Lesion determination method and device

Abstract

An electronic device according to one embodiment can acquire a first trend line relating to blood vessels from a medical image, determine lesion candidates among the blood vessels based on the first trend line, acquire a second trend line based on a reference point selected from around the lesion candidate, and determine a lesion site among the lesion candidates based on the acquired second trend line.

Description

[Technical field]

[0001] Below, techniques for determining lesions are provided. [Background technology]

[0002] Interventional procedures that insert stents using catheters to treat cardiovascular, cerebrovascular, and peripheral blood vessels are widely used. Before the procedure, the severity of the patient's lesion is evaluated using images from angiography. When confirmed through angiography, the treatment plan may change depending on the characteristics of the arteriosclerotic plaque. In particular, if there is a calcified lesion, the rupture of the lesion may cause myocardial infarction as the calcified fragments block the end of the branch. In addition, when there are multiple lesions in the coronary artery and there are many calcified lesions, referring to the SYNTAX score, a surgical method may be more favorable for the prognosis. In this regard, there is a demand for a technology that detects calcified lesions based on images from angiography based on X-rays instead of CT (Computer Tomography).

[0003] The above-mentioned background art was possessed or acquired by the inventors in the process of deriving the contents of the disclosure of this application, and is not necessarily publicly known art that was publicly disclosed prior to the filing of this application. Summary of the Invention [Problem to be solved by the invention]

[0004] The electronic device according to one embodiment is configured to detect multiple lesions in a blood vessel to be analyzed in a blood vessel image.

[0005] An electronic device according to one embodiment is adapted to search for lesion candidates and determine which are clinically significant.

[0006] However, the technical issues are not limited to the above-mentioned technical issues, and further technical issues may exist. [Means for solving the problem]

[0007] A lesion determination method performed by a processor according to one embodiment includes the steps of obtaining a first trendline for blood vessel diameter from a medical image, determining lesion candidates among the blood vessels based on the first trendline, obtaining a second trendline based on reference points selected from around the lesion candidates, and determining a lesion site among the lesion candidates based on the obtained second trendline.

[0008] The step of obtaining the first trend line includes a step of calculating a diameter within the vascular region to be analyzed in the medical image for each position along a center line based on a line perpendicular to the center line of the vascular region, and a step of obtaining the first trend line based on the calculated diameter.

[0009] The step of obtaining the first trend line may include the steps of: dividing a vascular region to be analyzed in the medical image into one or more vascular segments; calculating a regression line for the one or more vascular segments based on a regression analysis using a prior slope; eliminating outliers selected based on the calculated regression line from diameters at positions along a centerline within the vascular segment; and calculating a regression line based on the diameters from which the outliers have been eliminated.

[0010] The step of eliminating the outliers includes determining as the outliers diameter values ​​at positions along the centerline within the vessel segment that exceed a range determined with reference to the initial regression line.

[0011] The step of obtaining the first trend line may include a step of repeatedly removing the outliers and calculating the regression line until a ratio of diameters determined to be outliers among diameters at positions along a centerline within the vascular segment is less than a threshold abnormality ratio.

[0012] The step of obtaining the first trend line may include a step of dividing a vascular region to be analyzed in the medical image into one or more vascular segments, and a step of determining whether or not to merge trend lines calculated for each vascular segment of the one or more vascular segments and vascular segments adjacent to the vascular segment.

[0013] The step of dividing into one or more vascular segments may include a step of dividing the vascular region into the one or more vascular segments based on vascular branches, and the step of determining whether or not the trend lines are merged may include a step of calculating the trend line for the one or more vascular segments, and a step of determining whether or not the trend lines are merged based on trend values ​​of adjacent positions on the trend line based on the vascular branches.

[0014] The step of dividing into one or more vascular segments may include a step of determining whether to divide the vascular region into the one or more vascular segments based on the vascular branch based on a diameter value at the vascular branch of a first vascular segment that is close to an ostium of a coronary artery and a diameter value at the vascular branch of a second vascular segment that is far from the ostium of the coronary artery, among vascular segments adjacent to each other based on the vascular branch.

[0015] The step of calculating the trend line may include limiting a slope of the trend line that exceeds a reference slope to the reference slope.

[0016] The step of determining whether or not the trend lines are merged may include a step of determining a new trend line by merging the trend line for the first vascular segment and the trend line for the second vascular segment based on the fact that a trend value for a distal position in a trend line calculated for a first vascular segment, which is closer to the entrance of a coronary artery, among adjacent vascular segments, is smaller than a trend value for a proximal position in a trend line calculated for a second vascular segment, which is farther from the entrance of the coronary artery.

[0017] The step of determining the lesion candidate includes a step of determining, as the lesion candidate, a portion of a vascular region of the medical image that has a diameter smaller than a value obtained by applying a first ratio to the first trend line.

[0018] Obtaining a second trend line based on reference points selected from around the lesion candidate can include selecting local peaks around the lesion candidate that have a greater value than the first trend line as the reference points.

[0019] The step of selecting as the reference point may include a step of selecting as the reference point a point at which a value corresponding to a diameter of the vascular region is shown among values ​​obtained by applying a threshold reference ratio to the first trend line based on the local peak exceeding a value obtained by applying a threshold reference ratio to the first trend line.

[0020] The step of selecting as the reference point may include a step of attempting to redetect the local peak based on a value obtained by applying a threshold local ratio to the first trend line based on the fact that at least one of a first reference point (e.g., a proximal reference point) close to the entrance of the coronary artery and a second reference point (e.g., a distal reference point) far from the entrance of the coronary artery is not detected around the lesion candidate.

[0021] The lesion determination method may further include a step of excluding from the determination of the lesion site any lesion candidate that fails to detect at least one of a first reference point close to the entrance of the coronary artery and a second reference point far from the entrance of the coronary artery.

[0022] The step of determining the lesion site may include a step of determining, as the lesion site, a region corresponding to the lesion candidate that has a diameter smaller than a value obtained by applying a second ratio to the second trend line.

[0023] The step of determining the lesion location may include determining the second ratio based on a value at a corresponding point on the first trend line.

[0024] The step of determining the lesion site may include, when multiple lesion candidates are adjacent to each other, determining whether to determine the multiple lesion candidates and the intermediate region as a single lesion site based on a ratio between a maximum diameter value among diameter values ​​in an intermediate region between the multiple lesion candidates and a value along the first trend line at a point corresponding to the maximum diameter value.

[0025] The step of determining the lesion site may include a step of determining that, if multiple lesion candidates are adjacent to one another, the adjacent candidates are to be merged if the distance between the multiple lesion candidates is less than a predetermined value.

[0026] According to one embodiment, an electronic device includes an image acquisition unit that acquires medical images, a display that outputs the medical images, a memory that stores computer-executable instructions, and a processor that executes the instructions stored in the memory, and the instructions may be configured to output at least one of a first trend line relating to a global trend of blood vessel diameter for each of a plurality of blood vessel segments divided from a blood vessel included in the medical image, a reference point located above the first trend line, a second trend line relating to a local trend of the blood vessel diameter determined based on the reference point, and a lesion site located below the second trend line together with the medical image via the display. Effect of the Invention

[0027] An electronic device according to an embodiment can improve user convenience by providing automated segmentation and quantitative analysis of vascular images.

[0028] According to an embodiment, an electronic device can detect multiple lesions in blood vessels from medical images.

[0029] An electronic device according to one embodiment can provide information about lesions intuitively to analysts with little medical experience and / or knowledge by visualizing lesions and trend lines that serve as the basis for lesion assessment. [Brief description of the drawings]

[0030] [Figure 1] FIG. 1 illustrates an electronic device according to an embodiment.

[0031] [Diagram 2] FIG. 2 is a flow chart illustrating a lesion determination method according to one embodiment.

[0032] [Diagram 3]FIG. 3 illustrates vascular region segmentation and trend line merging according to one embodiment. [Figure 4] FIG. 4 illustrates vascular region segmentation and trend line merging according to one embodiment. [Diagram 5] FIG. 5 illustrates vascular region segmentation and trend line merging according to one embodiment. [Figure 6] FIG. 6 illustrates vascular region segmentation and trend line merging according to one embodiment. [Figure 7] FIG. 7 illustrates vascular region segmentation and trend line merging according to one embodiment. [Figure 8] FIG. 8 illustrates vascular region segmentation and trend line merging according to one embodiment. [Figure 9] FIG. 9 illustrates vascular region segmentation and trend line merging according to one embodiment.

[0033] [Figure 10] FIG. 10 illustrates lesion candidate determination according to one embodiment.

[0034] [Figure 11] FIG. 11 illustrates setting of reference points and obtaining of a second trend line according to one embodiment. [Figure 12] FIG. 12 illustrates setting of reference points and obtaining of a second trend line according to one embodiment. [Figure 13] FIG. 13 illustrates setting of reference points and obtaining of a second trend line according to one embodiment. [Figure 14] FIG. 14 illustrates setting of reference points and obtaining of a second trend line according to one embodiment.

[0035] [Figure 15] FIG. 15 illustrates determining lesion location according to one embodiment. [Figure 16] FIG. 16 illustrates determining lesion location according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0036] The specific structural or functional description of the embodiments is disclosed for the purpose of illustration only, and may be modified in various forms. Therefore, the embodiments are not limited to the specific disclosed forms, and the scope of the present specification includes modifications, equivalents, or alternatives within the technical spirit.

[0037] Although terms such as first or second may be used to describe multiple components, such terms should be construed only for the purpose of distinguishing one component from the other components. For example, a first component may be named a second component, and similarly, a second component may be named a first component.

[0038] When any component is referred to as being "connected" to another component, it is directly linked or connected to the other component, but it should be understood that there may be other components in between.

[0039] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, the terms "comprise" or "have" and the like indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, and should be understood as not precluding the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0040] 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 to which the present invention belongs. Commonly used predefined terms should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted as ideal or overly formal unless expressly defined in this specification.

[0041] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. In the description with reference to the drawings, the same components are given the same reference numerals regardless of the reference numerals, and redundant description thereof will be omitted.

[0042] FIG. 1 illustrates an electronic device according to an embodiment.

[0043] The electronic device 100 according to an embodiment is an apparatus for analyzing medical images, and includes an image acquisition unit 130 , a processor 110 , a display 140 , and a memory 120 .

[0044] The image acquisition unit 130 acquires a medical image 131. The medical image 131 in which blood vessels of a target object (e.g., a patient 190) are captured may also be displayed as a blood vessel image. For example, the image acquisition unit 130 may include an X-ray imaging device, and may capture the medical image 131 (e.g., a CAG image based on X-rays) through coronary angiography (hereinafter, "CAG") based on X-rays.

[0045] The medical image 131 may include one or more frames. In order to image blood vessels, a contrast agent is injected into the blood vessels of the subject 190, and the blood vessels of the subject 190 are imaged while the contrast agent is being maintained. Among the frames of the medical image 131, a frame in which the contrast agent is observed may be referred to as a contrast agent frame. In a CAG image based on X-rays, the intensity value of each pixel is the intensity due to the transmission of X-rays, and the intensity value of a point where the X-rays are absorbed by the contrast agent is indicated as low. In this specification, as an example of the medical image 131, an image of a contrast agent frame among CAG images based on X-rays will be mainly described. However, this is for convenience of explanation, and the present invention is not limited thereto, and the operation described below with reference to FIGS. 2 to 16 for lesion determination may be applied to other medical images in which blood vessels are imaged.

[0046] For reference, an example has been described in which the image acquisition unit 130 has X-ray imaging equipment to capture medical images 131, but is not limited to this, and the image acquisition unit 130 can also include a communication module for wired communication and / or wireless communication and receive vascular images (e.g., CAG images based on X-rays) from an external imaging device via the communication module.

[0047] The processor 110 may output at least one of a first trend line relating to a global trend of blood vessel diameters for each of a plurality of blood vessel segments divided from a blood vessel included in the medical image, a reference point located above the first trend line, a second trend line relating to a local trend of blood vessel diameters determined based on the reference point, and a lesion site located below the second trend line together with the medical image via the display 140. The first trend line may be indicated as a global trend line, and the second trend line may be indicated as a local trend line. The processor 110 may select at least one of the first trend line, the reference point, the second trend line, and the lesion site based on an input from a user (e.g., an analyst). The processor 110 may output a graphic representation indicating the selected information using the display 140. The operation of the processor 110 will be described with reference to FIGS. 2 to 16 below. For example, the acquisition of the first trend line will be described with reference to Figures 3 to 9 below, the determination of lesion candidates will be described with reference to Figure 10 below, the setting of reference points and the acquisition of the second trend line will be described with reference to Figures 11 to 14 below, and the determination of the lesion site will be described with reference to Figures 15 and 16 below.

[0048] The display 140 outputs the medical image 131. The processor 110 can also visualize (e.g., overlay) a graphical representation indicating at least one of the first trend line, the reference point, the second trend line, and the lesion location on the medical image 131 via the display 140.

[0049] The memory 120 stores at least some or all of the frames of the medical image 131. The memory 120 stores information about the detected lesions (e.g., the location, size, and blood vessel diameter of the lesions, etc.) The memory 120 can also temporarily and / or permanently store data and / or information required to perform a method for lesion determination through analysis of the medical image 131.

[0050] The electronic device 100 according to an embodiment can intuitively provide vascular information for quantitatively evaluating the severity of a lesion. The electronic device 100 can automatically set not only lesion candidates but also reference points for determining whether a lesion is present. The electronic device 100 can also identify multiple lesions in one blood vessel.

[0051] FIG. 2 is a flow chart illustrating a lesion determination method according to one embodiment.

[0052] First, in step 210, an electronic device (e.g., electronic device 100 of FIG. 1) obtains a first trendline for vessel diameter from a medical image. As described above with reference to FIG. 1, the medical image may be, but is not limited to, a CAG image based on X-rays. The vessel diameter indicates an inner diameter through which blood can flow in the vessel. However, for convenience of explanation, the present specification mainly refers to the diameter, but is not limited thereto, and may be expressed as the vessel width. The first trendline may also be shown as a global trendline, which is a trendline indicating a global trend of the vessel area and / or vessel segments divided from the vessel area.

[0053] Then, in step 220, the electronic device determines lesion candidates in the blood vessel based on the first trend line. The lesion candidates indicate portions of the blood vessel that may be candidates for potential lesions. The electronic device may determine a portion of the blood vessel as a lesion candidate based on a difference between values ​​along the first trend line (e.g., a first trend value) for the portion and a diameter value for the portion. The values ​​along the trend line may be referred to as trend values. Determining lesion candidates based on the first trend value and the diameter values ​​is described with reference to FIG. 10 below. The trend values ​​may also be used to determine whether trend lines merge, as described with reference to FIGs. 6 and 7 below.

[0054] Next, in step 230, the electronic device acquires a second trend line based on a reference point selected from the periphery of the lesion candidate. The peripheral part of the lesion candidate includes a part adjacent to the lesion candidate in a laterally direction close to the ostium of the coronary artery (e.g., a proximal part) and a part adjacent to the lesion candidate in a direction away from the ostium of the coronary artery (e.g., a distal part). In this specification, the coronary artery exemplarily indicates the entire blood vessel having a tree structure that branches from the aortic root and extends toward the heart. The electronic device may set a reference point in the periphery of the lesion candidate based on the first trend line. The reference point will be described later, and indicates a point on a blood vessel diameter graph that is a reference for acquiring the second trend line. The electronic device can acquire the second trend line by connecting two reference points that are set to be adjacent to each other. The setting of the reference point and the acquisition of the second trend line will be described with reference to FIGS. 11 to 14 below.

[0055] Then, in step 240, the electronic device determines a lesion location among the lesion candidates based on the obtained second trend line. The electronic device may determine at least a portion of the locations corresponding to the lesion candidates as the lesion location, or may exclude some of the lesion candidates from the lesion location determination. The determination of the lesion location will be described with reference to Figures 15 and 16 below.

[0056] 3-9 illustrate vascular region segmentation and trend line merging according to one embodiment.

[0057] FIG. 3 is a flow chart for explaining the division of vessel regions and the merging of trend lines. The trend lines described with reference to FIG. 3-FIG. 9 are first trend lines, e.g., global trend lines related to the global trends of vessel regions and / or vessel segments. For reference, the present specification mainly describes that the analysis targets are from the entrance of the coronary artery to the terminal vessels of each branch, but is not limited thereto. Exemplarily, the electronic device (e.g., electronic device 100 of FIG. 1) may determine whether or not to include a vessel bifurcation in the analysis target based on the diameter of the vessel bifurcation. The electronic device may exclude a vessel bifurcation from the analysis target if its diameter is less than an analysis threshold, and may include a vessel bifurcation in the analysis target if its diameter is equal to or greater than the analysis threshold.

[0058] First, in step 311, the electronic device calculates the diameter of the blood vessel region 480 to be analyzed from the medical image 400. For example, the electronic device can calculate the diameter in the blood vessel region 480 for each position along the center line 410 based on a line 420 perpendicular to the center line 410 of the blood vessel region 480 to be analyzed in the medical image 400. The center line 410 of the blood vessel region 480 is a line passing through the center of the blood vessel and connecting the center points of the blood vessel inner diameters longitudinally. The position along the center line 410 indicates a position that is separated by a certain length along the center line 410 from the starting position 401. The diameter at the position along the center line 410 indicates the length (or interval) between the blood vessel inner walls along the line 420 perpendicular to the center line 410 at that position. The electronic device can obtain blood vessel diameter information indicating the blood vessel diameter for each position along the center line 410. In FIG. 4, the blood vessel diameter information is shown in a blood vessel diameter graph 490. The blood vessel diameter graph 490 includes, for example, a graph showing a diameter of y mm at a position that is x mm (millimeters) away from the start position 401 along the center line 410. For reference, the start position 401 may be, for example, a point that indicates the entrance of a coronary artery, but is not limited thereto and may vary depending on the design. For example, the start position 401 may be set as the start point of a blood vessel segment, as a point in the blood vessel segment that is closest to the entrance of a coronary artery.

[0059] According to an embodiment, the electronic device can obtain a first trend line based on the diameter calculated as described above. For example, the electronic device can calculate the first trend line for a blood vessel segment divided from the blood vessel region 480 described below.

[0060] For example, in step 312, the electronic device divides the vascular region into one or more vascular segments. The electronic device according to an embodiment may divide the vascular region to be analyzed in the medical image into one or more vascular segments. For example, the electronic device may divide the vascular region into one or more vascular segments based on vessel bifurcation. In the process of dividing the vascular region into one or more vascular segments, the vascular bifurcation excluded from the analysis target may also be used as a division criterion. For reference, the electronic device according to an embodiment may skip the determination of lesion candidates and / or lesion sites for regions corresponding to vascular bifurcation.

[0061] For example, the electronic device may determine whether to divide the vascular region into one or more vascular segments based on the vascular branch based on a diameter value of a vascular branch of a first vascular segment close to the coronary artery entrance and a diameter value of a vascular branch of a second vascular segment far from the coronary artery entrance among vascular segments adjacent to each other based on the vascular branch. The diameter value of the vascular branch of the first vascular segment is a diameter value at a position far from the coronary artery entrance in the first vascular segment, and is therefore referred to as a distal diameter value of the first vascular segment. Similarly, the diameter value of the vascular branch of the second vascular segment is referred to as a proximal diameter value of the second vascular segment.

[0062] The electronic device can determine whether to divide the first and second vessel segments into separate segments based on a difference between a distal diameter value of the first vessel segment and a proximal diameter value of the second vessel segment. The electronic device divides the first and second vessel segments based on the difference between the distal diameter value of the first vessel segment and the proximal diameter value of the second vessel segment exceeding a division threshold. The electronic device can determine that the first and second vessel segments are the same vessel segment based on the difference between the distal diameter value of the first vessel segment and the proximal diameter value of the second vessel segment being equal to or less than the division threshold.

[0063] 5, an example is shown in which the first branch 502 is used as a reference to divide the vascular region into a first intermediate segment 520 and a second intermediate segment 530, and the second branch 503 is used as a reference to divide the vascular region into a second intermediate segment 530 and a distal segment 540. If the vascular region includes a coronary artery entrance 590, the segments can be divided (e.g., the boundary of the segments can be specified) based on the coronary artery entrance 590. The same method is applied to divide the vascular region into a proximal segment 510 and a first intermediate segment 520 based on a position 501 where the left anterior descending artery (LAD) and the left circumflex artery (LCX) branch off from the left main (LM).

[0064] Next, in step 313, the electronic device calculates trend lines for one or more vessel segments. The electronic device according to an embodiment may calculate a regression line for one or more vessel segments based on a regression analysis using a prior slope. The prior slope indicates a slope set as an initial value for the regression analysis, and has a different value depending on the position where the vessel segment is placed. For example, the prior slope of a vessel segment placed at a certain position may be different from the prior slope of another vessel segment placed at another position. The electronic device may eliminate outliers selected based on the prior regression line calculated from the diameters at positions along the center line in the vessel segment. The outliers are abnormal values ​​among the diameter values. For example, the electronic device may determine, as outliers, diameter values ​​that exceed a range determined based on the prior regression line among the diameters at positions along the center line in the vessel segment. The electronic device determines, as outliers, diameter values ​​that exceed a range [value along the regression line + a * std, value along the regression line + b * std] based on the regression line (or the prior regression line). std is the standard deviation of the regression line, and a and b are real numbers that indicate weights for setting the range for determining outliers. The electronic device can calculate the regression line based on the diameter from which the outliers are excluded.

[0065] The electronic device may repeat the process of removing the outliers and calculating the regression line until the ratio of diameters determined to be outliers among diameters at positions along the centerline in the blood vessel segment is less than a threshold abnormality ratio (e.g., n%, where n is a real number greater than 0 and less than 100). The electronic device may determine the regression line showing outliers less than the threshold abnormality ratio as a first trend line for the blood vessel segment.

[0066] Then, in step 314, the electronic device determines whether or not to merge the trend lines calculated for each vessel segment of the one or more vessel segments and vessel segments adjacent to the vessel segment (e.g., the trend lines calculated in step 313 described above). The one or more vessel segments are segmented from the vessel region being analyzed in the medical image. The electronic device determines whether or not to merge the trend lines based on trend values ​​of adjacent positions relative to the vessel branch in the trend lines. The trend value of a given position (e.g., a position x mm away from the starting position) in the vessel region and / or vessel segment indicates a value along the trend line corresponding to the position (e.g., a position x mm away from the starting position) as described above.

[0067] For example, the electronic device can determine a new trend line by merging the trend line for the first vessel segment and the trend line for the second vessel segment based on the fact that a trend value for a distal position (e.g., a distal trend value) in a trend line calculated for a first vessel segment that is closer to the entrance of the coronary artery is smaller than a trend value for a proximal position (e.g., a proximal trend value) in a trend line calculated for a second vessel segment that is farther from the entrance of the coronary artery among adjacent vessel segments. The electronic device can determine a new first trend line for the vessel segment determined as the merged trend lines based on a regression analysis.

[0068] For example, in the example shown in FIG. 6, the electronic device may determine whether to merge the first trend line 639 of the second middle segment 630 and the first trend line 649 of the distal segment 640. In the example shown in FIG. 6, the trend lines 639, 649 are merged for the second middle segment 630 and the distal segment 640 because the distal trend value 631 of the second middle segment 630 is less than the proximal trend value 641 of the distal segment 640. The electronic device may also determine whether to merge based further on a difference 651 between the distal trend value 631 of the second middle segment 630 and the proximal trend value 641 of the distal segment 640. The electronic device merges the trend lines 639, 649 based on the difference 651 between the trend values ​​of the segments at the vessel branch 650 being less than a merge threshold. Conversely, the electronic device may skip merging trend lines 639, 649 based on the difference 651 between the trend values ​​exceeding a merging threshold. The electronic device determines a new first trend line 670 using the diameter value 690 belonging to the second middle segment 630 and the diameter value 690 belonging to the distal segment 640. The diameter values ​​of the vessel branches between the second middle segment 630 and the distal segment 640 are excluded from the trend line calculation.

[0069] In addition, the electronic device may determine whether or not the trend lines 639, 649 of the divided vessel segments are merged in the order of the vessel segment farthest from the entrance of the coronary artery to the vessel segment closest to the entrance of the coronary artery. In FIG. 6, a new first trend line 670 is obtained by merging the trend lines 639, 649 of the distal segment 640 farthest from the entrance of the coronary artery and the second intermediate segment 630. Then, the electronic device may determine whether or not the trend lines of the first intermediate segment 620 and the proximal segment 610 are merged.

[0070] For example, in FIG. 7, the electronic device may determine whether to merge the new first trend line 770 (e.g., the first trend line 670 merged in FIG. 6) for the second middle segment 730 and the distal segment 740 into the first middle segment 720 based on the trend value difference 751 at the vessel branch 750. In the example shown in FIG. 7, the distal trend value 721 of the trend line 729 calculated for the first middle segment 720 may be greater than the proximal trend value 731 of the new first trend line 770. The electronic device may skip the merging between the first trend line 729 calculated for the first middle segment 720 and the new first trend line 770. The electronic device may resume merging trend lines from the first middle segment 720. For example, the electronic device may determine whether to merge the trend lines of the proximal segment 710 and the first intermediate segment 720 based on a difference between a distal trend value of the trend line 719 of the proximal segment 710 and a proximal trend value of the trend line 729 of the first intermediate segment 720 relative to the vessel branch 760. Because the distal trend value of the trend line 719 of the proximal segment 710 is less than the proximal trend value of the trend line 729 of the first intermediate segment 720, the electronic device may determine a different new first trend line 780 by merging the trend lines of the proximal segment 710 and the first intermediate segment 720. As a result, in the example shown in FIG. 7 , the electronic device may obtain a new first trend line 770 merged for the second intermediate segment 730 and the distal segment 740, and a different new first trend line 780 merged for the proximal segment 710 and the first intermediate segment 720.

[0071] For reference, as shown in FIG. 8, the electronic device can determine an upper slope limit for the trend line for each vessel segment. For example, the electronic device can limit the slope of the trend line that exceeds the reference slope to the reference slope. In the example shown in FIG. 8, the reference slope can be set to 0. If the slope of the trend line 848 calculated based on the diameter value 890 for the distal segment 840 exceeds 0, the electronic device can obtain a new first trend line 849 with a slope of 0.

[0072] FIG. 9 shows an exemplary first trend line obtained based on the linear regression and trend line merging described above.

[0073] An electronic device according to an embodiment may visualize a first trend line 909 obtained as described above with reference to FIGS. 3 to 8. In the example shown in FIG. 9, the first trend line 909 may be a trend line obtained for one or more blood vessel segments. The electronic device may output the first trend line 909 via a display together with a graph for the diameter values ​​990. When visualization of the first trend line 909 is activated by a user input, the electronic device may overlay and display the first trend line 909 on the graph for the diameter values ​​990. For reference, in the graph for the diameter values ​​990, the horizontal axis indicates the distance from a start position to an individual position, and the vertical axis indicates the diameter value at each position.

[0074] FIG. 10 illustrates lesion candidate determination according to one embodiment.

[0075] An electronic device according to an embodiment may determine a lesion candidate 1020 based on the first trend line 1009 as described above in step 220 of FIG. 2. For example, the electronic device may determine a portion of a diameter value 1090 of a blood vessel region of a medical image that has a smaller diameter than a value obtained by applying a first ratio to the first trend line 1009 as the lesion candidate 1020. Exemplarily, the first ratio may be a real number greater than 0 and less than 1, and the electronic device may determine a portion corresponding to a position having a diameter value equal to or smaller than the line 1010 obtained by multiplying the first trend line 1009 by the first ratio as the lesion candidate 1020. In FIG. 10, the first ratio is shown to be the same value for the entire region, but is not limited thereto. For reference, the electronic device may visualize the lesion candidate 1020 together with a graph of the diameter value 1090.

[0076] 11 to 14 explain the setting of reference points and the acquisition of a second trend line according to one embodiment.

[0077] In step 1131, the electronic device (e.g., electronic device 100 of FIG. 1) selects local peaks around the lesion candidate that have values ​​greater than the first trend line as reference points. The electronic device selects local peaks around the lesion candidate that have values ​​greater than the first trend line as reference points. For example, in the example shown in FIG. 12, the electronic device may select local peaks 1211, 1212, 1221, 1222, 1231 that have values ​​equal to or greater than the first trend line 1209 as reference points. As described above, the portion of the diameter value 1290 that is equal to or less than the first trend line 1209 may be determined to be the lesion candidates 1210, 1220 as described above. For each lesion candidate, reference points adjacent to the coronary artery entrance are shown as first reference points 1211, 1221, 1231 (eg, proximal reference points), and reference points further from the coronary artery entrance are shown as second reference points 1212, 1222 (eg, distal reference points).

[0078] As shown in FIG. 12, a pair of reference points must be detected for each lesion candidate, but only one reference point may be detected for some lesion candidates. For example, the electronic device may exclude a lesion candidate for which at least one of the first reference point close to the entrance of the coronary artery and the second reference point far from the entrance of the coronary artery is not detected from the lesion site determination. However, without being limited thereto, the electronic device may re-search for a reference point based on a line (not shown) obtained by decreasing the first trend line 1209 when some reference points are not searched for in the anterior-posterior region of the lesion candidate. For example, the electronic device may attempt to re-detect a local peak based on a value obtained by applying a threshold local ratio to the first trend line 1209 based on the fact that at least one of the first reference point close to the entrance of the coronary artery and the second reference point far from the entrance of the coronary artery (e.g., the distal reference point paired with the first reference point 1231 in FIG. 12) is not detected around the lesion candidate. The threshold local ratio may be a real number greater than 0 and less than 1. The electronic device can detect local peaks higher than a line (not shown) obtained by multiplying the first trend line 1209 by a threshold local ratio, in which case lesion candidates that still fail local peak detection can be excluded from determining the lesion site.

[0079] Then, in step 1132, the electronic device determines a reference point 1322 based on the first trend line when the local peak exceeds a value corresponding to a threshold reference ratio. For example, the electronic device may select a point at which a value corresponding to a diameter of the vascular region is shown among values ​​at which a threshold reference ratio (e.g., K, where K is a real number equal to or greater than 1) is applied to the first trend line based on the local peak exceeding a value at which a threshold reference ratio (e.g., K, where K is a real number equal to or greater than 1) is applied to the first trend line as the reference point 1322. In the example shown in FIG. 13 , the electronic device can detect a local peak 1321 on a first trend line 1309, and if a difference 1329 between the local peak 1321 and the first trend line 1309 exceeds a threshold, the electronic device can set another point as the reference point 1322 instead of the local peak 1321. For example, the electronic device can select as the reference point 1322 the point where the line 1310 intersects with the graph corresponding to the diameter value 1390 based on the local peak 1321 being higher than the line 1310 obtained by multiplying the first trend line by a threshold reference ratio.

[0080] Next, in step 1133, the electronic device obtains a second trend line 1450 by connecting the reference points for each lesion candidate. For example, as shown in FIG. 14, the electronic device can obtain a second trend line 1450 by connecting the first reference points 1411, 1421 and the second reference points 1412, 1422 for each lesion candidate. In step 1131, as described above, the second trend line 1450 is generated only for pairs of reference points, and the generation of the second trend line and the determination of the lesion site are excluded for a reference point where one of the proximal and distal reference points is missing (e.g., reference point 1431 in FIG. 14).

[0081] The electronic device according to an embodiment may visualize the acquired reference points and the second trend line as described above. For example, the electronic device may visualize at least one of the reference points and the second trend line by overlaying them on a graph for the diameter value 1490. The electronic device may output, using a display, a graphic representation corresponding to an item of the reference points and the second trend line that is activated by a user's input, together with the graph for the diameter value.

[0082] 15 and 16 illustrate the determination of lesion location according to one embodiment.

[0083] FIG. 15 explains the operation of determining a lesion site from among lesion candidates.

[0084] An electronic device according to an embodiment (e.g., electronic device 100 of FIG. 1) may determine a lesion location from a lesion candidate based on a second trend line as described in step 240 shown in FIG. 2. For example, the electronic device may determine, as a lesion location, a region corresponding to a lesion candidate that has a diameter smaller than a value obtained by applying a second ratio to the second trend line. In the example shown in FIG. 15, the electronic device may determine, as a lesion location 1580, a portion that is lower than lines 1561 and 1562 obtained by applying a second ratio to second trend lines 1551 and 1552. The second ratio (e.g., m) may be a real number greater than 0 and less than 1, and may have different values ​​for each lesion candidate and / or position. For example, in FIG. 15, the second ratio is illustrated as having the same value for the second trend line 1551 for the first lesion candidate and the second trend line 1552 for the second lesion candidate, but is not limited thereto. For example, the electronic device may determine the second ratio based on a value at a corresponding point on the first trend line. The electronic device may set the second ratio value applied to the second lesion candidate located distally relative to the entrance of the coronary artery to be smaller than the second ratio value applied to the first lesion candidate located proximally. For example, the electronic device may apply a second ratio value of 0.7 to the first lesion candidate located proximally and a second ratio value of 0.5 (or 0.3) to the second lesion candidate located distally. In other words, it can be understood that the lesion location is determined relatively conservatively for the first lesion candidate located proximally compared to the second lesion candidate located distally. The electronic device may also visualize the second trend lines 1551, 1552 together with a graph of the diameter value 1590.

[0085] FIG. 16 explains the operation of determining whether adjacent lesion sites are to be recognized as one lesion.

[0086] An electronic device according to an embodiment (e.g., electronic device 100 in FIG. 1) determines that lesion sites 1681, 1682 are included in the same lesion based on the fact that lesion sites 1681, 1682 determined based on second trend line 1651 are detected below the first trend line. In the example shown in FIG. 16, two lesion sites 1681, 1682 may be detected for one lesion candidate below line 1652 obtained by applying a second ratio to second trend line 1651. In this case, the electronic device determines that the two lesion sites 1681, 1682 are one lesion based on the fact that a local peak shown in the intermediate region between them is smaller than the first trend line.

[0087] As another example, when multiple lesion candidates are adjacent to each other, the electronic device determines whether to determine the multiple lesion candidates and intermediate regions as a single lesion site based on a ratio between the maximum diameter value and a value (e.g., a first trend value) of diameter values ​​1690 in an intermediate region between the multiple lesion candidates along a first trend line at a point corresponding to the maximum diameter value. For example, in the example shown in FIG. 16, the electronic device may extract the maximum diameter value of diameter values ​​1690 in an intermediate region between a first lesion site 1681 and a second lesion site 1682. The electronic device may determine that the two lesion sites 1681, 1682 are included in the same lesion based on the ratio between the extracted maximum diameter value and the first trend value at the position being within a predetermined range (e.g., a range including 1). The closer the ratio between the extracted maximum diameter value and the first trend value at the position is to 1, the more likely it is that the two lesion sites 1681, 1682 are included in the same lesion.

[0088] As another example, the electronic device may determine whether adjacent candidates among the plurality of lesion candidates belong to the same lesion based on the distance between the adjacent candidates. When the plurality of lesion candidates are adjacent to each other, the electronic device may determine that the adjacent candidates are to be merged if the distance between the plurality of lesion candidates is less than a predetermined value. For example, the electronic device may determine that the two lesion candidates are to be merged into one lesion if the distance between the two lesion candidates is less than 15 mm. Here, the predetermined value may be a value equal to or less than 15 mm, but is not limited thereto, and the predetermined value may vary according to a user setting.

[0089] In one embodiment, the electronic device can select at least one of the first trend line 1609, the lesion candidates, the reference points, the second trend line 1651 based on the reference points, and the lesion sites 1681, 1682 determined based on the second trend line based on user input and visualize a graphical representation corresponding to the selected item using a display along with a graph of the diameter value 1690.

[0090] The embodiments described above may be implemented using hardware components, software components, or a combination of hardware and software components. For example, the devices and components described herein may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or other devices that execute and respond to instructions. The processing device executes an operating system (OS) and one or more software applications that run on the operating system. The processing device also accesses, stores, manipulates, processes, and generates data in response to the execution of the software. For ease of understanding, the processing device may be described as being one in which only one processing device is used, but one skilled in the art will appreciate that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, the processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0091] Software may include computer programs, codes, instructions, or a combination of one or more thereof, capable of configuring or instructing a processing device to operate as desired, either independently or in combination. The software and / or data may be embodied in any type of machine, component, physical device, virtual device, computer storage medium or device, or transmitted signal wave, either permanently or temporarily, to be interpreted by the processing device or to provide instructions or data to the processing device. The software may be distributed over computer systems coupled to a network, and may be stored and executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

[0092] The method according to the present invention may be embodied in the form of program instructions to be executed by various computer means and recorded on a computer-readable recording medium. The recording medium may include program instructions, data files, data structures, and the like, alone or in combination. The recording medium and the program instructions may be specially designed and constructed for the purposes of the present invention, or may be well known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, flash memories, and the like. Examples of program instructions include not only machine language code, such as that generated by a compiler, but also high-level language code executed by a computer using an interpreter, etc.

[0093] The hardware devices described above may be configured to operate as one or more software modules to perform the operations illustrated in the present invention, and vice versa.

[0094] Although the embodiments have been described above with reference to limited drawings, those skilled in the art may apply various technical modifications and variations based on the above description. For example, the described techniques may be performed in a different order than described, and / or the components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different form than described, and may be replaced or substituted with other components or equivalents to achieve appropriate results.

[0095] Accordingly, other implementations, embodiments, and equivalents of the claims are intended to be within the scope of the following claims.

Claims

1. 1. A method of lesion determination performed by a processor, comprising: obtaining a first trendline for vessel diameter from a medical image; determining a lesion candidate among the blood vessels based on the first trend line; obtaining a second trend line based on reference points selected from a periphery of the suspected lesion; determining a lesion site among the lesion candidates based on the acquired second trend line; A method for determining a lesion, comprising:

2. The step of obtaining the first trend line includes: Segmenting one or more vessel segments from a vessel region of interest in the medical image; determining whether trend lines calculated for each of the one or more vessel segments and adjacent vessel segments to the one or more vessel segments merge; The method of claim 1 , comprising:

3. The step of dividing the vascular region into one or more vascular segments comprises dividing the vascular region into the one or more vascular segments based on vascular branches; The step of determining whether or not trend lines are merged comprises: calculating the trend line for the one or more vessel segments; determining whether the trend lines are merged based on diameter values ​​of adjacent positions of the trend lines with respect to the blood vessel branch; The method of claim 2 , comprising:

4. 4. The lesion determination method according to claim 3, wherein the step of dividing into one or more blood vessel segments includes a step of determining whether or not to divide the blood vessel region into the one or more blood vessel segments based on the blood vessel branch based on a diameter value at the blood vessel branch of a first blood vessel segment that is close to an entrance of a coronary artery and a diameter value at the blood vessel branch of a second blood vessel segment that is far from the entrance of the coronary artery, among blood vessel segments adjacent to each other based on the blood vessel branch.

5. 3. The method for determining lesions according to claim 2, wherein the step of determining whether or not the trend lines are merged includes a step of determining a new trend line by merging the trend line for the first vascular segment and the trend line for the second vascular segment based on the fact that a diameter value at a distal position of a trend line calculated for a first vascular segment close to an entrance of a coronary artery is smaller than a diameter value at a proximal position of a trend line calculated for a second vascular segment far from the entrance of the coronary artery.

6. 2. The lesion determination method according to claim 1, wherein the step of determining the lesion candidate includes a step of determining, as the lesion candidate, a portion of a vascular region of the medical image that has a diameter smaller than a value obtained by applying a first ratio to the first trend line.

7. 2. The method of claim 1, wherein the step of obtaining a second trend line based on reference points selected from around the lesion candidate comprises the step of selecting local peaks in the periphery of the lesion candidate that have a value greater than the first trend line as the reference points.

8. 8. The method of claim 7, wherein the step of selecting as the reference point comprises the step of selecting as the reference point a point at which a value corresponding to a diameter of the vascular region is shown among values ​​obtained by applying a threshold reference ratio to the first trend line, based on the local peak exceeding a value obtained by applying a threshold reference ratio to the first trend line.

9. 2. The lesion determination method according to claim 1, wherein the step of determining the lesion site includes a step of determining, as the lesion site, a region of the region corresponding to the lesion candidate that has a diameter smaller than a value obtained by applying a second ratio to the second trend line.

10. 2. The method of claim 1, wherein the step of determining the lesion area includes a step of determining whether to determine the multiple lesion candidates and the intermediate region as a single lesion area based on a ratio between a maximum diameter value among diameter values ​​in an intermediate region between the multiple lesion candidates and a value along the first trend line at a point corresponding to the maximum diameter value, when the multiple lesion candidates are adjacent to each other.

11. 2. The method of claim 1, wherein the step of determining the lesion site includes a step of determining to merge adjacent candidates if the distance between the multiple lesion candidates is less than a predetermined value when the multiple lesion candidates are adjacent to each other.

12. 1. An electronic device comprising: an image acquisition unit for acquiring medical images; a display for outputting the medical image; A memory for storing computer executable instructions; a processor for executing the instructions stored in the memory; Including, the command is configured to output, via the display, at least one of a first trend line relating to a global trend of blood vessel diameter for each of a plurality of blood vessel segments divided from a blood vessel included in the medical image, a reference point located above the first trend line, a second trend line relating to a local trend of the blood vessel diameter determined based on the reference point, and a lesion site located below the second trend line together with the medical image.

Images