WO2025225750A1 - Method and system for acquiring leg alignment image using partial x-ray image - Google Patents

Abstract

Disclosed is a method for acquiring a leg alignment image using a partial X-ray image comprising the steps of: acquiring a first source image, a second source image, and a third source image obtained by respectively photographing a hip joint, a knee joint, and an ankle joint on a grid forming a single coordinate plane; determining positions of a first reference point, a second reference point, and a third reference point for aligning the leg in the first source image, the second source image, and the third source image; and calculating an offset corresponding to the distance between an alignment line connecting the first reference point and the third reference point and the second reference point on the basis of coordinate values of the first reference point and the third reference point on the coordinate plane.

Description

Method and system for obtaining lower extremity alignment images using X-ray partial images

The present invention relates to a method and system for obtaining an alignment image of a lower extremity using a partial X-ray image, and more particularly, to a method and system for obtaining an alignment image of a lower extremity using a partial X-ray image, which can determine the degree of alignment of the entire lower extremity by utilizing a partial X-ray image of each joint of the lower extremity obtained in the process of performing a corrective osteotomy, including a high tibial osteotomy, for correcting a lower extremity deformity of the human body.

In general, genu varum and genu valgum, also known as bow legs, O-legs, and X-legs, are not only cosmetically unsightly, but also orthopedically desirable to correct because they can cause or worsen cartilage damage and degenerative arthritis by accumulating relatively excessive load on specific joints.

Various corrective osteotomy surgeries, including high tibial osteotomy, are performed to correct bowed legs. The most important thing in these surgeries is to accurately determine the alignment of the corrected legs during the surgery.

X-ray equipment that can be used outside the operating room before surgery can capture or synthesize images that can determine the alignment of the entire lower extremity, but there is currently no X-ray equipment that can obtain images to determine the alignment of the entire lower extremity during surgery.

C-arm X-ray equipment, which can be used during surgery, can only capture partial images of the body and cannot capture or synthesize images to determine the entire lower extremity. Currently, to determine the alignment of the entire lower extremity during surgery, C-arm X-ray equipment is mainly used to individually capture images of the hip joint, knee joint, and ankle joint, and then appropriately align the individual images.

A conventional method for obtaining an image of the alignment of the lower extremities, such as Korean Patent No. 10-1938361, uses individual images of each part of the lower extremities to determine the position where an imaginary line connecting the center point of the hip joint and the midpoint of the ankle joint passes through the knee joint, thereby obtaining an image capable of determining the alignment of the lower extremities.

However, since the conventional method of acquiring lower extremity alignment images uses partial images of each part for lower extremity alignment, it is impossible to create alignment images for the entire lower extremity with only C-arm X-ray images. In addition, the projection shape, which is a unique characteristic of X-rays, is a conical shape, and image distortion occurs due to reflection, refraction, diffraction, and interference phenomena of electromagnetic waves. In addition, deformation of the captured image occurs due to the characteristic of some curved surfaces at the edge of the X-ray detector of the X-ray imaging device. In order to solve this problem of image distortion, the image is viewed in real time during C-arm X-ray imaging, and the captured image is acquired by matching the reference point of each part and the center point of the X-ray generation part as much as possible. However, this process is difficult and time-consuming, making it difficult to create lower extremity alignment images.

The matters described as background technology above are only intended to enhance understanding of the background of the present invention, and should not be taken as an admission that they correspond to prior art already known to those skilled in the art.

Accordingly, the present invention aims to provide a method and system for obtaining a lower extremity alignment image using an X-ray partial image, which can help perform corrective osteotomy, including high tibial osteotomy, by accurately calculating an offset corresponding to the degree of deformation of the human body.

The problems to be solved by the present invention are not limited to those described above. Other problems and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, those skilled in the art will readily appreciate that the problems and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

As a means for solving the above technical problem, the present invention provides a method for obtaining a lower extremity alignment image using an X-ray partial image, the method including the steps of: obtaining a first source image, a second source image, and a third source image, each of which is photographed on a grid forming a single coordinate plane, of a hip joint, a knee joint, and an ankle joint; determining positions of a first reference point, a second reference point, and a third reference point for lower extremity alignment in the first source image, the second source image, and the third source image; and calculating an offset corresponding to a distance between a line connecting the first reference point and the third reference point and the second reference point based on coordinate values of the first reference point and the third reference point on the coordinate plane.

In an embodiment of the present invention, a step of modifying an image to correct deformation of a human body part and a grid that appear as image distortion in each of the first source image, the second source image, and the third source image may be further included.

In an embodiment of the present invention, the method may further include a step of determining a reference grid line for aligning the first source image, the second source image, and the third source image on the grid.

In an embodiment of the present invention, the method may further include a step of extracting a second alignment image centered on a modified reference point, which is obtained by moving the second reference point from the second source image by the offset along a line connecting the first reference point and the third reference point.

In an embodiment of the present invention, the method may further include: extracting a first alignment image centered on the first reference point from the first source image, extracting a third alignment image centered on the third reference point from the third source image; and aligning the first alignment image, the second alignment image, and the third alignment image in a row in sequence so that an alignment line, which is a line connecting the first reference point, the modified reference point, and the third reference point, is aligned.

In an embodiment of the present invention, the sizes of the first alignment image, the second alignment image, and the third alignment image may be the same.

In an embodiment of the present invention, the first reference point may be the center point of the hip joint appearing in the first source image, the second reference point may be the midpoint of the knee joint appearing in the second source image, and the third reference point may be the midpoint of the ankle joint appearing in the third source image.

In an embodiment of the present invention, a step of sequentially aligning the first source image, the second source image, and the third source image in a row so that the reference grid lines coincide with each other may be further included.

As another means for solving the above technical problem, the present invention provides a system for obtaining a lower extremity alignment image using an X-ray partial image, including an image processing unit that determines the positions of a first reference point, a second reference point, and a third reference point for lower extremity alignment in a first source image, a second source image, and a third source image, which respectively capture the hip joint, the knee joint, and the ankle joint of the lower extremity on a grid forming one coordinate plane, and calculates an offset corresponding to the distance between a line connecting the first reference point and the third reference point and the second reference point based on the coordinate values of the first reference point and the third reference point on the coordinate plane.

In an embodiment of the present invention, the image processing unit can modify the image to correct deformation of a human body part and a grid that appear as image distortion in each of the first source image, the second source image, and the third source image.

In an embodiment of the present invention, the image processing unit can determine a reference grid line for aligning the first to third source images on the grid.

In an embodiment of the present invention, the image processing unit can extract a second aligned image centered on a modified reference point in which the second reference point is moved by the offset amount along a line connecting the first reference point and the third reference point in the second source image.

In an embodiment of the present invention, the image processing unit may extract a first alignment image centered on the first reference point from the first source image, extract a third alignment image centered on the third reference point from the third source image, and sequentially align the first alignment image, the second alignment image, and the third alignment image so that alignment lines connecting the first reference point, the modified reference point, and the third reference point are aligned.

In an embodiment of the present invention, the sizes of the first alignment image, the second alignment image, and the third alignment image are the same, are equal to or smaller than the first source image, the second source image, and the third source image, and can have the same diameter value of the maximum possible length centered on the first reference point, the correction reference point, and the third reference point, respectively.

In an embodiment of the present invention, the first reference point may be the center point of the hip joint appearing in the first source image, the second reference point may be the midpoint of the knee joint appearing in the second source image, and the third reference point may be the midpoint of the ankle joint appearing in the third source image.

In an embodiment of the present invention, the image processing unit can extract the first reference point, the second reference point, and the third reference point from the first source image, the second source image, and the third source image, respectively, using a pre-learned artificial intelligence network.

In an embodiment of the present invention, the image processing unit can sequentially align the first source image, the second source image, and the third source image in a row so that the reference grid lines match.

According to the method and system for obtaining lower extremity alignment information using the above-described partial X-ray image, a partial image of the lower extremity is obtained by utilizing a grid representing one coordinate plane, and by appropriately processing the same, an offset corresponding to the degree of deformation of the lower extremity can be accurately calculated to obtain an alignment image of the bent lower extremity. Accordingly, according to the method and system for obtaining lower extremity alignment information using the above-described partial X-ray image, corrective osteotomy, including precise high tibial osteotomy, can be performed, thereby greatly improving the success rate thereof.

The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention belongs from the description below.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and together with the detailed description of the invention described below, serve to facilitate a better understanding of the technical idea of the present invention. Therefore, the present invention should not be interpreted as being limited to the matters described in the following drawings.

FIG. 1 is a block diagram illustrating a system for acquiring a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention.

FIG. 2 is a drawing illustrating in more detail the image processing unit of a system for obtaining a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention.

FIG. 3 is a flowchart of a method for obtaining a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention.

Figures 4 to 8 are drawings showing examples of grids and images applied in each step of Figure 3.

Hereinafter, a method and system for obtaining a lower limb alignment image using an X-ray partial image according to various embodiments of the present invention will be described in detail with reference to the attached drawings.

The specific structural or functional descriptions of the embodiments described below are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of this specification includes modifications, equivalents, or alternatives that fall within the technical scope.

Although terms such as "first" or "second" may be used to describe various components, these terms should be interpreted solely to distinguish one component from another. For example, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

When it is said that a component is "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but there may also be other components in between.

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises" or "has" should be understood to indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but not to exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art. Terms defined in commonly used dictionaries should be interpreted to have a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

First, a system for implementing a method for obtaining a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention will be described.

FIG. 1 is a block diagram illustrating a system for acquiring lower extremity alignment images using X-ray partial images according to an embodiment of the present invention, and FIG. 2 is a diagram illustrating an image processing unit of the system for acquiring lower extremity alignment images using X-ray partial images according to an embodiment of the present invention in more detail. A method for acquiring lower extremity alignment images using X-ray partial images according to an embodiment of the present invention can be implemented by a system such as that illustrated in FIG. 1 and FIG. 2.

Referring to FIG. 1, a system for obtaining an alignment image of a lower extremity using an X-ray partial image according to an embodiment of the present invention may include an X-ray photographing device (10) that X-rays individual parts of a lower extremity to generate a plurality of source images, and an image processing unit (20) that generates an alignment image of a lower extremity using the plurality of source images generated by the X-ray photographing device.

The X-ray photographing device (10) can be applied to various X-ray photographing devices used in the art, and in particular, it can be a C-arm X-ray photographing device that can take X-ray images of the lower extremities of a human body in a lying state, position the entire lower extremities on a grid forming a single coordinate plane, and obtain X-ray images of major joint parts of the lower extremities.

More specifically, the X-ray photographing device (10) can generate a first source image, a second source image, and a third source image, which respectively photograph the hip joint, knee joint, and ankle joint portions of the lower extremity on a grid forming one coordinate plane.

The first source image, the second source image, and the third source image generated by the X-ray photographing device (10) are provided to the image processing unit (20), and the image processing unit (20) can generate an alignment image of the lower extremity through image processing on the first source image, the second source image, and the third source image received.

The image processing unit (20) is a type of computing system that performs a processing algorithm on input source images to obtain a desired type of alignment image, and may be a computing system that includes a processor that performs a preset algorithm and a storage unit for storing information required in the image processing algorithm and image processing process.

Referring to FIG. 2, the image processing unit (20) may be configured to include a distortion correction unit (21), a reference point extraction unit (22), and an alignment image generation unit (23).

The distortion correction unit (21) is an element that receives the first source image, the second source image, and the third source image generated from the X-ray photographing device (10) and corrects the distortion generated in each source image.

Each input source image may include distortion, such as deformation of the shape of the photographed human body part and grid lines depending on the setting status of the X-ray photographing device (10). The distortion correction unit (21) may correct distortion of the human body part appearing in each of the first source image, the second source image, and the third source image and the grid used in the present invention, and may modify the image to correctly rearrange each source image that may be tilted. The distortion correction performed by the distortion correction unit (21) may be implemented through various image correction algorithms known in the field of image processing.

The reference point extraction unit (22) determines a reference grid line to be referenced in generating an alignment image of the lower limb, and can extract reference points necessary for lower limb alignment from each of the first source image, the second source image, and the third source image.

In addition, the reference point extraction unit (22) can extract reference points required for alignment from each of the first source image, the second source image, and the third source image, and determine their positions (coordinates) by referring to a grid representing a coordinate plane.

For example, the reference point extraction unit (22) can extract a first reference point corresponding to the center point of the hip joint from the first source image, a second reference point corresponding to the midpoint of the knee joint from the second source image, and a third reference point corresponding to the midpoint of the ankle joint from the third source image.

The technique of the reference point extraction unit (22) extracting the bone center point or midpoint of the lower extremity joint within the source images can be achieved through an image processing technology for X-ray images and an artificial intelligence network that has performed machine learning using a large amount of learning data in advance. That is, the X-ray image in which the transparent human body structure is overlapped has unclear boundaries and lines, and is composed of black and white series, making it difficult to distinguish the difference in color, so an image filtering technique can be applied, and then the coefficients closest to the point to be extracted can be analyzed and implemented. In addition, the reference point extraction unit (22) can be implemented by inputting a large amount of learning data prepared in advance into an artificial intelligence network designed to extract a specific point from an image, performing machine learning, performing verification thereon, and then applying the same.

In addition, the reference point extraction unit (22) can determine a reference grid line to be used as a reference for generating a lower limb alignment image. The reference grid line may be selected from among the grid lines that commonly appear in each source image among the grids forming the coordinate plane used when taking an X-ray of the lower limb, and preferably, the grid line may be determined as the grid line closest to the reference point of each source image.

In addition, the reference point extraction unit (22) can determine the coordinate values of the extracted reference points by referring to the grid forming a coordinate plane. The reference point extraction unit (22) can use the reference points to calculate an offset corresponding to the distance between the straight line connecting the first reference point and the third reference point and the second reference point. The specific technique for calculating the offset will be described in more detail in the description of an embodiment of a method for obtaining a lower limb alignment image using an X-ray partial image, which will be described later.

The aligned image generation unit (23) can generate an image in which the first to third source images are arranged in a row so that the determined reference grid lines match.

In addition, the alignment image generation unit (23) can generate a correction reference point, which is a point where a straight line passing through the second reference point is orthogonal to a straight line connecting the first reference point and the third reference point, based on the offset calculated in the reference point extraction unit (22), and can generate an alignment image that displays an alignment line passing through the first reference point, the third reference point, and the correction reference point.

The alignment image generation unit (23) can extract a first alignment image centered on a first reference point from a first source image, extract a second source image centered on a modified reference point from a second source image, and extract a third alignment image centered on a third reference point from a third source image.

Next, the alignment image generation unit (23) can align the extracted first to third alignment images in a row so that the alignment lines match, thereby obtaining the final alignment image of the lower extremity. At this time, the sizes of the first to third alignment images are in a range equal to or smaller than the first to third source images, and can have the same diameter value of the maximum possible length centered on the first reference point, the correction reference point, and the third reference point, respectively. Here, the same, smaller, or smaller range of the sizes of the images does not refer to a comparison of the sizes of the image files, but rather a comparison of the sizes of the displayed image areas.

A method for obtaining a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention implemented by a system as described above will be described in detail.

FIG. 3 is a flowchart of a method for obtaining a lower limb alignment image using an X-ray partial image according to an embodiment of the present invention, and FIGS. 4 to 8 are drawings showing examples of grids and images applied in each step of FIG. 3.

A method for obtaining a lower extremity alignment image using an X-ray partial image according to an embodiment of the present invention may start from a step (S11) of arranging the lower extremities of a human body on a grid and obtaining a first source image, a second source image, and a third source image each obtained by individually X-ray-photographing the hip joint, knee joint, and ankle joint, which are major joint parts of the lower extremities.

Fig. 4 illustrates an example of a grid in which the lower limbs of a human body are arranged, Fig. 5 illustrates an X-ray image of the entire lower limb taken together with the grid, and Fig. 6 illustrates an example of a source image.

A grid forming a coordinate plane as shown in Fig. 4 can be formed on a bed on which a human body is placed in a lying state for X-ray photography of the lower extremities. When a human body is placed in a lying state on this grid, the C-arm X-ray equipment can move to take X-ray images of each location corresponding to the major joints of the lower extremities.

As shown in Fig. 4, horizontal and vertical lines of the grid can be arranged at regular intervals to form a coordinate plane, and coordinate values can be assigned to each point on the grid.

Fig. 5 illustrates an example in which the entire lower limb is photographed on the grid illustrated in Fig. 4. Coordinate values can be assigned to each part of the photographed X-ray image, and accordingly, the distance between each point or the angle formed by a straight line can be derived.

Meanwhile, the area actually photographed by the C-arm X-ray equipment (10) is the area indicated by R1, R2, and R3 in FIG. 5. That is, the image photographing the area indicated by R1, R2, and R3 in FIG. 5 becomes the source image as shown in FIG. 6. An embodiment of the present invention appropriately processes these individual source images to create an aligned image as if the entire lower limb was photographed.

After the first source image (R1), the second source image (R2), and the third source image (R3) are acquired (S11) by the X-ray imaging equipment (10) and transmitted to the image processing unit (20), the distortion correction unit (21) can correct the distortion present in the first to third source images (R1-R3) (S12).

In step (S12), the distortion correction unit (21) can correct the deformation (distortion) of the human body parts and grids appearing in each of the first to third source images (R1-R3) and modify the image to appropriately rearrange the tilt.

Next, in step (S13), the reference point extraction unit (22) can extract reference points (A, B, C) required for alignment from each of the first source image (R1), the second source image (R1), and the third source image (R1) and determine the coordinates thereof by referring to a grid representing a coordinate plane (S13).

In step (S13), the reference point extraction unit (22) can extract a first reference point (A) corresponding to the center point of the hip joint from the first source image (R1), a second reference point (C) corresponding to the midpoint of the knee joint from the second source image (R2), and a third reference point (B) corresponding to the midpoint of the ankle joint from the third source image (R3).

As described above, the technique of extracting the bone center point of the lower extremity joint from the source images by the reference point extraction unit (22) can be achieved through an image processing technology for X-ray images and an artificial intelligence network that has performed machine learning using a large amount of learning data in advance.

Additionally, in step (S13), the reference point extraction unit (22) can determine the coordinate values of the extracted reference points (A, B, C) by referring to a grid forming a coordinate plane.

In addition, in step (S13), the reference point extraction unit (22) can determine a reference grid line (L*) to be referenced in generating a lower limb alignment image. The reference grid line determined in step (S13) can be selected from among grid lines that appear commonly in each source image among the grids forming the coordinate plane used when taking an X-ray of the lower limb, and preferably, can be determined as a grid line that is closest to the reference point of each source image.

Next, the reference point extraction unit (22) can calculate an offset (O) corresponding to the distance between the straight line connecting the first reference point (A) and the third reference point (B) and the second reference point (C) (S14). Here, the offset (O) corresponds to the distance between the midpoint of the knee joint of the lower limb that is aligned straightly, corresponding to the straight line connecting the center point of the hip joint and the midpoint of the ankle joint, and the midpoint of the knee joint of the lower limb that is actually X-rayed, and can be a numerical expression that can determine the degree of deformation of the entire lower limb.

In step (S14), the offset (O) can be derived in various ways.

For example, since the coordinates of the reference points (A, B, C) are known on the coordinate plane by the grid, the offset (O) can be calculated by calculating the distance between the equation of the straight line passing through the reference point (A) and the reference point (B) and the coordinate of the reference point (C) on the coordinate plane with the horizontal axis of the grid as the x-axis and the vertical axis of the grid as the y-axis. In addition, the coordinates of the modified reference point (C'), which is the point where the line drawn from the reference point (C) to the straight line passing through the reference point (A) and the reference point (B) intersect, can also be calculated.

In addition, since the length of each side of the triangle formed by the reference points (A, B, C) (the distance between the reference points) and the size of each interior angle of the triangle formed by the reference points (A, B, C) can be easily derived, the offset (O) can be calculated using various information such as the derived coordinates, straight lines, and shapes, and the coordinates of the point (C') where the straight line passing through the reference point (C) and the alignment line (L _a ) are orthogonal can also be easily obtained.

Next, in step (S15), the alignment image generation unit (23) can align the first to third source images (R1-R3) according to the direction of the determined reference grid line (L*) so that each source image (R1-R3) is arranged in a row in the lower direction. In step (S15), an example of the first to third source images (R1-R3) aligned in a row along the reference grid line (L*) is illustrated in FIG. 7. As shown in FIG. 7, in step (S15), each source image (R1-R3) can be aligned in that order so that the reference grid lines (L*) are aligned in a straight line with each other.

Next, in step (S16), the alignment image generation unit (23) can extract a first alignment image (S1) centered on the first reference point (A) from the first source image (R1), as illustrated in FIGS. 7 and 8, and can extract a third alignment image (S3) centered on the third reference point (B) from the third source image (R3). In addition, the alignment image generation unit (23) can extract a second alignment image (S2) centered on the modified reference point (C'), which is a point obtained by moving the second reference point (C) on the alignment line by the offset calculated in step (S15).

In step (S16), the alignment image generation unit (23) can obtain an alignment image of the lower body by aligning the extracted first to third alignment images in a row along an alignment line (L _a ). Here, the alignment line (L _a ) can be a straight line passing through the first reference point, the correction reference point, and the third reference point, and a straight line passing through the center of each alignment image.

In step (S16), the alignment image generation unit (23) can generate the first to third alignment images (S1-S3) so that their sizes are the same, are the same as or smaller than the source images (R1-R3), and have the same diameter value formed as long as possible centered on the first reference point (A), the correction reference point (C'), and the third reference point (B). By displaying an alignment line (L _a ), a reference point, and a correction reference point in the first to third alignment images (S1-S3), the distance between the alignment line (L _a ) and the second reference point (C) is visually displayed in the second alignment image (S2), so that the degree of correction required can be easily recognized.

As described above, the method and system for obtaining a lower extremity alignment image using an X-ray partial image according to various embodiments of the present invention can obtain an alignment image of a bent lower extremity by accurately calculating an offset corresponding to the degree of deformation of the lower extremity by obtaining a partial image of the lower extremity using a grid representing one coordinate plane and appropriately processing the same. Accordingly, the method and system for obtaining a lower extremity alignment image using an X-ray partial image according to various embodiments of the present invention can be of great help in performing corrective osteotomy, including high tibial osteotomy, for correcting lower extremity bending (deformation) of the human body.

Claims (17)

A step of acquiring a first source image, a second source image, and a third source image, each of which captures the hip joint, knee joint, and ankle joint portions on a grid forming one coordinate plane; A step of determining the positions of a first reference point, a second reference point, and a third reference point for alignment in the first source image, the second source image, and the third source image; and A step of calculating an offset corresponding to the distance between a line connecting the first reference point and the third reference point and the second reference point based on the coordinate values of the first reference point and the third reference point on the coordinate plane; A method for obtaining an alignment image of the lower extremities using an X-ray partial image including . In claim 1, A method for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that it further includes a step of modifying the image to correct deformation of a human body part and a grid that appear as image distortion in each of a first source image, a second source image, and a third source image. In claim 1, A method for obtaining a lower limb alignment image using an X-ray partial image, characterized in that it further includes a step of determining a reference grid line for aligning the first source image, the second source image, and the third source image on the grid. In claim 1, A method for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that it further includes a step of extracting a second alignment image centered on a modified reference point in which the second reference point is moved by the offset along a line connecting the first reference point and the third reference point in the second source image. In claim 4, A method for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that it further comprises a step of extracting a first alignment image centered on the first reference point from the first source image, and extracting a third alignment image centered on the third reference point from the third source image; and a step of sequentially aligning the first alignment image, the second alignment image, and the third alignment image in a row so that an alignment line, which is a line connecting the first reference point, the modified reference point, and the third reference point, is aligned. In claim 5, A method for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that the sizes of the first alignment image, the second alignment image, and the third alignment image are identical to each other. In claim 1, A method for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that the first reference point is the center point of the hip joint appearing in the first source image, the second reference point is the midpoint of the knee joint appearing in the second source image, and the third reference point is the midpoint of the ankle joint appearing in the third source image. In claim 2, A method for obtaining a lower limb alignment image using an X-ray partial image, characterized in that it further includes a step of sequentially aligning the first source image, the second source image, and the third source image so that the reference grid lines match each other. An image processing unit that determines the positions of a first reference point, a second reference point, and a third reference point for lower extremity alignment in a first source image, a second source image, and a third source image, which respectively capture the hip joint, knee joint, and ankle joint parts of a lower extremity on a grid forming a single coordinate plane, and calculates an offset corresponding to the distance between a line connecting the first reference point and the third reference point and the second reference point based on the coordinate values of the first reference point and the third reference point on the coordinate plane; A system for acquiring lower limb alignment images using X-ray partial images including . In claim 9, the image processing unit, A system for acquiring lower extremity alignment images using X-ray partial images, characterized in that the image is modified to correct deformation of human body parts and grids that appear as image distortion in each of the first source image, the second source image, and the third source image. In claim 9, the image processing unit, A system for acquiring an alignment image using an X-ray partial image, characterized in that it determines a reference grid line for aligning the first to third source images on the grid. In claim 9, the image processing unit, A system for obtaining a lower extremity alignment image using an X-ray partial image, characterized in that a second alignment image is extracted centered on a modified reference point in which the second reference point is moved by the offset amount along a line connecting the first reference point and the third reference point in the second source image. In claim 12, the image processing unit, A system for obtaining lower extremity alignment images using X-ray partial images, characterized in that a first alignment image centered on the first reference point is extracted from the first source image, a third alignment image centered on the third reference point is extracted from the third source image, and the first alignment image, the second alignment image, and the third alignment image are sequentially aligned so that alignment lines connecting the first reference point, the modified reference point, and the third reference point are aligned. In claim 13, A system for acquiring lower extremity alignment images using X-ray partial images, characterized in that the sizes of the first alignment image, the second alignment image, and the third alignment image are the same, are equal to or smaller than the first source image, the second source image, and the third source image, and have the same diameter value of the maximum possible length centered on the first reference point, the correction reference point, and the third reference point, respectively. In claim 9, A system for acquiring a lower extremity alignment image using an X-ray partial image, characterized in that the first reference point is the center point of the hip joint appearing in the first source image, the second reference point is the midpoint of the knee joint appearing in the second source image, and the third reference point is the midpoint of the ankle joint appearing in the third source image. In claim 9, the image processing unit, A system for obtaining a lower limb alignment image using an X-ray partial image, characterized in that the first reference point, the second reference point, and the third reference point are extracted from the first source image, the second source image, and the third source image, respectively, using a pre-learned artificial intelligence network. In claim 11, the image processing unit, A system for acquiring lower limb alignment images using X-ray partial images, characterized in that the first source image, the second source image, and the third source image are sequentially aligned so that the reference grid line matches.