KR102194797B1 - Method, device and program for lung image registration for histogram analysis of lung movement and method and program for analysis of registered lung image - Google Patents

Abstract

A lung image matching method for analyzing a histogram of lung motion is provided. The lung image matching method for analyzing the histogram of the lung motion includes a lung image acquisition step in which a computer acquires two lung images by tomography, and the computer divides a lung region from one of the two lung images. A floating image generating step of generating a floating image, wherein the computer generates a reference image by dividing a lung region from a lung image other than the floating image among the two lung images, and the computer A first matching step of entirely matching the floating image and the reference image, and wherein the computer matches the floating image with the reference image by matching internal structures of blood vessels and bronchi of the floating image and the reference image Including a matching step, in the case of matching the inspiratory lung image and the exhaled lung image, the floating image is an inspiratory lung image and the reference image is an exhaled lung image, and when matching the inspiratory lung images at different times, the floating The image is an inspiratory lung image at a reference point in time, and the reference image is an inspiratory lung image at a next point in time of the floating image, and when the exhaled lung images at different points in time are matched, the floating image is an exhaled lung image at the reference point in time and the reference The image is an expiratory lung image at the next point in the floating image, and the second matching step matches the internal structure of the blood vessel and the bronchi based on the mark indicating the branch point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessel. It is characterized by letting.

Description

Lung image registration method for histogram analysis of lung motion, its device, its program, and its analysis method and program of matched lung images {METHOD, DEVICE AND PROGRAM FOR LUNG IMAGE REGISTRATION FOR HISTOGRAM ANALYSIS OF LUNG MOVEMENT AND METHOD AND PROGRAM FOR ANALYSIS OF REGISTERED LUNG IMAGE}

The present invention relates to a lung image matching method for analyzing a histogram of lung motion and a method of analyzing the matched lung image.

Interstitial lung disease (ILD) is a collective term for a series of lung diseases that affect the epilepsy of the lung. The tissues between the alveoli (lungs) and the alveoli are called epilepsy, and when damage to the lung tissue is caused by some reason, inflammation occurs in other tissues in the epilepsy such as alveoli or capillaries, bronchioles, and lymphatic vessels. As this inflammation repeats and progresses as it is,'fibrosis', that is, the tissue becomes hard. The lungs become stiff and small, and gas exchange is impaired. In severe cases, respiratory failure leads to death.

In particular, idiopathic interstitial fibrosis (IPF) is the most common form of interstitial pulmonary disease, a unique type of chronic progressive fibrotic interstitial pneumonia of unknown origin and mainly occurs in the elderly. The overall prognosis for idiopathic interstitial fibrosis has declined from 30% to 50% in 5-year survival over the past few years.

As a method of diagnosing interstitial lung disease, the fibrotic ambience can be identified through the difference in shadows on computer tomography (CT) of the chest. In general, fibrosis tends to occur from the outside of the lungs. As the blood vessels become smaller and narrower from the pulmonary blood vessels to the capillaries, it occurs more often in areas where it is difficult to reach the corners.

Since the diagnosis of interstitial lung disease is difficult to accurately diagnose because the degree of fibrosis is subjectively evaluated in chest CT, objective quantification is important.

Korean Registered Patent Publication No. 10-1144579, 2012.05.09.

Quantifying the degree of respiratory pulmonary dilatation for objective quantification in the diagnosis of interstitial pulmonary disease as described above may be based on image matching between inspiratory and expiratory CT scans. However, there is a problem in that it is difficult to quantify the degree of respiratory pulmonary dilatation due to difficulty in accurate image matching between inspiratory and expiratory CT scans.

Accordingly, an object to be solved by the present invention is to provide an accurate method for matching images of exhalation and inhalation in order to quantify the degree of inspiratory lung expansion.

In addition, the problem to be solved by the present invention is to provide a method for analyzing a histogram of lung motion using a matched lung image.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

In the lung image matching method for analyzing a histogram of lung motion according to an embodiment of the present invention for solving the above-described problem, a lung image acquisition step in which a computer acquires two lung images by tomography, the computer A floating image generation step of generating a floating image by dividing a lung area from one of the two lung images, wherein the computer divides the lung area from the floating image and the other lung image among the two lung images. A reference image generation step of generating a reference image, a first matching step in which the computer matches the floating image and the reference image as a whole, and the computer matches the internal structure of blood vessels and bronchi of the floating image and the reference image And a second matching step of matching the floating image with the reference image, and when matching the inspiratory lung image and the exhaled lung image, the floating image is an exhalation lung image and the reference image is an inspiratory lung image, In the case of matching the inspiratory lung images of different viewpoints, the floating image is the inspiratory lung image of the reference viewpoint, the reference image is the inspiratory lung image of the next viewpoint of the floating image, and when the exhalation lung images of different viewpoints are matched , The floating image is an expiratory lung image at a reference point of view, and the reference image is an expiratory lung image at a point next to the floating image, and the second matching step displays a mark indicating a branch point of a bronchi and a branch point of a peripheral pulmonary vessel. It is characterized by matching the internal structure of blood vessels and bronchi based on one marker.

In the lung image matching method for analyzing a histogram of lung motion according to an embodiment of the present invention for solving the above-described problem, after the second registration step, the computer performs the lung image matched by the second registration step. And a third matching step of locally matching using lung damping-based strain matching.

The first matching step is characterized in that the computer matches the floating image with the reference image using affine registration.

The second matching step is characterized in that the computer matches the internal structures of the blood vessels and the bronchi of the floating image and the reference image using thin plate spline warping.

The third matching step is characterized in that the computer matches using a daemon algorithm.

The inspiratory lung image and the expiratory lung image are an inspiratory lung image and an exhaled lung image at the same time point.

The method for analyzing the matched lung image according to another embodiment of the present invention for solving the above-described problem includes the expiratory lung image and the inhalation lung image based on the matched lung image with respect to the expiratory lung image and the inhalation lung image by a computer. Measuring the degree of lung expansion (DLE) for each pixel between images in the x-axis, y-axis, z-axis, and 3D, the computer dividing the lungs according to a predetermined criterion, and the Comprising the step of forming a histogram for at least one of the entire lung, the upper lung, the lower lung, and each lung lobe by using a histogram parameter, and the matched lung image is an inspiratory lung image by a computer tomography. And obtaining an expiratory lung image, obtaining a lung image, generating a floating image by dividing a lung region from the inspiratory lung image by the computer, and generating a floating image, wherein the computer partitioning the lung region from the exhaled lung image A reference image generation step of generating a reference image, a first matching step in which the computer matches the floating image and the reference image as a whole, and the computer matches the internal structure of blood vessels and bronchi of the floating image and the reference image And a second matching step of matching the floating image with the reference image, wherein the second matching step includes a blood vessel and a blood vessel based on a mark indicating a branch point of a bronchi and a mark indicating a branch point of a peripheral pulmonary blood vessel. It is characterized by matching the internal structure of the bronchi.

The predetermined criterion is to divide each lung lobe or divide the right lung or the left lung into upper lung and lower lung, respectively, at a branch point of the lower lung bronchi among the bronchi of the right lung or the bronchi of the left lung.

The histogram parameter may include a degree of lung expansion of at least one of mean, standard deviation, skewness, kurtosis, and percentile in each lung image of at least one of the whole lung, the upper lung, and the lower lung; DLE) is characterized by using a probability distribution.

The second matching step is characterized in that the computer matches the internal structures of the blood vessels and the bronchi of the floating image and the reference image using thin plate spline warping.

The matched lung image is matched, further comprising a third matching step, in which the computer locally matches the lung image matched by the second matching step using lung attenuation-based deformation matching.

A lung image matching apparatus for analyzing a histogram of lung motion according to another embodiment of the present invention for solving the above-described problem includes a lung image acquisition unit for acquiring an inhalation lung image and an exhalation lung image by tomography, and the inhalation lung. A floating image generation unit that generates a floating image by dividing a lung region from an image, a reference image generation unit that generates a reference image by dividing a lung area from the expiratory lung image, and totally matches the floating image and the reference image , A first matching unit, a second matching unit for matching the floating image with the reference image by matching the internal structures of the blood vessels and the bronchi of the floating image and the reference image, and the second matching unit, a branch point of the bronchi It is characterized in that the internal structure of the blood vessel and the bronchi is matched based on the mark indicating the mark and the mark indicating the branch point of the peripheral pulmonary blood vessel.

A lung image matching apparatus for analyzing a histogram of lung motion according to another embodiment of the present invention for solving the above-described problem, locally uses the lung image matched by the second matching unit by using lung attenuation-based deformation matching. It further includes a third matching portion to match.

The second matching unit is characterized in that the internal structures of the blood vessels and the bronchi of the floating image and the reference image are matched using thin plate spline warping.

A lung image matching program for analyzing a histogram of lung motion according to another embodiment of the present invention for solving the above-described problem is combined with a computer that is hardware, and stored in a medium to execute any one of the above methods. do.

A method of analyzing a matched lung image according to another embodiment of the present invention for solving the above-described problem is combined with a computer, which is hardware, and stored in a medium in order to execute any one of the above methods.

Other specific details of the present invention are included in the detailed description and drawings.

According to the present invention, by matching the internal structure based on the mark indicating the branch point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessels in the reference image and the floating image, the degree of pulmonary dilation is quantified and more accurately lung image Can match.

In addition, according to the present invention, it is possible to check whether the lung image is correctly matched by calculating an error in image matching.

In addition, according to the present invention, a histogram of lung motion may be analyzed using a method of analyzing each lung motion of a matched lung image of a normal person and a matched lung image of a patient.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a view for explaining a lung image matching method for analyzing a histogram of lung motion according to an embodiment of the present invention.
2 and 3 are blood vessels and bronchi of the floating image and the reference image using thin plate spline warping (TPS warping) between the floating image and the reference image in the lung image matching method according to an embodiment of the present invention. It is a diagram for explaining a method of matching and matching the internal structure of the.
4 is a diagram for explaining a step of locally matching in the lung image matching method.
5 is a diagram for explaining a method of determining the accuracy of image registration in the lung image matching method.
6 is a diagram illustrating a method of analyzing a matched lung image.
7 is a view for explaining comparing lung images of patients with interstitial lung disease and normal people in a method of analyzing lung movement.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, only the present embodiments are intended to complete the disclosure of the present invention, It is provided to fully inform the technician of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used in the specification, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements. Throughout the specification, the same reference numerals refer to the same elements, and “and/or” includes each and all combinations of one or more of the mentioned elements. Although "first", "second", and the like are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc., as shown in the figure It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to orientation.

In the present specification, a'computer' includes all various devices capable of performing arithmetic processing and providing results to a user. For example, computers are not only desktop PCs and notebooks, but also smart phones, tablet PCs, cellular phones, PCS phones, and synchronous/asynchronous systems. A mobile terminal of the International Mobile Telecommunication-2000 (IMT-2000), a Palm Personal Computer (PC), a personal digital assistant (PDA), and the like may also be applicable. In addition, the computer may correspond to a medical computer, a medical PC, a medical tablet, or a medical device, and may correspond to a server that receives a request from a client and performs information processing.

In the present specification, the term "computed tomography" includes all images acquired by a medical image processing method using tomography generated by computer processing. For example, computed tomography images include CT (Computer tomography), Nuclear Magnetic Resonance Computed Tomography (NMR-CT), positron emission tomography (PET), and CBCT (conebeam CT). May be applicable.

In the present specification, a'reference image' is an image that becomes a reference for image matching, and a'floating image' is an image to be matched with respect to the reference image.

In this specification,'affine matching' refers to matching using affine transformation, and affine transformation is a function in the affine space that preserves points, straight lines, and planes. After affine transformation, a set of parallel lines is parallel. And the affine transform maintains the ratio of the distance between points on a straight line, but does not necessarily maintain the distance between points or the angle between points.

In this specification,'thin plate spline warping' is a warping of a thin plate spline, and'thin plate spline' is a two-dimensional analogue of a three-dimensional spline, which is a physical analogy related to bending a thin metal sheet, 'Warping' is a geometric process that moves the position of a pixel. In general, geometric processing such as enlargement or reduction of an image obtains a uniform return result by applying a certain rule to all pixels. In other words, it has the same effect as bending an image drawn on a rubber plate arbitrarily, and is an image processing technique in which two images are arbitrarily bent and matched when matching.

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

1 is a view for explaining a lung image matching method for analyzing a histogram of lung motion according to an embodiment of the present invention.

Referring to FIG. 1, in the lung image matching method according to an embodiment of the present invention, a lung image acquisition step in which a computer acquires two lung images by tomography (S100), and a computer performs one of the two lung images. A floating image generation step of generating a floating image by dividing the lung area from the image (S120), a reference image generation step in which a computer generates a reference image by dividing the lung area from the floating image and the other lung image among two lung images (S140), a first matching step in which the computer matches the floating image and the reference image as a whole (S160), and a second matching step of matching the floating image to the reference image by matching the internal structures of blood vessels and bronchi of the floating image and the reference image It includes (S180).

Since the lung image acquisition step (S100) includes all lung images acquired by computed tomography, CT (Computer tomography), Nuclear Magnetic Resonance Computed Tomography (NMR-CT), positron tomography All lung images acquired using positron emission tomography (PET) and CBCT (conebeamCT) are included.

In the floating image generation step (S120), the floating image is an image obtained by dividing the lung region from one of the two lung images, and in the reference image generation step (S140), the reference image is one of the two lung images, which is different from the floating image. As an image obtained by dividing the lung region from the lung image of the lung, to divide the lung region from the lung image, for example, the lung can be divided by binarization of -400 to -200HU (Hounsfield unit), and is limited to the above example. And the Hounsfield value can divide the lungs according to a predetermined value.

In one embodiment, when the inspiratory lung image and the expiratory lung image are matched, the floating image is an exhalation lung image and the reference image is an inspiratory lung image. The inspiratory lung image and the expiratory lung image are the inspiratory lung image and the expiratory lung image at the same time point.

In another embodiment, in the case of matching the inspiratory lung images of different viewpoints, the floating image is the inspiratory lung image of the reference time point and the reference image is the inspiratory lung image of the next time point of the floating image.

In another embodiment, in the case of matching the expiratory lung images of different viewpoints, the floating image is the expiratory lung image of the reference time point and the reference image is the expiratory lung image of the next time point of the floating image.

In the first matching step S160 of entirely matching the floating image and the reference image, in an embodiment, the computer may match the floating image with the reference image using affine registration. That is, the floating image and the reference image can be matched as a whole by maintaining the distance ratio.

The second matching step (S180) of matching the floating image with the reference image by matching the internal structure of the blood vessel and the bronchi of the floating image and the reference image is, in an embodiment, a mark indicating a branch point of the bronchi and a branch point of the peripheral pulmonary vessel Based on the mark marked with, the internal structures of blood vessels and bronchi are matched and matched.

In addition, as another embodiment, the second registration step (S180) may be matched using thin plate spline warping in order to match the internal structure of the blood vessel and the bronchi of the floating image and the reference image. .

2 and 3 are blood vessels and bronchi of the floating image and the reference image using thin plate spline warping (TPS warping) between the floating image and the reference image in the lung image matching method according to an embodiment of the present invention. It is a diagram for explaining a method of matching and matching the internal structure of the.

Figure 2 (a) is a diagram showing the bifurcation points of the bronchi for image matching using thin plate spline warping, and there is a mark showing 22 to 30 bifurcation points, and Fig. 2 (b) shows the use of thin plate spline warping. For image registration, there is a mark showing the bifurcation points of the bronchi and the bifurcation points of the peripheral pulmonary vessels, and a predetermined number (eg, 38 to 46) of the bifurcation points is indicated.

In the result of image registration according to an embodiment of the present invention to be described later, a comparison between the result of performing image registration using only the branch point of the bronchi and the result of performing image registration using the branch point of the bronchi and the branch point of the peripheral pulmonary blood vessels. I can confirm.

FIG. 3 is a diagram showing a method of matching images using thin plate spline warping using the branch points shown in FIGS. 2A and 2B.

Referring to FIG. 3, it can be seen that the mark of the reference image and the mark of the floating image are matched, and the arrangement of the dots is distorted.

The thin plate spline warping is to more accurately match the internal structures of blood vessels and bronchi, and image registration is performed based on a mark indicating a bifurcation point. As shown in FIG. 2, a scene plate spline function is calculated from a mark indicating a branch point of the reference image and the floating image, and the floating image is transformed toward the reference image.

4 is a diagram for explaining a step of locally matching in the lung image matching method.

4, the lung image matching method according to an embodiment of the present invention includes a third matching step (S200) of locally matching the lung images matched by the second matching step using lung attenuation-based deformation matching. Include more.

In addition, the third matching step (S200) of locally matching the lung image using the lung attenuation-based deformation matching may be performed using a daemon algorithm.

The daemon algorithm is an algorithm that satisfies Equation 1 below, and the daemon algorithm sets a voxel of a predetermined size at the lung boundary of each of the reference image and the floating image, and obtains a gradient of the image from the voxel. In a method of matching an image using a daemon algorithm, a corresponding voxel of a reference image and a floating image is searched, and a daemon force is calculated according to slope information of the corresponding voxel.

<Equation 1>

I is the density and slope of the reference image, J is the density of the floating image, and α is the weight (an arbitrary value as a weight for the term I(x)-J(T(x))).

5 is a diagram for explaining a method of determining the accuracy of image registration in the lung image matching method.

5, the lung image matching method according to another embodiment of the present invention uses a lung attenuation-based modified matching for the lung image matched by the second matching step in the case of matching the inspiratory lung image and the expiratory lung image. Then, after the third matching step (S200) of locally matching, determining the accuracy of image matching (S220).

Determining the accuracy of image matching (S200) is at least one of the first matching step, the second matching step, and the third matching step, when the reference image and the floating image are matched in each step, the reference image and the floating image The image registration error is calculated using at least one of the average distance of the bronchoscopic markers of the image, the average distance of the peripheral pulmonary blood vessels of the reference image and the floating image, and the accuracy of the image registration is determined.

6 is a diagram for describing a method of analyzing lung motion using a matched lung image.

7 is a view for explaining comparing lung images of patients with interstitial lung disease and normal people in a method of analyzing lung movement.

Referring to FIG. 6, in the method of analyzing the matched lung image according to an embodiment of the present invention, the step of determining, by a computer, the matching accuracy of the matched lung image with respect to the expiratory lung image and the inhalation lung image (S300), Measuring the degree of lung expansion for each pixel between the exhaled lung image and the inspiratory lung image based on the lung image in the x-axis, y-axis, z-axis, and 3D (S320), dividing the lung according to a predetermined criterion Step S340 and forming a histogram for at least one of the entire lung, the upper lung, the lower lung, and each lung lobe by using the histogram parameter (S360).

In the method of analyzing the matched lung image, the matched lung image is a lung image acquisition step (S100) in which a computer acquires an inhalation lung image and an exhalation lung image, as described above in the description of FIG. A floating image generation step (S120) of generating a floating image by dividing the lung area from the expiratory lung image (S140), a reference image generation step of generating a reference image by dividing the lung area from the expiratory lung image (S140), the floating image and the reference image And a second matching step (S180) of matching the floating image with the reference image by matching the internal structures of the blood vessels and the bronchi of the floating image and the reference image as a whole (S160).

The second matching step (S180) of matching the floating image with the reference image by matching the internal structure of the blood vessel and the bronchi of the floating image and the reference image is, in an embodiment, a mark indicating a branch point of the bronchi and a branch point of the peripheral pulmonary vessel Based on the mark marked with, the internal structures of blood vessels and bronchi are matched and matched.

In addition, as another embodiment, the second registration step (S180) may be matched using thin plate spline warping in order to match the internal structure of the blood vessel and the bronchi of the floating image and the reference image. .

In the method of analyzing the matched lung image, the matched lung image further comprises a third matching step (S200) of locally matching the lung image matched by the second matching step using lung attenuation-based deformation matching. Can be.

The predetermined criterion is to divide each lung lobe or divide the right lung or the left lung into upper lung and lower lung, respectively, at a branch point of the lower lung bronchi among the bronchi of the right lung or the bronchi of the left lung.

In the step of forming a histogram using the histogram parameter for at least one of the entire lung, upper lung, lower lung, and each lung lobe (S360), the histogram parameter is at least one of the entire lung, upper lung, lower lung, and each lobe. The probability distribution of the degree of lung expansion (DLE) of at least one of the mean, standard deviation, skewness, kurtosis, and percentile of each lung image of is used.

The order of FIG. 6 is only an example, and the matched lung images may include all images matched by the image matching method described in the description of FIGS. 1 to 5.

For comparison of lung images of patients with interstitial lung disease and normal people, refer to FIG. 7.

Figure 7 (a) is a lung image of a patient with interstitial lung disease, Figure 7 (b) is a lung image of a normal person. Referring to FIGS. 7A and 7B, it can be seen that in the case of a patient with interstitial lung disease, fibrosis proceeds, unlike the lung image of a normal person, resulting in a narrower lung area.

In order to accurately and quantitatively analyze this, it is possible to accurately analyze the movements of the right lung and the left lung in all axes based on the x-axis, y-axis, z-axis, and 3D.

In the method of analyzing the matched lung image of the present invention, as an example, the average (Mean; M) as a parameter of the histogram may be calculated by Equation 2 below.

<Equation 2>

x is the individual value in the histogram, and P(x) is the probability of x.

In addition, in another embodiment, a standard deviation (SD) as a parameter of the histogram may be calculated by Equation 3 below.

<Equation 3>

In addition, as another embodiment, skewness (SK), which is a measure of asymmetry with respect to the average of the distribution of the degree of lung expansion, as a parameter of the histogram may be calculated by Equation 4 below.

<Equation 4>

If the tail of the histogram by skewness is spread to the right, it is positive, and if the tail of the histogram is spread to the left, it is negative.

In addition, as another embodiment, Kurtosis (K), which is a measure of the relative flatness of the histogram, may be calculated by Equation 5 below.

<Equation 5>

When the kurtosis is high, the peak of the distribution is sharp and the tail is long and thick, and when the kurtosis is low, the peak of the distribution is round and the tail is shorter and thinner.

In addition, as another embodiment, entropy (E) for measuring the variability of the distribution of the degree of lung expansion may be calculated by Equation 6 below.

<Equation 6>

Entropy (E) increases as the volatility of P(x) increases.

In addition, in another embodiment, uniformity (U), which is a measure of the homogeneity of the distribution of the degree of lung expansion, may be calculated by Equation 7 below.

<Equation 7>

Uniformity (U) is maximized when all P(x) are equal.

As a result of image registration according to an embodiment of the present invention, an analysis result of image registration will be described for each example.

In order to evaluate the effect of the image registration method for lung motion analysis, the landmark error rates of three different modified registration methods were calculated and compared by Equation 8 below.

<Equation 8>

N is the total number of markers, R is the number of markers in the reference image, and D is the number of modified markers in the floating image.

In method 1, after the first matching step (S160), only the third matching step (S200) using a daemon algorithm is performed, and in method 2, after the first matching step (S160), the second matching step (S180) is performed. , As shown in Figure 2 (a), a second matching step is performed using a thin plate spline warping using a mark indicating only the bifurcation of the bronchi, and a third matching step (S200) using a daemon algorithm is performed, In Method 3, after the first registration step (S160), the second registration step (S180) is performed, but as shown in FIG. 2(b), using a label indicating the branch point of the bronchi and the branch point of the peripheral lung blood vessel The second matching step is performed using plane warping, and the third matching step (S200) is performed using a daemon algorithm.

Table 1 below shows the results of calculating the labeling error rate by performing image matching using methods 1, 2 and 3 on the right lung among lung images of patients with interstitial lung disease. The mean, standard deviation, minimum and maximum values are calculated by calculating the difference in Euclidean distance between each marker of the floating image and the reference image.

(mm) Early Affine Matching Method 1 Method 2 Method 3 Average 11.2 5.9 3.5 3.3 1.5 Standard Deviation 5.5 5.2 3.6 2.9 1.0 Minimum value 1.3 1.1 1.1 1.2 0.3 Maximum value 18.7 19.7 15.8 12.8 4.3

Referring to Table 1, for image matching of the patient's right lung, Method 3, that is, after the first matching step (S160), and then performing the second matching step (S180), as shown in FIG. 2(b). The error rate is highest when the second registration step is performed using thin plate spline warping and the third registration step (S200) using a daemon algorithm is performed using a mark indicating the branch point of the bronchi and the branch point of the peripheral lung vessels. Less results can be confirmed. Table 2 below shows the results of calculating the labeling error rate by performing image matching using methods 1, 2, and 3 on the left lung among lung images of patients with interstitial lung disease.

(mm) Early Affine Matching Method 1 Method 2 Method 3 Average 13.6 6.8 6.5 4.7 1.8 Standard Deviation 8.0 6.9 7.6 3.2 0.8

Referring to Table 2, for image registration of the left lung of the patient, method 3, that is, after the first registration step (S160), a second registration step (S180) is performed, as in the image registration of the right lung. , A second matching step is performed using a thin plate spline warping using a mark indicating the branch point of the bronchi and the branch point of the peripheral pulmonary blood vessel as shown in (b) of FIG. 2, and a third matching step using a daemon algorithm (S200 ), you can see the result with the lowest error rate. Table 3 below shows the results of calculating the label error rate by performing image matching using methods 1, 2, and 3 for the right lung among normal lung images. to be.

(mm) Early Affine Matching Method 1 Method 2 Method 3 Average 17.1 12.6 10.1 5.7 2.8 Standard Deviation 7.3 5.3 3.5 2.5 1.3 Minimum value 8.1 5.2 5.9 2.3 1.1 Maximum value 28.3 24.0 17.0 10.5 5.0

Referring to Table 3, in the case of image registration of the normal right lung, as in the case of the patient, method 3, that is, after the first registration step (S160), a second registration step (S180) is performed, but FIG. As shown in (b) of (b), a second matching step is performed using thin plate spline warping using a mark indicating the branch point of the bronchi and the branch point of the peripheral pulmonary blood vessel, and the third matching step (S200) using a daemon algorithm is performed. In one case, the result with the lowest error rate can be confirmed. Table 4 below shows the results of calculating the labeling error rate by performing image matching using methods 1, 2, and 3 for the left lung among the lung images of a normal person.

(mm) Early Affine Matching Method 1 Method 2 Method 3 Average 21.0 9.8 11.0 5.1 2.4 Standard Deviation 9.0 5.8 6.4 2.4 1.2

Referring to Table 4, even in the case of image matching of the normal left lung, Method 3, that is, after the first matching step (S160), a second matching step (S180) is performed, but as shown in FIG. 2(b) In the same way, when the second matching step is performed using thin plate spline warping using the mark indicating the branch points of the bronchi and the branch points of the peripheral pulmonary vessels, and the third matching step (S200) using the daemon algorithm is performed, the error rate is reduced. In another embodiment of the present invention, a lung image matching apparatus for analyzing a histogram of lung motion according to another embodiment of the present invention includes a lung image acquisition unit that acquires an inhalation lung image and an exhalation lung image by computed tomography, and A floating image generation unit that generates a floating image by dividing a lung area from a lung image, a reference image generation unit that generates a reference image by dividing the lung area from the expiratory lung image, and a first matching unit that entirely matches the floating image and the reference image And a second matching unit for matching the floating image with the reference image by matching the internal structures of the blood vessels and the bronchi of the floating image and the reference image.

In an embodiment, the second matching unit matches the image by matching the internal structure of the blood vessel and the bronchi based on the mark indicating the branch point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessel.

In addition, in another embodiment, the second matching unit matches the image by matching the internal structures of the blood vessels and the bronchi of the floating image and the reference image using thin plate spline warping.

In addition, a lung image matching apparatus for analyzing a histogram of lung motion according to another embodiment of the present invention includes a third matching unit that locally matches the lung image matched by the second matching unit using a lung attenuation-based deformation matching. It may contain more.

The contents of the above-described lung image matching method may be applied equally to each configuration of the lung image matching apparatus.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules include Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You can understand. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

Claims (16)

A lung image acquisition step in which a computer acquires two lung images by tomography;
Generating, by the computer, a floating image by dividing a lung region from one of the two lung images;
A reference image generating step, wherein the computer generates a reference image by dividing a lung region from the floating image and another lung image among the two lung images;
A first matching step in which the computer entirely matches the floating image and the reference image;
A second matching step in which the computer matches the floating image with the reference image by matching internal structures of blood vessels and bronchi of the floating image and the reference image; And
A third matching step, wherein the computer locally matches the lung image matched by the second matching step using lung attenuation-based deformation matching,
In the case of matching the inspiratory lung image and the expiratory lung image,
The floating image is an expiratory lung image and the reference image is an inspiratory lung image,
In case of matching inspiratory lung images from different time points,
The floating image is an inspiratory lung image at a reference point in time, and the reference image is an inspiratory lung image at a point next to the floating image,
In the case of matching expiratory lung images from different time points,
The floating image is an expiratory lung image at a reference point of view, and the reference image is an expiratory lung image at a point next to the floating image
The second matching step,
Characterized in that based on the mark indicating the branch point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessels, the internal structure of the blood vessel and the bronchi are matched
Lung image registration method for histogram analysis of lung motion. delete The method of claim 1,
The first matching step,
Characterized in that the computer matches the floating image to the reference image using affine registration,
Lung image registration method for histogram analysis of lung motion. The method of claim 1,
The second matching step,
The computer is characterized in that using thin plate spline warping (thin plate spline warping) to match the internal structures of the blood vessels and the bronchi of the floating image and the reference image,
Lung image registration method for histogram analysis of lung motion. The method of claim 1,
The third matching step,
Lung image matching method for analyzing a histogram of lung motion, characterized in that the computer matches using a daemon algorithm. The method of claim 1,
The inspiratory lung image and the expiratory lung image,
Inspiratory lung images and expiratory lung images at the same time point,
Lung image registration method for histogram analysis of lung motion. The degree of lung expansion (DLE) for each pixel between the expiratory lung image and the inspiratory lung image is determined by the computer based on the lung image matched with the expiratory lung image and the inspiratory lung image. , measuring about the z-axis and 3D;
Dividing the lungs by the computer according to a predetermined criterion; And
Forming, by the computer, a histogram for at least one of the whole lung, the divided upper lung, the lower lung, and each lung lobe using a histogram parameter,
The matched lung image,
A lung image acquisition step in which a computer acquires an inspiratory lung image and an exhaled lung image by tomography;
A floating image generating step in which the computer generates a floating image by dividing a lung region from the inspiratory lung image;
A reference image generation step, wherein the computer generates a reference image by dividing a lung region from the exhaled lung image;
A first matching step in which the computer entirely matches the floating image and the reference image; And
The computer includes a second matching step of matching the floating image with the reference image by matching the internal structures of blood vessels and bronchi of the floating image and the reference image,
The second matching step,
Based on the mark indicating the bifurcation point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessels,
Analysis method of matched lung images. The method of claim 7,
The predetermined criteria are:
Dividing into each lung lobe, or dividing the right lung or the left lung into upper and lower lungs, respectively, at a branch point of the lower lung bronchus among the bronchi of the right lung or the bronchi of the left lung,
Analysis method of matched lung images. The method of claim 7,
The histogram parameter is,
Degree of lung expansion of at least one of mean, standard deviation, skewness, kurtosis, and percentile in each lung image of at least one of the whole lung, the divided upper lung, the lower lung, and each lung lobe; DLE), characterized in that using the probability distribution,
Analysis method of matched lung images. The method of claim 7,
The second matching step,
The computer is characterized in that using thin plate spline warping (thin plate spline warping) to match the internal structures of the blood vessels and the bronchi of the floating image and the reference image,
Analysis method of matched lung images. The method of claim 7,
The matched lung image,
The computer is matched further comprising a third matching step of locally matching the lung image matched by the second matching step by using lung attenuation-based deformation matching,
Analysis method of matched lung images. A lung image acquisition unit that acquires an inhalation lung image and an exhalation lung image by tomography;
A floating image generator configured to generate a floating image by dividing a lung region from the inspiratory lung image;
A reference image generator configured to generate a reference image by dividing a lung region from the exhaled lung image;
A first matching unit for entirely matching the floating image and the reference image;
A second matching unit for matching the floating image with the reference image by matching the internal structures of the blood vessels and bronchi of the floating image and the reference image; And
A third matching unit for locally matching the lung image matched by the second matching unit using a lung attenuation-based deformation matching,
The second matching portion,
Characterized in that based on the mark indicating the branch point of the bronchi and the mark indicating the branch point of the peripheral pulmonary blood vessels, the internal structure of the blood vessel and the bronchi are matched
Lung image matching device for histogram analysis of lung motion. delete The method of claim 12,
The second matching portion,
Characterized in that by using thin plate spline warping (thin plate spline warping) to match the internal structure of the blood vessel and the bronchi of the floating image and the reference image,
Lung image matching device for histogram analysis of lung motion. A lung image matching program for analyzing a histogram of lung motion, which is combined with a computer which is hardware and stored in a medium to execute the method of any one of claims 1, 3 to 6. A program for analyzing matched lung images, which is combined with a computer as hardware and stored in a medium to execute the method of any one of claims 7 to 11.

Images