KR102425843B1 - Method and apparatus for evaluating internal organ using kurtosis map based on medical images - Google Patents

Abstract

The present invention relates to an apparatus and method for calculating a disease index based on a medical image, comprising: a region of interest setting unit for extracting a region of interest in which an organ of interest is captured from a medical image; a histogram analyzer generating a histogram of the ROI and calculating kurtosis and skewness of the ROI based on the histogram; a kurtosis map generator for generating a kurtosis map of the region of interest by color-coding the brightness value for each voxel in the region of interest into a kurtosis value for each voxel; and a disease index calculator that guides the kurtosis, the skewness, and the kurtosis map to the medical staff as the disease index of the organ of interest.

Description

Apparatus and method for providing disease diagnosis information using a medical image-based kurtosis map {Method and apparatus for evaluating internal organ using kurtosis map based on medical images}

The present invention relates to a medical image-based disease diagnosis information providing apparatus and method for evaluating and guiding a patient's disease level using a medical image, and for evaluating and guiding a patient's disease level in units of organs.

In the medical field, a doctor displays a medical image obtained by photographing a patient on a monitor, reads the medical image displayed on the monitor, and observes a state or change over time of a lesion. In image diagnosis using a medical image, a doctor diagnoses what an abnormal shadow or the like is from a medical image to be diagnosed.

In the reading written by the doctor during the imaging diagnosis, the results of judging what abnormal shadows, etc. are detected and the opinion of the reading that is the basis for the judgment are described.

At this time, it cannot be said that the opinion of the doctor or the presumed disease name recorded by the doctor is always correct. For example, when a doctor cannot spend a lot of time to read one medical image, or a doctor with low reading experience observes an abnormal shade that is difficult to find in a medical image or an abnormal shade that is difficult to capture a characteristic, There was a possibility of omitting the disease or misjudgment of the presumed disease name.

In order to solve problems that may occur in the reading of medical images, a system for automatically detecting a diseased region when analyzing a medical image by digitizing the medical image and supporting the reading of the medical image by a computer is being developed.

However, there is a limitation in that such a computer-aided system is focused on the detection of a diseased region, and cannot propose a technology for more simply quantitatively evaluating and guiding the disease degree of the entire organ of interest.

Accordingly, an object of the present invention is to provide an apparatus and method for providing medical image-based disease diagnosis information that processes and analyzes a medical image in a histogram manner to evaluate and guide the patient's disease level in units of organs.

As a means for solving the above problem, according to an embodiment of the present invention, there is provided a region of interest setting unit for extracting a region of interest in which an organ of interest is photographed from a medical image; a histogram analyzer generating a histogram of the ROI and calculating kurtosis and skewness of the ROI based on the histogram; a kurtosis map generator for generating a kurtosis map of the ROI by color-coding a brightness value for each voxel in the region of interest into a kurtosis value for each voxel; and a disease index calculator for guiding the kurtosis, the skewness, and the kurtosis map to the medical staff as the disease index of the organ of interest.

(i = 1, 2, 3, …, n)"의 식에 따라 상기 관심 영역내 복셀별 밝기 값을 복셀별 첨도값으로 환산하며, 상기 N는 복셀 개수, 상기 Y_i는 i번째 복셀 밝기 값, 상기 s는 표준편차인 것을 특징으로 한다. The kurtosis map generator

(i = 1, 2, 3, ..., n)", the luminance value for each voxel in the region of interest is converted into a kurtosis value for each voxel, where N is the number of voxels, and Y _i is the brightness value of the i-th voxel. , wherein s is the standard deviation.

The apparatus further comprises a disease index calculator for calculating a disease index by comparing and analyzing the kurtosis, the skewness, and the kurtosis map with a preset disease evaluation standard, and guides the medical staff to the disease index.

The disease index calculator further comprises a function of further calculating and guiding the treatment index by tracking and monitoring the kurtosis, the skewness, and the kurtosis map for the region of interest of the same patient medical image.

As a means for solving the above problem, the method comprising: extracting a region of interest in which an organ of interest is photographed from a medical image according to another embodiment of the present invention; generating a histogram of the region of interest and calculating kurtosis and skewness of the region of interest based on the histogram; generating a kurtosis map of the region of interest by converting the brightness value for each voxel in the region of interest into a kurtosis value for each voxel and color coding, and using the kurtosis, the skewness, and the kurtosis map as a disease indicator of the organ of interest providing a method for calculating a medical image-based disease index, comprising: guiding a medical staff as

The present invention additionally generates and guides a disease index guiding the patient's disease level in addition to the medical image, so that the medical staff can more quickly and accurately determine the patient's disease level.

In particular, the present invention processes and analyzes a region of interest in which an organ of interest is captured in a medical image in a histogram manner, so that the degree of disease of a patient can be evaluated and guided in units of organs.

1 is a diagram illustrating an apparatus and method for providing medical image-based disease diagnosis information according to an embodiment of the present invention.
2 is a diagram illustrating a method for evaluating a medical image-based disease index according to an embodiment of the present invention.
3 is a diagram for explaining a histogram according to an embodiment of the present invention.
4 is a diagram for explaining a kurtosis map according to an embodiment of the present invention.
5 is a diagram illustrating an example of a guidance screen for medical staff according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

However, in describing the present invention, if it is determined that a detailed description of a related well-known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. Even if the terms are the same, if the indicated parts are different, it is to be said in advance that the reference numerals do not match.

And the terms to be described later are terms set in consideration of the function in the present invention, which may vary according to the intention or custom of medical personnel such as the experimenter and the measurer, so the definition should be made based on the content throughout this specification.

In this specification, terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

The terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate the overall understanding, the same reference numerals are used for the same components in the drawings, and duplicate descriptions of the same components are omitted.

1 is a diagram illustrating an apparatus and method for providing medical image-based disease diagnosis information according to an embodiment of the present invention.

As shown in FIG. 1 , the apparatus 100 for calculating a disease index of the present invention interworks with a medical imaging apparatus 200 such as a CT imaging device, an MR imaging device, and an ultrasound imaging device to select any one of these devices. A medical image acquisition unit 110 that receives and stores a medical image obtained through the 120), after generating a histogram for the region of interest, the histogram analyzer 130 calculates the kurtosis and skewness of the histogram, dividing the brightness value for each voxel in the region of interest by the kurtosis of the histogram, and converting it into a color code A kurtosis map generator 140 that generates a kurtosis map of the region of interest, a disease index calculator 150 that guides medical staff using the kurtosis, skewness, and kurtosis maps as disease indicators of the organ of interest, and the kurtosis, skewness, and kurtosis maps and a disease index calculation unit 160 that calculates a disease index by comparing and analyzing with a preset disease evaluation standard and guides the medical staff to the disease index calculation unit 160 .

For reference, when most organs of the human body are in a disease state, the image homogeneity is deteriorated compared to a normal state. For example, in the case of the liver, as a succinct cut occurs, a deviation in brightness values between voxels corresponding to the liver region increases, and an average brightness value also increases or decreases abnormally.

Accordingly, in the present invention, by analyzing the image homogeneity of the organ of interest in the medical image through the histogram, the kurtosis and skewness of the histogram can be obtained and provided as disease indicators indicating the degree of disease.

In addition, the present invention provides a kurtosis map by additionally calculating and using a kurtosis value for each voxel, so that a medical staff can easily evaluate the degree of disease of an organ of interest based on more diverse information.

Hereinafter, a medical image-based disease index evaluation method according to an embodiment of the present invention will be described with reference to FIGS. 2 to 5 .

2 is a diagram illustrating a method for evaluating a medical image-based disease index according to an embodiment of the present invention.

First, when a medical image is selected and displayed on the screen, the region of interest setting unit 120 determines an organ of interest under the consent of the medical staff, and extracts and sets a region of interest (ROI) in which the organ of interest is photographed from the medical image (S1). ).

In this case, the region of interest may be automatically detected based on anatomical elements (position, shape, etc.) of the organ of interest, but if necessary, a medical staff may directly set the medical image while visually checking the medical image.

Then, the histogram analyzer 130 generates a histogram of the ROI (S2). In this case, the histogram is a frequency distribution table that shows the number corresponding to the class and frequency as a graph. In the present invention, the number of voxels corresponding to each brightness value can be identified through the histogram.

When the histogram is generated through step S2, the histogram analyzer 130 calculates kurtosis and skewness of the histogram (S3).

Skewness is a statistic indicating the degree of asymmetry of a distribution, and indicates the degree of normal distribution, and can be calculated according to Equation (1).

[Equation 1]

In this case, N is the number of voxels, Y _i is the brightness value of the i-th voxel, and s is the standard deviation.

The kurtosis is a number indicating the smoothness and sharpness of the part centered on the mode of the frequency curve. For example, the kurtosis of a normal distribution is 0, and if the kurtosis is greater than 0, it has a longer tail and a pointed shape than the normal distribution. On the other hand, when the kurtosis is less than 0, the tail has a shorter tail than the normal distribution, and the central part has a smoother shape.

[Equation 2]

[Equation 3]

(i = 1, 2, 3, …, n)

(i = 1, 2, 3, …, n)

The kurtosis value of the region of interest is calculated by Equation 2, and the kurtosis map generator 140 calculates a kurtosis value for each voxel by Equation 3 using the brightness value Y _i for each voxel. Then, each voxel-specific kurtosis value is converted into a color code according to a preset color code conversion reference table, and two-dimensionally arranged based on the voxel position, thereby generating a kurtosis map of the ROI (S4).

The disease index calculator 150 displays the kurtosis and skewness obtained in step S3 and the kurtosis map obtained in step S4 as disease indicators on the screen, so that the medical staff can more accurately determine the patient's disease level by referring to these information so that it can be grasped (S5).

In addition, the disease index calculation unit 160 is used to compare and analyze the patient's kurtosis and skewness with preset disease evaluation criteria, so that the disease index can be additionally calculated and then guided to the medical staff (S6).

The disease evaluation criteria of step S6 is basically the result of indexing the disease degree of patients from image data that can be assumed to be standard normal distribution (eg, diffusion-weighted MRI image), and then collecting and statistical results of medical image analysis by disease index As such, it may be composed of an average value of kurtosis and an average value of skewness by disease index.

Accordingly, the present invention compares and analyzes the patient's kurtosis and skewness with the information for each disease index to determine the disease index with the highest similarity, and to determine it as the patient's disease index.

In addition, in the present invention, when the medical image of the same patient is acquired several times over a long-term treatment period by tracking and monitoring the condition of the same patient, the disease index of the same patient is also followed and monitored, and then treatment is performed based on the degree of change in the disease index. It also makes it possible to obtain and provide additional indices.

For example, when there is no disease, the kurtosis map value, that is, the disease index converges to 0, and when a disease occurs, the disease index value becomes greater than 0. Also, the disease index value increases as the vaginal severity increases. If the disease index of the patient is changed from 3 to 2 in this state, the therapeutic index may be calculated as "+1" according to the expression "disease index before treatment - disease index after treatment=therapeutic index".

3 is a diagram for explaining a histogram according to an embodiment of the present invention.

As shown in FIG. 3 , it can be seen that the histogram of the present invention has the brightness value as the X-axis and the number of voxels as the Y-axis.

Accordingly, the range and deviation of the brightness values of each voxel included in the region of interest are identified through the histogram, and through this, the image homogeneity of the region of interest can be indirectly determined.

4 is a diagram for explaining a kurtosis map according to an embodiment of the present invention.

Referring to FIG. 4 , the kurtosis map of the present invention may be provided overlaid on the region of interest, and the color code for each voxel in the kurtosis map varies according to the severity (F1-F3) of liver fibrosis in patients with chronic liver disease. It can be seen that it varies considerably.

That is, through the color distribution of the kurtosis map, it is possible to immediately recognize and determine the degree of a patient's disease without a separate analysis operation.

5 is a diagram illustrating an example of a screen for guiding medical staff according to an embodiment of the present invention.

As shown in FIG. 5 , the present invention provides a brain medical image and additionally acquires and provides a histogram kurtosis and skewness, and a kurtosis map of a region of interest as disease indicators.

Accordingly, medical staff can diagnose the patient's disease state by referring not only to medical images, but also to objective disease indicators such as histogram kurtosis, skewness, and kurtosis map.

Of course, as described above, by additionally guiding the patient's disease index and treatment index, the medical staff can also refer to these information to diagnose the patient's disease state.

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

Claims (5)

a region of interest setting unit for extracting a region of interest in which an organ of interest is captured from a medical image;
a histogram analyzer generating a histogram of the ROI and calculating kurtosis and skewness of the ROI based on the histogram;
a kurtosis map generator for generating a kurtosis map of the ROI by color-coding a brightness value for each voxel in the region of interest into a kurtosis value for each voxel;
a disease indicator calculator for guiding a medical staff to use the kurtosis, skewness, and kurtosis map as disease indicators of an organ of interest; and
Comprising a disease index calculator that compares and analyzes the kurtosis, the skewness, and the kurtosis map with a preset disease evaluation standard to calculate a disease index and guide the medical staff,
The disease index calculation unit
After tracking and monitoring the disease index of the same patient over a long period of time, the apparatus for calculating a disease index based on medical images further comprises a function of additionally acquiring and providing a therapeutic index based on the degree of change in the disease index. According to claim 1, wherein the kurtosis map generator
"

(i = 1, 2, 3, ..., n)", the luminance value for each voxel in the region of interest is converted into a kurtosis value for each voxel, where N is the number of voxels, and Y _i is the brightness value of the i-th voxel. , wherein s is a standard deviation of a medical image-based disease index calculation device. delete delete In the medical image-based disease index calculation method of the medical image-based disease index calculation device,
extracting, by the medical image-based disease index calculation device, a region of interest in which an organ of interest is captured from a medical image;
generating, by the medical image-based disease index calculating device, a histogram of the region of interest, and calculating kurtosis and skewness of the region of interest based on the histogram;
generating a kurtosis map of the region of interest by color-coding the brightness value of each voxel in the region of interest by the medical image-based disease indicator calculating device and color-coding the brightness value of each voxel; and
and guiding, by the medical image-based disease indicator calculating device, the kurtosis, the skewness, and the kurtosis map to the medical staff as disease indicators of the organ of interest;
Informing the medical staff
The disease index is calculated by comparing and analyzing the kurtosis, the skewness, and the kurtosis map with a preset disease evaluation standard, and after monitoring the disease index of the same patient over a long period of time, treatment is performed based on the degree of change in the disease index After additionally acquiring the index, a method for calculating a disease index based on medical images, characterized in that it further comprises a function of further guiding the medical staff about the disease index and the treatment index.

Images