CN114418977A - Method and device for coronary angiography quantitative analysis based on angiography video - Google Patents
Method and device for coronary angiography quantitative analysis based on angiography video Download PDFInfo
- Publication number
- CN114418977A CN114418977A CN202210018415.6A CN202210018415A CN114418977A CN 114418977 A CN114418977 A CN 114418977A CN 202210018415 A CN202210018415 A CN 202210018415A CN 114418977 A CN114418977 A CN 114418977A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel point
- blood vessel
- video
- target detection
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the invention relates to a method and a device for coronary angiography quantitative analysis based on an angiography video, wherein the method comprises the following steps: acquiring an angiography video; extracting video frame images to generate a first image sequence; performing target detection and semantic segmentation processing of a narrow blood vessel on each first image in the first image sequence based on an image target detection and semantic segmentation model so as to obtain one or more target detection frames for marking the narrow blood vessel and a narrow blood vessel mask image in each target detection frame on each first image; carrying out image optimization processing on the first image sequence to obtain an appointed number of optimized images; and performing coronary angiography quantitative analysis on the blood vessel mask image of the narrow section in each target detection frame on each optimal image to generate a corresponding blood vessel stenosis rate. The method can avoid excessive dependence on manual experience in the traditional method, and improve the image extraction accuracy and the stenosis rate calculation precision.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a coronary angiography quantitative analysis method and device based on an angiography video.
Background
Coronary stenosis can lead to insufficient blood supply to the heart, thereby causing myocardial dysfunction and/or disease. The angiography technology is based on the principle that X-rays cannot penetrate through a developer, the developer is injected into a blood vessel of a detection object, and an angiography video is output by performing image shooting on the process that the developer passes through the blood vessel under the X-rays. When detecting the stenosis of the coronary artery, conventionally, an angiography video of the coronary artery is obtained based on an angiography technology, and then a doctor selects a video image with a stenosis section blood vessel from the angiography video according to personal experience to perform quantitative Analysis of the stenosis rate of the blood vessel, which is also called Qualitative Comparative Analysis (QCA), so as to calculate the corresponding stenosis rate of the blood vessel. Such an operation mode is too dependent on human factors, such as the working experience of people and the recognition capability of human eyes, and is very likely to cause problems of inaccurate video image extraction, insufficient narrow rate calculation precision, and the like.
Disclosure of Invention
The invention aims to provide a method, a device, electronic equipment and a computer readable storage medium for coronary angiography quantitative analysis based on an angiography video, which are used for carrying out video interception and video frame image extraction on the angiography video of coronary vessels, carrying out target detection and semantic segmentation processing on narrow-segment vessels on an extracted image sequence based on an image target detection and semantic segmentation model, optimizing an extracted image based on confidence coefficient of target identification, and carrying out coronary angiography quantitative analysis on each narrow-segment vessel on the optimized image to generate a corresponding angiostenosis rate. The method can avoid excessive dependence on manual experience in the traditional method, and improve the image extraction accuracy and the stenosis rate calculation precision.
In order to achieve the above object, a first aspect of the embodiments of the present invention provides a method for coronary angiography quantitative analysis based on an angiography video, where the method includes:
acquiring an angiography video of coronary angiography;
extracting video frame images of the angiography video to generate a corresponding first image sequence;
performing target detection and semantic segmentation processing on a narrow blood vessel on each first image in the first image sequence based on a preset image target detection and semantic segmentation model, so as to obtain one or more target detection frames for marking the narrow blood vessel and a narrow blood vessel mask image in each target detection frame on each first image; each target detection frame corresponds to a detection frame confidence;
performing image optimization processing on the first image sequence according to the confidence of the detection frame to obtain an appointed number of optimized images;
and performing coronary angiography quantitative analysis on the blood vessel mask image of the narrow section in each target detection frame on each preferred image to generate a corresponding blood vessel narrow rate.
Preferably, the extracting the video frame image of the angiography video to generate a corresponding first image sequence specifically includes:
video interception is carried out on the angiography video, and the video content of the coronary artery filling phase of the contrast agent is reserved to generate a corresponding intercepted angiography video;
according to the time sequence, carrying out video frame image extraction processing on the intercepted contrast video to generate a corresponding video frame image sequence, and carrying out statistics on the number of video frame images of the video frame image sequence to generate a corresponding first total number; the sequence of video frame images comprises a plurality of video frame images;
when the first total number does not exceed a preset image total number threshold value, taking each video frame image as a corresponding first image, and sequencing all the obtained first images according to time sequence to generate a first image sequence;
when the first total number exceeds the image total number threshold value, extracting the video frame images with all odd indexes as the corresponding first images from the video frame image sequence, or extracting the video frame images with all even indexes as the corresponding first images; and sequencing all the obtained first images according to the time sequence to generate the first image sequence.
Preferably, the image target detection and semantic segmentation model comprises a Mask R-CNN model; when the image target detection and semantic segmentation model is a Mask R-CNN model, a residual error network ResNet50 is used as a characteristic extraction backbone network.
Preferably, the performing image optimization processing on the first image sequence according to the detection frame confidence to obtain an appointed number of optimized images specifically includes:
in the first image sequence, performing mean calculation on the detection frame confidence coefficients of all the target detection frames on each first image to generate a corresponding first image average confidence coefficient;
and sequencing all the first images according to the sequence of the average confidence degrees of the corresponding first images from large to small, and taking the first images with the appointed number which are sequenced at the top as the preferred images.
Preferably, the performing coronary angiography quantitative analysis on the stenosis section blood vessel mask image in each of the target detection frames on each of the preferred images to generate a corresponding blood vessel stenosis rate specifically includes:
traversing each target detection frame on the current preferred image, and recording the currently traversed target detection frame as a current target detection frame;
identifying blood vessel edges and blood vessel center lines of the narrow blood vessel mask image in the current target detection frame to generate corresponding first blood vessel edges and first center lines; the first central line comprises a plurality of central line pixel points PiWhereinFirst central line pixel point P1The point closest to the coronary artery entrance in the blood flow direction and the last central line pixel point PNI is more than or equal to 1 and less than or equal to N, wherein N is the total number of central line pixel points of the first central line;
according to the first blood vessel edge, carrying out pixel point P on each central line on the first central lineiAnalyzing the corresponding vessel diameter length to generate a corresponding first vessel diameter di；
According to the central line pixel point P1To the central line pixel point PNAnd each central line pixel point PiOf said first vessel diameter diFor each of the center line pixel points PiAnalyzing the corresponding stenosis rate to generate a corresponding first stenosis rate ri；
From all the obtained first stenosis rates riSelecting a maximum value as the blood vessel stenosis rate corresponding to the stenosis section blood vessel mask image within the current target detection frame.
Further, according to the first blood vessel edge, each center line pixel point P on the first center line is processediAnalyzing the corresponding vessel diameter length to generate a corresponding first vessel diameter diThe method specifically comprises the following steps:
pixel point P according to the central lineiThe direction relation with the adjacent eight-domain pixel point is that the pixel point P passes through the central lineiMaking four straight lines which are respectively marked as a first straight line, a second straight line, a third straight line and a fourth straight line; the first straight line passes through the central line pixel point PiThe upper left adjacent pixel point and the central line pixel point PiAnd said center line pixel point PiThe right lower adjacent pixel point; the second straight line passes through the central line pixel point PiThe upper adjacent pixel point of (2), the central line pixel point PiAnd said center line pixel point PiThe lower adjacent pixel point of (1); the third straight line passes through the central line pixel point PiThe upper right adjacent pixel point and the central line pixel pointPiAnd said center line pixel point PiThe left lower adjacent pixel point; the third straight line passes through the central line pixel point PiRight-hand adjacent pixel point and central line pixel point PiAnd said center line pixel point PiThe left adjacent pixel point of (1);
marking the line segments of the first, second, third and fourth straight lines intersected with the first blood vessel edge as corresponding first, second, third and fourth line segments respectively; calculating the line segment lengths of the first line segment, the second line segment, the third line segment and the fourth line segment to generate corresponding first line segment length, second line segment length, third line segment length and fourth line segment length; and selecting the minimum value from the first, second, third and fourth line segment lengths as the pixel point P corresponding to the central lineiCorresponding first vessel diameter di。
Further, the pixel point P according to the central line1To the central line pixel point PNAnd each central line pixel point PiOf said first vessel diameter diFor each of the center line pixel points PiAnalyzing the corresponding stenosis rate to generate a corresponding first stenosis rate riThe method specifically comprises the following steps:
according to the first vessel diameter d1And the first vessel diameter dNConstructing a pixel point P reflecting the central line1To the central line pixel point PNLinear function f (i) of the linear change relationship of blood vessel, f (i) ═ d1+k*(i-1)，k＝(dN-d1)/(N-1)；
According to the linear variation relation function f (i), each central line pixel point P is subjected toiCalculating the corresponding linear variable diameter length to generate a corresponding first reference diameter d’ i；
According to the first vessel diameter diAnd said first reference diameter d’ iCalculating each central line pixel point PiCorresponding said first stenosis rate ri，ri＝1-di/d’ i。
A second aspect of an embodiment of the present invention provides an apparatus for implementing the method according to the first aspect, where the apparatus includes: the system comprises an acquisition module, an image preprocessing module, a narrow-section blood vessel processing module, an image optimizing module and a quantitative analysis module;
the acquisition module is used for acquiring an angiography video for coronary angiography;
the image preprocessing module is used for extracting video frame images of the angiography video to generate a corresponding first image sequence;
the narrow-segment blood vessel processing module is used for carrying out narrow-segment blood vessel target detection and semantic segmentation processing on each first image in the first image sequence based on a preset image target detection and semantic segmentation model, so that one or more target detection frames for marking a narrow-segment blood vessel and a narrow-segment blood vessel mask image in each target detection frame are obtained on each first image; each target detection frame corresponds to a detection frame confidence;
the image optimization module is used for performing image optimization processing on the first image sequence according to the detection frame confidence degree to obtain an appointed number of optimized images;
the quantitative analysis module is used for performing coronary angiography quantitative analysis on the stenosis section blood vessel mask image in each target detection frame on each preferred image to generate a corresponding blood vessel stenosis rate.
A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;
the processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps of the first aspect;
the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a computer, cause the computer to perform the method of the first aspect.
The embodiment of the invention provides a coronary angiography quantitative analysis method based on an angiography video, a device, electronic equipment and a computer readable storage medium, wherein the coronary angiography video is subjected to video interception and video frame image extraction processing, the extracted image sequence is subjected to target detection and semantic segmentation processing of a narrow blood vessel based on an image target detection and semantic segmentation model, the extracted image is optimized based on confidence coefficient of target identification, and each narrow blood vessel is subjected to coronary angiography quantitative analysis on the optimized image to generate a corresponding blood vessel stenosis rate. The method gets rid of the excessive dependence on the manual experience in the traditional method, and improves the image extraction accuracy and the stenosis rate calculation precision.
Drawings
Fig. 1 is a schematic diagram of a method for performing coronary angiography quantitative analysis based on an angiography video according to an embodiment of the present invention;
fig. 2 is a block diagram of an apparatus for performing coronary angiography quantitative analysis based on an angiography video according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic diagram of a method for performing coronary angiography quantitative analysis based on an angiography video according to an embodiment of the present invention, and the method mainly includes the following steps:
Here, the coronary angiography is imaging of a process in which a contrast medium is injected into a blood vessel to be detected and the contrast medium passes through the coronary blood vessel under X-ray, and the angiography video is video data obtained by the imaging.
the method specifically comprises the following steps: step 21, video interception is carried out on the angiography video, and the video content of the coronary artery filling phase of the contrast agent is reserved to generate a corresponding intercepted angiography video;
here, because the angiogram video includes the whole-process video content from the time when the contrast agent is injected into the blood vessel to the time when the contrast agent gradually fills the whole coronary artery and then gradually dissipates, the embodiment of the present invention focuses on the video content after the contrast agent reaches the coronary artery, and in order to improve the data analysis efficiency, the angiogram video is subjected to video interception in advance, and there are various ways of interception; one of the two methods is to set a relative time threshold according to the implementation experience of coronary artery angiography and cut off the video data in the angiography video before the relative time threshold, and to retain the video data after the relative time threshold as the video content of the contrast agent filling coronary artery phase to generate a corresponding cut-off angiography video;
step 22, extracting and processing video frame images of the captured contrast video according to a time sequence to generate a corresponding video frame image sequence, and counting the number of the video frame images of the video frame image sequence to generate a corresponding first total number; wherein the sequence of video frame images comprises a plurality of video frame images;
each type of video data is provided with a corresponding video sampling frame rate parameter by default, the video frame images of the captured angiography video are extracted according to the video sampling frame rate parameter corresponding to the angiography video, each extracted frame image is a video frame image, and the video frame images are sequenced according to the time sequence to obtain a video frame image sequence;
step 23, when the first total number does not exceed the preset image total number threshold, taking each video frame image as a corresponding first image, and sequencing all the obtained first images according to the time sequence to generate a first image sequence; when the first total number exceeds the total number threshold value of the images, extracting video frame images with all odd indexes of the sequencing indexes from the video frame image sequence as corresponding first images, or extracting video frame images with all even indexes of the sequencing indexes as corresponding first images; and sequencing all the obtained first images according to the time sequence to generate a first image sequence.
Here, if the number of images in the video frame image sequence is too large, the model operation efficiency in the subsequent steps is affected, and in order to improve the model operation efficiency, the number of images in the video frame image sequence needs to be controlled in advance; the control method is that a total number threshold value of images is preset, and whether the total number of the images in the video frame image sequence, namely the first total number, exceeds the threshold value is identified; if the number of the images does not exceed the threshold value, the number of the images in the video frame image sequence does not need to be reduced, each video frame image is directly used as a first image, and the first image sequence consisting of the first images is sent to the subsequent steps for processing; if the number of the images exceeds the threshold, the number of the images in the video frame image sequence needs to be reduced, in order to ensure that effective data is not lost due to image reduction, a method of frame extraction and reduction on adjacent images is adopted during reduction to achieve the purpose of not losing the effective data, and the frame extraction and reduction on the adjacent images is performed when all odd frames or all even frames are extracted from the video frame image sequence to form a first image sequence.
each target detection frame corresponds to one detection frame confidence coefficient; the image target detection and semantic segmentation model comprises a Mask R-CNN model; when the image target detection and semantic segmentation model is a Mask R-CNN model, a residual error network ResNet50 is used as a characteristic extraction backbone network.
The image target detection and semantic segmentation model is used for carrying out narrow-segment blood vessel target detection on the input first image, so as to obtain one or more target detection frames for marking a narrow-segment blood vessel, and the detection frame confidence of each target detection frame is used for identifying the confidence of the in-frame image as a narrow-segment blood vessel image; the image target detection and semantic segmentation model is also used for performing image semantic segmentation on the identified target, namely the identified narrow-segment blood vessel in each target detection frame, and taking the segmented mask image as a narrow-segment blood vessel mask image;
the image target detection and semantic segmentation model can be realized in various ways, wherein one way is realized by a neural network architecture based on a Mask R-CNN model; when the image target detection and semantic segmentation model is specifically a Mask R-CNN model, the neural network structure thereof can refer to the ' Mask R-CNN ' published by authors Kaiming He, Georgia Gkioxari, Piotr Doll ' ar and Ross Girshick, and includes: a feature extraction Network layer, a Region candidate Network (RPN) layer, a Region Of Interest (ROI Align) Network layer, and a Region header (ROI HEAD) Network layer; the feature extraction network layer is connected with the regional candidate network layer, and the regional candidate network layer is connected with the regional alignment network layer; the area alignment network layer is connected with the area head network layer; the regional head network layer comprises; the two sub-networks are respectively a target detection branch network and a target division branch network; the target detection branch network is used for outputting a target detection frame and a detection frame confidence coefficient of a narrow-section blood vessel, and the target segmentation branch network is used for outputting a narrow-section blood vessel mask image;
the Feature extraction Network layer of the embodiment of the invention is specifically composed of a five-level Residual error Network (ResNet) and a corresponding five-level Feature Pyramid Network (FPN); the regional candidate network layer comprises a five-level regional candidate network and corresponds to the five-level feature pyramid network; when the five-level residual error network is realized, the embodiment of the invention uses a ResNet-50 network structure for realizing and uses the ResNet-50 network structure as a backbone network for feature extraction.
Step 4, performing image optimization processing on the first image sequence according to the confidence of the detection frame to obtain an appointed number of optimized images;
the method specifically comprises the following steps: in the first image sequence, carrying out mean value calculation on the detection frame confidence coefficients of all target detection frames on each first image to generate a corresponding first image average confidence coefficient; and sequencing all the first images according to the sequence of the average confidence degrees of the corresponding first images from large to small, and taking the first images with the appointed number which are sequenced at the front as preferred images.
Here, the higher the average confidence of the first image is, the more obvious the vessel features of the narrow section on the corresponding first image are; the specified number is set according to specific requirements, for example, if the specified number is 3, the current step will extract 3 first images with most obvious narrow-segment blood vessel characteristics from the first image sequence as preferred images.
the method specifically comprises the following steps: step 51, traversing each target detection frame on the current preferred image, and recording the currently traversed target detection frame as a current target detection frame;
step 52, identifying the blood vessel edge and the blood vessel center line of the narrow blood vessel mask image in the current target detection frame to generate a corresponding first blood vessel edge and a first center line;
wherein the first central line comprises a plurality of central line pixel points PiWherein the first central line pixel point P1The point closest to the coronary artery entrance in the blood flow direction and the last central line pixel point PNI is more than or equal to 1 and less than or equal to N, wherein N is the total number of central line pixel points of the first central line;
here, there are various methods for implementing blood vessel edge recognition on a narrow-segment blood vessel mask image; performing binarization processing on the image content of the current target detection frame to obtain a first binary image, wherein the pixel values of all pixel points of an original narrow-section blood vessel mask image on the first binary image are converted into a preset foreground pixel value A, and the pixel values of all pixel points except the narrow-section blood vessel mask image are converted into a preset background pixel value B; then, performing point-by-point traversal on each pixel point of which the pixel value on the first binary image is the foreground pixel value A, and regarding the current traversed pixel point as an edge point if one pixel value of the adjacent eight-domain pixel points of the current traversed pixel point is the background pixel value B during the traversal; after traversing is completed, all edge points are sequentially connected in a clockwise or anticlockwise mode to obtain a closed curve which is the edge of the blood vessel; here, the adjacent eight-domain pixel points are actually eight pixel points, namely an upper left adjacent pixel point, an upper right adjacent pixel point, a right adjacent pixel point, a lower left adjacent pixel point and a left adjacent pixel point of the pixel point;
here, there are various methods for identifying the center line of the blood vessel in the mask image of the narrow blood vessel; performing binarization processing on the image content of the current target detection frame to obtain a second binary image, wherein the pixel values of all pixel points of the original narrow-section blood vessel mask image on the second binary image are converted into a preset foreground pixel value A, and the pixel values of all pixel points outside the narrow-section blood vessel mask image are converted into a preset background pixel value B; on the premise of not changing the topological property of the blood vessel image, performing centerline extraction processing on the narrow blood vessel mask image of the first binary image based on a topological refinement method to generate a first centerline; here, the topological property of the blood vessel image mainly refers to the connectivity of the blood vessel;
when obtaining the first central line, for marking the direction of the central line, a point closest to the coronary artery entrance, namely a narrow section entrance point is specially used as a first central line pixel point P of the first central line1The point farthest from the coronary artery entrance, i.e., the exit point of the stenosis, is taken as the farthest point of the first centerlineThe next central line pixel point PN；
Step 53, according to the first blood vessel edge, aligning each center line pixel point P on the first center lineiAnalyzing the corresponding vessel diameter length to generate a corresponding first vessel diameter di；
The method specifically comprises the following steps: step 531, pressing the center line pixel point PiThe direction relation with the adjacent eight-domain pixel point, the over-center line pixel point PiMaking four straight lines which are respectively marked as a first straight line, a second straight line, a third straight line and a fourth straight line;
wherein, the first straight line passes through the central line pixel point PiUpper left adjacent pixel point and central line pixel point PiAnd a center line pixel point PiThe right lower adjacent pixel point; second straight line passing through central line pixel point PiUpper adjacent pixel point, central line pixel point PiAnd a center line pixel point PiThe lower adjacent pixel point of (1); third straight line passing through center line pixel point PiUpper right adjacent pixel point, center line pixel point PiAnd a center line pixel point PiThe left lower adjacent pixel point; third straight line passing through center line pixel point PiRight-hand adjacent pixel point and central line pixel point PiAnd a center line pixel point PiThe left adjacent pixel point of (1);
step 532, marking the line segments of the first, second, third and fourth straight lines intersected with the first blood vessel edge as corresponding first, second, third and fourth line segments respectively; calculating the line segment lengths of the first line segment, the second line segment, the third line segment and the fourth line segment to generate corresponding first line segment length, second line segment length, third line segment length and fourth line segment length; and selecting the minimum value from the first, second, third and fourth line segment lengths as a pixel point P with the central lineiCorresponding first vessel diameter di；
Here, the over-center line pixel P is first knowniThe vessel diameter to the first vessel edge should be at all over-center line pixel points PiWithin the linear range of (d); only 4 lines can be actually made on the image by passing through any pixel point, namely the first, second, third and fourth lines, namely the pixel point P passing through the center lineiThe vessel diameter to the first vessel edge can only be one of the first, second, third and fourth line segments; after the selection range of the blood vessel diameter is determined, the length of the shortest line segment is taken as a center line pixel point PiCorresponding first vessel diameter di；
Step 54, according to the central line pixel point P1To the central line pixel point PNAnd each central line pixel point PiFirst vessel diameter diFor each central line pixel point PiAnalyzing the corresponding stenosis rate to generate a corresponding first stenosis rate ri；
The method specifically comprises the following steps: step 541, based on the first vessel diameter d1And a first vessel diameter dNConstructing a pixel point P reflecting the central line1To the central line pixel point PNLinear function f (i) of the linear change relationship of blood vessel, f (i) ═ d1+k*(i-1)，k＝(dN-d1)/(N-1)；
Step 542, according to the linear variation relation function f (i), for each central line pixel point PiCalculating the corresponding linear variable diameter length to generate a corresponding first reference diameter d’ i；
Here, under the condition that no stenosis or mutation of the blood vessel occurs, the diameter of the blood vessel should have a certain linear relationship with the distance between the position of the blood vessel and the entrance of the coronary artery, and for a section of branch blood vessel, the diameter of the entrance and the exit of the branch blood vessel also have a certain linear relationship; the normal caliber of any point on a section of blood vessel, namely the first reference diameter d, can be obtained by confirming the linear relation of the inlet and the outlet of the section of blood vessel’ i；
543, according to the first blood vessel diameter diAnd a first reference diameter d’ iCalculating each central line pixel point PiCorresponding first stenosis rate ri，ri＝1-di/d’ i；
Here, if a stenosis mutation occurs at a certain position in a certain section of blood vessel, the diameter of the stenosis at the position is obtained, that is, the first diameterDiameter d of blood vesseliAnd then based on the corresponding first reference diameter d’ iThe stenosis rate of the blood vessel at the position, i.e. the first stenosis rate r, can be calculatedi；
From all the obtained first stenosis rates r, step 55iSelecting the maximum value as a blood vessel stenosis rate corresponding to a stenosis section blood vessel mask image in the current target detection frame;
here, the embodiment of the present invention takes the maximum stenosis rate in a segment of blood vessel as the blood vessel stenosis rate of the segment of blood vessel, that is, the mask image of the narrowed segment of blood vessel in the current target detection frame;
and step 56, taking the next unprocessed target detection frame as the current target detection frame, and continuing to process in step 52 until the blood vessel stenosis rates of all the narrow-segment blood vessel mask images in the target detection frames on the current preferred image are confirmed.
Through the steps 1-5, a plurality of preferred images can be extracted from a section of angiography video, and the angiostenosis rate of one or more narrow-segment blood vessels on each preferred image can be obtained through coronary angiography quantitative analysis. After the analysis results of a plurality of preferred images are obtained, a plurality of preferred images with the target detection frame of the narrow blood vessel and the blood vessel stenosis rate can be simultaneously provided for a doctor as parameter data; or carrying out image fusion on a plurality of preferable images, carrying out average value calculation on the blood vessel stenosis rate of the narrow section of the blood vessel at the same position, and finally providing a fused image with a narrow section of blood vessel target detection frame and the blood vessel stenosis rate average value for a doctor to serve as parameter data.
Fig. 2 is a block diagram of an apparatus for performing coronary angiography quantitative analysis based on an angiography video according to a second embodiment of the present invention, where the apparatus may be a terminal device or a server for implementing the method according to the second embodiment of the present invention, or an apparatus connected to the terminal device or the server for implementing the method according to the second embodiment of the present invention, and for example, the apparatus may be an apparatus or a chip system of the terminal device or the server. As shown in fig. 2, the apparatus includes: an acquisition module 201, an image preprocessing module 202, a stenosis section blood vessel processing module 203, an image optimization module 204 and a quantitative analysis module 205.
The acquisition module 201 is used to acquire angiographic video of coronary angiography.
The image preprocessing module 202 is configured to perform video frame image extraction on the angiography video to generate a corresponding first image sequence.
The narrow blood vessel processing module 203 is used for carrying out narrow blood vessel target detection and semantic segmentation processing on each first image in the first image sequence based on a preset image target detection and semantic segmentation model, so as to obtain one or more target detection frames for marking the narrow blood vessel and a narrow blood vessel mask image in each target detection frame on each first image; each target detection frame corresponds to a detection frame confidence.
The image optimization module 204 is configured to perform image optimization on the first image sequence according to the detection frame confidence to obtain a specified number of optimized images.
The quantitative analysis module 205 is configured to perform coronary angiography quantitative analysis on the stenosis mask image within each target detection frame on each of the preferred images to generate a corresponding stenosis rate.
The device for coronary angiography quantitative analysis based on the angiography video provided by the embodiment of the invention can execute the method steps in the method embodiment, and the implementation principle and the technical effect are similar, so that the detailed description is omitted.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the obtaining module may be a processing element separately set up, or may be implemented by being integrated in a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the functions of the determining module. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when some of the above modules are implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can invoke the program code. As another example, these modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, 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. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, bluetooth, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), etc.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. The electronic device may be the terminal device or the server, or may be a terminal device or a server connected to the terminal device or the server and implementing the method according to the embodiment of the present invention. As shown in fig. 3, the electronic device may include: a processor 301 (e.g., a CPU), a memory 302, a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiving operation of the transceiver 303. Various instructions may be stored in memory 302 for performing various processing functions and implementing the methods and processes provided in the above-described embodiments of the present invention. Preferably, the electronic device according to an 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 implement communication connections between the elements. The communication port 306 is used for connection communication between the electronic device and other peripherals.
The system bus mentioned in fig. 3 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM) and may also include a Non-Volatile Memory (Non-Volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, including a central processing unit CPU, a Network Processor (NP), and the like; but also a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
It should be noted that the embodiment of the present invention also provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the method and the processing procedure provided in the above-mentioned embodiment.
The embodiment of the invention also provides a chip for running the instructions, and the chip is used for executing the method and the processing process provided by the embodiment.
The embodiment of the invention provides a coronary angiography quantitative analysis method based on an angiography video, a device, electronic equipment and a computer readable storage medium, wherein the coronary angiography video is subjected to video interception and video frame image extraction processing, the extracted image sequence is subjected to target detection and semantic segmentation processing of a narrow blood vessel based on an image target detection and semantic segmentation model, the extracted image is optimized based on confidence coefficient of target identification, and each narrow blood vessel is subjected to coronary angiography quantitative analysis on the optimized image to generate a corresponding blood vessel stenosis rate. The method gets rid of the excessive dependence on the manual experience in the traditional method, and improves the image extraction accuracy and the stenosis rate calculation precision.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for coronary angiography based quantitative analysis based on angiography video, the method comprising:
acquiring an angiography video of coronary angiography;
extracting video frame images of the angiography video to generate a corresponding first image sequence;
performing target detection and semantic segmentation processing on a narrow blood vessel on each first image in the first image sequence based on a preset image target detection and semantic segmentation model, so as to obtain one or more target detection frames for marking the narrow blood vessel and a narrow blood vessel mask image in each target detection frame on each first image; each target detection frame corresponds to a detection frame confidence;
performing image optimization processing on the first image sequence according to the confidence of the detection frame to obtain an appointed number of optimized images;
and performing coronary angiography quantitative analysis on the blood vessel mask image of the narrow section in each target detection frame on each preferred image to generate a corresponding blood vessel narrow rate.
2. The method for coronary angiography quantitative analysis based on angiography video according to claim 1, wherein the video frame image extraction on the angiography video to generate the corresponding first image sequence specifically comprises:
video interception is carried out on the angiography video, and the video content of the coronary artery filling phase of the contrast agent is reserved to generate a corresponding intercepted angiography video;
according to the time sequence, carrying out video frame image extraction processing on the intercepted contrast video to generate a corresponding video frame image sequence, and carrying out statistics on the number of video frame images of the video frame image sequence to generate a corresponding first total number; the sequence of video frame images comprises a plurality of video frame images;
when the first total number does not exceed a preset image total number threshold value, taking each video frame image as a corresponding first image, and sequencing all the obtained first images according to time sequence to generate a first image sequence;
when the first total number exceeds the image total number threshold value, extracting the video frame images with all odd indexes as the corresponding first images from the video frame image sequence, or extracting the video frame images with all even indexes as the corresponding first images; and sequencing all the obtained first images according to the time sequence to generate the first image sequence.
3. The method for coronary angiography based on angiography video according to claim 1,
the image target detection and semantic segmentation model comprises a Mask R-CNN model; when the image target detection and semantic segmentation model is a Mask R-CNN model, a residual error network ResNet50 is used as a characteristic extraction backbone network.
4. The method of claim 1, wherein the image-optimized processing of the first image sequence according to the detection frame confidence level to obtain a specified number of optimized images includes:
in the first image sequence, performing mean calculation on the detection frame confidence coefficients of all the target detection frames on each first image to generate a corresponding first image average confidence coefficient;
and sequencing all the first images according to the sequence of the average confidence degrees of the corresponding first images from large to small, and taking the first images with the appointed number which are sequenced at the top as the preferred images.
5. The method according to claim 1, wherein the coronary angiography quantitative analysis on the stenosis section blood vessel mask image in each of the target detection frames on the respective preferred images generates a corresponding blood vessel stenosis rate, and specifically comprises:
traversing each target detection frame on the current preferred image, and recording the currently traversed target detection frame as a current target detection frame;
identifying blood vessel edges and blood vessel center lines of the narrow blood vessel mask image in the current target detection frame to generate corresponding first blood vessel edges and first center lines; the first central line comprises a plurality of central line pixel points PiWherein the first central line pixel point P1The point closest to the coronary artery entrance in the blood flow direction and the last central line pixel point PNI is more than or equal to 1 and less than or equal to N, wherein N is the total number of central line pixel points of the first central line;
for each of the centers on the first centerline according to the first vessel edgeLine pixel point PiAnalyzing the corresponding vessel diameter length to generate a corresponding first vessel diameter di；
According to the central line pixel point P1To the central line pixel point PNAnd each central line pixel point PiOf said first vessel diameter diFor each of the center line pixel points PiAnalyzing the corresponding stenosis rate to generate a corresponding first stenosis rate ri；
From all the obtained first stenosis rates riSelecting a maximum value as the blood vessel stenosis rate corresponding to the stenosis section blood vessel mask image within the current target detection frame.
6. The method of claim 5, wherein said first vessel edge is used to determine a point P for each centerline pixel on said first centerlineiAnalyzing the corresponding vessel diameter length to generate a corresponding first vessel diameter diThe method specifically comprises the following steps:
pixel point P according to the central lineiThe direction relation with the adjacent eight-domain pixel point is that the pixel point P passes through the central lineiMaking four straight lines which are respectively marked as a first straight line, a second straight line, a third straight line and a fourth straight line; the first straight line passes through the central line pixel point PiThe upper left adjacent pixel point and the central line pixel point PiAnd said center line pixel point PiThe right lower adjacent pixel point; the second straight line passes through the central line pixel point PiThe upper adjacent pixel point of (2), the central line pixel point PiAnd said center line pixel point PiThe lower adjacent pixel point of (1); the third straight line passes through the central line pixel point PiThe upper right adjacent pixel point and the central line pixel point PiAnd said center line pixel point PiThe left lower adjacent pixel point; the third straight line passes through the central line pixel point PiRight-hand adjacent pixel point and central line pixel point PiAnd said center line pixel point PiThe left adjacent pixel point of (1);
marking the line segments of the first, second, third and fourth straight lines intersected with the first blood vessel edge as corresponding first, second, third and fourth line segments respectively; calculating the line segment lengths of the first line segment, the second line segment, the third line segment and the fourth line segment to generate corresponding first line segment length, second line segment length, third line segment length and fourth line segment length; and selecting the minimum value from the first, second, third and fourth line segment lengths as the pixel point P corresponding to the central lineiCorresponding first vessel diameter di。
7. The method for coronary angiography based on angiography video according to claim 5, wherein the pixel point P according to the center line1To the central line pixel point PNAnd each central line pixel point PiOf said first vessel diameter diFor each of the center line pixel points PiAnalyzing the corresponding stenosis rate to generate a corresponding first stenosis rate riThe method specifically comprises the following steps:
according to the first vessel diameter d1And the first vessel diameter dNConstructing a pixel point P reflecting the central line1To the central line pixel point PNLinear function f (i) of the linear change relationship of blood vessel, f (i) ═ d1+k*(i-1)，k＝(dN-d1)/(N-1)；
According to the linear variation relation function f (i), each central line pixel point P is subjected toiCalculating corresponding linearly varying diameter lengths to generate corresponding first reference diameters d'i；
According to the first vessel diameter diAnd the first reference diameter d'iCalculating each central line pixel point PiCorresponding said first stenosis rate ri，ri＝1-di/d’i。
8. An apparatus for carrying out the method steps of angiographic video-based quantitative analysis of coronary angiography according to any of claims 1-7, characterized in that it comprises: the system comprises an acquisition module, an image preprocessing module, a narrow-section blood vessel processing module, an image optimizing module and a quantitative analysis module;
the acquisition module is used for acquiring an angiography video for coronary angiography;
the image preprocessing module is used for extracting video frame images of the angiography video to generate a corresponding first image sequence;
the narrow-segment blood vessel processing module is used for carrying out narrow-segment blood vessel target detection and semantic segmentation processing on each first image in the first image sequence based on a preset image target detection and semantic segmentation model, so that one or more target detection frames for marking a narrow-segment blood vessel and a narrow-segment blood vessel mask image in each target detection frame are obtained on each first image; each target detection frame corresponds to a detection frame confidence;
the image optimization module is used for performing image optimization processing on the first image sequence according to the detection frame confidence degree to obtain an appointed number of optimized images;
the quantitative analysis module is used for performing coronary angiography quantitative analysis on the stenosis section blood vessel mask image in each target detection frame on each preferred image to generate a corresponding blood vessel stenosis rate.
9. An electronic device, comprising: a memory, a processor, and a transceiver;
the processor is used for being coupled with the memory, reading and executing the instructions in the memory to realize the method steps of any one of claims 1 to 7;
the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed by a computer, cause the computer to perform the method of any of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018415.6A CN114418977A (en) | 2022-01-07 | 2022-01-07 | Method and device for coronary angiography quantitative analysis based on angiography video |
| PCT/CN2022/097245 WO2023130663A1 (en) | 2022-01-07 | 2022-06-07 | Coronary angiogram quantitative analysis method and apparatus based on angiogram video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018415.6A CN114418977A (en) | 2022-01-07 | 2022-01-07 | Method and device for coronary angiography quantitative analysis based on angiography video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114418977A true CN114418977A (en) | 2022-04-29 |
Family
ID=81271742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210018415.6A Pending CN114418977A (en) | 2022-01-07 | 2022-01-07 | Method and device for coronary angiography quantitative analysis based on angiography video |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114418977A (en) |
| WO (1) | WO2023130663A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708259A (en) * | 2022-05-24 | 2022-07-05 | 深圳市铱硙医疗科技有限公司 | CTA (computed tomography angiography) -based head and neck vascular stenosis detection method, device, equipment and medium |
| WO2023130663A1 (en) * | 2022-01-07 | 2023-07-13 | 乐普（北京）医疗器械股份有限公司 | Coronary angiogram quantitative analysis method and apparatus based on angiogram video |
| CN116612102A (en) * | 2023-05-31 | 2023-08-18 | 上海博动医疗科技股份有限公司 | Vascular image processing system, vascular image processing device, and storage medium |
| CN116681716A (en) * | 2023-08-04 | 2023-09-01 | 杭州脉流科技有限公司 | Method, device, equipment and storage medium for dividing intracranial vascular region of interest |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703948B (en) * | 2023-08-03 | 2023-11-14 | 杭州脉流科技有限公司 | Intracranial vessel tree segmentation method and device based on deep neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11369278B2 (en) * | 2017-11-28 | 2022-06-28 | Beijing Keya Medical Technology Co., Ltd. | Methods and systems for determining lumen volume and coronary blood flow |
| CN109222980A (en) * | 2018-06-19 | 2019-01-18 | 北京红云智胜科技有限公司 | Method of the measurement coronarogram based on deep learning as blood vessel diameter |
| CN111657883B (en) * | 2020-06-03 | 2021-05-04 | 北京理工大学 | Coronary artery SYNTAX score automatic calculation method and system based on sequence radiography |
| CN114418977A (en) * | 2022-01-07 | 2022-04-29 | 乐普（北京）医疗器械股份有限公司 | Method and device for coronary angiography quantitative analysis based on angiography video |
-
2022
- 2022-01-07 CN CN202210018415.6A patent/CN114418977A/en active Pending
- 2022-06-07 WO PCT/CN2022/097245 patent/WO2023130663A1/en unknown
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023130663A1 (en) * | 2022-01-07 | 2023-07-13 | 乐普（北京）医疗器械股份有限公司 | Coronary angiogram quantitative analysis method and apparatus based on angiogram video |
| CN114708259A (en) * | 2022-05-24 | 2022-07-05 | 深圳市铱硙医疗科技有限公司 | CTA (computed tomography angiography) -based head and neck vascular stenosis detection method, device, equipment and medium |
| CN114708259B (en) * | 2022-05-24 | 2022-08-16 | 深圳市铱硙医疗科技有限公司 | CTA (computed tomography angiography) -based head and neck vascular stenosis detection method, device, equipment and medium |
| CN116612102A (en) * | 2023-05-31 | 2023-08-18 | 上海博动医疗科技股份有限公司 | Vascular image processing system, vascular image processing device, and storage medium |
| CN116681716A (en) * | 2023-08-04 | 2023-09-01 | 杭州脉流科技有限公司 | Method, device, equipment and storage medium for dividing intracranial vascular region of interest |
| CN116681716B (en) * | 2023-08-04 | 2023-10-10 | 杭州脉流科技有限公司 | Method, device, equipment and storage medium for dividing intracranial vascular region of interest |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023130663A1 (en) | 2023-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114418977A (en) | Method and device for coronary angiography quantitative analysis based on angiography video | |
| JP7383010B2 (en) | Medical image recognition method and system, model training method, computer device, and program | |
| Balakrishna et al. | Automatic detection of lumen and media in the IVUS images using U-Net with VGG16 Encoder | |
| CN114419500A (en) | Method and device for screening diastolic and systolic images based on cardiac ultrasound video | |
| CN110751636B (en) | Fundus image retinal arteriosclerosis detection method based on improved coding and decoding network | |
| WO2022087853A1 (en) | Image segmentation method and apparatus, and computer-readable storage medium | |
| CN114419499B (en) | Method and device for processing ejection fraction data based on heart ultrasonic video | |
| CN114170134A (en) | Stenosis assessment method and device based on intracranial DSA image | |
| CN112991346B (en) | Training method and training system for learning network for medical image analysis | |
| WO2023130661A1 (en) | Method and apparatus for processing two-dimensional spectral doppler echocardiographic image | |
| WO2023137948A1 (en) | Processing method and apparatus for analyzing fractional flow reserve on the basis of angiographic image | |
| CN111667478A (en) | Method and system for identifying carotid plaque through CTA-MRA cross-modal prediction | |
| CN114511670B (en) | Blood vessel reconstruction method, device, equipment and medium based on dynamic perfusion image | |
| CN113538277B (en) | Neural network-based tomography image noise reduction method and device | |
| CN111738992B (en) | Method, device, electronic equipment and storage medium for extracting lung focus area | |
| CN113989293A (en) | Image segmentation method and training method, device and equipment of related model | |
| CN112101456A (en) | Attention feature map acquisition method and device and target detection method and device | |
| CN113724203B (en) | Model training method and device applied to target feature segmentation in OCT image | |
| CN114418976A (en) | Analysis method and device of angiography image | |
| Huang et al. | POST-IVUS: A perceptual organisation-aware selective transformer framework for intravascular ultrasound segmentation | |
| US20240005510A1 (en) | Method and apparatus of nidus segmentation, electronic device, and storage medium | |
| CN112651960A (en) | Image processing method, device, equipment and storage medium | |
| CN113658145B (en) | Liver ultrasonic standard tangent plane identification method and device, electronic equipment and storage medium | |
| CN114998582A (en) | Coronary artery blood vessel segmentation method, device and storage medium | |
| CN115775233A (en) | Processing method and device for measuring characteristic dimension based on cardiac ultrasound video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |