Blood vessel labeling verification method and device based on SYNTAX labeling specification, terminal and medium

Abstract

The invention provides a blood vessel labeling verification method and device based on SYNTAX labeling specifications, a terminal and a medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring coronary blood vessel labeling information input by a user; wherein the coronary blood vessel labeling information comprises endpoint coordinates and length of each blood vessel segment on the coronary blood vessel; based on a radiography machine position corresponding to the coronary blood vessel labeling information, determining a segment connection rule suitable for the coronary blood vessel labeling information; wherein the segment connection rule is a coronary artery segment connection logic and sequence defined based on anatomy, and comprises one or more of segment continuity, segment relative position and segment length; and based on the endpoint coordinates and the length of each blood vessel segment, judging whether the coronary blood vessel labeling information accords with a segment connection rule or not, and obtaining a verification result of the coronary blood vessel labeling information. According to the method, the blood vessel labeling completed by a doctor can be logically verified, and the accuracy of coronary blood vessel examination labeling can be improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a blood vessel annotation verification method, device, terminal and medium based on SYNTAX annotation specification. Background Art

[0002] In the diagnosis of coronary artery lesions, the SYNTAX (SYNergy between PCI with TAXUS and Cardiac Surgery) score is a commonly used quantitative standard for assessing the severity of coronary artery lesions. The SYNTAX score divides the coronary vessels into multiple segments, and different segments correspond to specific medical anatomical structures. Due to the different locations of the lesions, the impact of the same lesion on the patient may be significantly different. Therefore, in coronary image analysis, semantic segmentation of the vessels is the basis for subsequent analysis, and accurate vessel annotation is the key to achieving this segmentation.

[0003] With the advancement of technology, many hospitals now use computer-aided systems for vascular annotation. Computer-aided systems can automatically detect vascular boundaries, calculate the percentage of stenosis, and provide data on changes in vascular diameter. They can also automatically generate quantitative indicators such as SYNTAX scores. However, current computer-aided systems mainly use image processing technology to improve the accuracy of vascular segmentation and boundary detection, and use pattern recognition technology to identify vascular structures and their lesion characteristics in vascular images. When doctors manually annotate coronary images, there may be errors such as order, position, and deviation. The current computer-aided system only performs image processing and is difficult to identify the above errors in the vascular annotations completed by doctors. Summary of the invention

[0004] The embodiment of the present invention provides a blood vessel annotation verification method, device, terminal and medium based on the SYNTAX annotation specification to solve the problem of verifying blood vessel annotation.

[0005] In a first aspect, an embodiment of the present invention provides a blood vessel annotation verification method based on the SYNTAX annotation specification, comprising: Acquire the coronary vessel annotation information input by the user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel; Based on the angiography position corresponding to the coronary vessel annotation information, determining the segment connection rule applicable to the coronary vessel annotation information; wherein the segment connection rule is the connection logic and sequence between coronary segments based on the anatomical definition, including one or more of segment continuity, segment relative position and segment length; Based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained.

[0006] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the distance between the coordinates of the end point of the first segment and the coordinates of the start point of the second segment is less than a preset distance threshold, it is determined that the first segment and the second segment are connected in sequence; wherein the first segment and the second segment are different vascular segments.

[0007] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the distances between the coordinates of the ending point of the third segment, the coordinates of the starting point of the fourth segment, and the coordinates of the starting point of the fifth segment are all less than the preset distance threshold, the starting point of the fifth segment is determined to be the dividing point between the third segment and the fourth segment; wherein the third segment, the fourth segment, and the fifth segment are different vascular segments.

[0008] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the midpoint of the sixth segment is located below and to the left of the midpoint of the seventh segment, it is determined that the seventh segment intersects the diagonal line from the upper right to the lower left of the coronary angiography image before the sixth segment; wherein the sixth segment and the seventh segment are different vascular segments.

[0009] In a possible implementation, when the angiography position is the left coronary left shoulder position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5, 6, and 7 are connected in sequence, the starting point of segment 9 is the dividing point between segment 6 and segment 7, and the starting point of segment 10 is the dividing point between segment 7 and segment 8; If segment 10 does not exist, the difference between the lengths of segment 7 and segment 8 is less than a preset difference threshold; If segment 9 and segment 9a exist, segment 9 intersects the diagonal line from the upper right to the lower left of the coronary angiography image before segment 9a.

[0010] In a possible implementation, when the angiography position is the left coronary left foot position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5 , 11 , and 13 are connected in sequence. The starting point of segment 12 is the dividing point between segment 5 and segment 11 , and the starting point of segment 12a is the dividing point between segment 11 and segment 13 .

[0011] In a possible implementation, when the angiography position is the right coronary left oblique anterior position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 1, 2, 3, and 4 are connected in sequence, and segments 3 and 16 are connected in sequence.

[0012] In a second aspect, an embodiment of the present invention provides a blood vessel annotation verification device based on the SYNTAX annotation specification, comprising: An acquisition module is used to acquire the coronary vessel annotation information input by the user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel; A determination module is used to determine the segment connection rule applicable to the coronary vessel annotation information based on the angiography machine position corresponding to the coronary vessel annotation information; wherein the segment connection rule is the connection logic and sequence between coronary segments based on anatomical definition, including one or more of segment continuity, segment relative position and segment length; The verification module is used to determine whether the coronary vessel labeling information complies with the segment connection rules based on the endpoint coordinates and length of each vascular segment, and obtain the verification result of the coronary vessel labeling information.

[0013] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0015] The embodiment of the present invention provides a vascular annotation verification method, device, terminal and medium based on the SYNTAX annotation specification. In combination with the angiography position, an appropriate segment connection rule is selected to verify the coronary vascular annotation information. Through the continuity, relative position and length between the vascular segments, it is judged whether the coronary vascular annotation information conforms to the specific connection relationship and medical specifications of the segments in the SYNTAX annotation specification, so as to realize logical verification of the vascular annotation completed by the doctor, and improve the accuracy of the coronary vascular examination annotation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 is a flow chart of an implementation of a blood vessel annotation verification method based on the SYNTAX annotation specification provided by an embodiment of the present invention; Figure 2A is a schematic diagram of left coronary artery annotation information based on the SYNTAX annotation specification provided by an embodiment of the present invention; Figure 2B is a schematic diagram of right coronary artery annotation information based on the SYNTAX annotation specification provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a blood vessel annotation verification device based on the SYNTAX annotation specification provided by an embodiment of the present invention; Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0020] The method provided by the present invention is mainly suitable for verifying the vascular annotation of digital subtraction angiography (DSA) images. CT is a static tomography technology based on X-rays, while DSA is a dynamic imaging technology, which is mainly used to observe the condition of the heart arteries during interventional surgery. This difference determines that DSA has unique advantages in evaluating blood flow conditions and identifying the degree of stenosis, and is particularly suitable for surgical navigation and treatment decisions. The basic principle of DSA is to digitally input two frames of X-ray images taken before and after the injection of contrast agent into an image computer, and obtain clear pure vascular images through subtraction, enhancement and re-imaging processes, while showing vascular shadows in real time. DSA has the advantages of high contrast resolution, short examination time, small amount of contrast agent, low concentration, significantly reduced patient X-ray absorption, and film saving. It is of great significance in the clinical diagnosis of vascular diseases.

[0021] DSA focuses on observing vascular stenosis rather than plaques like CT does. Multiple stenosis sites may constitute a lesion, which is crucial for accurately assessing the condition. Lesions in different locations affect blood flow in different ways, so it is necessary to anatomically segment the coronary vessels and give different coefficients according to the specific location to calculate the SYNTAX score and determine its impact on health.

[0022] In medical diagnosis and when generating training data for the coronary vessel segmentation model, DSA images need to be manually segmented based on the SYNTAX annotation specifications. However, due to the subjectivity of doctors when marking the location of DSA image segments, changes in heart size, and individual differences, accurate labeling becomes difficult. By setting clear specifications, consistency and accuracy can be ensured even in complex or abnormal cases. By screening the training images in this way and performing data post-processing on the output of the segmentation model, better automated segmentation and annotation effects can be achieved.

[0023] Accurately locating and identifying key points in blood vessels is of great importance for 3D reconstruction and possible future surgical navigation technology. DSA not only helps doctors understand the specific condition of the patient's heart more intuitively, but also provides valuable data support for future surgical planning. By accurately capturing these key points, more accurate 3D reconstruction of the heart can be achieved, thereby improving the success rate of surgery.

[0024] The vascular annotation verification method based on the SYNTAX annotation specification provided by the present invention is used to constrain data during data preprocessing, training, and post-processing to improve model performance. This includes using pre-processing or post-processing algorithms to correct recognition results to ensure the consistency and reliability of model output. In this way, not only can the learning effect of the AI ​​model be optimized, but also more scientific support can be provided for clinical decision-making.

[0025] In summary, verifying DSA images based on the SYNTAX annotation specification is not only necessary, but also a key step in promoting the development of medical image analysis to a higher level of accuracy. It helps to overcome the limitations of existing technologies and provide strong technical support for the design of personalized medical solutions.

[0026] See also Figure 1 , which shows a flow chart of the implementation of the blood vessel annotation verification method based on the SYNTAX annotation specification provided by an embodiment of the present invention, and is described in detail as follows: Step 101, obtaining coronary vessel annotation information input by a user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel.

[0027] In this embodiment, when annotating the coronary vessels, the basic steps of medical annotation are as follows: 1. Vessel outline marking: The doctor first marks the overall outline of the blood vessel.

[0028] 2. Vessel centerline marking: The doctor marks the centerline of the blood vessel within the outline.

[0029] 3. Segment labeling.

[0030] After the labeling is completed, the endpoint coordinates of each labeled vascular segment can be obtained, and then the following information of each segment can be extracted: (1) The starting and ending points of the segment; (2) The length of the segment.

[0031] With this information, a Segment class can be defined, which contains the following properties and methods to describe the coronary vessel annotation information and to perform verification: class Segment: def __init__(self, start_x, start_y, end_x, end_y, length): self.start_x = start_x # Starting point x coordinate self.start_y = start_y# Starting point y coordinate self.end_x = end_x # End point x coordinate self.end_y = end_y# End point y coordinate self.length = length# segment length def midpoint(self): """Calculate the coordinates of the midpoint of the segment""" mid_x = (self.start_x + self.end_x) / 2 mid_y = (self.start_y + self.end_y) / 2 return (mid_x, mid_y) Step 102, based on the angiography machine position corresponding to the coronary vessel annotation information, determine the segment connection rule applicable to the coronary vessel annotation information; wherein the segment connection rule is the connection logic and sequence between coronary segments based on the anatomical definition, including one or more of segment continuity, segment relative position and segment length.

[0032] In this embodiment, in order to ensure the accuracy of the annotation, the annotation results need to be automatically checked according to the SYNTAX specification. Different camera positions have sections to be observed, corresponding to corresponding section rules and processes.

[0033] The premise of verification based on a certain rule is that all segments involved in the rule exist, and users can add or subtract segments based on their understanding of the medical structure based on these basic rules.

[0034] Step 103, based on the endpoint coordinates and length of each vascular segment, determine whether the coronary vessel labeling information complies with the segment connection rule, and obtain a verification result of the coronary vessel labeling information.

[0035] In this embodiment, point distance check operators, point position check operators and length check operators can be defined to compare and analyze the distances, positional relationships and lengths between the endpoints of each vascular segment, and these operators can be called according to specific segment connection rules to determine whether the coronary vessel annotation information complies with the SYNTAX specification.

[0036] The embodiment of the present invention combines the angiography position and selects appropriate segment connection rules to verify the coronary vessel annotation information. Through the continuity, relative position and length between the vessel segments, it is judged whether the coronary vessel annotation information conforms to the specific connection relationship of the segments and the medical specifications in the SYNTAX annotation specification, thereby achieving logical verification of the vessel annotations completed by the doctor, and improving the accuracy of the coronary vessel examination annotations.

[0037] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the distance between the coordinates of the end point of the first segment and the coordinates of the start point of the second segment is less than a preset distance threshold, it is determined that the first segment and the second segment are connected in sequence; wherein the first segment and the second segment are different vascular segments.

[0038] In this embodiment, the specific information of the point distance check operator Distance (point1_x, point1_y, point2_x, point2_y, threshold) is as follows: enter: point1_x, point1_y: x and y of the first point point2_x, point2_y: x and y of the second point threshold: distance threshold Output: Return True if the Euclidean distance between two points is less than or equal to threshold. Return False: if the distance between two points>threshold Specific implementation logic: Specific implementation logic: def Distance(point1_x, point1_y,point2_x, point2_y, threshold): distance = ((point1_x - point2_x)**2 + (point1_y - point2_y)**2)**0.5 return distance<= threshold function: used to verify whether the connection between two adjacent segments meets the expected anatomical distance.

[0039] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the distances between the coordinates of the ending point of the third segment, the coordinates of the starting point of the fourth segment, and the coordinates of the starting point of the fifth segment are all less than the preset distance threshold, the starting point of the fifth segment is determined to be the dividing point between the third segment and the fourth segment; wherein the third segment, the fourth segment, and the fifth segment are different vascular segments.

[0040] In this embodiment, the point distance check operator can also judge the distance between three points. For example, when the angiography position is the left coronary and left shoulder position, the verification rules involved include: the starting point of segment 9 should be the dividing point between segment 6 and segment 7. At this time, the point distance check operator needs to be called to determine whether the distances between the starting point of segment 9, the end point of segment 6, and the starting point of segment 7 are all less than or equal to the threshold. If they meet the requirements, the verification is passed.

[0041] In a possible implementation, based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained, including: If the midpoint of the sixth segment is located below and to the left of the midpoint of the seventh segment, it is determined that the seventh segment intersects the diagonal line from the upper right to the lower left of the coronary angiography image before the sixth segment; wherein the sixth segment and the seventh segment are different vascular segments.

[0042] In this embodiment, the specific information of the point location verification operator Location(segment1, segment2) is as follows: enter: segment1: the first segment object segment2: the second segment object Output: Returns True if the midpoint of segment2 is below and to the left of the midpoint of segment1 Return False: if the midpoint of segment2 is above and to the right of the midpoint of segment1. Specific implementation logic: def Location(segment1, segment2): mid1_x, mid1_y = segment1.midpoint() mid2_x, mid2_y = segment2.midpoint() return not (mid2_x>mid1_x and mid2_y>mid1_y) Function: Determine the relative position of adjacent segments and ensure that the anatomy of the marked segments complies with the SYNTAX rules.

[0043] In a possible implementation, when the angiography position is the left coronary left shoulder position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5, 6, and 7 are connected in sequence, the starting point of segment 9 is the dividing point between segment 6 and segment 7, and the starting point of segment 10 is the dividing point between segment 7 and segment 8; If segment 10 does not exist, the difference between the lengths of segment 7 and segment 8 is less than a preset difference threshold; If segment 9 and segment 9a exist, segment 9 intersects the diagonal line from the upper right to the lower left of the coronary angiography image before segment 9a.

[0044] In this embodiment, see Figure 2A , Figure 2B The correspondence between the segment numbers and names of the coronary artery segments is shown in Table 1.

[0045] Table 1

[0046] Length check operator Length(segment1, segment2, threshold) enter: segment1: the first segment object segment2: the second segment object threshold: length difference threshold Output: Return True: if the difference between the lengths of two segments is ≤ threshold Returns False: if the length difference > threshold Specific implementation logic: def Length(segment1, segment2, threshold): length_diff = abs(segment1.length - segment2.length) return length_diff<= threshold Function: Used to verify whether the lengths of adjacent segments are as expected.

[0047] The rules and procedures for left crown and left shoulder position verification are as follows: Verification rules: 1. Segment connection rules: (1) The end point of segment 5 should be the starting point of segment 6, the end point of segment 6 should be the starting point of segment 7, and the end point of segment 7 should be the end point of segment 8.

[0048] (2) The starting point of segment 9 should be the dividing point between segments 6 and 7.

[0049] (3) The starting point of segment 10 should be the dividing point between segments 7 and 8.

[0050] (4) If segment 10 does not exist, the lengths of segments 7 and 8 should be similar.

[0051] 2. Special Rules If there are two branches that may be 9 / 9a in the figure, then by drawing a diagonal line from the upper right to the lower left, the branch that intersects with the diagonal line first is segment 9, and the branch that intersects with the diagonal line later is segment 9a.

[0052] Automatic marking inspection process: 1. Segment connection rule verification (1) Continuity check of segments 5, 6, 7, and 8 The rules require: The end point of segment 5 should be the start point of segment 6; The end point of segment 6 should be the start point of segment 7; The end point of segment 7 should be the end point of segment 8.

[0053] Verification steps: For segments 5 and 6, the point distance check operator Distance(segment5.end_x,segment5.end_y,segment6.start_x,segment6.start_y,threshold) is called to determine whether the distance between the end point of segment 5 and the start point of segment 6 is less than or equal to the threshold threshold to verify the anatomical rationality of their connection.

[0054] For segment 6 and segment 7, and segment 7 and segment 8, repeat the above steps, and check the connection relationship between adjacent segments one by one to ensure continuity.

[0055] (2) Verification of the starting points of segments 9 and 10 The rules require: The starting point of segment 9 should be the dividing point between segments 6 and 7; The starting point of segment 10 should be the dividing point between segments 7 and 8.

[0056] Verification steps: The distances between the start point of segment 9, the end point of segment 6, and the start point of segment 7 must all be less than or equal to the threshold threshold. Call the operators Distance(segment6.end_x,segment6.end_y, segment7.start_x,segment7.start_y,threshold), Distance(segment6.end_x,segment6.end_y,segment9.start_x,segment9.start_y, threshold), Distance(segment7.start_x,segment7.start_y, segment9.start_x,segment9.start_y, threshold) The distances between the start point of segment 10, the end point of segment 7, and the start point of segment 8 must all be less than or equal to the threshold value.

[0057] (4) Verification when segment 10 does not exist The rules require: If segment 10 is not present, segments 7 and 8 should be similar in length.

[0058] Verification steps: Call the length check operator Length(segment7, segment8, threshold) to verify whether the length difference between segment 7 and segment 8 is less than or equal to the threshold threshold.

[0059] 2. Special rule verification (1) Branch verification of segments 9 and 9a The rules require: If there are two branches that may be 9 / 9a in the figure, then by drawing a diagonal line from the upper right to the lower left, the branch that intersects with the diagonal line first is segment 9, and the branch that intersects with the diagonal line later is segment 9a.

[0060] Verification steps: If 9 and 9a exist in the doctor's annotation, call Location(segment9a, segment9) to check whether it meets the rules.

[0061] In a possible implementation, when the angiography position is the left coronary left foot position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5 , 11 , and 13 are connected in sequence. The starting point of segment 12 is the dividing point between segment 5 and segment 11 , and the starting point of segment 12a is the dividing point between segment 11 and segment 13 .

[0062] In this embodiment, the left crown foot position verification rules and procedures are as follows: Segment connection rules: (1) The end point of segment 5 should be the start point of segment 11, and the end point of segment 11 should be the start point of segment 13.

[0063] (2) The starting point of segment 12 should be the dividing point between segments 5 and 11.

[0064] (3) The starting point of segment 12a should be the dividing point between segments 11 and 13.

[0065] Annotation automatic inspection process Segment connection rule verification (1) Continuity check of segments 5, 11, and 13 The rules require: The end point of segment 5 should be the start point of segment 11; The end point of segment 11 should be the start point of segment 13.

[0066] Verification steps: For segments 5 and 11, the point distance check operator Distance(segment5.end_x,segment5.end_y,segment11.start_x,segment11.start_y, threshold) is called to determine whether the distance between the end point of segment 5 and the start point of segment 11 is less than or equal to the threshold threshold to verify the anatomical rationality of their connection.

[0067] Repeat the above steps for segments 11 and 13.

[0068] (2) Verification of the starting point of segments 12 and 12a The rules require: The starting point of segment 12 should be the dividing point between segments 5 and 11; The starting point of segment 12a should be the dividing point between segment 11 and segment 13.

[0069] Verification steps: The distances between the end point of segment 5, the start point of segment 11, and the start point of segment 12 must all be less than or equal to the threshold threshold. Call the operators Distance(segment5.end_x,segment5.end_y, segment11.start_x,segment11.start_y,threshold), Distance(segment5.end_x,segment5.end_y,segment12.start_x,segment12.start_y, threshold), Distance(segment11.start_x,segment11.start_y, segment12.start_x,segment12.start_y, threshold) The distances between the end point of segment 11, the start point of segment 13, and the start point of segment 12a must all be less than or equal to the threshold value.

[0070] In a possible implementation, when the angiography position is the right coronary left oblique anterior position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 1, 2, 3, and 4 are connected in sequence, and segments 3 and 16 are connected in sequence.

[0071] In this embodiment, the right crown left anterior oblique position verification rules and procedures are as follows: Segment connection rules: (1) The end point of segment 1 should be the starting point of segment 2, the end point of segment 2 should be the starting point of segment 3, and the end point of segment 3 should be the starting point of segment 4.

[0072] (2) The end point of segment 3 should be the starting point of segment 16.

[0073] Automatic marking inspection process: Segment connection rule verification Continuity check of segments 1, 2, 3, 4, 16 The rules require: The end point of segment 1 should be the start point of segment 2; The end point of segment 2 should be the start point of segment 3; The end point of segment 3 should be the start point of segment 4; The end point of segment 3 should be the start point of segment 16; Verification steps: For segments 1 and 2, the point distance check operator Distance(segment1.end_x,segment1.end_y,segment2.start_x,segment2.start_y, threshold) is called to determine whether the distance between the end point of segment 1 and the start point of segment 2 is less than or equal to the threshold threshold to verify the anatomical rationality of their connection.

[0074] Repeat the above steps for segments 2 and 3, segments 3 and 4, and segments 3 and 16.

[0075] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0076] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0077] Figure 3 The structure diagram of the blood vessel annotation verification device based on the SYNTAX annotation specification provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows: like Figure 3 As shown, the blood vessel annotation verification device 3 based on the SYNTAX annotation specification includes: The acquisition module 31 is used to acquire the coronary vessel annotation information input by the user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel; A determination module 32 is used to determine the segment connection rule applicable to the coronary vessel annotation information based on the angiography machine position corresponding to the coronary vessel annotation information; wherein the segment connection rule is the connection logic and sequence between coronary segments based on anatomical definition, including one or more of segment continuity, segment relative position and segment length; The verification module 33 is used to determine whether the coronary vessel labeling information complies with the segment connection rule based on the endpoint coordinates and length of each vessel segment, and obtain the verification result of the coronary vessel labeling information.

[0078] In a possible implementation, the verification module 33 is specifically used to: If the distance between the coordinates of the end point of the first segment and the coordinates of the start point of the second segment is less than a preset distance threshold, it is determined that the first segment and the second segment are connected in sequence; wherein the first segment and the second segment are different vascular segments.

[0079] In a possible implementation, the verification module 33 is specifically used to: If the distances between the coordinates of the ending point of the third segment, the coordinates of the starting point of the fourth segment, and the coordinates of the starting point of the fifth segment are all less than the preset distance threshold, the starting point of the fifth segment is determined to be the dividing point between the third segment and the fourth segment; wherein the third segment, the fourth segment, and the fifth segment are different vascular segments.

[0080] In a possible implementation, the verification module 33 is specifically used to: If the midpoint of the sixth segment is located below and to the left of the midpoint of the seventh segment, it is determined that the seventh segment intersects the diagonal line from the upper right to the lower left of the coronary angiography image before the sixth segment; wherein the sixth segment and the seventh segment are different vascular segments.

[0081] In a possible implementation, when the angiography position is the left coronary left shoulder position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5, 6, and 7 are connected in sequence, the starting point of segment 9 is the dividing point between segment 6 and segment 7, and the starting point of segment 10 is the dividing point between segment 7 and segment 8; If segment 10 does not exist, the difference between the lengths of segment 7 and segment 8 is less than a preset difference threshold; If segment 9 and segment 9a exist, segment 9 intersects the diagonal line from the upper right to the lower left of the coronary angiography image before segment 9a.

[0082] In a possible implementation, when the angiography position is the left coronary left foot position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 5 , 11 , and 13 are connected in sequence. The starting point of segment 12 is the dividing point between segment 5 and segment 11 , and the starting point of segment 12a is the dividing point between segment 11 and segment 13 .

[0083] In a possible implementation, when the angiography position is the right coronary left oblique anterior position, the segment connection rules applicable to the coronary vessel annotation information include: Segments 1, 2, 3, and 4 are connected in sequence, and segments 3 and 16 are connected in sequence.

[0084] The embodiment of the present invention combines the angiography position and selects appropriate segment connection rules to verify the coronary vessel annotation information. Through the continuity, relative position and length between the vessel segments, it is judged whether the coronary vessel annotation information conforms to the specific connection relationship of the segments and the medical specifications in the SYNTAX annotation specification, thereby achieving logical verification of the vessel annotations completed by the doctor, and improving the accuracy of the coronary vessel examination annotations.

[0085] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the blood vessel annotation verification method based on the SYNTAX annotation specification are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 3 Functions of the modules / units 31 to 33 are shown.

[0086] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 may be divided into Figure 3 Modules / units 31 to 33 are shown.

[0087] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0088] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0089] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0090] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0091] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0096] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned vascular annotation verification method embodiment based on the SYNTAX annotation specification can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0097] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A blood vessel annotation verification method based on SYNTAX annotation specification, characterized in that: include: Acquire the coronary vessel annotation information input by the user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel; Based on the angiography position corresponding to the coronary vessel annotation information, determining a segment connection rule applicable to the coronary vessel annotation information; wherein the segment connection rule is a connection logic and sequence between coronary segments based on an anatomical definition, including one or more of segment continuity, segment relative position and segment length; Based on the endpoint coordinates and length of each vascular segment, it is determined whether the coronary vessel labeling information complies with the segment connection rule, and a verification result of the coronary vessel labeling information is obtained.

2. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: The step of judging whether the coronary vessel labeling information complies with the segment connection rule based on the endpoint coordinates and length of each vessel segment, and obtaining the verification result of the coronary vessel labeling information, includes: If the distance between the coordinates of the ending point of the first segment and the coordinates of the starting point of the second segment is less than a preset distance threshold, it is determined that the first segment and the second segment are connected in sequence; wherein the first segment and the second segment are different vascular segments.

3. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: The step of judging whether the coronary vessel labeling information complies with the segment connection rule based on the endpoint coordinates and length of each vessel segment, and obtaining the verification result of the coronary vessel labeling information, includes: If the distances between the coordinates of the ending point of the third segment, the coordinates of the starting point of the fourth segment, and the coordinates of the starting point of the fifth segment are all less than a preset distance threshold, the starting point of the fifth segment is determined to be the dividing point between the third segment and the fourth segment; wherein the third segment, the fourth segment, and the fifth segment are different vascular segments.

4. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: The step of judging whether the coronary vessel labeling information complies with the segment connection rule based on the endpoint coordinates and length of each vessel segment, and obtaining the verification result of the coronary vessel labeling information, includes: If the midpoint of the sixth segment is located below and to the left of the midpoint of the seventh segment, it is determined that the seventh segment intersects the diagonal line from the upper right to the lower left of the coronary angiography image before the sixth segment; wherein the sixth segment and the seventh segment are different vascular segments.

5. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: When the angiography position is the left coronary left shoulder position, the segment connection rules applicable to the coronary vessel labeling information include: Segments 5, 6, and 7 are connected in sequence, the starting point of segment 9 is the dividing point between segment 6 and segment 7, and the starting point of segment 10 is the dividing point between segment 7 and segment 8; If segment 10 does not exist, the difference between the lengths of segment 7 and segment 8 is less than a preset difference threshold; If segment 9 and segment 9a exist, segment 9 intersects the diagonal line from the upper right to the lower left of the coronary angiography image before segment 9a.

6. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: When the angiography position is the left coronary left foot position, the segment connection rules applicable to the coronary vessel labeling information include: Segments 5 , 11 , and 13 are connected in sequence. The starting point of segment 12 is the dividing point between segment 5 and segment 11 , and the starting point of segment 12a is the dividing point between segment 11 and segment 13 .

7. The blood vessel annotation verification method based on the SYNTAX annotation specification according to claim 1, characterized in that: When the angiography position is the right coronary left oblique anterior position, the segment connection rules applicable to the coronary vessel labeling information include: Segments 1, 2, 3, and 4 are connected in sequence, and segments 3 and 16 are connected in sequence.

8. A blood vessel annotation verification device based on the SYNTAX annotation specification, characterized in that: include: An acquisition module, used to acquire the coronary vessel annotation information input by the user; wherein the coronary vessel annotation information includes the endpoint coordinates and length of each vessel segment on the coronary vessel; A determination module is used to determine the segment connection rule applicable to the coronary vessel annotation information based on the angiography machine position corresponding to the coronary vessel annotation information; wherein the segment connection rule includes one or more of the connection logic and sequence between coronary segments defined based on anatomy, segment continuity, segment relative position and segment length; The verification module is used to determine whether the coronary vessel labeling information complies with the segment connection rule based on the endpoint coordinates and length of each vessel segment, and obtain a verification result of the coronary vessel labeling information.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images