WO2023130664A1 - 一种血管造影图像的分析方法和装置 - Google Patents

一种血管造影图像的分析方法和装置 Download PDF

Info

Publication number
WO2023130664A1
WO2023130664A1 PCT/CN2022/097246 CN2022097246W WO2023130664A1 WO 2023130664 A1 WO2023130664 A1 WO 2023130664A1 CN 2022097246 W CN2022097246 W CN 2022097246W WO 2023130664 A1 WO2023130664 A1 WO 2023130664A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
pixel
blood vessel
generate
diameter
Prior art date
Application number
PCT/CN2022/097246
Other languages
English (en)
French (fr)
Inventor
吴泽剑
张碧莹
曹君
Original Assignee
乐普（北京）医疗器械股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 乐普（北京）医疗器械股份有限公司 filed Critical 乐普（北京）医疗器械股份有限公司
Publication of WO2023130664A1 publication Critical patent/WO2023130664A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • G06T2207/20192—Edge enhancement; Edge preservation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30172—Centreline of tubular or elongated structure
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning

Definitions

  • the invention relates to the technical field of data processing, in particular to an angiography image analysis method and device.
  • Quantitative analysis of stenosis rate of vascular stenosis on coronary angiography images is also called qualitative comparative analysis (quantitative coronary arteriography, QCA), and relevant information such as vessel diameter and stenosis rate of stenosis can be obtained.
  • QCA analysis operations rely on personnel experience to manually mark stenotic blood vessels from contrast images, and manually measure and calculate the manual marking points through image rulers to obtain information such as the diameter of the stenotic segment and the stenosis rate of the stenotic segment. This method of operation is highly dependent on manual experience, and often occurs due to lack of experience of personnel and inaccurate selection of maps, resulting in tools that cannot be analyzed or that the analysis accuracy is not high.
  • the object of the present invention is to provide an analysis method, device, electronic equipment and computer-readable storage medium for angiographic images, aiming at the defects of the prior art.
  • the diameter of each point on the center line is measured, and then based on the obtained diameter of each point, the diameter change rate of each point is further calculated as the corresponding vascular stenosis rate.
  • the first aspect of the embodiment of the present invention provides an angiographic image analysis method, the method comprising:
  • the first center line According to the direction from one end point to the other end point of the first center line, sort the pixels on the first center line to generate a first pixel point sequence; the first pixel point sequence includes a plurality of first pixel;
  • the blood vessel image measure and calculate the blood vessel diameter at each of the first pixel positions to generate a corresponding first diameter; and sort the first diameter according to the sort order of the corresponding first pixel points to generate first diameter sequence;
  • the first diameter sequence identify the blood vessel stenosis rate at each of the first pixel positions to generate a corresponding first stenosis rate; and sort the first pixel according to the sort order of the corresponding first pixel
  • the stenosis rate is sorted to generate the first stenosis rate sequence
  • the first pixel point sequence, the first diameter sequence and the first stenosis rate sequence as the blood vessel stenosis analysis data of the angiography image.
  • performing binarization processing and image noise reduction processing on the first image to generate a first binary image specifically includes:
  • the pixels of the binarized image include foreground pixels and background pixels;
  • the pixel values of the foreground pixels are preset foreground Pixel value A, the pixel value of the background pixel point is a preset background pixel value B;
  • the binary image is first expanded and then corroded, and the operation result is used as the first binary image.
  • performing blood vessel identification processing on the first binary image to generate a corresponding blood vessel image specifically includes:
  • the edge points On the first binary image, sequentially connect the edge points clockwise or counterclockwise to form a closed blood vessel edge line; and use the blood vessel edge line and sub-images within the edge line as corresponding The blood vessel image.
  • the blood vessel diameter at each of the first pixel positions is measured and calculated to generate a corresponding first diameter, which specifically includes:
  • the length of the four intersecting line segments is the shortest Calculate the line segment length of an intersecting line segment, and use the calculation result as the first diameter corresponding to the current first pixel point.
  • identifying the vascular stenosis rate at each of the first pixel positions to generate a corresponding first stenosis rate specifically includes:
  • the second aspect of the embodiment of the present invention provides a device for implementing the method described in the first aspect above, including: an acquisition module, an image preprocessing module, a centerline extraction module, and a data analysis module;
  • the acquisition module is used to acquire angiographic images
  • the image preprocessing module is used to detect vascular stenosis on the angiographic image, and use the detected sub-image of the stenosis as the first image; and perform binarization processing and image noise reduction on the first image processing to generate a first binary image; and performing blood vessel identification processing on the first binary image to generate a corresponding blood vessel image;
  • the centerline extraction module is used to perform centerline extraction processing on the blood vessel image of the first binary image based on a topology thinning method to generate a first centerline without changing the topological properties of the blood vessel image; and press From one end point of the first center line to the other end point, sort the pixels on the first center line to generate a first pixel point sequence; the first pixel point sequence includes a plurality of first pixels point;
  • the data analysis module is used to measure and calculate the diameter of the blood vessel at each of the first pixel positions according to the blood vessel image to generate a corresponding first diameter; and sort the corresponding first pixel points in order
  • the first diameters are sorted to generate a first diameter sequence; and according to the first diameter sequence, the blood vessel stenosis rate at each of the first pixel positions is identified to generate a corresponding first stenosis rate; and according to the corresponding Sorting the first stenosis rate to generate a first stenosis rate sequence in the sorting order of the first pixel points; and using the first pixel point sequence, the first diameter sequence and the first stenosis rate sequence as the first stenosis rate sequence
  • the vessel stenosis analysis data of the above angiographic image is returned.
  • the third aspect of the embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;
  • the processor is configured to be coupled with the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;
  • the transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.
  • the fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer executes the above-mentioned first aspect. method directive.
  • An embodiment of the present invention provides an analysis method, device, electronic device, and computer-readable storage medium for an angiography image.
  • image extraction is performed on the stenotic segment of the angiography image, and binarization is performed on the extracted image, and then the The vessel edge is extracted from the binary image to obtain the vessel image, and then the centerline of the vessel image is extracted based on the topology thinning method, and then the diameter of each point on the centerline is calculated based on the geometric relationship between the extracted vessel centerline and the vessel edge. Measure, and then further calculate the diameter change rate of each point based on the obtained diameter of each point as the corresponding vascular stenosis rate.
  • Fig. 1 is a schematic diagram of an angiographic image analysis method provided by Embodiment 1 of the present invention
  • FIG. 2 is a schematic diagram of the first coordinate space provided by Embodiment 1 of the present invention.
  • Fig. 3 is a module structure diagram of an angiographic image analysis device provided in Embodiment 2 of the present invention.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention.
  • An angiographic image analysis method provided in Embodiment 1 of the present invention as shown in FIG. 1 is a schematic diagram of an angiographic image analysis method provided in Embodiment 1 of the present invention. The method mainly includes the following steps:
  • Step 1 acquire angiographic images.
  • the angiography image may be a coronary angiography image, or may be an angiography image of other parts and other types of blood vessels.
  • step 2 the blood vessel stenosis part is detected on the angiography image, and the detected sub-image of the stenosis part is used as the first image.
  • the embodiment of the present invention adopts the target detection model based on machine deep learning technology to detect the stenosis part of the angiography image and output the corresponding target detection frame, and the sub-image covered by the target detection frame can be extracted as the sub-image of the stenosis part That is the first image.
  • Step 3 performing binarization processing and image noise reduction processing on the first image to generate a first binary image
  • the recognition accuracy of blood vessel edges can be improved through binarization and image denoising
  • step 31 performing binarization processing on the first image to generate a corresponding binarized image
  • the pixels of the binarized image include foreground pixels and background pixels; the pixel value of the foreground pixel is a preset foreground pixel value A, and the pixel value of the background pixel is a preset background pixel value B;
  • the foreground pixel value A is generally preset as a white gray value
  • the background pixel value B is generally preset as a black gray value; of course, it is also possible to set a binary value for the foreground pixel value A and the background pixel based on design requirements.
  • Set value B for example, use 0/1 binary value to set foreground pixel value A to 1 and background pixel value B to 0;
  • Step 32 based on the image closing operation principle of image morphology, perform image closing operation on the binarized image by first dilating and then corroding, and use the operation result as the first binary image.
  • the image closing operation principle of image morphology is to perform image expansion processing on the image first, and then perform image erosion processing; the purpose is to fill the internal holes of the graphics in the original image, and make the area of each graphics not change significantly.
  • the edge connection of graphics is smoother; for the specific implementation principles of image closing operation, image expansion, and image erosion, please refer to related technical implementations, and I will not repeat them here;
  • Step 4 performing blood vessel recognition processing on the first binary image to generate a corresponding blood vessel image
  • step 41 traversing the pixel points of the preset foreground pixel value A for each pixel value on the first binary image; when traversing, performing a traversal on the pixel values of the eight-field pixel points currently traversing the pixel points Obtain and generate the corresponding first pixel value set; if at least one pixel value in the first pixel value set is consistent with the preset background pixel value B, mark the currently traversed pixel point as an edge point;
  • the so-called eight-field pixels are actually the upper left adjacent pixel, upper upper adjacent pixel, upper right adjacent pixel, right adjacent pixel, lower right adjacent pixel, and lower adjacent pixel of a certain pixel in the image. point, the lower left adjacent pixel, and the left adjacent pixel; the embodiment of the present invention stipulates that when judging whether a foreground pixel, that is, a pixel whose pixel value is the preset foreground pixel value A, is an edge point, Identify whether the pixels in the eight domains include background pixels, as long as one of the pixels in the eight domains is a background pixel, that is, the pixel value is background pixel value B, then the currently judged pixel is an edge point;
  • Step 42 On the first binary image, sequentially connect edge points clockwise or counterclockwise to form a closed blood vessel edge line; and use the blood vessel edge line and sub-images within the edge line as corresponding blood vessel images.
  • Step 5 under the premise of not changing the topological properties of the blood vessel image, perform centerline extraction processing on the blood vessel image of the first binary image based on the topology thinning method to generate the first centerline;
  • the topological properties of blood vessel images mainly refer to the connectivity of blood vessels
  • step 51 creating a connectivity judgment rule that maintains the topological properties of the blood vessel image
  • the connectivity judgment rule includes a plurality of sub-rules, and each sub-rule corresponds to one or more 3 ⁇ 3 pixel value template matrices;
  • Step 52 copy the first binary image to generate a corresponding second binary image, and record the blood vessel image area on the second binary image as the blood vessel image area;
  • Step 53 based on the topological shape rules, traverse the pixels in each row of the second binary image from left to right, and mark the pixels that do not meet the connectivity judgment rules as unnecessary pixels; in the second binary image After completing a traversal of all pixels in , record the non-essential pixels whose pixel value is the foreground pixel value A as the newly added background pixel, and set the pixel value of all the newly added background pixel to the background pixel value B, and new Increase the number of background pixels to obtain the new number; if the new number is not 0, then traverse the pixels of each row of the second binary image after setting again from left to right until the current traversal The number of new additions is 0; and the pixel points in the blood vessel image area on the final second binary image whose pixel value is the foreground pixel value A are all marked as necessary pixel points;
  • the newly added background pixel is the pixel whose value is the background pixel value B;
  • the pixel values of the current traversing pixel and its corresponding eight-field pixel are extracted to form a 3 ⁇ 3 pixel value matrix, which is recorded as the traversing point pixel matrix, and the traversing point pixel
  • the matrix is compared with the template matrix of each sub-rule of the connectivity judgment rule one by one; it should be noted that if the current traversal pixel is an image boundary pixel, the eight domain pixels will be missing.
  • the pixel value of the missing point is set to the background pixel value B by default;
  • the current traversal pixel corresponding to the current traversal point pixel matrix satisfies Connectivity judgment rules, that is to say, if deleting the current traversal pixel point will affect the topological connectivity properties of the blood vessel image, the pixel point should not be marked as an unnecessary pixel point; when the traversal point pixel matrix and any sub-rule template matrix are When there is no coincidence, the current traversal pixel corresponding to the current traversal point pixel matrix does not meet the connectivity judgment rules, that is to say, if deleting the current traversal pixel will not affect the topological connectivity of the blood vessel image, the pixel should be marked as non-connectivity. Necessary pixels;
  • the preset connectivity judgment rule includes the following five sub-rules,
  • Sub-rule 1 The pixel value template matrix is A is the preset foreground pixel value; this rule indicates that if the traversal point pixel matrix is consistent with the template matrix of the current rule, deleting the current traversal pixel point (corresponding to the center point of the template matrix) will cause holes to affect the topological properties of the image connectivity;
  • Sub-rule 2 The pixel value template matrix is B is the preset background pixel value; this rule indicates that if the traversal point pixel matrix is consistent with the template matrix of the current rule, deleting the current traversal pixel point (corresponding to the center point of the template matrix) will cause a fault between the upper and lower layers and affect the topological properties of the image connectivity;
  • Sub-rule 3 The pixel value template matrix is This rule indicates that if the traversal point pixel matrix is consistent with the template matrix of the current rule, then deleting the current traversal pixel point (corresponding to the center point of the template matrix) will cause holes to affect the connectivity of the topological properties of the image;
  • Subrule 4 The pixel value template matrix is This rule indicates that if the traversal point pixel matrix is consistent with the template matrix of the current rule, then deleting the current traversal pixel point (corresponding to the center point of the template matrix) will cause the upper layer endpoint to be reduced, thereby losing the endpoint of the connected shape of the image and affecting the connectivity of the topological properties of the image sex;
  • Subrule 5 The template matrix of pixel values includes and This rule indicates that if the traversal point pixel matrix is consistent with the template matrix of the current rule, then deleting the current traversal pixel point (corresponding to the center point of the template matrix) will cause the connected endpoints to be reduced, thereby losing the endpoints of the connected shape of the image and affecting the connectivity of the topological properties of the image sex;
  • the overall pixel point distribution structure of the second binary image is in It is the pixels of the blood vessel image; the first traversal is performed on the pixels of each row of the second binary image from left to right:
  • the first pixel from the left in the first line is the boundary point.
  • the pixel value of the missing point (lower left, left, upper left, upper and upper right) in its eight domain pixels is set to B, then the corresponding traversal The dot pixel matrix is Use sub-rules 1, 2, 3, 4, 5 to compare the pixel value template matrix with the traversal point pixel matrix in turn and find that they all do not overlap, then the first pixel from the left of the first row is regarded as not satisfying the connectivity judgment rule and mark them as non-essential pixels; by analogy, the traversal point pixel matrix of the remaining pixels in the first row cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, and 5, so All pixels in row 1 are marked as non-essential pixels;
  • the traversal point pixel matrix of all pixels in the second row cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, and 5, so all pixels in the second row are marked as unnecessary pixels ;
  • the traversal point pixel matrix of the 1st and 2nd pixels in the 3rd row cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, 5, so the 1st and 2nd pixels in the 3rd row are marked is a non-essential pixel; and the traversal point pixel matrix of the third pixel in the third row is If it coincides with the pixel value template matrix of sub-rule 1, the current traversal pixel point, that is, the third pixel point in the third row, is regarded as a pixel point that satisfies the connectivity judgment rule and is not marked as an unnecessary pixel point; the third row and the fourth pixel point , the traversal point pixel matrix of 5 pixels cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, and 5, so the 4th and 5th pixels in the third row are marked as unnecessary pixels ;
  • the traversal point pixel matrix of the 1st, 2nd, 4th, and 5th pixels in the 4th row cannot coincide with the pixel value template matrix of the sub-rule 1, 2, 3, 4, 5, so the 1st, 2nd, 4th row of the 4th row , 5 pixels are marked as non-essential pixels; while the 3rd pixel in the 4th row is similar to the 3rd pixel in the 3rd row, the corresponding traversal point pixel matrix is It coincides with the pixel value template matrix of sub-rule 1, so the third pixel in the fourth row is a pixel that satisfies the connectivity judgment rule and is not marked as an unnecessary pixel;
  • the traversal point pixel matrix of all pixels in the 5th and 6th rows cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, and 5, so all the pixels in the 5th and 6th rows are marked is a non-essential pixel;
  • the first traversal of the second binary image ends, and the non-essential pixel whose pixel value is the foreground pixel value A is recorded as a newly added background pixel and all newly added
  • the pixel value of the background pixel is set to the background pixel value B so that the new second binary image obtained is
  • the number of newly added background pixels is counted and the number of newly added pixels is 10; because the newly added number of background pixels this time is greater than 0, the pixels in each row of the second binary image need to be calculated again from left to Right for a second traversal:
  • the traversal point pixel matrix of all pixels in row 1 and row 2 cannot coincide with the pixel value template matrix of subrules 1, 2, 3, 4, and 5, so all pixels in row 1 and row 2 are marked is a non-essential pixel;
  • the traversal point pixel matrix of the third pixel in the third row is If it coincides with one of the pixel value template matrices in sub-rule 5, the current traversal pixel point, that is, the third pixel point in the third row, is regarded as a pixel point that satisfies the connectivity judgment rule and is not marked as an unnecessary pixel point; while the third pixel point
  • the traversal point pixel matrix of other pixels except the 3rd row cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, 5, so the other pixels in the 3rd row except the 3rd Points are marked as non-essential pixels;
  • the traversal point pixel matrix of the third pixel in the fourth row is If it coincides with one of the pixel value template matrices in sub-rule 5, the current traversal pixel point, that is, the third pixel point in the fourth row, is regarded as a pixel point that satisfies the connectivity judgment rule and is not marked as an unnecessary pixel point; while the fourth The traversal point pixel matrix of other pixels except the 3rd row cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, 5, so the other pixels in the 4th row except the 3rd Points are marked as non-essential pixels;
  • the traversal point pixel matrix of all pixels in the 5th and 6th rows cannot coincide with the pixel value template matrix of sub-rules 1, 2, 3, 4, and 5, so all the pixels in the 5th and 6th rows are marked is a non-essential pixel;
  • the first traversal of the second binary image ends, and the non-essential pixel whose pixel value is the foreground pixel value A is recorded as a newly added background pixel and all newly added
  • the pixel value of the background pixel is set to the background pixel value B so that the new second binary image obtained is This is unchanged from the binary image after the first traversal, and the corresponding number of newly added background pixels is 0.
  • Step 54 according to the one-to-one correspondence between the pixels in the second binary image and the pixels in the first binary image, sequentially connect the pixels corresponding to each necessary pixel on the first binary image, and use the connecting lines as first centerline.
  • step 53 that is, connect the third pixel point in the third row and the third pixel point in the fourth row in the first binary image to obtain the first center line.
  • the cutting angle at both ends of the blood vessel in the first binary image may not be perpendicular to the blood vessel due to the influence of the segmentation angle. direction, which may lead to a deviation in the positioning of the centerline pixel points located at the two ends of the blood vessel; therefore, after step 54, the processing method of deleting the specified proportion points at both ends of the first centerline can be used to improve the second.
  • the positioning accuracy of the pixel points on the first central line so as to achieve the purpose of improving the positioning accuracy of the first central line.
  • Step 6 sorting the pixels on the first center line in the direction from one end point of the first center line to the other end point to generate a first sequence of pixel points
  • the first pixel point sequence includes a plurality of first pixel points.
  • Step 7 According to the blood vessel image, measure and calculate the blood vessel diameter at each first pixel point position to generate a corresponding first diameter; and sort the first diameters according to the sort order of the corresponding first pixel points to generate a first diameter sequence.
  • the blood vessel diameter at the position of each first pixel point is measured to generate the corresponding first diameter, which specifically includes: passing through each first pixel point and making four straight lines in four directions connected to its eight domain pixel points Respectively intersect with the blood vessel edge lines of the blood vessel image to obtain four corresponding intersecting line segments; and calculate the length of the shortest intersecting line segment among the four intersecting line segments, and use the calculation result as the first pixel corresponding to the current first pixel point a diameter.
  • the four straight lines are the straight line 1 passing through the upper left adjacent pixel point-the first pixel point-the lower right adjacent pixel point, the straight line 2 passing through the upper adjacent pixel point-the first pixel point-the lower adjacent pixel point, and the straight line passing through The line 3 from the upper right adjacent pixel - the first pixel - the lower left adjacent pixel, the line 4 passing through the right adjacent pixel - the first pixel - the left adjacent pixel; lines 1, 2, 3, 4 and the center line
  • the intersecting line segments at the edges of blood vessels at both ends are recorded as intersecting line segments 1, 2, 3, and 4; the length of the shortest line segment among intersecting line segments 1, 2, 3, and 4 is taken as the first diameter.
  • Step 8 according to the first diameter sequence, identify the blood vessel stenosis rate at each first pixel point position to generate the corresponding first stenosis rate; and sort the first stenosis rate according to the sorting order of the corresponding first pixel point to generate The first stenosis rate series.
  • the vascular stenosis rate at each first pixel point position to generate the corresponding first stenosis rate, which specifically includes: taking the pixel point index of the first centerline as the horizontal axis, and taking the pixel point
  • the corresponding blood vessel diameter is the vertical axis to construct a two-dimensional coordinate space, which is recorded as the first coordinate space; the pixel index of each first pixel point on the first center line is the horizontal axis coordinate, and the corresponding first diameter is the vertical axis coordinate, Mark the corresponding coordinate point on the first coordinate space and record it as the first coordinate point; connect each first coordinate point in sequence to obtain the first diameter change curve; connect the first and last first coordinate point with a straight line to obtain The first diameter reference line; through each first coordinate point, make a horizontal axis vertical line of the first coordinate space, and record the blood vessel diameter ordinate value of the intersection point of the horizontal axis vertical line and the first diameter reference line as the corresponding first reference Diameter; calculate the first stenos
  • the first pixel point on the first central line whose pixel index is x 1 corresponds to the first diameter y 1 .
  • Step 9 return the first pixel point sequence, the first diameter sequence and the first stenosis rate sequence as the blood vessel stenosis analysis data of the angiography image.
  • the pixel-level blood vessel centerline, blood vessel diameter and blood vessel stenosis can be added to each blood vessel sampling point on the angiography image rate semantic parameters, thereby improving the recognition accuracy of angiographic images; it is also possible to perform mean or weighted mean calculation on the above-mentioned first stenosis rate sequence, and use the calculation result as the average stenosis rate of the current segment of blood vessels for users to carry out statistical analysis;
  • the maximum value may be extracted from the above-mentioned first stenosis rate sequence as the maximum stenosis rate of the current segment blood vessel for statistical analysis by the user.
  • Fig. 3 is a module structure diagram of an angiographic image analysis device provided in Embodiment 2 of the present invention.
  • the device can be a terminal device or a server implementing the method of the embodiment of the present invention, or can be connected to the above-mentioned terminal device or server.
  • An apparatus for implementing the method in the embodiment of the present invention for example, the apparatus may be an apparatus or chip system of the above-mentioned terminal device or server.
  • the device includes: an acquisition module 201 , an image preprocessing module 202 , a central line extraction module 203 and a data analysis module 204 .
  • the acquiring module 201 is used for acquiring angiography images.
  • the image preprocessing module 202 is used to detect the stenosis part of the blood vessel on the angiography image, and use the detected sub-image of the stenosis part as the first image; and perform binarization processing and image noise reduction processing on the first image to generate the first two value map; and performing blood vessel recognition processing on the first binary image to generate a corresponding blood vessel image.
  • the centerline extraction module 203 is used to extract the centerline of the blood vessel image of the first binary image based on the topology thinning method to generate the first centerline without changing the topological properties of the blood vessel image; In the direction from one end point to the other end point, the pixels on the first center line are sorted to generate a first pixel point sequence; the first pixel point sequence includes a plurality of first pixel points.
  • the data analysis module 204 is used to measure and calculate the diameter of the blood vessel at each first pixel point position according to the blood vessel image to generate a corresponding first diameter; and sort the first diameter according to the sorting order of the corresponding first pixel point to generate a first Diameter sequence; and according to the first diameter sequence, identify the vascular stenosis rate at each first pixel point position to generate a corresponding first stenosis rate; and sort the first stenosis rate according to the sort order of the corresponding first pixel point Generate a first stenosis rate sequence; and return the first pixel point sequence, the first diameter sequence, and the first stenosis rate sequence as blood vessel stenosis analysis data of the angiography image.
  • An angiographic image analysis device provided in an embodiment of the present invention can execute the method steps in the above method embodiments, and its implementation principle and technical effect are similar, and will not be repeated here.
  • each module of the above device is only a division of logical functions, and may be fully or partially integrated into one physical entity or physically separated during actual implementation.
  • these modules can all be implemented in the form of calling software through processing elements; they can also be implemented in the form of hardware; some modules can also be implemented in the form of calling software through processing elements, and some modules can be implemented in the form of hardware.
  • the acquisition module can be a separate processing element, or it can be integrated into a chip of the above-mentioned device.
  • it can also be stored in the memory of the above-mentioned device in the form of program code, and a certain processing element of the above-mentioned device can Call and execute the functions of the modules identified above.
  • each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.
  • the above modules may be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits (Application Specific Integrated Circuit, ASIC), or, one or more digital signal processors ( Digital Signal Processor, DSP), or, one or more Field Programmable Gate Arrays (Field Programmable Gate Array, FPGA), etc.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • FPGA Field Programmable Gate Array
  • the processing element may be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or other processors that can call program codes.
  • these modules can be integrated together and implemented in the form of a System-on-a-chip (SOC).
  • SOC System-on-a-chip
  • all or part of them may be implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the above-mentioned computers may be general-purpose computers, special-purpose computers, computer networks, or other programmable devices.
  • the above-mentioned computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the above-mentioned computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the above-mentioned usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a solid state disk (solid state disk, SSD)) and the like.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention.
  • the electronic device may be the aforementioned terminal device or server, or may be a terminal device or server connected to the aforementioned terminal device or server to implement the method of the embodiment of the present invention.
  • the electronic device may include: a processor 301 (such as a CPU), a memory 302 , and a transceiver 303 ;
  • Various instructions may be stored in the memory 302 for completing various processing functions and realizing the methods and processing procedures provided in the above-mentioned embodiments of the present invention.
  • the electronic device involved in this embodiment of the present invention further includes: a power supply 304 , a system bus 305 and a communication port 306 .
  • the system bus 305 is used to realize the communication connection among the components.
  • the above-mentioned communication port 306 is used for connection and communication between the electronic device and other peripheral devices.
  • the system bus mentioned in FIG. 4 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the system bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used to realize the communication between the database access device and other devices (such as client, read-write library and read-only library).
  • the memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk memory.
  • processor can be general-purpose processor, comprises central processing unit CPU, network processor (Network Processor, NP) etc.; Can also be digital signal processor DSP, application-specific integrated circuit ASIC, field programmable gate array FPGA or other available Program logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU central processing unit
  • NP Network Processor
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • embodiments of the present invention also provide a computer-readable storage medium, and instructions are stored in the storage medium, and when it is run on a computer, the computer executes the methods and processing procedures provided in the above-mentioned embodiments.
  • the embodiment of the present invention also provides a chip for running instructions, and the chip is used for executing the method and the processing procedure provided in the foregoing embodiments.
  • An embodiment of the present invention provides an analysis method, device, electronic device, and computer-readable storage medium for an angiography image.
  • image extraction is performed on the stenotic segment of the angiography image, and binarization is performed on the extracted image, and then the The vessel edge is extracted from the binary image to obtain the vessel image, and then the centerline of the vessel image is extracted based on the topology thinning method, and then the diameter of each point on the centerline is calculated based on the geometric relationship between the extracted vessel centerline and the vessel edge. Measure, and then further calculate the diameter change rate of each point based on the obtained diameter of each point as the corresponding vascular stenosis rate.
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrically programmable ROM
  • EEPROM electrically erasable programmable ROM
  • registers hard disk, removable disk, CD-ROM, or any other Any other known storage medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Geometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

本发明实施例涉及一种血管造影图像的分析方法和装置，所述方法包括：获取血管造影图像；进行血管狭窄部位检测并将检测出的狭窄部位子图像作为第一图像；进行二值化和图像降噪生成第一二值图；进行血管识别生成血管图像；在不改变血管图像拓扑性质的前提下，对第一二值图的血管图像进行中心线提取生成第一中心线；对第一中心线上的像素点进行排序生成第一像素点序列；对各个第一像素点位置处的血管直径进行测算生成第一直径；对各个第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；将第一像素点序列、第一直径序列和第一狭窄率序列作为血管造影图像的血管狭窄分析数据进行返回。通过本发明可以提高分析准确度。

Description

一种血管造影图像的分析方法和装置
本申请要求于2022年1月7日提交中国专利局、申请号为202210017847.5、发明名称为“一种血管造影图像的分析方法和装置”的中国专利申请的优先权。
技术领域
本发明涉及数据处理技术领域，特别涉及一种血管造影图像的分析方法和装置。
背景技术
通过对冠状动脉造影图像进行血管狭窄部位的狭窄率定量分析也称为定性比较分析(quantitative coronary arteriography，QCA)，可以得到诸如狭窄段的血管直径、血管狭窄率等相关信息。常规的QCA分析操作都是凭借人员经验从造影图像中手动标记出狭窄段血管，并通过图像标尺对手动标记点进行人工测量、计算，从而得到狭窄段直径、狭窄段狭窄率等信息。这种操作方式，对人工经验的依赖度很高，常常会出现因人员经验不足、选图不准导致工具无法分析或分析精度不高的情况。
发明内容
本发明的目的，就是针对现有技术的缺陷，提供一种血管造影图像的分析方法、装置、电子设备及计算机可读存储介质，首先对血管造影图像的血管狭窄段进行图像提取并对提取图像进行二值化处理，再对二值图进行血管边缘提取从而得到血管图像，再基于拓扑细化方法对血管图像进行血管中心线提取，再基于提取出的血管中心线与血管边缘的几何关系对中心线上各点的直 径进行测量，再基于得到的各点直径进一步算出各点的直径变化率作为对应的血管狭窄率。通过本发明，可以摆脱对人工经验的依赖，可以提高数据分析准确度。
为实现上述目的，本发明实施例第一方面提供了一种血管造影图像的分析方法，所述方法包括：
获取血管造影图像；
对所述血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像；
对所述第一图像进行二值化处理和图像降噪处理生成第一二值图；
对所述第一二值图进行血管识别处理生成对应的血管图像；
在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对所述第一二值图的所述血管图像进行中心线提取处理生成第一中心线；
按从所述第一中心线的一个端点到另一个端点的方向，对所述第一中心线上的像素点进行排序生成第一像素点序列；所述第一像素点序列包括多个第一像素点；
根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的所述第一像素点的排序顺序对所述第一直径进行排序生成第一直径序列；
根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的所述第一像素点的排序顺序对所述第一狭窄率进行排序生成第一狭窄率序列；
将所述第一像素点序列、所述第一直径序列和所述第一狭窄率序列作为所述血管造影图像的血管狭窄分析数据进行返回。
优选的，所述对所述第一图像进行二值化处理和图像降噪处理生成第一二值图，具体包括：
对所述第一图像进行二值化处理生成对应的二值化图像；所述二值化图 像的像素点包括前景像素点和背景像素点；所述前景像素点的像素值为预设的前景像素值A，所述背景像素点的像素值为预设的背景像素值B；
基于图像形态学的图像闭运算原理，对所述二值化图像进行先膨胀后腐蚀的图像闭运算操作，并将运算结果作为所述第一二值图。
优选的，所述对所述第一二值图进行血管识别处理生成对应的血管图像，具体包括：
对所述第一二值图上每个像素值为预设的前景像素值A的像素点进行遍历；遍历时，对当前遍历像素点的八领域像素点的像素值进行获取生成对应的第一像素值集合；若所述第一像素值集合中至少有一个像素值与预设的背景像素值B一致，则将所述当前遍历像素点标记为边缘点；
在所述第一二值图上，按顺时针或逆时针方向对所述边缘点进行依次连接构成闭合的血管边缘线；并将所述血管边缘线和边缘线以内的子图像，作为对应的所述血管图像。
优选的，所述根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径，具体包括：
过各个所述第一像素点沿与其八领域像素点连接的四个方向做四条直线分别与所述血管图像的血管边缘线相交，从而得到对应的四条相交线段；并对四条相交线段中长度最短的一条相交线段的线段长度进行计算，并将计算结果作为与当前第一像素点对应的所述第一直径。
优选的，所述根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率，具体包括：
以所述第一中心线的像素点索引为横轴、以像素点对应的血管直径为纵轴构建二维坐标空间记为第一坐标空间；
以各个所述第一像素点在所述第一中心线上的像素点索引为横轴坐标、对应的所述第一直径为纵轴坐标，在所述第一坐标空间上标记出对应的坐标点记为第一坐标点；
对各个所述第一坐标点进行依次连接得到第一直径变化曲线；
对第一个和最后一个所述第一坐标点进行直线连接得到第一直径参考线；
过各个所述第一坐标点做所述第一坐标空间的横轴垂线，并将横轴垂线与所述第一直径参考线的交点的血管直径纵坐标数值记为对应的第一参考直径；
计算各个所述第一像素点对应的所述第一狭窄率r，r＝(1-d 1/d 2)×100％，d 1为各个所述第一像素点对应的所述第一直径，d 2为各个所述第一像素点对应的所述第一参考直径。
本发明实施例第二方面提供了一种实现上述第一方面所述的方法的装置，包括：获取模块、图像预处理模块、中心线提取模块和数据分析模块；
所述获取模块用于获取血管造影图像；
所述图像预处理模块用于对所述血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像；并对所述第一图像进行二值化处理和图像降噪处理生成第一二值图；并对所述第一二值图进行血管识别处理生成对应的血管图像；
所述中心线提取模块用于在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对所述第一二值图的所述血管图像进行中心线提取处理生成第一中心线；并按从所述第一中心线的一个端点到另一个端点的方向，对所述第一中心线上的像素点进行排序生成第一像素点序列；所述第一像素点序列包括多个第一像素点；
所述数据分析模块用于根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的所述第一像素点的排序顺序对所述第一直径进行排序生成第一直径序列；并根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的所述第一像素点的排序顺序对所述第一狭窄率进行排序生成第一狭窄率序列；并将所述第一像素点序列、所述第一直径序列和所述第 一狭窄率序列作为所述血管造影图像的血管狭窄分析数据进行返回。
本发明实施例第三方面提供了一种电子设备，包括：存储器、处理器和收发器；
所述处理器用于与所述存储器耦合，读取并执行所述存储器中的指令，以实现上述第一方面所述的方法步骤；
所述收发器与所述处理器耦合，由所述处理器控制所述收发器进行消息收发。
本发明实施例第四方面提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，当所述计算机指令被计算机执行时，使得所述计算机执行上述第一方面所述的方法的指令。
本发明实施例提供了一种血管造影图像的分析方法、装置、电子设备及计算机可读存储介质，首先对血管造影图像的血管狭窄段进行图像提取并对提取图像进行二值化处理，再对二值图进行血管边缘提取从而得到血管图像，再基于拓扑细化方法对血管图像进行血管中心线提取，再基于提取出的血管中心线与血管边缘的几何关系对中心线上各点的直径进行测量，再基于得到的各点直径进一步算出各点的直径变化率作为对应的血管狭窄率。通过本发明，摆脱了对人工经验的依赖，提高了数据分析准确度。
附图说明
图1为本发明实施例一提供的一种血管造影图像的分析方法示意图；
图2为本发明实施例一提供的第一坐标空间示意图；
图3为本发明实施例二提供的一种血管造影图像的分析装置的模块结构图；
图4为本发明实施例三提供的一种电子设备的结构示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部份实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
本发明实施例一提供的一种血管造影图像的分析方法，如图1为本发明实施例一提供的一种血管造影图像的分析方法示意图所示，本方法主要包括如下步骤：
步骤1，获取血管造影图像。
这里，血管造影图像可以为冠状动脉造影图像，也可以为其他部位、其他类型血管的造影图像。
步骤2，对血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像。
这里，本发明实施例采用基于机器深度学习技术的目标检测模型对血管造影图像进行血管狭窄部位检测并输出对应的目标检测框，将目标检测框覆盖的子图像提取出来既可作为狭窄部位子图像也就是第一图像。
步骤3，对第一图像进行二值化处理和图像降噪处理生成第一二值图；
这里，通过二值化与图像降噪可以提高血管边缘的识别精度；
具体包括：步骤31，对第一图像进行二值化处理生成对应的二值化图像；
其中，二值化图像的像素点包括前景像素点和背景像素点；前景像素点的像素值为预设的前景像素值A，背景像素点的像素值为预设的背景像素值B；
这里，前景像素值A一般预设为白色的灰度值，背景像素值B一般预设为黑色的灰度值；当然也可以基于设计需要，另行设定二值对前景像素值A和背景像素值B进行设定，例如采用0/1二值设定前景像素值A为1、背景像素值B为0；
步骤32，基于图像形态学的图像闭运算原理，对二值化图像进行先膨胀后腐蚀的图像闭运算操作，并将运算结果作为第一二值图。
这里，图像形态学的图像闭运算原理是对图像先进行图像膨胀处理，再进行图像腐蚀处理；其目的是为了填充原始图像中图形的内部空洞，并在不明显改变各图形面积的前提下使得图形边缘连接更平滑；关于图像闭运算以及图像膨胀、图像腐蚀的具体实现原理，可参看相关技术实现，在此不做一一赘述；
步骤4，对第一二值图进行血管识别处理生成对应的血管图像；
具体包括：步骤41，对所述第一二值图上每个像素值为预设的前景像素值A的像素点进行遍历；遍历时，对当前遍历像素点的八领域像素点的像素值进行获取生成对应的第一像素值集合；若第一像素值集合中至少有一个像素值与预设的背景像素值B一致，则将当前遍历像素点标记为边缘点；
这里，所谓八领域像素点实际就是图像中某个像素点的左上相邻像素点、上方相邻像素点、右上相邻像素点、右方相邻像素点、右下相邻像素点、下方相邻像素点、左下相邻像素点和左方相邻像素点这八个像素点；本发明实施例规定在判断一个前景像素点也就是像素值为预设的前景像素值A的像素点是否为边缘点时，对其八领域像素点中是否包括背景像素点进行识别，只要八领域像素点中有一个为背景像素点也就是像素值为背景像素值B，那么当前被判断的像素点就是边缘点；
步骤42，在第一二值图上，按顺时针或逆时针方向对边缘点进行依次连接构成闭合的血管边缘线；并将血管边缘线和边缘线以内的子图像，作为对应的血管图像。
步骤5，在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对第一二值图的血管图像进行中心线提取处理生成第一中心线；
这里，血管图像拓扑性质主要指的是血管的连通性；
具体包括：步骤51，创建保持血管图像拓扑性质的连通性判断规则；
这里，连通性判断规则包括多个子规则，每个子规则对应一个或多个3×3的像素值模板矩阵；
步骤52，复制第一二值图生成对应的第二二值图，将第二二值图上的血 管图像区域记为血管图像区域；
步骤53，基于拓扑形状规则，对第二二值图每行的像素点从左到右进行遍历，将不满足连通性判断规则的像素点标记为非必要像素点；在对第二二值图的所有像素点完成一次遍历之后，将像素值为前景像素值A的非必要像素点记为新增背景像素点，并将所有新增背景像素点的像素值设为背景像素值B，并新增背景像素点的数量进行统计得到新增数量；若新增数量不为0则对再次对设置后的第二二值图每行的像素点从左到右进行遍历，直到当次遍历得到的新增数量为0为止；并将最终第二二值图上处于血管图像区域的像素值为前景像素值A的像素点都标记为必要像素点；
这里，新增背景像素点就是新增的像素值为背景像素值B的像素点；
在对每个像素点进行遍历时，将当前遍历像素点及其对应的八领域像素点的像素值提取出来组成一个3×3的像素值矩阵记为遍历点像素矩阵，并将该遍历点像素矩阵与连通性判断规则的各个子规则的模板矩阵进行逐一比对；需要说明的是，若当前遍历像素点为图像边界像素点则其八领域像素点会有缺失，此时在构建遍历点像素矩阵时默认将缺失点的像素值设为背景像素值B；
在对遍历点像素矩阵与各个子规则的模板矩阵进行逐一比对时，当该遍历点像素矩阵与任一子规则的模板矩阵完全重合时，视当前遍历点像素矩阵对应的当前遍历像素点满足连通性判断规则，也就是说若删除当前遍历像素点会影响血管图像的拓扑连通性质，应不对该像素点做非必要像素点标记；当该遍历点像素矩阵与任一子规则的模板矩阵都不重合时，视当前遍历点像素矩阵对应的当前遍历像素点不满足连通性判断规则，也就是说若删除当前遍历像素点不会影响血管图像的拓扑连通性质，应将该像素点标记为非必要像素点；
例如，预设连通性判断规则包含以下5个子规则，
子规则1：像素值模板矩阵为
Figure PCTCN2022097246-appb-000001
A即为预设的前景像素值；该规则指明若遍历点像素矩阵与当前规则的模板矩阵一致，则删除当前遍历像素点(对应模板矩阵的中心点)会导致出现孔洞从而影响图像拓扑性质的连通性；
子规则2：像素值模板矩阵为
Figure PCTCN2022097246-appb-000002
B即为预设的背景像素值；该规则指明若遍历点像素矩阵与当前规则的模板矩阵一致，则删除当前遍历像素点(对应模板矩阵的中心点)会导致上下层断层从而影响图像拓扑性质的连通性；
子规则3：像素值模板矩阵为
Figure PCTCN2022097246-appb-000003
该规则指明若遍历点像素矩阵与当前规则的模板矩阵一致，则删除当前遍历像素点(对应模板矩阵的中心点)会导致出现孔洞从而影响图像拓扑性质的连通性；
子规则4：像素值模板矩阵为
Figure PCTCN2022097246-appb-000004
该规则指明若遍历点像素矩阵与当前规则的模板矩阵一致，则删除当前遍历像素点(对应模板矩阵的中心点)会导致上层端点被消减从而丢失图像连通形状的端点、影响图像拓扑性质的连通性；
子规则5：像素值模板矩阵包括
Figure PCTCN2022097246-appb-000005
和
Figure PCTCN2022097246-appb-000006
该规则指明若遍历点像素矩阵与当前规则的模板矩阵一致，则删除当前遍历像素点(对应模板矩阵的中心点)会导致连通端点被消减从而丢失图像连通形状的端点、影响图像拓扑性质的连通性；
若第二二值图整体像素点分布结构为
Figure PCTCN2022097246-appb-000007
其中
Figure PCTCN2022097246-appb-000008
就是血管图像的像素点；对第二二值图每行的像素点从左到右进行第一次遍历：
第1行左起第1个像素点，该点为边界点默认将其八领域像素点中的缺失点(左下、左方、左上、上方和右上)的像素值设为B，则对应的遍历点像素矩阵为
Figure PCTCN2022097246-appb-000009
使用子规则1、2、3、4、5的像素值模板矩阵与遍历点像素矩阵依次进行对比发现都能不重合，则视第1行左起第1个像素点为不满足连通性判断规则的像素点并将其标记为非必要像素点；依次类推，第1行其余像素点的遍历点像素矩阵也都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第1行所有像素点都被标记为非必要像素点；
同理,第2行所有像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第2行所有像素点都被标记为非必要像素点；
第3行第1、2个像素点的遍历点像素矩阵也不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第3行第1、2个像素点都被标记为非必要像素点；而第3行第3个像素点的遍历点像素矩阵为
Figure PCTCN2022097246-appb-000010
与子规则1的像素值模板矩阵重合，则视当前遍历像素点也就是第3行第3个像素点为满足连通性判断规则的像素点不对其做非必要像素点标记；第3行第4、5个像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第3行第4、5个像素点都被标记为非必要像素点；
第4行第1、2、4、5个像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，因此第4行第1、2、4、5个像素点都被标记为非必要像素点；而第4行第3个像素点与第3行第3个像素点类似，其 对应的遍历点像素矩阵为
Figure PCTCN2022097246-appb-000011
与子规则1的像素值模板矩阵重合，所以第4行第3个像素点为满足连通性判断规则的像素点不对其做非必要像素点标记；
第5行、第6行所有像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第5行、第6行所有像素点都被标记为非必要像素点；
在处理完第6行最后一个像素点之后，对第二二值图的第一次遍历结束，将像素值为前景像素值A的非必要像素点记为新增背景像素点并将所有新增背景像素点的像素值设为背景像素值B从而得到的新的第二二值图为
Figure PCTCN2022097246-appb-000012
对新增背景像素点的数量进行统计得到新增数量为10；因为本次新增背景像素点的新增数量10大于0，则需再次对第二二值图每行的像素点从左到右进行第二次遍历：
第1行、第2行所有像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第1行、第2行所有像素点都被标记为非必要像素点；
第3行第3个像素点的遍历点像素矩阵为
Figure PCTCN2022097246-appb-000013
与子规则5的其中一个像素值模板矩阵重合，则视当前遍历像素点也就是第3行第3个像素点为满足连通性判断规则的像素点不对其做非必要像素点标记；而第3行除第3个之外的其他像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第3行除第3个之外的其他像素点都被标记为非必要像素点；
第4行第3个像素点的遍历点像素矩阵为
Figure PCTCN2022097246-appb-000014
与子规则5的其中一个像素值模板矩阵重合，则视当前遍历像素点也就是第4行第3个像素点为满足连通性判断规则的像素点不对其做非必要像素点标记；而第4行除第3个之外的其他像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第4行除第3个之外的其他像素点都被标记为非必要像素点；
第5行、第6行所有像素点的遍历点像素矩阵都不能与子规则1、2、3、4、5的像素值模板矩阵重合，所以第5行、第6行所有像素点都被标记为非必要像素点；
在处理完第6行最后一个像素点之后，对第二二值图的第一次遍历结束，将像素值为前景像素值A的非必要像素点记为新增背景像素点并将所有新增背景像素点的像素值设为背景像素值B从而得到的新的第二二值图为
Figure PCTCN2022097246-appb-000015
这与第一次遍历结束后的二值图相比没有变化，对应的新增背景像素点的数量也就是增数量为0，这种情况下无需继续对第二二值图进行再次遍历，而是将最终第二二值图上处于血管图像区域的像素值为前景像素值A的像素点都标记为必要像素点，也就是将第3行第3个像素点和第4行第3个像素点记为必要像素点；
步骤54，根据第二二值图与第一二值图像素点的一一对应关系，在第一二值图上对与各个必要像素点对应的像素点进行顺次连接，并将连接线作为第一中心线。
这里，以步骤53的示例为例，也就是对第一二值图中的第3行第3个像素点和第4行第3个像素点进行连接得到第一中心线。
需要说明的是，因为第一二值图的原始图像也就是第一图像为血管造影图像的局部分割图像，受分割角度的影响可能导致第一二值图中血管两端的切割角度不是垂直于血管走向的，从而可能导致位于血管两个端头的中心线像素点的定位出现偏差；因此，在步骤54之后可通过对第一中心线两端各删除指定比例点数这种处理方式，来提高第一中心线上像素点的定位精度，从而达到提高第一中心线定位精度的目的。
步骤6，按从第一中心线的一个端点到另一个端点的方向，对第一中心线上的像素点进行排序生成第一像素点序列；
其中，第一像素点序列包括多个第一像素点。
步骤7，根据血管图像，对各个第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的第一像素点的排序顺序对第一直径进行排序生成第一直径序列。
进一步的，根据血管图像，对各个第一像素点位置处的血管直径进行测算生成对应的第一直径，具体包括：过各个第一像素点沿与其八领域像素点连接的四个方向做四条直线分别与血管图像的血管边缘线相交，从而得到对应的四条相交线段；并对四条相交线段中长度最短的一条相交线段的线段长度进行计算，并将计算结果作为与当前第一像素点对应的第一直径。
这里，四条直线分别为过左上相邻像素点-第一像素点-右下相邻像素点的直线1，过上方相邻像素点-第一像素点-下方相邻像素点的直线2，过右上相邻像素点-第一像素点-左下相邻像素点的直线3，过右方相邻像素点-第一像素点-左方相邻像素点的直线4；直线1、2、3、4与中心线两端血管边缘的相交线段记为相交线段1、2、3、4；将相交线段1、2、3、4中最短一条的线段长度作为第一直径。
步骤8，根据第一直径序列，对各个第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的第一像素点的排序顺序对第一狭窄率进行排序生成第一狭窄率序列。
进一步的，根据第一直径序列，对各个第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率，具体包括：以第一中心线的像素点索引为横轴、以像素点对应的血管直径为纵轴构建二维坐标空间记为第一坐标空间；以各个第一像素点在第一中心线上的像素点索引为横轴坐标、对应的第一直径为纵轴坐标，在第一坐标空间上标记出对应的坐标点记为第一坐标点；对各个第一坐标点进行依次连接得到第一直径变化曲线；对第一个和最后一个第一坐标点进行直线连接得到第一直径参考线；过各个第一坐标点做第一坐标空间的横轴垂线，并将横轴垂线与第一直径参考线的交点的血管直径纵坐标数值记为对应的第一参考直径；计算各个第一像素点对应的第一狭窄率r，r＝(1-d 1/d 2)×100％，d 1为各个第一像素点对应的第一直径，d 2为各个第一像素点对应的第一参考直径。
这里，以图2为本发明实施例一提供的第一坐标空间示意图为例，第一中心线上像素点索引为x 1的第一像素点，其对应的第一直径为y 1，在第一坐标空间上对应的第一坐标点为P 1(x 1,y 1)；从第一坐标点P 1(x 1,y 1)做的横轴垂线与第一直径参考线的交点就是P 2(x 1,y 2)，其血管直径纵坐标数值就是y 2，那么第一中心线上像素点索引为x 1的第一像素点对应的第一狭窄率r＝(1-d 1/d 2)×100％＝(1-y 1/y 2)×100％。
步骤9，将第一像素点序列、第一直径序列和第一狭窄率序列作为血管造影图像的血管狭窄分析数据进行返回。
这里，基于上述步骤1-9得到的第一像素点序列、第一直径序列和第一狭窄率序列，可以为血管造影图像上各个血管采样点增加像素级的血管中心线、血管直径和血管狭窄率语义参数，从而提高了血管造影图像的辨识精度；还可以对上述第一狭窄率序列进行均值或加权均值计算，并将计算结果作为当前片段血管的平均狭窄率以供用户进行统计分析；还可以从上述第一狭窄率序列中提取最大值作为当前片段血管的最大狭窄率以供用户进行统计分析。
图3为本发明实施例二提供的一种血管造影图像的分析装置的模块结构 图，该装置可以为实现本发明实施例方法的终端设备或者服务器，也可以为与上述终端设备或者服务器连接的实现本发明实施例方法的装置，例如该装置可以是上述终端设备或者服务器的装置或芯片系统。如图3所示，该装置包括：获取模块201、图像预处理模块202、中心线提取模块203和数据分析模块204。
获取模块201用于获取血管造影图像。
图像预处理模块202用于对血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像；并对第一图像进行二值化处理和图像降噪处理生成第一二值图；并对第一二值图进行血管识别处理生成对应的血管图像。
中心线提取模块203用于在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对第一二值图的血管图像进行中心线提取处理生成第一中心线；并按从第一中心线的一个端点到另一个端点的方向，对第一中心线上的像素点进行排序生成第一像素点序列；第一像素点序列包括多个第一像素点。
数据分析模块204用于根据血管图像，对各个第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的第一像素点的排序顺序对第一直径进行排序生成第一直径序列；并根据第一直径序列，对各个第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的第一像素点的排序顺序对第一狭窄率进行排序生成第一狭窄率序列；并将第一像素点序列、第一直径序列和第一狭窄率序列作为血管造影图像的血管狭窄分析数据进行返回。
本发明实施例提供的一种血管造影图像的分析装置，可以执行上述方法实施例中的方法步骤，其实现原理和技术效果类似，在此不再赘述。
需要说明的是，应理解以上装置的各个模块的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且这些模块可以全部以软件通过处理元件调用的形式实现；也可以全部以 硬件的形式实现；还可以部分模块通过处理元件调用软件的形式实现，部分模块通过硬件的形式实现。例如，获取模块可以为单独设立的处理元件，也可以集成在上述装置的某一个芯片中实现，此外，也可以以程序代码的形式存储于上述装置的存储器中，由上述装置的某一个处理元件调用并执行以上确定模块的功能。其它模块的实现与之类似。此外这些模块全部或部分可以集成在一起，也可以独立实现。这里所描述的处理元件可以是一种集成电路，具有信号的处理能力。在实现过程中，上述方法的各步骤或以上各个模块可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。
例如，以上这些模块可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(Application Specific Integrated Circuit，ASIC)，或，一个或多个数字信号处理器(Digital Signal Processor，DSP)，或，一个或者多个现场可编程门阵列(Field Programmable Gate Array，FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(Central Processing Unit，CPU)或其它可以调用程序代码的处理器。再如，这些模块可以集成在一起，以片上系统(System-on-a-chip，SOC)的形式实现。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机程序指令时，全部或部分地产生按照本发明实施例所描述的流程或功能。上述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。上述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，上述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线路(Digital Subscriber Line，DSL))或无线(例如红外、无线、蓝牙、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行 传输。上述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。上述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
图4为本发明实施例三提供的一种电子设备的结构示意图。该电子设备可以为前述的终端设备或者服务器，也可以为与前述终端设备或者服务器连接的实现本发明实施例方法的终端设备或服务器。如图4所示，该电子设备可以包括：处理器301(例如CPU)、存储器302、收发器303；收发器303耦合至处理器301，处理器301控制收发器303的收发动作。存储器302中可以存储各种指令，以用于完成各种处理功能以及实现本发明上述实施例中提供的方法和处理过程。优选的，本发明实施例涉及的电子设备还包括：电源304、系统总线305以及通信端口306。系统总线305用于实现元件之间的通信连接。上述通信端口306用于电子设备与其他外设之间进行连接通信。
在图4中提到的系统总线可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。该系统总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。通信接口用于实现数据库访问装置与其他设备(例如客户端、读写库和只读库)之间的通信。存储器可能包含随机存取存储器(Random Access Memory，RAM)，也可能还包括非易失性存储器(Non-Volatile Memory)，例如至少一个磁盘存储器。
上述的处理器可以是通用处理器，包括中央处理器CPU、网络处理器(Network Processor，NP)等；还可以是数字信号处理器DSP、专用集成电路ASIC、现场可编程门阵列FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
需要说明的是，本发明实施例还提供一种计算机可读存储介质，该存储 介质中存储有指令，当其在计算机上运行时，使得计算机执行上述实施例中提供的方法和处理过程。
本发明实施例还提供一种运行指令的芯片，该芯片用于执行上述实施例中提供的方法和处理过程。
本发明实施例提供了一种血管造影图像的分析方法、装置、电子设备及计算机可读存储介质，首先对血管造影图像的血管狭窄段进行图像提取并对提取图像进行二值化处理，再对二值图进行血管边缘提取从而得到血管图像，再基于拓扑细化方法对血管图像进行血管中心线提取，再基于提取出的血管中心线与血管边缘的几何关系对中心线上各点的直径进行测量，再基于得到的各点直径进一步算出各点的直径变化率作为对应的血管狭窄率。通过本发明，摆脱了对人工经验的依赖，提高了数据分析准确度。
专业人员应该还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上所述的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施方式而已，并不用于限定本发明的保护范围，凡在本发明的精神和原则之内，所做的任何 修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (8)

  1. 一种血管造影图像的分析方法，其特征在于，所述方法包括：
    获取血管造影图像；
    对所述血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像；
    对所述第一图像进行二值化处理和图像降噪处理生成第一二值图；
    对所述第一二值图进行血管识别处理生成对应的血管图像；
    在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对所述第一二值图的所述血管图像进行中心线提取处理生成第一中心线；
    按从所述第一中心线的一个端点到另一个端点的方向，对所述第一中心线上的像素点进行排序生成第一像素点序列；所述第一像素点序列包括多个第一像素点；
    根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的所述第一像素点的排序顺序对所述第一直径进行排序生成第一直径序列；
    根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的所述第一像素点的排序顺序对所述第一狭窄率进行排序生成第一狭窄率序列；
    将所述第一像素点序列、所述第一直径序列和所述第一狭窄率序列作为所述血管造影图像的血管狭窄分析数据进行返回。
  2. 根据权利要求1所述的血管造影图像的分析方法，其特征在于，所述对所述第一图像进行二值化处理和图像降噪处理生成第一二值图，具体包括：
    对所述第一图像进行二值化处理生成对应的二值化图像；所述二值化图像的像素点包括前景像素点和背景像素点；所述前景像素点的像素值为预设的前景像素值A，所述背景像素点的像素值为预设的背景像素值B；
    基于图像形态学的图像闭运算原理，对所述二值化图像进行先膨胀后腐 蚀的图像闭运算操作，并将运算结果作为所述第一二值图。
  3. 根据权利要求1所述的血管造影图像的分析方法，其特征在于，所述对所述第一二值图进行血管识别处理生成对应的血管图像，具体包括：
    对所述第一二值图上每个像素值为预设的前景像素值A的像素点进行遍历；遍历时，对当前遍历像素点的八领域像素点的像素值进行获取生成对应的第一像素值集合；若所述第一像素值集合中至少有一个像素值与预设的背景像素值B一致，则将所述当前遍历像素点标记为边缘点；
    在所述第一二值图上，按顺时针或逆时针方向对所述边缘点进行依次连接构成闭合的血管边缘线；并将所述血管边缘线和边缘线以内的子图像，作为对应的所述血管图像。
  4. 根据权利要求1所述的血管造影图像的分析方法，其特征在于，所述根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径，具体包括：
    过各个所述第一像素点沿与其八领域像素点连接的四个方向做四条直线分别与所述血管图像的血管边缘线相交，从而得到对应的四条相交线段；并对四条相交线段中长度最短的一条相交线段的线段长度进行计算，并将计算结果作为与当前第一像素点对应的所述第一直径。
  5. 根据权利要求1所述的血管造影图像的分析方法，其特征在于，所述根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率，具体包括：
    以所述第一中心线的像素点索引为横轴、以像素点对应的血管直径为纵轴构建二维坐标空间记为第一坐标空间；
    以各个所述第一像素点在所述第一中心线上的像素点索引为横轴坐标、对应的所述第一直径为纵轴坐标，在所述第一坐标空间上标记出对应的坐标点记为第一坐标点；
    对各个所述第一坐标点进行依次连接得到第一直径变化曲线；
    对第一个和最后一个所述第一坐标点进行直线连接得到第一直径参考线；
    过各个所述第一坐标点做所述第一坐标空间的横轴垂线，并将横轴垂线与所述第一直径参考线的交点的血管直径纵坐标数值记为对应的第一参考直径；
    计算各个所述第一像素点对应的所述第一狭窄率r，r＝(1-d 1/d 2)×100％，d 1为各个所述第一像素点对应的所述第一直径，d 2为各个所述第一像素点对应的所述第一参考直径。
  6. 一种用于实现权利要求1-5任一项所述的血管造影图像的分析方法步骤的装置，其特征在于，所述装置包括：获取模块、图像预处理模块、中心线提取模块和数据分析模块；
    所述获取模块用于获取血管造影图像；
    所述图像预处理模块用于对所述血管造影图像进行血管狭窄部位检测，并将检测出的狭窄部位子图像作为第一图像；并对所述第一图像进行二值化处理和图像降噪处理生成第一二值图；并对所述第一二值图进行血管识别处理生成对应的血管图像；
    所述中心线提取模块用于在不改变血管图像拓扑性质的前提下，基于拓扑细化方法对所述第一二值图的所述血管图像进行中心线提取处理生成第一中心线；并按从所述第一中心线的一个端点到另一个端点的方向，对所述第一中心线上的像素点进行排序生成第一像素点序列；所述第一像素点序列包括多个第一像素点；
    所述数据分析模块用于根据所述血管图像，对各个所述第一像素点位置处的血管直径进行测算生成对应的第一直径；并按对应的所述第一像素点的排序顺序对所述第一直径进行排序生成第一直径序列；并根据所述第一直径序列，对各个所述第一像素点位置处的血管狭窄率进行识别生成对应的第一狭窄率；并按对应的所述第一像素点的排序顺序对所述第一狭窄率进行排序生成第一狭窄率序列；并将所述第一像素点序列、所述第一直径序列和所述第 一狭窄率序列作为所述血管造影图像的血管狭窄分析数据进行返回。
  7. 一种电子设备，其特征在于，包括：存储器、处理器和收发器；
    所述处理器用于与所述存储器耦合，读取并执行所述存储器中的指令，以实现权利要求1-5任一项所述的方法步骤；
    所述收发器与所述处理器耦合，由所述处理器控制所述收发器进行消息收发。
  8. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机指令，当所述计算机指令被计算机执行时，使得所述计算机执行权利要求1-5任一项所述的方法的指令。
PCT/CN2022/097246 2022-01-07 2022-06-07 一种血管造影图像的分析方法和装置 WO2023130664A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210017847.5 2022-01-07
CN202210017847.5A CN114418976A (zh) 2022-01-07 2022-01-07 一种血管造影图像的分析方法和装置

Publications (1)

Publication Number Publication Date
WO2023130664A1 true WO2023130664A1 (zh) 2023-07-13

Family

ID=81271290

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/097246 WO2023130664A1 (zh) 2022-01-07 2022-06-07 一种血管造影图像的分析方法和装置

Country Status (2)

Country Link
CN (1) CN114418976A (zh)
WO (1) WO2023130664A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117974543A (zh) * 2023-10-23 2024-05-03 郑州大学 一种用于血管介入手术的图像处理方法、系统及存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114418976A (zh) * 2022-01-07 2022-04-29 乐普（北京）医疗器械股份有限公司 一种血管造影图像的分析方法和装置
CN116612102A (zh) * 2023-05-31 2023-08-18 上海博动医疗科技股份有限公司 血管图像处理系统、装置及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190029625A1 (en) * 2015-03-31 2019-01-31 Agency For Science, Technology And Research Method and apparatus for assessing blood vessel stenosis
CN110490040A (zh) * 2019-05-30 2019-11-22 浙江理工大学 一种识别dsa冠状动脉图像中局部血管狭窄程度的方法
CN112037170A (zh) * 2020-07-23 2020-12-04 上海交通大学附属第六人民医院 一种血管狭窄的检出方法、装置以及计算机存储介质
CN114418976A (zh) * 2022-01-07 2022-04-29 乐普（北京）医疗器械股份有限公司 一种血管造影图像的分析方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190029625A1 (en) * 2015-03-31 2019-01-31 Agency For Science, Technology And Research Method and apparatus for assessing blood vessel stenosis
CN110490040A (zh) * 2019-05-30 2019-11-22 浙江理工大学 一种识别dsa冠状动脉图像中局部血管狭窄程度的方法
CN112037170A (zh) * 2020-07-23 2020-12-04 上海交通大学附属第六人民医院 一种血管狭窄的检出方法、装置以及计算机存储介质
CN114418976A (zh) * 2022-01-07 2022-04-29 乐普（北京）医疗器械股份有限公司 一种血管造影图像的分析方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117974543A (zh) * 2023-10-23 2024-05-03 郑州大学 一种用于血管介入手术的图像处理方法、系统及存储介质
CN117974543B (zh) * 2023-10-23 2024-09-20 郑州大学 一种用于血管介入手术的图像处理方法、系统及存储介质

Also Published As

Publication number Publication date
CN114418976A (zh) 2022-04-29

Similar Documents

Publication Publication Date Title
WO2023130664A1 (zh) 一种血管造影图像的分析方法和装置
CN110781885A (zh) 基于图像处理的文本检测方法、装置、介质及电子设备
WO2023130663A1 (zh) 基于血管造影视频进行冠脉造影定量分析的方法和装置
CN112560862B (zh) 文本识别方法、装置及电子设备
CN110334390B (zh) Cad中外墙识别方法、装置、存储介质及处理器
TW202040511A (zh) 資料處理方法、瑕疵的檢測方法、計算設備及儲存媒體
CN112837290A (zh) 一种基于种子填充算法的裂缝图像自动识别方法
CN113240623B (zh) 一种路面病害检测方法及装置
CN113011509B (zh) 肺部支气管的分类方法、装置、电子设备和存储介质
CN115082444B (zh) 一种基于图像处理的铜管焊缝缺陷检测方法及系统
CN115273115A (zh) 一种文档元素标注方法、装置、电子设备和存储介质
WO2023137948A1 (zh) 基于血管造影图像分析血流储备分数的处理方法和装置
CN113505261A (zh) 数据标注方法、装置以及数据标注模型训练方法、装置
WO2024040856A1 (zh) 一种缺陷检测方法、装置、电子设备及存储介质
CN114387332B (zh) 一种管道测厚方法及装置
CN114596302A (zh) 一种pcb板缺陷检测方法、系统、介质、设备及终端
WO2024125434A1 (zh) 基于区域一致性的建筑物主角度修正方法
CN114299057A (zh) 血管中心线的提取方法和存储介质
CN114119569A (zh) 基于机器学习的成像测井图像裂缝分割与识别方法和系统
CN113887375A (zh) 一种文本识别方法、装置、设备及存储介质
CN113435289A (zh) 空间分割方法、装置、设备及存储介质
CN117523087A (zh) 基于内容识别的三维模型优化方法
CN111857703A (zh) 一种界面中图层的匹配方法、装置及电子设备
CN115147359B (zh) 肺叶分割网络模型训练方法、装置、电子设备及存储介质
CN113808144B (zh) 基于直方图拟合的密度峰值聚类土壤图像阴影检测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22918120

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE