Method and device for setting the spinal canal area of CT data and non-transitory computer readable recording medium

Abstract

A method for setting a spinal canal region in CT (Computed Tomography) data according to the present invention may include: a step of generating a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from CT (Computed Tomography) data in which the upper body of a subject is photographed, performed by one or more processors; a step of generating a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; a step of generating a reference line based on the first spinal canal line on the sagittal MIP image; a step of generating a coronal curved MIP image of the subject from the CT data along the reference line; a step of generating a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image; and a step of setting a spinal canal region in each of a plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for setting a spinal canal region in CT (Computed Tomography) data and a non-transient computer-readable recording medium. More specifically, the invention relates to a method and apparatus for setting a spinal canal region in CT data by detecting and setting a region corresponding to the spinal canal in upper body CT data of a subject, and a non-transient computer-readable recording medium storing a program for performing the method. Background Technology

[0002] CT (Computed Tomography) is an imaging diagnostic method that obtains cross-sectional images or three-dimensional images by transmitting X-rays through a subject's body and reconstructing the differences in absorption using a computer. When using CT, disease diagnosis can be achieved by distinguishing differences in tissue density.

[0003] Meanwhile, with the advancement of Artificial Intelligence (AI) technology, AI is also being utilized in the diagnosis of diseases using CT data. In this regard, the demand for various CT data for training AI models is increasing.

[0004] For the efficient training of AI models, CT data needs to be processed efficiently. For example, to train an AI model for diagnosing spinal diseases such as herniated discs, CT data with defined regions corresponding to the spinal canal is required as training data. Prior art literature

[0005] Korean Registered Patent No. 2588305 "AI-based apparatus and method for geometric alignment and preprocessing of raw CT images", registered on Oct. 6, 2023 The problem to be solved

[0006] The present invention aims to solve the aforementioned problems, and the objective of the present invention is to provide a method and apparatus for setting a spinal canal region in CT data and efficiently detecting and setting a region corresponding to the spinal canal in CT data regarding the upper body of a subject, as well as a non-transient computer-readable recording medium.

[0007] The problems of the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by a person skilled in the art to which the present invention pertains from the description below. means of solving the problem

[0008] According to one aspect of the present invention, a method for setting a spinal canal region in CT data is provided, comprising: a step of generating a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from Computed Tomography (CT) data in which the upper body of a subject is captured, performed by one or more processors; a step of generating a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; a step of generating a reference line based on the first spinal canal line on the sagittal MIP image; a step of generating a coronal curved MIP image of the subject from the CT data along the reference line; a step of generating a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image; and a step of setting a spinal canal region in each of a plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line.

[0009] In a method for setting a spinal canal region of CT data according to one aspect of the present invention, the step of generating the sagittal plane MIP image may include: a step of extracting a central region of each of the plurality of cross-sectional view images; and a step of generating the sagittal plane MIP image through maximum intensity projection on the central region of the plurality of cross-sectional view images.

[0010] In a method for setting a spinal canal region of CT data according to one aspect of the present invention, the central region of each cross-sectional view image may be composed of a predetermined section of the horizontal center of each cross-sectional view image.

[0011] In a method for setting a spinal canal region of CT data according to one aspect of the present invention, in the step of generating the reference line, the reference line may be set by connecting points spaced apart from the first spinal canal line by a distance set posteriorly on the sagittal plane MIP image.

[0012] In a method for setting a spinal canal region of CT data according to one aspect of the present invention, the step of setting a spinal canal region in each of the plurality of cross-sectional view images may include: determining a point set by the first spinal canal line and the second spinal canal line in each of the cross-sectional view images as a spinal canal point; and setting a predetermined surrounding area centered on the spinal canal point as a spinal canal region.

[0013] According to another aspect of the present invention, the apparatus comprises: a memory storing one or more instructions; and one or more processors operably connected to the memory; wherein the one or more processors execute the one or more instructions to generate a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from Computed Tomography (CT) data in which the subject's upper body is photographed; generate a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; generate a reference line based on the first spinal canal line on the sagittal MIP image; generate a coronal curved MIP image of the subject from the CT data along the reference line; and generate a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image. And a CT data spinal canal region setting device is provided for setting a spinal canal region in each of the plurality of cross-sectional view images (axial view images) included in the CT data based on the first spinal canal line and the second spinal canal line.

[0014] In a spinal canal region setting device for CT data according to one aspect of the present invention, the sagittal plane MIP image can be generated through maximum intensity projection on a central region formed by a predetermined section of the horizontal center of each of the plurality of cross-sectional view images.

[0015] In a device for setting a spinal canal region of CT data according to one aspect of the present invention, the reference line may be set by connecting points spaced apart from the first spinal canal line by a distance set posteriorly on the sagittal plane MIP image.

[0016] In a device for setting spinal canal regions of CT data according to one aspect of the present invention, each spinal canal region may be set as a predetermined region centered on a point set by the first spinal canal line and the second spinal canal line in each of the cross-sectional view images.

[0017] According to another aspect of the present invention, a non-transitory computer-readable recording medium storing at least one instruction that can be executed by one or more processors, wherein the at least one instruction is executed by the one or more processors to generate a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from Computed Tomography (CT) data in which the upper body of a subject is photographed; generate a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; generate a reference line based on the first spinal canal line on the sagittal MIP image; generate a coronal curved MIP image of the subject from the CT data along the reference line; and generate a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image. And a non-transient computer-readable recording medium is provided for setting spinal canal regions in each of the plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line. Effects of the invention

[0018] According to the above configuration, the method and apparatus for setting a spinal canal region of CT data and the non-transient computer-readable recording medium according to the present invention can efficiently detect and set a region corresponding to the spinal canal in CT data regarding the upper body of a subject.

[0019] The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention. Brief explanation of the drawing

[0020] FIG. 1 is a flowchart of a method for setting a spinal canal region of CT data according to one embodiment of the present invention. FIG. 2 is a detailed flowchart of the step of generating a sagittal plane MIP image of a method for setting a spinal canal region of CT data according to one embodiment of the present invention. FIG. 3 is a diagram showing an example of a sagittal plane MIP image generated in the step of generating a sagittal plane MIP image of a method for setting a spinal canal region of CT data according to an embodiment of the present invention. FIG. 4 is a diagram showing an example of a first spinal canal line generated in the step of generating a first spinal canal line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention. FIG. 5 is a diagram showing an example of a reference line generated in the step of generating a reference line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention. FIG. 6 is a diagram showing an example of a coronal plane curve MIP image generated in the step of generating a coronal plane curve MIP image of a method for setting a spinal canal region of CT data according to one embodiment of the present invention. FIG. 7 is a diagram showing an example of a second spinal canal line generated in the step of generating a second spinal canal line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention. FIG. 8 is a detailed flowchart of the step of setting the spinal canal region of a method for setting the spinal canal region of CT data according to one embodiment of the present invention. FIG. 9 is a diagram showing an example of a spinal canal region set in the step of setting a spinal canal region of a method for setting a spinal canal region of CT data according to one embodiment of the present invention. FIG. 10 is a diagram showing the configuration of a spinal canal region setting device for CT data according to one embodiment of the present invention. Specific details for implementing the invention

[0021] Hereinafter, embodiments of the present invention are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the invention. The present invention may be embodied in various different forms and is not limited to the embodiments described herein. To clearly explain the present invention, parts unrelated to the description in the drawings have been omitted, and the same reference numerals have been used throughout the specification for identical or similar components.

[0022] The words and terms used in this specification and claims are not limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the invention in accordance with the principles by which the inventor defines terms and concepts to best describe his invention.

[0023] In this specification, terms such as “comprising” or “having” are intended to describe the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should not be understood as precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] FIG. 1 is a flowchart of a method for setting a spinal canal region of CT data according to one embodiment of the present invention.

[0025] A method (S100) for setting a spinal canal region in CT data according to one embodiment of the present invention detects and sets the spinal canal region of a subject in CT (Computed Tomography) data in which the upper body of a subject is photographed. CT data in which the spinal canal region is set according to the method (S100) for setting a spinal canal region in CT data can be utilized as data for training an AI (Artificial Intelligence) model. For example, CT data in which the spinal canal region is set according to the method (S100) for setting a spinal canal region in CT data can be provided for training an AI model for determining spinal-related diseases.

[0026] A method (S100) for setting a spinal canal region of CT data according to one embodiment of the present invention may be performed by one or more processors. The one or more processors may comprise a hardware unit that executes one or more instructions. For example, the one or more processors may include at least one Arithmetic Logic Unit (ALU) and a register.

[0027] One or more of the above instructions may be for executing an AI model that detects and sets spinal canal regions in CT data. Additionally, one or more of the above instructions may be for executing a program that detects and sets spinal canal regions in CT data.

[0028] Referring to FIG. 1, a method (S100) for setting a spinal canal region of CT data according to one embodiment of the present invention can be performed as follows.

[0029] First, one or more processors generate a sagittal Maximum Intensity Projection (MIP) image of the subject's spine from CT (Computed Tomography) data in which the subject's upper body is captured (S110).

[0030] CT data in which the upper body of the subject is photographed includes multiple axial view images regarding the upper body of the subject. In other words, multiple axial view images can be stacked to form three-dimensional CT data.

[0031] In addition, MIP refers to a 3D technique that takes only the highest attenuation rate (signal) value among the voxels constituting the image and displays it. In this case, the unit of the attenuation rate value can be the Housefield unit (HU). More specifically, MIP can select and display only the voxels with the highest HU value among the voxels arranged parallel to the direction according to a specified projection angle.

[0032] FIG. 2 is a detailed flowchart of the step of generating a sagittal plane MIP image of a method for setting a spinal canal region of CT data according to one embodiment of the present invention.

[0033] Referring to FIG. 2, the step (S110) of generating a sagittal plane MIP image can be performed as follows.

[0034] First, one or more processors extract the center region of each of the plurality of cross-sectional view images (S111).

[0035] As described above, the CT data includes a plurality of cross-sectional view images regarding the upper body of the subject. The central region of each of the plurality of cross-sectional view images can be set as a region including the spinal canal.

[0036] In one embodiment of the present invention, the center area of ​​each cross-sectional view image may be composed of a predetermined section of the horizontal center of each cross-sectional view image. More specifically, the center area of ​​each cross-sectional view image may be composed of a slice of a predetermined section of the horizontal center of each cross-sectional view image (for example, a section having a predetermined width to the left and right of the horizontal center of each cross-sectional view image). For example, the horizontal width of the center area may have a value selected from 2 to 5 cm.

[0037] FIG. 3 is a diagram showing an example of a sagittal plane MIP image generated in the step of generating a sagittal plane MIP image of a method for setting a spinal canal region of CT data according to an embodiment of the present invention.

[0038] FIG. 3(a) shows three examples among a plurality of cross-sectional view images included in CT data, namely a first cross-sectional view image (A1), a second cross-sectional view image (A2), and a third cross-sectional view image (A3). FIG. 3(a) is an exemplary representation of some of the plurality of cross-sectional view images constituting CT data.

[0039] The first cross-sectional view image (A1) may be a cross-sectional image included in the cervical spine portion of the subject, the second cross-sectional view image (A2) may be a cross-sectional image included in the thoracic spine portion of the subject, and the third cross-sectional view image (A3) may be a cross-sectional image included in the lumbar spine portion of the subject.

[0040] A predetermined section of the horizontal center in the first cross-sectional view image (A1) may be extracted as the first central area (AC1), a predetermined section of the horizontal center in the second cross-sectional view image (A2) may be extracted as the second central area (AC2), and a predetermined section of the horizontal center in the third cross-sectional view image (A3) may be extracted as the third central area (AC3).

[0041] Next, one or more processors generate the sagittal plane MIP image through maximum intensity projection on the central region of the plurality of cross-sectional view images (S112).

[0042] Referring to FIG. 3(b), a sagittal plane MIP image (S_MIP) of a subject (P) is shown, which is generated by maximum intensity projection (MIP) at a predetermined angle for a plurality of center regions including a first center region (AC1), a second center region (AC2), and a third center region (AC3) extracted from a plurality of cross-sectional view images including a first cross-sectional view image (A1), a second cross-sectional view image (A2), and a third cross-sectional view image (A3).

[0043] After the step (S110) of generating a sagittal plane MIP image, one or more processors generate a first spinal canal line that extends along a portion corresponding to the spinal canal of the subject (P) in the sagittal plane MIP image (S_MIP) (S120).

[0044] FIG. 4 is a diagram showing an example of a first spinal canal line generated in the step of generating a first spinal canal line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention.

[0045] Referring to FIG. 4(a), one or more processors detect and set sagittal spinal canal points (SP1, SP2, SP3, …, SPn) corresponding to the spinal canal in the sagittal plane MIP image (S_MIP). The sagittal plane MIP image (S_MIP) is a representation of the horizontal center region of a plurality of cross-sectional view images constituting CT data in the sagittal plane. Therefore, sagittal spinal canal points can be detected and set as many times as the number of cross-sectional view images included in the CT data.

[0046] Referring to Fig. 4(b), a first spinal canal line (L1) can be generated by connecting the detected and set sagittal spinal canal points (SP1, SP2, SP3, …, SPn) in the sagittal plane MIP image (S_MIP).

[0047] Next, one or more processors generate a reference line (R) based on the first spinal canal line (L1) on the sagittal plane MIP image (S_MIP) (S130).

[0048] FIG. 5 is a diagram showing an example of a reference line generated in the step of generating a reference line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention.

[0049] Referring to FIG. 5, a reference line (R) can be established by connecting points located at a distance (d) set posteriorly from the first spinal canal line (L1) on the sagittal plane MIP image (S_MIP). For example, one or more processors can establish a line connecting points located at a distance (e.g., 3 cm) set posteriorly from the first spinal canal line (L1) as the reference line (R).

[0050] In this way, when a reference line (R) is established by connecting points spaced posteriorly from the first spinal canal line (L1) by a distance (d), the point where the subject's ribs branch is clearly visible in the coronal curved MIP image generated based on the reference line (R), and one or more processors can set the point where the ribs branch as a point corresponding to the spinal canal in the coronal curved MIP image. Accordingly, the efficiency of detection and setting can be improved.

[0051] Next, one or more processors generate a coronal curve MIP image of the subject from the CT data along a reference line (R) (S140).

[0052] The coronal plane curve MIP image (C_MIP) refers to a combination of multiple cross-sectional view images constituting CT data, wherein a view on the coronal plane where the reference line (R) passes through is extracted from each of the images and combined into a single image.

[0053] FIG. 6 is a diagram showing an example of a coronal plane curve MIP image generated in the step of generating a coronal plane curve MIP image of a method for setting a spinal canal region of CT data according to one embodiment of the present invention.

[0054] The coronal plane curve MIP image (C_MIP) shown in Fig. 6 shows the result of combining a view on the coronal plane, where the point where the reference line (R) passes through is placed, from each of the multiple cross-sectional view images into a single image.

[0055] In this regard, the length of the image (video) can be set through the header of the CT data's DICOM.

[0056] Next, one or more processors generate a second spinal canal line that extends along the portion corresponding to the spinal canal of the subject (P) in the coronal plane curve MIP image (C_MIP) (S150).

[0057] FIG. 7 is a diagram showing an example of a second spinal canal line generated in the step of generating a second spinal canal line of a method for setting a spinal canal region of CT data according to an embodiment of the present invention.

[0058] Referring to FIGS. 7 (a) and (b), one or more processors detect and set coronal spinal canal points (CP1, CP2, CP3, …, CPn) corresponding to the spinal canal in the coronal plane curve MIP image (C_MIP). The coronal plane curve MIP image (C_MIP) is formed by extracting views on the coronal plane in which a reference line (R) passes through each of the multiple cross-sectional view images constituting the CT data and combining them into a single image. Therefore, coronal spinal canal points can be detected and set as many times as the number of multiple cross-sectional view images included in the CT data.

[0059] Referring to Fig. 7(c), a second spinal canal line (L2) can be generated by connecting the detected and set coronal spinal canal points (CP1, CP2, CP3, …, CPn) in the coronal curve MIP image (S_MIP).

[0060] Finally, one or more processors set a spinal canal region in each of the plurality of cross-sectional view images included in the CT data based on the first spinal canal line (L1) and the second spinal canal line (L2) (S160).

[0061] FIG. 8 is a detailed flowchart of the step of setting the spinal canal region of a method for setting the spinal canal region of CT data according to an embodiment of the present invention. FIG. 9 is a diagram showing an example of a spinal canal region set in the step of setting the spinal canal region of a method for setting the spinal canal region of CT data according to an embodiment of the present invention.

[0062] Referring to FIGS. 8 and FIGS. 9, the step (S160) of establishing the spinal canal region can be performed as follows.

[0063] First, one or more processors determine the point set by the first spinal canal line (L1) and the second spinal canal line (L2) in each of the cross-sectional view images as the spinal canal point (S161).

[0064] Referring to Fig. 9, among the multiple cross-sectional view images included in the CT data, AP1 cross-sectional view image (A_AP1) selected from the cervical spine portion of the subject, AP2 cross-sectional view image (A_AP2) selected from the thoracic spine portion of the subject, and AP3 cross-sectional view image (A_AP3) selected from the lumbar spine portion of the subject are shown.

[0065] At this time, in the AP1 cross-sectional view image (A_AP1), the AP2 cross-sectional view image (A_AP2) selected from the thoracic spine portion of the subject, and the AP3 cross-sectional view image (A_AP3) selected from the lumbar spine portion of the subject, the horizontal direction can be defined as the X-axis and the vertical direction as the Y-axis.

[0066] Meanwhile, the horizontal direction of the sagittal plane MIP image (S_MIP) becomes the Y-axis direction on the cross-sectional view image. Therefore, among the multiple sagittal plane spinal canal points existing on the sagittal plane MIP image (S_MIP), the horizontal coordinate Y1 of the spinal canal point located at a height corresponding to the AP1 cross-sectional view image (A_AP1) can be determined as the Y-coordinate of the spinal canal point on the AP1 cross-sectional view image (A_AP1).

[0067] In addition, among the multiple sagittal plane spinal canal points existing on the sagittal plane MIP image (S_MIP), the horizontal coordinate Y2 of the spinal canal point located at a height corresponding to the AP2 cross-sectional view image (A_AP2) and the horizontal coordinate Y3 of the spinal canal point located at a height corresponding to the AP3 cross-sectional view image (A_AP3) can be determined as the Y-coordinate of the spinal canal point on the AP2 cross-sectional view image (A_AP2) and the Y-coordinate of the spinal canal point on the AP3 cross-sectional view image (A_AP3), respectively.

[0068] Meanwhile, in the coronal curve MIP image (C_MIP), the horizontal direction becomes the X-axis direction in the cross-sectional view image. Therefore, among the multiple sagittal spinal canal points existing on the coronal curve MIP image (C_MIP), the horizontal coordinate X1 of the spinal canal point located at a height corresponding to the AP1 cross-sectional view image (A_AP1) can be determined as the X-coordinate of the spinal canal point on the AP1 cross-sectional view image (A_AP1).

[0069] Additionally, among the multiple sagittal spinal canal points existing on the coronal curve MIP image (C_MIP), the horizontal coordinate X2 of the spinal canal point located at a height corresponding to the AP2 cross-sectional view image (A_AP2) and the horizontal coordinate X3 of the spinal canal point located at a height corresponding to the AP3 cross-sectional view image (A_AP3) can be determined as the X-coordinate of the spinal canal point on the AP2 cross-sectional view image (A_AP2) and the X-coordinate of the spinal canal point on the AP3 cross-sectional view image (A_AP3), respectively.

[0070] Next, one or more processors set a predetermined area surrounding the spinal canal point as a spinal canal area (S162).

[0071] One or more processors can each set a spinal canal region based on a spinal canal point present in each cross-sectional view image. For example, one or more processors can set an area within a predetermined radius centered on a spinal canal point present in each cross-sectional view image as the spinal canal region. Additionally, a square area of ​​a predetermined size with the spinal canal point positioned at its center can also be set as the spinal canal region.

[0072] Referring to Fig. 9, in the AP1 cross-sectional view image (A_AP1), the coordinates (X1, Y1) are set as the spinal canal point. Additionally, in the AP2 cross-sectional view image (A_AP2) and the AP3 cross-sectional view image (A_AP3), the coordinates (X2, Y2) and (X3, Y3) are set as the spinal canal points, respectively.

[0073] In addition, in the AP1 cross-sectional view image (A_AP1), a square area of ​​a predetermined size with coordinates (X1, Y1) placed at the center is set as the AP1 cross-sectional spinal canal area (S1). In the AP2 cross-sectional view image (A_AP2), a square area of ​​a predetermined size with coordinates (X2, Y2) placed at the center is set as the AP2 cross-sectional spinal canal area (S2), and in the AP3 cross-sectional view image (A_AP3), a square area of ​​a predetermined size with coordinates (X3, Y3) placed at the center is set as the AP3 cross-sectional spinal canal area (S3). For example, the length of one side of the square can be set to 3 to 5 cm.

[0074] Through this method, spinal canal regions can be detected and defined for each of the multiple cross-sectional view images included in the CT data. The spinal canal region definition information is stored in the CT data and can be provided as training data for an AI model.

[0075] The above describes a method (S100) for setting a spinal canal region of CT data according to one embodiment of the present invention. Below, we will examine a device for setting a spinal canal region of CT data according to one embodiment of the present invention.

[0076] FIG. 10 is a diagram showing the configuration of a spinal canal region setting device for CT data according to one embodiment of the present invention.

[0077] A spinal canal region setting device (100) for CT data according to one embodiment of the present invention can perform a spinal canal region setting method (S100) for CT data. In other words, the description regarding the spinal canal region setting method (S100) for CT data can be applied as is to the spinal canal region setting device (100) for CT data.

[0078] Referring to FIG. 10, a spinal canal region setting device (100) for CT data according to one embodiment of the present invention may include a memory (110) and a processor (120).

[0079] The memory (110) stores one or more instructions. The one or more instructions may be executed by a processor (120). The memory (110) may include a hardware device configured to store and execute one or more instructions.

[0080] For example, the memory (110) may include a storage medium such as ROM, RAM, flash memory, etc. Additionally, the memory (110) may include magnetic media such as floppy disks and magnetic tapes, optical media such as CD-ROM (Compact Disk Read Only Memory) and DVD (Digital Video Disk), magneto-optical media such as floptical disks, etc.

[0081] The processor (120) is operably connected to the memory (110). There may be one or more processors (120). The processor (120) executes the one or more instructions. For example, the processor (120) may be a hardware unit that performs operations and control within a computer. The processor (120) may include at least one Arithmetic Logic Unit (ALU) and a register.

[0082] One or more processors (120) can execute the one or more instructions to generate a sagittal Maximum Intensity Projection (MIP) image of the subject's spine from Computed Tomography (CT) data in which the subject's upper body is captured, generate a first spinal canal line extending along the part corresponding to the subject's spinal canal in the sagittal MIP image, generate a reference line based on the first spinal canal line in the sagittal MIP image, generate a coronal curved MIP image of the subject from the CT data along the reference line, generate a second spinal canal line extending along the part corresponding to the subject's spinal canal in the coronal curved MIP image, and set a spinal canal region in each of the plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line.

[0083] At this time, the sagittal plane MIP image can be generated by projecting maximum intensity onto a central region consisting of a predetermined section of the horizontal center of each of the plurality of cross-sectional view images.

[0084] In addition, the reference line can be established by connecting points spaced posteriorly from the first spinal canal line on the sagittal plane MIP image.

[0085] Meanwhile, each of the above spinal canal regions may be set as a predetermined region centered on the point set by the first spinal canal line and the second spinal canal line in each of the above cross-sectional view images.

[0086] In addition, the present invention provides a non-transitory computer-readable recording medium that stores at least one instruction that can be executed by one or more processors.

[0087] The above instructions are executed by one or more processors to generate a sagittal Maximum Intensity Projection (MIP) image of the subject's spine from Computed Tomography (CT) data in which the subject's upper body is captured, generate a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image, generate a reference line based on the first spinal canal line on the sagittal MIP image, generate a coronal curved MIP image of the subject from the CT data along the reference line, generate a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image, and set a spinal canal region in each of a plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line.

[0088] The above instructions may include machine code generated by a compiler. Additionally, the above instructions may include high-level language code executable by a computer.

[0089] The above recording medium may include a hardware device configured to store and execute program instructions, such as magnetic media (such as hard disks, floppy disks, and magnetic tapes), optical recording media (such as CD-ROMs, Digital Video Disks, and CD-ROMs), magneto-optical media (such as floptical disks), ROMs, RAMs, flash memory, etc.

[0090] Although embodiments of the present invention have been described, the spirit of the present invention is not limited by the embodiments presented in this specification. Those skilled in the art who understand the spirit of the present invention may easily propose other embodiments within the scope of the same spirit by adding, changing, deleting, or adding components, and such are also to be considered to fall within the spirit of the present invention. Explanation of the symbols

[0091] 100: Spinal canal region setting device for CT data 110: Memory 120: Processor

Claims

Claim 1 A method for setting a spinal canal region in CT data, comprising: a step of generating a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from Computed Tomography (CT) data in which the upper body of a subject is captured, performed by one or more processors; a step of generating a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; a step of generating a reference line based on the first spinal canal line on the sagittal MIP image; a step of generating a coronal curved MIP image of the subject from the CT data along the reference line; a step of generating a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image; and a step of setting a spinal canal region in each of a plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line. Claim 2 A method for setting a spinal canal region of CT data, wherein the step of generating the sagittal plane MIP image comprises: a step of extracting a central region of each of the plurality of cross-sectional view images; and a step of generating the sagittal plane MIP image through maximum intensity projection on the central region of the plurality of cross-sectional view images. Claim 3 A method for setting the spinal canal area of ​​CT data according to claim 2, wherein the central area of ​​each cross-sectional view image is formed by a predetermined section of the horizontal center of each cross-sectional view image. Claim 4 A method for setting a spinal canal region of CT data, wherein, in the step of generating the reference line, the reference line is set by connecting points spaced posteriorly from the first spinal canal line on the sagittal plane MIP image. Claim 5 A method for setting a spinal canal region in CT data according to claim 1, wherein the step of setting a spinal canal region in each of the plurality of cross-sectional view images comprises: a step of determining a point set by the first spinal canal line and the second spinal canal line in each of the cross-sectional view images as a spinal canal point; and a step of setting a predetermined surrounding area centered on the spinal canal point as a spinal canal region. Claim 6 The apparatus comprises: a memory storing one or more instructions; and one or more processors operably connected to the memory; wherein the one or more processors execute the one or more instructions to generate a sagittal Maximum Intensity Projection (MIP) image of the subject's spine from Computed Tomography (CT) data in which the subject's upper body is photographed; generate a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; generate a reference line based on the first spinal canal line on the sagittal MIP image; generate a coronal curved MIP image of the subject from the CT data along the reference line; and generate a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image. A CT data spinal canal region setting device that sets a spinal canal region in each of a plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line. Claim 7 In claim 6, the above sagittal plane MIP image is a CT data spinal canal region setting device generated through maximum intensity projection on a central region formed by a predetermined section of the horizontal center of each of the plurality of cross-sectional view images. Claim 8 In claim 6, the above reference line is a CT data spinal canal region setting device that is set by connecting points spaced posteriorly from the first spinal canal line on the sagittal plane MIP image. Claim 9 A CT data spinal canal region setting device, wherein each of the above spinal canal regions is set as a predetermined region centered on the point set by the first spinal canal line and the second spinal canal line in each of the above cross-sectional view images. Claim 10 A non-transitory computer-readable recording medium storing at least one instruction that can be executed by one or more processors, wherein the at least one instruction is executed by the one or more processors to generate a sagittal Maximum Intensity Projection (MIP) image of a subject's spine from Computed Tomography (CT) data in which the upper body of a subject is photographed; generate a first spinal canal line extending along a portion corresponding to the subject's spinal canal in the sagittal MIP image; generate a reference line based on the first spinal canal line on the sagittal MIP image; generate a coronal curved MIP image of the subject from the CT data along the reference line; and generate a second spinal canal line extending along a portion corresponding to the subject's spinal canal in the coronal curved MIP image. A non-transient computer-readable recording medium for setting spinal canal regions in each of the plurality of axial view images included in the CT data based on the first spinal canal line and the second spinal canal line.

Images