameters to repair the tissue damage. Diagnosing.

Here, the set percentage may be set equally or differently with respect to the N sections.

In addition, according to another embodiment of the present invention, the tissue damage diagnosis apparatus through the density analysis of the computed tomography image image input unit for receiving a computed tomography image of the cross-section of the tissue, and the image to quantify the tissue And a controller for diagnosing damage, wherein the controller converts a pixel value of the image into a Hounsfield Unit (HU) value, extracts an area corresponding to the tissue from the image, and extracts the extracted tissue. Extracting the density distribution curve of the hounsfield unit value of the region corresponding to, dividing the area of the density distribution curve of the hounsfield unit value into N sections by a set percentage unit, and the hounsfield unit values of the N sections The section length of may be calculated as a parameter, and damage of the tissue may be diagnosed using the calculated parameter.

According to the present invention, a new morphological indicator for quantitative analysis of brain tissue is proposed by determining parameters for diagnosis by focusing on the morphological characteristics of the density distribution of Hounsfield unit values, thereby expanding the research. Has the effect of providing.

In addition, there is an effect of expanding the theory in the field of diagnosing diseases using morphological characteristics of density distributions corresponding to tissues and lesions derived from tomography images as well as brain diseases.

1 is a flowchart of a diagnostic method through density analysis of a computed tomography image image according to an exemplary embodiment.
2 is a flowchart for calculating parameters in a diagnostic method through density analysis of a computed tomography image image according to an exemplary embodiment.
3 is a density distribution curve for explaining a parameter in the diagnostic method through the density analysis of the computed tomography image image in accordance with an embodiment of the present invention.
4 is a view for explaining the relationship between skewness, kurtosis and density distribution curve in the diagnostic method through the density analysis of the computed tomography image image according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a relationship between each parameter and a disease diagnosis in a diagnosis method through density analysis of a computed tomography image image according to an exemplary embodiment.

Hereinafter, a diagnostic apparatus, a diagnostic method, and a recording medium recording the same through a density analysis of a computed tomography image image according to an exemplary embodiment of the present invention will be described in detail with reference to the accompanying drawings. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted for simplicity of explanation, and like reference numerals designate like parts throughout the specification.

In the present invention, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized by both. In addition, one unit may be realized using two or more pieces of hardware, or two or more units may be realized by one piece of hardware.

In order to clarify the understanding of the present invention, description of well-known technology for the features of the present invention will be omitted. The embodiments are detailed description to assist in understanding the present invention, and do not limit the scope of the present invention. Therefore, equivalents that perform the same function as the present invention also fall within the scope of the present invention.

Hereinafter, specific embodiments will be described with reference to the accompanying drawings.

1 is a flowchart of a diagnostic method through density analysis of a computed tomography image image according to an exemplary embodiment.

Referring to FIG. 1, in the diagnostic method through density analysis of a computed tomography image image according to an exemplary embodiment, first, a pixel value of the computed tomography image is converted into a HU (Hounsfield Unit) value (S110). An area corresponding to the brain tissue may be extracted (S120), and a density distribution curve of the HU value may be extracted (S130). In addition, the diagnostic method through the density analysis of the computed tomography image image may calculate a parameter (S140), and diagnose ischemic injury (S150).

Specifically, the ischemic injury diagnosis method through density analysis of a computed tomography image image may convert the pixel value of the computed tomography image of the brain cross-sectional image to a hounsfield unit value. In general, computed tomography (CT) is a technique of obtaining a cross-sectional image obtained by cutting a human body (brain) horizontally by taking a picture of a circular machine having an X-ray generator. An X-ray generator is located on one side of the subject and an X-ray detector is configured on the opposite side, so that the aimed X-ray beam passes through the desired area in various directions with uniform intensity, and the amount of X-rays attenuated on the other side After measuring by measuring with a detector, an image can be constructed. At this time, the degree of absorption of the X-rays is called a hounsfield unit named after the computed tomography value or the inventor of the computed tomography. The value of HU is 0 for water, -1000 for air, +1000 for dense bone, and other materials have values between -1000 and +1000 depending on the attenuation of X-rays, respectively.

As described above, in converting the pixel value of the computed tomography image of the brain taken into the HU value, the process of removing the artifacts of the machine and the artifacts of the image may be further included. That is, the HU value of the machine is very similar to the HU value of the bone, and since the artifact removal method of the computed tomography image removes the artifact by using the HU value in the last step, the mechanical artifact removal may be preceded. The process of eliminating machine artifacts can be removed by using the feature that the space between the machine and the brain is empty in the computed tomography image and that the machine is located only on the left, right, and bottom of the computed tomography image. Can be.

In order to analyze computed tomography images from which mechanical artifacts have been removed, a pixel set having a positive HU value may be searched to determine whether the pixel set having a positive HU value is a mechanical artifact, and the pixel set may be removed if it is a mechanical artifact. have.

After removing the artifacts, regions corresponding to brain tissue can be extracted. Each pixel of a computed tomography image is divided into an effective pixel and an invalid pixel, a reference point is set, and an effective pixel in which a hounsfield unit value is set from the reference point in an upward direction, a downward direction, a left direction, and a right direction. Automatic masking technique can be used to extract the area corresponding to brain tissue by selecting. In detail, the automatic masking process may classify each pixel of the computed tomography image into valid pixels corresponding to tissues and invalid pixels corresponding to a black background. In this case, the criterion of the invalid pixel value may be set to −1000. The range of effective pixel values representing tissue pixels including eyes, nose, and brain may be set to 69 to 89. In addition, a four-way effective pixel search algorithm for searching for effective pixels in four directions from a reference point may be used in the process of automatically masking tissue pixels.

Next, the density distribution curve of the hounsfield unit value of the region corresponding to the extracted brain tissue may be extracted. The HU value of the region corresponding to the brain tissue in the computed tomography image has a value between 0 and 79. One density distribution curve can be extracted by adding the number of pixels having respective HU values. In detail, the number of pixels having the respective HU values may be divided by the total number of pixels to derive the ratio of the pixels having the respective HU values to the entire CT picture. For each slice, a multi-level density distribution graph that reflects the entire three-dimensional cerebral brain can be output using the ratio occupied by the entire CT photograph having the respective HU values through the above process. At this time, the HU value is represented by λ and has a value between 0 and 79. At this time, if λ _P is expressed as the ratio of the HU value in the density distribution curve, Equation 1 below is established. Therefore, the area under the density distribution curve is always '100'.

That is, the method of extracting the density distribution curve of the hounsfield unit value counts the number of pixels having the hounsfield unit value, which is a total of 0 or more and 79 or less, respectively, and calculates the hounsfield unit value of each pixel. The density distribution curve of the hounsfield unit value can be extracted by dividing by the total number of pixels counted. In addition, the density distribution curve of the hounsfield unit value may be extracted by adding the number of pixels having the hounsfield unit value to each slice unit for each 3D tomography image.

Subsequently, the area of the density distribution curve of the hounsfield unit value can be divided into quadrants to calculate the interval length of the quartered hounsfield unit value as a parameter. A detailed method of calculating the parameter will be described in detail below with reference to FIG. 2.

Finally, the calculated parameters can be used to diagnose ischemic injury. In particular, the method of diagnosing ischemic injury may diagnose ischemic injury using morphological parameters. Here, when the sum of the parameter L2 and the parameter L3 is defined as IQR (InterQuartile Range), the morphological parameter may be represented as a result of multiplying the IQR by skewness or kurtosis.

Skewness may be calculated by Equation 2 below, and kurtosis may be calculated by Equation 3 below.

Where _P is a Hounsfield value, m is the mean, and s is the standard deviation.

2 is a flowchart for calculating parameters in a diagnostic method through density analysis of a computed tomography image image according to an exemplary embodiment.

Referring to Figure 2, the process of calculating the parameter in the diagnostic method through the density analysis of the computed tomography image image in accordance with an embodiment of the present invention calculates the total area of the density distribution curve (S141), 25%, 50%, 75%, and 100% regions may be divided (S143), and P1, P2, P3, and P4 may be determined (S145), and L1, L2, L3, and L4 may be calculated (S147).

Specifically, the process of calculating the parameter calculates the total area of the density distribution curve in the direction of increasing HU value from the point where the HU value is '0', and thus 25%, 50%, 75%, 100% of the total area. Separate dls areas.

Determine the HU values (P1, P2, P3, P4) up to each of the divided areas, and substitute the determined HU values (P1, P2, P3, P4) into Equation 4 below to determine the parameters (L1, L2, L3, L4) can be calculated.

3 is a density distribution curve for explaining a parameter in the diagnostic method through the density analysis of the computed tomography image image in accordance with an embodiment of the present invention.

Referring to FIG. 3, parameters L1, L2, L3, and L4 in the diagnostic method through the density analysis of the computed tomography image image according to an exemplary embodiment of the present invention indicate the length of each area section of the density distribution curve. .

The shape of the density distribution curve varies the parameters L1, L2, L3, L4, which are the length of each area section, which is related to skewness and kurtosis.

4 is a view for explaining the relationship between skewness, kurtosis and density distribution curve in the diagnostic method through the density analysis of the computed tomography image image according to an embodiment of the present invention.

Referring to FIG. 4, skewness, which is a morphological analysis parameter of density distribution of a computed tomography image image, is determined by Equation 2 above, and kurtosis is determined by the above equation. It can be calculated by Equation 3.

Distortion is a morphological characteristic that is skewed to the left or to the right of the central axis at 50% of the area. If it is biased to the left from the central axis, it can be classified as Higher Skewness. If it is biased to the right from the central axis, it can be classified as Lower Skewness. That is, if the skewness value is positive, the density distribution curve is interpreted as having a longer right tail (that is, L4 is longer), and if the skewness value is negative, the right tail is shorter.

Also, the higher the kurtosis, the sharper the density distribution curve is, indicating a greater number of rare outlier values. Kurtosis is related to the parameters L2, L3.

FIG. 5 is a diagram illustrating a relationship between each parameter and a disease diagnosis in a diagnosis method through density analysis of a computed tomography image image according to an exemplary embodiment.

Referring to FIG. 5, quartile parameters may be used for morphological analysis of density distribution curves of computed tomography (CT) to assess ischemic injury.

Specifically, the value obtained by adding the parameters L2 and L3 may be defined as an interquartle range (IQR), and the value obtained by multiplying the value by the skewness and kurtosis may be calculated. The above multiplied value is the compactness reflecting the ratio of white matter to gray matter in the distribution of pixels in the computed tomography image.

Comparing the predictive performance of ischemic secondary brain injury and normal using IQR to assess ischemic damage, the area under the receiver operating curve (AUC) is greater than 0.800 for all subjects. In particular, Kurtosis * (L2 + L3) has an area under the curve of 0,869, which can be used as a very good parameter for ischemic injury evaluation.

Ischemic damage diagnosis method through the density analysis of the computed tomography image image according to an embodiment of the present invention, if the combination of parameters (ie Kurtosis * (L2 + L3)) value is more than the set reference value, ischemic damage is to be evaluated as serious Can be.

By the above method, real-time quantified ischemic injury diagnosis can be performed, and accuracy can be improved.

In the above-described method for diagnosing damage to a tissue by analyzing density of a computed tomography image image according to an exemplary embodiment of the present invention, an application basically installed in a terminal (or an electronic device) (this is a platform basically installed in a terminal or It may be executed by an application (program) directly installed on the terminal through an application providing server, such as an application store server, an application or a web server associated with the service. It may be.

In this sense, the damage diagnosis method of the tissue through the computed tomography image density analysis according to an embodiment of the present invention described above is implemented as an application (program) basically installed in the terminal or directly installed by the user, It may be recorded on a computer-readable recording medium. Such a program is recorded on a recording medium readable by a computer and executed by a computer so that the above functions can be executed. As described above, a program for executing a method for diagnosing damage to tissues through computed tomography image image density analysis according to an embodiment of the present invention may be read by a processor (CPU) of a computer, such as C, C ++, JAVA, and machine language. Code may be coded in the computer language of.

Functional programs for implementing the present invention, and related code and code segments, are easily made by programmers in the technical field to which the present invention pertains, in consideration of the system environment of a computer that reads a recording medium and executes the program. Can be deduced or changed. Recordable media that can be read by a computer recording the above program include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical media storage device, and the like.

In the above description, all elements constituting the embodiments of the present invention are described as being combined or operating in combination, but the present invention is not necessarily limited to the embodiments. In other words, within the scope of the present invention, all of the components can be selectively combined to operate at least one. In addition, although all of the components may be implemented in one independent hardware, each or all of the components may be selectively combined to perform some or all functions combined in one or a plurality of hardware. It may be implemented as a computer program having a. Codes and code segments constituting the computer program may be easily inferred by those skilled in the art. Such a computer program may be stored in a computer readable storage medium and read and executed by a computer, thereby implementing embodiments of the present invention. The storage medium of the computer program may include a magnetic recording medium, an optical recording medium, and the like.

In addition, according to another embodiment of the present invention, it is possible to expand not only to diagnose ischemic damage of brain tissue, but also to diagnose tissue damage.

Specifically, according to another embodiment of the present invention, the step of converting the pixel value of the computed tomography image of the cross-sectional image of the tissue to Hounsfield Unit (HU) value, the area corresponding to the tissue in the image Extracting a step, extracting a density distribution curve of a hounsfield unit value of a region corresponding to the extracted tissue, dividing the area of the density distribution curve of the hounsfield unit value into N sections by a set percentage, Computing the interval length of the Hounsfield unit values of the N intervals as a parameter, and diagnosing the damage of the tissue using the calculated parameters.

The step of converting the HU value and extracting the density distribution curve may be converted or extracted using the same or similar method as described above.

In another embodiment of the present invention, the area of the density distribution curve is divided into N sections by a set percentage, the N section lengths are calculated as parameters, and the damage of tissues is amplified using the calculated parameters, the lengths of the sections. can do. Here, the set percentage may be set evenly or differently for the N sections.

In addition, according to another embodiment of the present invention, it may be implemented as a diagnostic device for performing a diagnosis of damage to the tissue through the density analysis of the computed tomography image image. The diagnostic apparatus according to another embodiment of the present invention may include an input unit and a control unit.

The input unit may receive a computed tomography image of a cross section of the tissue. The input unit may be connected to a photographing module capable of capturing an image, or may receive an image photographed by an external device in cooperation with a communication unit.

The control unit converts the pixel value of the image into a Hounsfield Unit (HU) value, extracts a region corresponding to the tissue in the image, and density distribution curves of the Hounsfield unit value of the region corresponding to the extracted tissue. Can be extracted. In addition, the control unit divides the area of the density distribution curve of the Hounsfield unit value into N sections by the set percentage unit, calculates the section length of the Hounsfield unit values of the N sections as a parameter, and uses the calculated parameter. To diagnose tissue damage. The control unit calculates the HU value using CT images of brain tissues to diagnose ischemic injury, divides the density distribution curve into four area areas, and then multiplies kurtosis by IQR. Can be evaluated

The above description is merely illustrative of the technical idea of the present invention, and those skilled in the art to which the present invention pertains may make various modifications and changes without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention but to describe the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

L1, L2, L3, L4: Parameters L2 + L3: IQR
Skewness: Dwarf Kurtosis: Kurtosis

Claims (12)

In the ischemic damage monitoring method through the density analysis of the computed tomography image image performed in the apparatus for diagnosing the damage of the tissue through the density analysis of the computed tomography image image,
Converting pixel values of a computed tomography image of a brain cross-section into Hounsfield Unit (HU) values;
Extracting an area corresponding to brain tissue from the image;
Extracting a density distribution curve of a hounsfield unit value of a region corresponding to the extracted brain tissue;
Dividing the area of the density distribution curve of the hounsfield unit value into quadrants to calculate the interval length of the quartered hounsfield unit value as a parameter; And
Monitoring the ischemic injury using the calculated parameters;
Extracting the density distribution curve of the hounsfield unit value,
Counting the number of pixels having the hounsfield unit value of which the sum of 0 or more and 79 is 100, and dividing the hounsfield unit value of each pixel by the counted total number of pixels, the density of the hounsfield unit value A method for monitoring ischemic injury through density analysis of computed tomography image images for extracting distribution curves.
The method of claim 1,
Extracting a region corresponding to the brain tissue,
Each pixel of the computed tomography image is divided into an effective pixel and an invalid pixel, and a reference point is set so that the hounsfield unit values are in a set range from the reference point in an upward direction, a downward direction, a left direction, and a right direction. A method for monitoring ischemic injury through density analysis of a computed tomography image image by selecting an effective pixel and extracting a region corresponding to the brain tissue.
delete The method of claim 1,
Extracting the density distribution curve,
Ischemicity through density analysis of computed tomography image images extracting density distribution curves of the hounsfield unit values by adding the number of pixels having the hounsfield unit values for each slice unit for each 3D tomography image. How to monitor for damage.
In the ischemic damage monitoring method through the density analysis of the computed tomography image image performed in the apparatus for diagnosing the damage of the tissue through the density analysis of the computed tomography image image,
Converting pixel values of a computed tomography image of a brain cross-section into Hounsfield Unit (HU) values;
Extracting an area corresponding to brain tissue from the image;
Extracting a density distribution curve of a hounsfield unit value of a region corresponding to the extracted brain tissue;
Dividing the area of the density distribution curve of the hounsfield unit value into quadrants to calculate the interval length of the quartered hounsfield unit value as a parameter; And
Monitoring the ischemic injury using the calculated parameters;
The step of calculating with the parameter,
Calculating the total area of the density distribution curve in a direction in which the hounsfield unit value increases from the point where the hounsfield unit value is 0;
Dividing an area of 25%, 50%, 75%, 100% of the total area;
Determining hounsfield unit values (P1, P2, P3, P4) up to each of the divided regions; And
Calculating the parameters (L1, L2, L3, L4) by substituting the determined hounsfield unit values (P1, P2, P3, P4) into the following equations;

Is configured to include, ischemic damage monitoring method through the density analysis of the computed tomography image image.
The method of claim 5,
Monitoring the ischemic injury,
Monitoring the ischemic injury using morphological parameters,
A method for monitoring ischemic injury through density analysis of computed tomography images.
The method of claim 6,
The morphological parameter is computed tomography image, which is expressed as a result of multiplying skewness or kurtosis by the IQR when the sum of the parameter L2 and the parameter L3 is defined as an IQR (InterQuartile Range). Method for monitoring ischemic damage through density analysis of images.
The method of claim 7, wherein
The skewness and kurtosis are calculated by the following equations,

,

Where λ _P is the Hounsfield unit value, m is the mean, and σ is the standard deviation.
A method for monitoring ischemic injury through density analysis of computed tomography images.
A computer-readable recording medium having recorded thereon a program for executing an ischemic damage monitoring method by analyzing the density of a computed tomography image image according to any one of claims 1, 2, and 4 to 8.
In the method of monitoring the damage of the tissue through the density analysis of the computed tomography image image performed in the apparatus for diagnosing the damage of the tissue through the density analysis of the computed tomography image image,
Converting a pixel value of a computed tomography image of a cross section of the tissue into a Hounsfield Unit (HU) value;
Extracting an area corresponding to tissue from the image;
Extracting a density distribution curve of a hounsfield unit value of a region corresponding to the extracted tissue;
Dividing the area of the density distribution curve of the hounsfield unit value into N sections by a set percentage unit, and calculating a section length of the Hounsfield unit values of the N sections as a parameter; And
Monitoring for damage to the tissue using the calculated parameters;
Damage monitoring method of the tissue through the density analysis of the computed tomography image image comprising a.
The method of claim 10,
The set percentage may be equally or differently set for the N sections, and the damage monitoring method of the tissue through density analysis of the computed tomography image image.
An input unit for receiving a computed tomography image of a cross section of the tissue; And
A control unit for quantifying the image to diagnose tissue damage;
Including,
The control unit converts a pixel value of the image into a Hounsfield Unit (HU) value, extracts a region corresponding to a tissue from the image, and a hounsfield unit of a region corresponding to the extracted tissue. Extracting the density distribution curve of the value, dividing the area of the density distribution curve of the Hounsfield unit value into N sections by a set percentage, and calculating the section length of the Hounsfield unit values of the N sections as a parameter And an apparatus for diagnosing damage to a tissue through density analysis of a computed tomography image image, comprising diagnosing damage to the tissue using the calculated parameter.

Images