Medical image analysis support system and method for providing medical image analysis results

Abstract

A medical image analysis support system according to an embodiment of the present invention includes a lesion reading unit that reads medical image information including a plurality of medical image images of a patient's body, estimates the presence of a lesion from the plurality of medical image images, and detects the position and information of the estimated lesion, and an image reading information generation unit that generates image reading information in which a marking related to the lesion is displayed on a scout image including at least one of the medical image images in which the lesion is present and a medical image generated based on the plurality of medical image images to represent the lesion, wherein the marking is displayed to correspond to the position of the lesion in the scout image, and is displayed in a different diagram depending on the type of the lesion.

Description

[Technical Field]

[0001] The present invention relates to a medical image analysis support system and a method for providing medical image analysis results, and more particularly to a medical image analysis support system for supporting the diagnosis of lesions in medical images and a method for providing medical image analysis results using the same. [Background technology]

[0002] Many hospitals use medical imaging information systems (PACS, Picture Archiving Communications Systems) that work in conjunction with equipment that captures medical images such as X-ray, CT, and MRI images.

[0003] The medical image information system digitally stores the captured medical images and transmits them to the clinician's PC, allowing the clinician to view the images and diagnose the patient's condition.

[0004] In particular, CT and MRI images are composed of 300 consecutive cross-sectional images, placing a burden on clinicians to check all 300 images thoroughly to ensure accurate diagnosis. Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention provides a medical image analysis support system and a method for providing medical image analysis results that allow a user to more conveniently and accurately diagnose lesions.

[0006] The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, a medical image analysis support system according to an embodiment of the present invention comprises a lesion interpretation unit that interprets medical image information including a plurality of medical image images of a patient's body, estimates the presence of a lesion from the plurality of medical image images, and detects the position and information of the estimated lesion; and an interpretation information generation unit that generates interpretation information that displays a marking related to the lesion on a scout image that includes at least one of the plurality of medical image images in which the lesion is present and a medical image generated to represent the lesion based on the plurality of medical image images, wherein the marking is displayed to correspond to the position of the lesion on the scout image and is displayed in different diagrams depending on the type of the lesion.

[0008] To solve the above problem, a method for providing medical image analysis results according to an embodiment of the present invention includes interpreting medical image information including a plurality of medical image images of a patient's body, estimating the presence of a lesion from the plurality of medical image images, detecting the position and information of the estimated lesion, and generating interpretation information that displays a marking related to the lesion on a scout image that includes at least one of the plurality of medical image images in which the lesion is present and a medical image generated to represent the lesion based on the plurality of medical image images, wherein the marking is displayed to correspond to the position of the lesion on the scout image and is displayed in different diagrams depending on the type of the lesion.

[0009] Other details of the invention are included in the detailed description and drawings. [Effects of the Invention]

[0010] According to the embodiment of the present invention, at least the following effects are obtained.

[0011] Users can diagnose lesions more conveniently and accurately.

[0012] The effects of the present invention are not limited to the above-mentioned examples, and various other effects are included in this specification. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating a system in which a medical image analysis support system according to an embodiment of the present invention is used. [Figure 2] 1 is a flowchart illustrating a method for providing a medical image analysis result according to an embodiment of the present invention. [Figure 3] 1 is a diagram illustrating medical imaging information according to an embodiment including a plurality of medical imaging images; [Figure 4] FIG. 10 is a diagram showing a first medical video image in which a first lesion is detected. [Figure 5] FIG. 10 is a diagram showing a second medical video image in which a second lesion is detected. [Figure 6] FIG. 10 is a diagram for explaining a method for generating a scout image. [Figure 7] FIG. 10 is a diagram showing a first scout image in which a marking is displayed on a first lesion. [Figure 8] FIG. 10 is a diagram showing a second scout image in which a marking is displayed on a second lesion. [Figure 9] FIG. 10 is a diagram showing an example of a scout image in which markings are displayed on multiple lesions. [Figure 10] 3 is a flowchart for explaining step S30 in FIG. 2. [Figure 11] FIG. 1 is a diagram illustrating a schematic configuration of data in DICOM format. [Figure 12] 10A and 10B are diagrams for explaining a method of utilizing a scout image according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0014] The advantages and features of the present invention, as well as methods for achieving them, will become more apparent by reference to the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and can be realized in various different forms. The present embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully convey the scope of the invention to those skilled in the art. The present invention is defined solely by the scope of the claims.

[0015] Furthermore, the embodiments described herein are described with reference to cross-sectional views and / or schematic diagrams that are ideal exemplary views of the present invention. Therefore, the shapes of the exemplary views may be modified due to manufacturing techniques and / or tolerances. Furthermore, in each drawing shown in the present invention, each component may be slightly enlarged or reduced in size for convenience of explanation. The same reference numerals refer to the same components throughout the specification.

[0016] Hereinafter, the present invention will be described with reference to the drawings illustrating a medical image analysis support system and a method for providing medical image analysis results using the same according to an embodiment of the present invention.

[0017] FIG. 1 is a diagram illustrating a system in which a medical image analysis support system according to an embodiment of the present invention is used, and FIG. 2 is a flowchart illustrating a method for providing medical image analysis results according to an embodiment of the present invention.

[0018] 1, a medical image analysis support system 1 according to an embodiment of the present invention is communicably connected to a PACS (Picture Archiving Communications System, 2). PACS is a medical image information system that is widely used in hospitals today.

[0019] In this embodiment, the medical image analysis support system 1 will be described based on PACS2 as an example of a medical image information system to which it is connected, but the medical image analysis support system 1 according to one embodiment of the present invention can also be connected to and used in a communicative manner with other medical image information systems other than PACS2.

[0020] The medical image analysis support system 1 can be located in a remote location outside a hospital, and in this case, can be communicably connected to the PACS 2 via a wired or wireless remote communication network. For example, the medical image analysis support system 1 and the PACS 2 can be connected via a wide area network such as the Internet.

[0021] Alternatively, the medical image analysis support system 1 can be located in a hospital that operates a PACS 2. In this case, the medical image analysis support system 1 can be communicably connected to the PACS 2 via a wired or wireless communication network within the hospital.

[0022] The medical image analysis support system 1 can be communicatively connected to a terminal having an input device and a screen. The terminal can be an electronic device such as a desktop computer, a laptop computer, a tablet, or a smartphone.

[0023] The medical image analysis support system 1 is located in a remote location relative to the terminal and can be communicatively connected to the terminal via a wired or wireless remote communication network. For example, the medical image analysis support system 1 can be connected to the terminal in a cloud-based manner to provide services.

[0024] Alternatively, the medical image analysis support system 1 can be provided as software installed on a terminal.

[0025] Alternatively, some components of the medical image analysis support system 1 may be provided as software installed on a terminal, and other components may be provided in a remote location and communicatively connected to the terminal via a wired or wireless remote communication network.

[0026] Referring to FIG. 1, a medical image analysis support system 1 according to an embodiment of the present invention may include a medical image information receiving unit 10, a lesion interpretation unit 20, an interpretation information generating unit 30, and an interpretation information transmitting unit 40.

[0027] Also, referring to FIG. 2, a method for providing medical image analysis results according to one embodiment of the present invention may include step S10 of acquiring medical image information, step S20 of interpreting the medical image information to detect lesions, step S30 of generating interpretation information, and step S40 of transmitting the generated interpretation information.

[0028] In step S10 of acquiring medical image information, the medical image information receiving unit 11 receives medical image information stored in the PACS 2 or generated by a medical imaging device linked to the PACS 2 from the PACS 2. The medical image information may be data in the DICOM (Digital Imaging Communication in Medicine) format, which is a standardized medical image information that is currently widely used. In this embodiment, the explanation will be based on medical image information including medical images captured using a medical imaging device such as a CT (Computer Tomography) or MRI (Magnetic Resonance Imaging), which is a set of multiple medical image images of consecutive cross sections of a patient's body.

[0029] In step S20 of interpreting the medical image information to detect lesions, the lesion interpretation unit 20 interprets multiple medical image images included in the medical image information acquired by the medical image information receiving unit 10 to estimate the presence of a lesion and detects the position information of the estimated lesion within the image. The lesion interpretation unit 20 can be configured to interpret the medical image based on artificial intelligence (AI) and detect lesions estimated to exist within the image.

[0030] For example, the lesion interpretation unit 20 can detect intrapulmonary nodules using a CAD (Computer Aided Detection) algorithm for images of lung regions in multiple medical images (e.g., CT images) included in the medical image information. The lesion interpretation unit 20 can interpret the position, size, volume, type, Hounsfield, category, etc. of the detected nodules.

[0031] Types can be classified as non-solid nodules, part-solid nodules, solid nodules, calcification nodules, and unknown. Categories can be classified as 1, 2, 3, 4A, and 4B according to Lung-RADs. Categories can be classified based on the size, volume, type, and Hounsfield information of the detected nodules.

[0032] FIG. 3 is a diagram illustrating medical imaging information according to one embodiment including a plurality of medical imaging images.

[0033] 3, medical image information 100 can include a plurality of medical image images 101. For example, the medical image information 100 can include 360 ​​axial slice images 101.

[0034] The lesion interpretation unit 20 interprets each medical image 101, estimates the presence of a lesion in each medical image 101, and detects the position and information of the estimated lesion.

[0035] For convenience of explanation, the following description will be based on the case where the lesion interpretation unit 20 estimates the presence of a lesion in two medical video images 102 and 103.

[0036] FIG. 4 is a diagram showing a first medical image in which a first lesion is detected, and FIG. 5 is a diagram showing a second medical image in which a second lesion is detected.

[0037] Referring to FIG. 3, each pixel of each medical video image 101 can be represented by three-axis coordinates (x, y, z).

[0038] 4, the first lesion N1 detected in the first medical image 102 is located on the coordinates (X1, Y1, Z1). The z-axis coordinate of all pixels in the first medical image 102 is the same as Z1.

[0039] 5, the second lesion N2 detected in the second medical image 103 is located on the coordinates (X2, Y2, Z2). The z-axis coordinate of all pixels in the second medical image 103 is the same as Z2.

[0040] The lesion interpretation unit 20 can interpret not only the positional information of the first lesion N1 and the second lesion N2, but also the size, volume, type, Hounsfield, category, etc. of the first lesion N1 and the second lesion N2, as described above.

[0041] In step S30 of generating interpretation information, the interpretation information generating unit 30 generates interpretation information using information related to the lesion detected by the lesion interpretation unit 20.

[0042] The image interpretation information generating unit 30 can generate a scout image as image interpretation information.

[0043] FIG. 6 is a diagram for explaining a method for generating a scout image, FIG. 7 is a diagram showing a first scout image in which a marking is displayed on a first lesion, and FIG. 8 is a diagram showing a second scout image in which a marking is displayed on a second lesion.

[0044] 3 to 6, the first lesion N1 is located on a first Y plane 201, and the second lesion N2 is located on a second Y plane 202. As shown in FIG.

[0045] The image interpretation information generating unit 30 can generate a coronal image showing the first lesion N1 as a scout image showing the first lesion N1. In this case, the image interpretation information generating unit 30 generates a coronal image showing the first lesion N1 as a scout image showing the first lesion N1. In this case, the image interpretation information generating unit 30 generates a scout image showing the first lesion N1 as a scout image showing the first lesion N1. In the plurality of medical video images 101, the y-axis coordinate value of the first lesion N1 (Y -1 ) and an image of the same pixels, a coronal image depicting the first lesion N1 can be generated as a first scout image 300 as shown in FIG.

[0046] Furthermore, the image interpretation information generating unit 30 can generate a coronal image in which the second lesion N2 is expressed as a scout image in which the second lesion N2 is expressed. In this case, the image interpretation information generating unit 30 generates a scout image in which the second lesion N2 is expressed as a coronal image in which the second lesion N2 is expressed as a scout image in which the second lesion N2 is expressed. -2 ) and an image of the same pixels can be combined to generate a coronal image depicting the second lesion N2 as a second scout image 400, as shown in the drawing.

[0047] When the interpretation information generation unit 30 generates a sagittal image as a scout image, the interpretation information generation unit 30 can generate the sagittal image as a scout image by combining images of pixels in multiple medical video images 101 whose x-axis coordinate values ​​are the same as the x-axis coordinate of the lesion.

[0048] Alternatively, when the interpretation information generating unit 30 uses an axial image as a scout image, the interpretation information generating unit 30 can use the medical video image 101 as the scout image without generating a new scout image.

[0049] 7, the image interpretation information generating unit 30 can generate image interpretation information by displaying a first marking 301 for a first lesion N1 on a first scout image 300. Also, referring to FIG. 8, the image interpretation information generating unit 30 can generate image interpretation information by displaying a second marking 401 for a second lesion N2 on a second scout image 400.

[0050] 7 and 8, markings 301, 401 can be displayed to correspond to the location of the lesion on the scout image. For example, markings 301, 401 can be displayed to overlap the location of the lesion on the scout image, to indicate the location of the lesion, or to surround at least a portion of the lesion.

[0051] The interpretation information generating unit 30 displays the markings 301, 401 in different diagrams depending on the type of lesion, so that a user checking the scout image can easily recognize the type of lesion for which the marking is displayed simply by checking the marking.

[0052] For example, if the lesion is a nodule, the nodule can be classified into types such as non-solid nodule, part-solid nodule, solid nodule, calcification nodule, and unknown.

[0053] The interpretation information generating unit 30 may, for example, mark a non-solid nodule using a dotted line diagram, a part-solid nodule using a solid line diagram, a solid nodule using a double solid line diagram, a calcification nodule using a filled diagram, and an unknown using an X-shaped diagram.

[0054] (See Figure 9.) Marking can be shown in a diagram that has differences not only in line type but also in line thickness, line color, etc.

[0055] Meanwhile, the image interpretation information generating unit 30 may display the size of the diagram in relation to the size of the lesion. That is, the image interpretation information generating unit 30 may display a diagram with larger markings as the size of the lesion increases. Therefore, a user viewing the scout image can easily recognize the absolute or relative size of the lesion marked by simply checking the markings.

[0056] 7 and 8, the interpretation information generating unit 30 may display markings 302, 303, 402, and 403 relating to lesions located on different Y planes on each scout image 300, 400. In this case, the markings 301, 401 relating to lesions located on the same plane as the scout image 300, 400 can be displayed so as to be distinguished from the markings 302, 303, 402, and 403 relating to lesions located on a plane different from that of the scout image 300, 400. For example, the markings 301, 401 relating to lesions located on the same plane as the scout image 300, 400 can be displayed in a darker, bolder, or different color than the markings 302, 303, 402, and 403 relating to lesions located on a plane different from that of the scout image 300, 400.

[0057] FIG. 9 is a diagram showing an example of a scout image in which markings are displayed on each of a plurality of lesions.

[0058] Referring to FIG. 9, the interpretation information generating unit 30 can also generate interpretation information in which markings 501, 502, 503, 504, 505, and 506 relating to all lesions interpreted in the medical image information 100 are displayed on one scout image 500.

[0059] In step S40 of transmitting the generated interpretation information, the interpretation information transmitting unit 40 can transmit the interpretation information generated in step S30 to the PACS2.

[0060] The interpretation information transmitted by the interpretation information transmission unit 40 to the PACS 2 may be data in DICOM format. Therefore, the hospital receiving the interpretation information can check the scout image and markings included in the interpretation information using the PACS 2.

[0061] The interpretation information may include at least one of a scout image generated for each lesion and displaying markings, as shown in Figures 7 and 8, and a single scout image displaying markings for all lesions.

[0062] FIG. 10 is a flowchart for explaining step S30 in FIG.

[0063] Referring to Figure 10, step S30 of generating interpretation information may include step S31 of displaying markings related to the lesion on the scout image, step S32 of determining coordinate information of the lesion, and step S33 of determining header information of the interpretation information.

[0064] Step S31 of displaying markings relating to the lesion on the scout image has already been described with reference to FIGS. 6 to 8, and therefore further description thereof will be omitted.

[0065] The medical image analysis support system and the method for providing medical image analysis results according to an embodiment of the present invention may further include step S32 and step S33.

[0066] In step S32 of determining coordinate information of the lesion, the image interpretation information generating unit 30 calculates coordinate information of the detected lesion.

[0067] FIG. 11 is a diagram showing an outline of the structure of data in the DICOM format.

[0068] The plurality of slice image information 110 constituting the DICOM format medical image information 100 includes DICOM header information 111 and DICOM image information 112. The DICOM image information 112 includes information for constituting the slice image 101 described above.

[0069] The DICOM header information 111 records various information related to the DICOM image information 112. For example, the DICOM header information 111 includes patient information, imaging device information, image position patient information 111a, pixel spacing information 111b, and the like.

[0070] In step S32, the interpretation information generating unit 30 calculates coordinate information of the detected lesion using the image position patient information 111a and the pixel interval information 111b.

[0071] Step S32 will be described in more detail with reference to FIG.

[0072] The interpretation information generating unit 30 can confirm the image position patient information 111a and pixel interval information 111b from the DICOM header information 111 of the first medical video image 102 in which the first lesion N1 is detected.

[0073] X1 means the number of pixels from the upper left corner of the first medical video image 102 to the pixel where the first lesion N1 is detected in the x direction (see FIG. 3).

[0074] Y1 means the number of pixels from the upper left corner of the first medical video image 102 in the y direction (see FIG. 3) to the pixel where the first lesion N1 is detected.

[0075] The pixel interval information 111b means information relating to the interval between pixels.

[0076] The image position patient information 111a includes information regarding the reference coordinates of the first medical image 102. Referring to Figure 3, the medical image information 100 includes a plurality of axial medical images 101, and the image position patient information 111a of each axial medical image 101 has the same x-coordinate and y-coordinate, but differs only in z-coordinate.

[0077] The coordinates indicated by the image position patient information 111 a may be the upper left corner of each medical video image 101 or the center of each medical video image 101 .

[0078] The interpretation information generating unit 30 can calculate the coordinate information of the first lesion N1 using the following mathematical formula.

[0079] X real =u+S x X1 Y real =v+S y Y1

[0080] The coordinates indicated by the image position patient information 111a are (u, v, w), Sx is the x-axis pixel interval in the pixel interval information 111b, and Sy is the y-axis pixel interval in the pixel interval information 111b.

[0081] X real means the actual x-coordinate of the first lesion N1, and Y real denotes the actual y coordinate of the first lesion N1.

[0082] The actual z coordinate of the first lesion N1 is the same as w.

[0083] The image interpretation information generating unit 30 uses (X real ,Y real ,w) can be generated.

[0084] In step S33 of determining header information of the image interpretation information, the image interpretation information generating unit 30 determines image position patient information from the DICOM header information for the scout image as coordinate information of the lesion calculated in step S32.

[0085] That is, the image interpretation information generating unit 30 extracts the image position patient information from the DICOM header information of the image interpretation information including the scout image for the first lesion N1, and sets the image position patient information to (X real ,Y real , w).

[0086] Alternatively, the image interpretation information generating unit 30 may generate image position patient information from the DICOM header information of the image interpretation information including the scout image for the first lesion N1, as follows: (u, Y real , w).

[0087] In step S40 of transmitting the generated interpretation information, the interpretation information transmitting unit 40 can transmit the interpretation information generated through steps S31 and S32 to the PACS 2.

[0088] 12 is a diagram for explaining a method for utilizing a scout image according to the present invention, and is a diagram schematically illustrating an execution screen of software for checking medical image information in DICOM format using a PACS.

[0089] 12, a tool area A may be displayed on one side of the screen, a scout image area B may be displayed in the center of the screen, and a medical image area C may be displayed on the other side of the screen. For convenience of explanation, a three-part screen configuration is shown, but the screen configuration may be modified in various ways. For example, the order of at least some of the tool area A, scout image area B, and medical image area C may be changed, or at least some of the three areas (A, B, and C) may be further divided to display additional information or images.

[0090] When the software is executed and the interpretation information including the scout image is opened, a scout image is displayed in the scout image area B with a marking 301 at the position of the lesion, as shown in FIG.

[0091] Among the software tools for checking medical image information in DICOM format, when a marking 301 or a lesion is clicked using a 3D cursor A1, a medical image in which the lesion is located is displayed in the medical image area C. The medical image is an original medical image included in the medical image information 100, and may be an image without markings or the like.

[0092] The software uses the coordinates in the scout image clicked by the 3D cursor to cause the corresponding medical video image to be displayed in medical video image area C.

[0093] However, as shown in FIG. 12, when the scout image is a coronal image, clicking on the marking 301 or the lesion using the 3D cursor A1 identifies the x and z coordinates of the marking 301 or the lesion, but not the y coordinate.

[0094] Therefore, even if the user clicks on the marking 301 or the lesion using the 3D cursor A1 in the scout image of the interpretation information for which steps S32 and S33 have not been performed, the axial medical image displayed in the medical image area C can be identified using the clicked x-coordinate and z-coordinate, but the position of the lesion N1 cannot be identified within the axial medical image. Therefore, the user must search for the position of the lesion N1 within the axial medical image again.

[0095] However, steps S32 and S33 allow the image position patient information (X real ,Y real , w), the x and z coordinates of the clicked position on the scout image using the 3D cursor A1 and the image position patient information are (X real ,Y real , w) to identify the axial medical image displayed in the medical image area C, and at the same time, to determine the position of the lesion N1 in the axial medical image (X click ,Y real ,Z click ) or (X real ,Y real,Z click ) can be specified as X click means the x-coordinate where you clicked using 3D cursor A1, and Z click means the x-coordinate clicked using 3D cursor A1.

[0096] Referring to FIG. 12, within the medical video image area C, X click or X real A vertical line corresponding to the value and Y real A horizontal line corresponding to the value can be displayed, and the intersection of the vertical line and the horizontal line is the location of the lesion N1, so that the user can easily identify the lesion N1 in the medical video image.

[0097] Or, within the medical image area C, X click or X real Vertical lines and Y values real Alternatively, only one of the horizontal lines corresponding to the values ​​may be displayed, and in this case, the user can find the lesion N1 on either the vertical line or the horizontal line in the medical image, making it easier to identify the lesion N1 in the medical image.

[0098] Alternatively, steps S32 and S33 may be performed to set the image position patient information (u, Y real , w), the x and z coordinates clicked using the 3D cursor A1 in the scout image and the image position patient information (u, Y real , w) to identify the axial medical image displayed in the medical image area C, and at the same time, to determine the position of the lesion in the axial medical image (X click ,Y real ,Z click ) can be identified as

[0099] Those skilled in the art will understand that the present invention can be embodied in other specific forms without changing the technical spirit or essential characteristics thereof. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and are not limiting. The scope of the present invention is defined not by the above detailed description but by the claims that follow, and all modifications and variations that fall within the meaning and scope of the claims and their equivalents should be construed as being within the scope of the present invention.

Claims

1. a lesion image reading unit that reads medical image information including a plurality of medical image images of a patient's body, estimates the presence of a lesion from the plurality of medical image images, and detects the position and information of the estimated lesion; and an image interpretation information generating unit that generates image interpretation information in which a marking related to the lesion is displayed on a scout image including at least one of the medical image images in which the lesion is present and a medical image generated based on the plurality of medical image images so as to represent the lesion, The lesion interpretation unit, based on an artificial intelligence model trained to interpret the lesion, Detecting lesions within the plurality of medical video images; and determining the type of the detected lesion as at least one of a non-solid nodule, a part-solid nodule, a solid nodule, a calcification nodule, and an unknown; The marking is displayed in the scout image to correspond to the position of the lesion, and is displayed in a diagram divided according to the type of the lesion determined through the lesion interpretation unit.

2. The medical image analysis support system according to claim 1 , wherein the size of the diagram is displayed so as to be related to the size of the lesion.

3. A medical image analysis support system as described in claim 1, wherein the diagram is displayed using dotted lines, solid lines, or double solid lines depending on the type of lesion.

4. the medical image information and the interpretation information include data in a DICOM (Digital Imaging and Communications in Medicine) format, 2. The medical image analysis support system of claim 1, wherein the interpretation information generation unit determines the image position patient coordinate information in the DICOM header information of the interpretation information based on the image position patient coordinate information in the DICOM header information of the medical video image in which the lesion is present and the position information of the lesion within the medical video image in which the lesion is present.

5. 5. The medical image analysis support system of claim 4, wherein the interpretation information generation unit determines the position information of the lesion based on pixel spacing information in the DICOM header information of the medical image in which the lesion is present and the number of pixels between the lesion and a reference point corresponding to the coordinate information of the image position of the patient.

6. Based on an artificial intelligence model trained to interpret lesions, medical image information including a plurality of medical images of a patient's body is interpreted, the presence of a lesion is estimated from the plurality of medical images, and the position and information of the estimated lesion are detected; determining the type of the lesion as at least one of a non-solid nodule, a part-solid nodule, a solid nodule, a calcification nodule, and an unknown nodule based on the artificial intelligence model; generating interpretation information in which a marking relating to the lesion is displayed on a scout image including at least one of the medical image images in which the lesion is present and a medical image generated based on the plurality of medical image images so as to represent the lesion; The marking is displayed in the scout image so as to correspond to the position of the lesion, and is displayed in a diagram divided according to the determined type of lesion.

7. The method of claim 6 , wherein the size of the diagram is displayed in relation to the size of the lesion.

8. A method for providing medical image analysis results as described in claim 6, wherein the diagram is displayed using dotted lines, solid lines, or double solid lines depending on the type of lesion.

9. The method for providing medical image analysis results according to claim 6, further comprising determining image position patient coordinate information in the DICOM header information of the interpretation information based on image position patient coordinate information in the DICOM header information of the medical image in which the lesion is present and position information of the lesion within the medical image in which the lesion is present.

10. 10. The method for providing medical image analysis results according to claim 9, wherein the position information of the lesion is determined based on pixel spacing information in the DICOM header information of the medical image in which the lesion is present and the number of pixels between the lesion and a reference point corresponding to the coordinate information of the image position of the patient.

11. The image interpretation information generating unit calculates three-dimensional coordinate information of the lesion using the position information of the lesion, The calculated three-dimensional coordinate information is determined as the image position patient value in the DICOM header information of the scout image; The medical image analysis support system includes: obtaining a user selection for the marking displayed on the scout image; and displaying a medical video image in which the lesion is located based on the determined image position patient value. The medical image analysis support system according to claim 4.

Images