Method for generating bull's-eye diagram and related device

Abstract

The invention discloses a bullseye map generation method and a related device, and relates to the technical field of medical image recognition, and the method comprises the steps: determining a plurality of frames of horizontal long-axis images, a plurality of frames of vertical long-axis images and a plurality of frames of short-axis images of a myocardial under a mandrel coordinate system; identifying the image to obtain a multi-frame ellipse center, an ellipse long-axis radius of a multi-frame horizontal long-axis image, an ellipse long-axis radius of a multi-frame vertical long-axis image and a circular radius of a multi-frame short-axis image; determining a target frame interval in the short axis direction based on the identified information; and based on the short-axis image corresponding to the target frame interval, determining a multi-frame circular ring and a multi-frame myocardial region, and zooming the multi-frame myocardial region to each corresponding frame circular ring to obtain a multi-frame myocardial circular ring, thereby determining a bull's-eye map of the myocardium. The target map is quickly generated by accurately analyzing and processing the tomography image of the specific frame, the dependence on a large number of samples is reduced, and the generation efficiency of the target map is improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical image recognition, and in particular to a method for generating a bull's eye image and a related device. Background Art

[0002] In the field of medical image recognition and analysis, the bull's-eye diagram, as a tool that intuitively displays myocardial metabolism or perfusion, can highlight the difference between estimation and completion, and is crucial for evaluating cardiac function and diagnosing heart disease.

[0003] Currently, the generation of the bull's-eye image mainly relies on machine learning technology through learning and analyzing tomography image samples.

[0004] However, the machine learning process requires collecting and processing a large number of tomography image samples, which is not only time-consuming but also difficult to implement when sample resources are limited. Summary of the invention

[0005] In view of the above problems, the present application provides a method and a related device for generating a bull's eye graph, in order to reduce the dependence on a large number of samples and improve the efficiency of generating the bull's eye graph. The specific scheme is as follows:

[0006] The first aspect of the present application provides a method for generating a bull's eye graph, characterized by comprising:

[0007] Determine a tomographic image of the myocardium in a cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes multiple frames of horizontal long axis images, multiple frames of vertical long axis images, and multiple frames of short axis images;

[0008] Identify the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images, and the multi-frame short-axis images to obtain a multi-frame ellipse center, an ellipse long-axis radius of the multi-frame horizontal long-axis images, an ellipse long-axis radius of the multi-frame vertical long-axis images, and a circular radius of the multi-frame short-axis images;

[0009] Determining a target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center;

[0010] Based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, a multi-frame annulus and a multi-frame myocardial region are determined, and the multi-frame myocardial region is scaled to the corresponding annulus of each frame to obtain a multi-frame myocardial annulus;

[0011] Determine the target frame myocardial ring, project the other frame myocardial rings onto the target frame myocardial ring, and convert the projected image into polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings in the multiple frame myocardial rings except the target frame myocardial ring.

[0012] In a possible implementation, determining a tomographic image of the myocardium in a cardiac axis coordinate system includes:

[0013] Acquire a tomographic image of the myocardium in a human coordinate system;

[0014] Performing coordinate system rotation on the tomographic image of the myocardium in the human body coordinate system to obtain a rotated tomographic image;

[0015] Bilinear interpolation is performed on the rotated tomographic image to obtain a tomographic image of the myocardium in a cardiac axis coordinate system.

[0016] In a possible implementation, determining the target frame interval in the short axis direction based on the ellipse major axis radius of the multiple frames of horizontal long axis images, the ellipse major axis radius of the multiple frames of vertical long axis images, the circular radius of the multiple frames of short axis images, and the center of the multiple frames of ellipse includes:

[0017] Acquire the pixel size of the multiple frames of horizontal long-axis images, the pixel size of the multiple frames of vertical long-axis images, and the inter-slice spacing of the multiple frames of short-axis images;

[0018] Based on the inter-layer spacing of the multiple-frame short-axis images, the pixel size of the multiple-frame horizontal long-axis images, and the radius of the ellipse major axis of the multiple-frame horizontal long-axis images, a first frame interval in the short-axis direction is calculated;

[0019] Based on the inter-layer spacing of the multiple frames of short-axis images, the pixel size of the multiple frames of vertical long-axis images, and the radius of the ellipse major axis of the multiple frames of vertical long-axis images, a second frame interval in the short-axis direction is calculated;

[0020] taking a frame interval with a larger range between the first frame interval in the short-axis direction and the second frame interval in the short-axis direction as a candidate frame interval in the short-axis direction;

[0021] Based on the circular radius of the multi-frame short-axis images and the center of the multi-frame ellipse, a target frame section in the short-axis direction is determined from the candidate frame sections in the short-axis direction.

[0022] In a possible implementation, determining the target frame interval in the short axis direction from the candidate frame intervals in the short axis direction based on the circular radius of the multi-frame short axis images and the multi-frame ellipse center includes:

[0023] Filtering out a starting frame in the short-axis direction from the candidate frame intervals in the short-axis direction, wherein the vertex of the circular radius of the short-axis image corresponding to the starting frame in the short-axis direction is the apex of the heart;

[0024] Filtering out an end frame in the direction of the short axis from the candidate frame intervals in the direction of the short axis, wherein the center of the ellipse corresponding to the end frame in the direction of the short axis is the heart bottom;

[0025] Based on the start frame in the short-axis direction and the end frame in the short-axis direction, a target frame section in the short-axis direction is determined.

[0026] In a possible implementation, determining the multi-frame rings and the multi-frame myocardial regions based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval includes:

[0027] Detecting the short-axis image corresponding to the target frame interval to obtain the center and radius of the outer circles of multiple frames;

[0028] Based on the acquired number of frames of the target frame interval and the maximum outer circle radius, the ring width of each frame in the target frame interval is calculated, and based on the ring width of each frame, the corresponding centers of the outer circles of multiple frames and the radii of the outer circles of multiple frames are combined to obtain the multi-frame circular ring, wherein the centers of the outer circles of multiple frames of the multi-frame circular ring coincide with each other;

[0029] The short-axis image corresponding to the target frame interval is divided to obtain the multi-frame myocardial area.

[0030] In a possible implementation, the bull's-eye image of the myocardium includes a plurality of segments, and the method further includes:

[0031] calculating the standardized uptake value of each of the segments and the average standardized uptake value of the bull's eye image;

[0032] For each segment, the percentage of the standardized uptake value of the segment to the average standardized uptake value of the bull's-eye graph was calculated, and the percentage was used as the score of the segment.

[0033] A second aspect of the present application provides a device for generating a bull's eye image, characterized by comprising:

[0034] A first determining unit is used to determine a tomographic image of the myocardium in a cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes a plurality of frames of horizontal long axis images, a plurality of frames of vertical long axis images, and a plurality of frames of short axis images;

[0035] an identification unit, used for identifying the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images and the multi-frame short-axis images, and obtaining the multi-frame ellipse center, the ellipse long-axis radius of the multi-frame horizontal long-axis images, the ellipse long-axis radius of the multi-frame vertical long-axis images and the circular radius of the multi-frame short-axis images;

[0036] A second determining unit is used to determine a target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center;

[0037] A third determination unit is used to determine the multi-frame annulus and the multi-frame myocardial region based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, and scale the multi-frame myocardial region to the corresponding annulus of each frame to obtain the multi-frame myocardial annulus;

[0038] The fourth determination unit is used to determine the target frame myocardial ring, project the other frame myocardial rings onto the target frame myocardial ring, and convert the image obtained after projection into polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings among the multiple frame myocardial rings except the target frame myocardial ring.

[0039] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for generating a bull's eye image of the above-mentioned first aspect or any implementation of the first aspect.

[0040] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0041] The memory is used to store computer programs;

[0042] The processor is used to execute the computer program so that the electronic device can implement the method for generating a bull's eye image according to the first aspect or any implementation manner of the first aspect.

[0043] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can generate the method of the bull's eye diagram of the above-mentioned first aspect or any implementation method of the first aspect.

[0044] By means of the above technical scheme, the present application provides a method for generating a bull's eye image and a related device, the method comprising determining a multi-frame horizontal long-axis image, a multi-frame vertical long-axis image and a multi-frame short-axis image of the myocardium in a cardiac axis coordinate system; identifying the images to obtain a multi-frame ellipse center, an ellipse long-axis radius of the multi-frame horizontal long-axis image, an ellipse long-axis radius of the multi-frame vertical long-axis image and a circular radius of the multi-frame short-axis image; determining a target frame interval in the short-axis direction based on the identified information; determining a multi-frame ring and a multi-frame myocardial area based on the number of frames of the acquired target frame interval and the short-axis image corresponding to the target frame interval, and scaling the multi-frame myocardial area to the corresponding frame rings to obtain a multi-frame myocardial ring; determining a target frame myocardial ring, projecting other frame myocardial rings onto the target frame myocardial ring, and converting the image obtained after the projection to polar coordinates to obtain a bull's eye image of the myocardium, wherein the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are multiple frame myocardial rings in the multi-frame myocardial ring except the target frame myocardial ring. The bull's-eye map is quickly generated by accurately analyzing and processing tomographic images of specific frames, which reduces the dependence on a large number of samples and improves the efficiency of generating the bull's-eye map. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0046] Figure 1 A schematic diagram of a process for generating a bull's eye image provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the horizontal long axis, vertical long axis and short axis of the myocardium provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a short-axis image corresponding to a target frame provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of a ring provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of a myocardial ring provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of an image obtained after projection provided by an embodiment of the present application;

[0052] Figure 7 A schematic diagram of a bull's eye diagram of the myocardium provided in an embodiment of the present application;

[0053] Figure 8 A schematic diagram of a color bull's eye image of the myocardium provided in an embodiment of the present application;

[0054] Fig. 9 A schematic diagram of the structure of a device for generating a bull's eye image provided in an embodiment of the present application;

[0055] Fig.10 A schematic diagram of the hardware structure of a device for generating a bull's eye image provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0057] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0058] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0059] In order to reduce the dependence on a large number of samples and improve the efficiency of generating a bull's-eye map, the present application provides a method for generating a bull's-eye map. The method for generating a bull's-eye map provided by the present application is further described in detail below in combination with the accompanying drawings and specific implementation methods.

[0060] Please refer to the attached Figure 1 , Figure 1 A schematic diagram of a method for generating a bull's eye image provided in an embodiment of the present application. The method may include the following steps:

[0061] Step S101: determining a tomographic image of the myocardium in the cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes multiple frames of horizontal long-axis images, multiple frames of vertical long-axis images, and multiple frames of short-axis images.

[0062] In the present application, a tomographic image of the myocardium in a human body coordinate system is first obtained. Then, the coordinate system of the tomographic image of the myocardium in the human body coordinate system is rotated to obtain a rotated tomographic image. Finally, bilinear interpolation is performed on the rotated tomographic image to obtain a tomographic image of the myocardium in a cardiac axis coordinate system.

[0063] The tomographic images of the myocardium are usually acquired in the human body's own coordinate system. However, due to the influence of factors such as human body posture and scanning equipment position, the directly acquired myocardial tomographic images are not conducive to subsequent analysis and processing. Therefore, the tomographic images of the myocardium in the human body coordinate system are converted into tomographic images in the cardiac axis coordinate system. The cardiac axis coordinate system is a coordinate system centered on the heart, which is more consistent with the morphology and function of the heart, and helps to more accurately analyze the morphology and function of the myocardium.

[0064] A tomography device can be used to scan the human body, obtain a tomography image of the myocardium in a human coordinate system, calculate a rotation matrix from the human coordinate system to the heart axis coordinate system, and use the rotation matrix to rotate the tomography image of the myocardium in the human coordinate system to obtain a rotated tomography image. It should be noted that the tomography device can be a single photon emission computed tomography device, a positron emission tomography device, etc.

[0065] Specifically, the Euler angles are required to determine the rotation matrix from the conventional coordinate system to the spindle coordinate system. The Euler angles include the precession angle ψ, the nutation angle θ, and the rotation angle φ. Set the original position of the spindle coordinate system Ox′y′z′ to coincide with the conventional coordinate system Oxyz. First, rotate the precession angle ψ around the Oz axis, which can be expressed as the rotation matrix Z(ψ); then rotate the nutation angle θ around the N axis obtained by the previous rotation, which can be expressed as the rotation matrix N(θ); finally, rotate the rotation angle φ around the Oz' axis, which can be expressed as the rotation matrix Z'(φ). Based on the rotation matrix Z(ψ), the rotation matrix N(θ) and the rotation matrix Z'(φ), determine the rotation matrix R(ψ, θ,φ), where Z, N, Z' and R are rotation operators. For details, refer to the following formula:

[0066]

[0067] Since the rotation operation may cause the change of the pixel position of the image, resulting in pixel dislocation or vacancy, bilinear interpolation is a commonly used image interpolation method used to fill these vacant pixel positions and maintain the smoothness of the image.

[0068] The rotated tomographic image can be scanned to identify the locations of pixel misalignment or vacancy, and then a bilinear interpolation algorithm is used to calculate and fill the pixel values ​​of these vacant locations based on the values ​​of surrounding pixels. The above steps are repeated until all vacant locations are filled to obtain the final tomographic image of the myocardium in the cardiac axis coordinate system.

[0069] The tomographic images of the myocardium in the cardiac axis coordinate system usually acquire multiple frames of images at different angles to comprehensively evaluate the structure and function of the heart. These images include multiple frames of horizontal long axis images, multiple frames of vertical long axis images, and multiple frames of short axis images. For details, please refer to Figure 2 , Figure 2 A schematic diagram of the horizontal long axis, vertical long axis and short axis of the myocardium provided in an embodiment of the present application.

[0070] Step S102: Identify the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images and the multi-frame short-axis images to obtain the multi-frame ellipse center, the ellipse long-axis radius of the multi-frame horizontal long-axis images, the ellipse long-axis radius of the multi-frame vertical long-axis images and the circular radius of the multi-frame short-axis images.

[0071] In the present application, since the shape of the myocardium may be different in tomographic images in different directions, each frame of the image needs to be identified separately to obtain key features in multiple frames of horizontal long-axis images, multiple frames of vertical long-axis images, and multiple frames of short-axis images.

[0072] In order to accurately extract these features from each frame of the image, an ellipse detection algorithm can be used. Usually, the ellipse detection algorithm performs edge detection on the image, extracts the edge information in the image, and uses the geometric properties of the ellipse (such as the tangent line at any point on the ellipse is perpendicular to the two radii of the ellipse center passing through the point, etc.) to identify the ellipse shape in the image, as well as key parameters such as the ellipse center, the ellipse major axis radius, and the ellipse minor axis radius.

[0073] It should be noted that the ellipse detection algorithm is an image processing technology that can accurately identify ellipse-shaped targets in complex image backgrounds. Advanced ellipse detection algorithms include random Hough transform algorithms, edge-based ellipse fitting algorithms, etc.

[0074] In addition, the image quality can be improved through preprocessing steps, thereby further improving the accuracy of ellipse detection, such as image denoising, contrast enhancement, USM (Unsharp Mask Sharpening) sharpening, etc.

[0075] Step S103: Determine the target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center.

[0076] In the present application, the pixel size of multiple-frame horizontal long-axis images, the pixel size of multiple-frame vertical long-axis images, and the inter-layer spacing of multiple-frame short-axis images are first obtained. Then, based on the inter-layer spacing of multiple-frame short-axis images, the pixel size of multiple-frame horizontal long-axis images, and the ellipse major axis radius of multiple-frame horizontal long-axis images, the first frame interval in the short-axis direction is calculated. Then, based on the inter-layer spacing of multiple-frame short-axis images, the pixel size of multiple-frame vertical long-axis images, and the ellipse major axis radius of multiple-frame vertical long-axis images, the second frame interval in the short-axis direction is calculated. Then, the frame interval with a larger range in the first frame interval in the short-axis direction and the second frame interval in the short-axis direction is used as a candidate frame interval in the short-axis direction. Finally, based on the circular radius of the multi-frame short-axis images and the center of the multi-frame ellipse, the target frame interval in the short-axis direction is determined from the candidate frame intervals in the short-axis direction.

[0077] It should be noted that the pixel size of the horizontal long-axis image refers to the number of pixels in the horizontal and vertical directions of the image; the pixel size of the multi-frame vertical long-axis image refers to the number of pixels in the horizontal and vertical directions of the vertical long-axis image. The inter-slice spacing of the multi-frame short-axis image refers to the physical distance between two adjacent short-axis images.

[0078] Specifically, the pixel size of multiple frames of horizontal long-axis images can be used to convert the long-axis radius of the ellipse in the horizontal long-axis image into an actual physical size, and the inter-slice spacing of multiple frames of short-axis images and the converted physical size can be used to estimate the approximate position of the myocardium in the short-axis direction, and the frame number range of the myocardium in the short-axis direction can be obtained, and this range constitutes the first frame interval. The pixel size of multiple frames of vertical long-axis images can be used to convert the long-axis radius of the ellipse in the vertical long-axis image into an actual physical size, and the inter-slice spacing of multiple frames of short-axis images and the converted physical size can be used to estimate the approximate position of the myocardium in the short-axis direction, and the frame number range of the myocardium in the short-axis direction can be obtained, and this range constitutes the second frame interval.

[0079] In order to more likely include the complete myocardial region, the larger one of the first frame interval and the second frame interval is used as a candidate frame interval in the short-axis direction.

[0080] First, the starting frame in the short axis direction is selected from the candidate frame interval in the short axis direction. The vertex of the circular radius of the short axis image corresponding to the starting frame in the short axis direction is the apex of the heart. Then, the ending frame in the short axis direction is selected from the candidate frame interval in the short axis direction. The center of the ellipse corresponding to the ending frame in the short axis direction is the base of the heart. Finally, based on the starting frame in the short axis direction and the ending frame in the short axis direction, the target frame interval in the short axis direction is determined.

[0081] In each short-axis image frame of the candidate frame interval, observe and measure the major axis radius and center of the ellipse. The apex is a key anatomical feature of the myocardium, which is usually shown as the vertex of the major axis radius of the ellipse in the short-axis image. Therefore, the frame corresponding to the apex of the circular radius of the short-axis image can be used as the starting frame in the short-axis direction. The base of the heart is another key anatomical feature of the myocardium, which is usually shown as the center of the ellipse in the short-axis image. Therefore, the frame corresponding to the base of the heart in the short-axis image can be used as the ending frame in the short-axis direction.

[0082] The target frame interval in the short axis direction is determined from the start frame to the end frame. The short axis image corresponding to the target frame interval includes the heart area from the apex to the base of the heart, which is the key area for subsequent image analysis or diagnosis. For ease of understanding, please refer to Figure 3 , Figure 3 A schematic diagram of a short-axis image corresponding to a target frame provided in an embodiment of the present application.

[0083] Step S104: Based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, determine the multi-frame rings and the multi-frame myocardial area, and scale the multi-frame myocardial area to the corresponding frame rings to obtain the multi-frame myocardial rings.

[0084] In the present application, the short-axis image corresponding to the target frame interval is first detected to obtain the center of the multi-frame outer circle and the radius of the multi-frame outer circle. Then, based on the number of frames in the target frame interval and the maximum outer circle radius, the ring width of each frame in the target frame interval is calculated, and based on the ring width of each frame, the corresponding center of the multi-frame outer circle and the radius of the multi-frame outer circle are combined to obtain a multi-frame ring, and the center of the multi-frame outer circle of the multi-frame ring coincides. Finally, the short-axis image corresponding to the target frame interval is divided to obtain a multi-frame myocardial area.

[0085] Specifically, the Hough transform circle detection algorithm can be used to detect each short-axis image in the target frame interval, find the outer boundary circle of the myocardial tissue in each frame, and extract the outer circle center and outer circle radius. It should be noted that the Hough transform circle detection algorithm is an image processing technology that can automatically detect circular structures in images.

[0086] By comparing all outer circle radii, the outer circle with the largest radius and the corresponding outer circle center can be found. The largest outer circle radius is divided by the number of frames in the target frame interval to calculate the ring width of each frame, thereby ensuring that each frame has a uniform or regularly changing ring width.

[0087] For each frame, a ring is drawn with the center of the outer circle as the center and the outer diameter as the outer boundary (the inner diameter can also be calculated considering the ring width). Each frame image corresponds to a ring, and the centers of these rings coincide, indicating that they are all at the same myocardial center position, but the radius varies from frame to frame. For easier understanding, please refer to Figure 4 , Figure 4 A schematic diagram of a ring provided in an embodiment of the present application.

[0088] The watershed segmentation algorithm can be used to accurately segment the myocardial tissue from the surrounding structures for each short-axis image corresponding to the target frame interval, and obtain the myocardial region in each short-axis image. It should be noted that the watershed segmentation algorithm is a segmentation method based on the image topology structure, which is usually used to process grayscale images or binary images. In myocardial segmentation, the algorithm can identify the boundary between myocardial tissue and surrounding tissue, thereby achieving accurate segmentation.

[0089] The scaled size of the myocardial region can be determined based on the multi-frame rings, and then the bilinear interpolation method is used to scale each frame of the myocardial region to the scaled size, and finally the multi-frame myocardial ring is obtained by adding it to the corresponding position in the filled rings of each frame. The multi-frame myocardial ring not only contains the information of the myocardial region, but also is associated with the overall structure of the myocardium through the ring. For ease of understanding, please refer to Figure 5 , Figure 5 A schematic diagram of a myocardial ring provided in an embodiment of the present application. It should be noted that bilinear interpolation is a commonly used image scaling method, which can achieve a smooth scaling effect while maintaining image details.

[0090] Step S105: Determine the target frame myocardial ring, project the other frame myocardial rings onto the target frame myocardial ring, and convert the projected image to polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings except the target frame myocardial ring.

[0091] In this application, among the multiple frames of myocardial annulus, a frame with the outer circle of the myocardial annulus as the apex is selected as the target frame, and the myocardial annulus of this frame is used as the reference to project the myocardial annulus of all other frames except the target frame onto the plane where the myocardial annulus of the target frame is located. During the projection process, it is ensured that the radial areas corresponding to each layer do not overlap with each other to maintain the clarity and accuracy of the myocardial structure. For ease of understanding, please refer to Figure 6 , Figure 6 A schematic diagram of an image obtained after projection provided in an embodiment of the present application.

[0092] The projected image is converted to the polar coordinate system (r, θ), where r represents the radial distance (from the apex to the edge of the myocardium) and θ represents the central angle (the angle around the apex). In the polar coordinate system, the myocardial rings of each frame are superimposed together to form a bull's-eye image of the myocardium. The bull's-eye image of the myocardium shows the myocardial structure from the apex to the base of the heart, and each layer of the myocardial area is clearly distinguishable in the radial and circumferential directions. The bull's-eye image of the myocardium is divided into multiple rings in the order from the apex to the base of the heart, and each ring is further divided into 1, 4, 6, and 6 segments according to the central angle, for a total of 17 segments, which helps to analyze and evaluate the myocardium in more detail. For ease of understanding, please refer to the specific Figure 7 , Figure 7 A schematic diagram of a bull's eye image of the myocardium provided in an embodiment of the present application. The image data type processed is the ushort type, so 65535 can be used as the maximum value, the pixel mean of each partition is divided by the maximum value, and the percentage obtained is multiplied by 100 to obtain the score of the partition.

[0093] In summary, the present application provides a method for generating a bull's eye image, which includes determining multiple horizontal long-axis images, multiple vertical long-axis images, and multiple short-axis images of the myocardium in a cardiac axis coordinate system; identifying the images to obtain the center of a multi-frame ellipse, the ellipse major axis radius of the multi-frame horizontal long-axis images, the ellipse major axis radius of the multi-frame vertical long-axis images, and the circular radius of the multi-frame short-axis images; determining a target frame interval in the short-axis direction based on the identified information; determining a multi-frame ring and a multi-frame myocardial area based on the number of frames of the acquired target frame interval and the short-axis image corresponding to the target frame interval, and projecting the myocardial rings of other frames onto the myocardial ring of the target frame, and converting the image obtained after the projection to polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the myocardial ring of the target frame is the apex, and the myocardial rings of other frames are the multi-frame myocardial rings except the myocardial ring of the target frame in the multi-frame myocardial rings, the center of the outer circle corresponding to the myocardial ring of the target frame is the apex, and the myocardial rings of other frames are the multi-frame myocardial rings except the myocardial ring of the target frame in the multi-frame myocardial rings. The bull's-eye map is quickly generated by accurately analyzing and processing tomographic images of specific frames, which reduces the dependence on a large number of samples and improves the efficiency of generating the bull's-eye map.

[0094] Furthermore, based on the above embodiment, the method may further include: calculating the standardized uptake value of each segment and the average standardized uptake value of the bull's eye graph. For each segment, the percentage of the standardized uptake value of the segment to the average standardized uptake value of the bull's eye graph is calculated, and the percentage is used as the score of the segment.

[0095] It should be noted that the standardized uptake value is a commonly used quantitative indicator in medical imaging to evaluate the degree of tissue uptake of radioactive tracers. The calculation of the standardized uptake value usually involves dividing the average pixel value in a segment by a reference value (such as injection dose, body weight, etc.).

[0096] In this application, the standardized uptake value of each segment and the average standardized uptake value of all segments of the bull's-eye map (the average standardized uptake value of the bull's-eye map) are calculated based on the pixel value in each segment. For each segment, the percentage of its standardized uptake value to the average standardized uptake value of the bull's-eye map is calculated, and this percentage is used as the score of the segment to evaluate the myocardial uptake capacity or functional status of the segment. By calculating the percentage score, the level of each segment relative to the bull's-eye map can be quantitatively evaluated, making the evaluation result more objective and accurate.

[0097] The score of each segment can also be mapped to RGB space for color coding. Different colors represent different score ranges, thus generating a colored bull's-eye map partition unit. The colored bull's-eye map provides an intuitive visual representation, which facilitates the rapid identification of abnormal areas of myocardial function. For ease of understanding, please refer to Figure 8 , Figure 8 This is a schematic diagram of a color bull's-eye image of the myocardium provided in an embodiment of the present application.

[0098] A method for generating a bull's eye image provided in an embodiment of the present application is introduced above. A device for executing the method for generating a bull's eye image will be introduced below.

[0099] See also Fig. 9 , Fig. 9 This is a schematic diagram of the structure of a device for generating a bull's eye image provided in an embodiment of the present application. Figure 3 As shown, the generating device of the bull's eye diagram comprises:

[0100] The first determining unit 11 is used to determine a tomographic image of the myocardium in the cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes multiple frames of horizontal long axis images, multiple frames of vertical long axis images and multiple frames of short axis images.

[0101] The identification unit 12 is used to identify the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images and the multi-frame short-axis images to obtain the multi-frame ellipse center, the ellipse major axis radius of the multi-frame horizontal long-axis images, the ellipse major axis radius of the multi-frame vertical long-axis images and the circular radius of the multi-frame short-axis images.

[0102] The second determination unit 13 is used to determine the target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center.

[0103] The third determination unit 14 is used to determine the multi-frame rings and multi-frame myocardial areas based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, and scale the multi-frame myocardial areas to the corresponding rings of each frame to obtain the multi-frame myocardial rings.

[0104] The fourth determination unit 15 is used to determine the target frame myocardial ring, and project the other frame myocardial rings onto the target frame myocardial ring, and convert the image obtained after the projection into polar coordinates to obtain a bull's eye image of the myocardium, wherein the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings among the multiple frame myocardial rings except the target frame myocardial ring.

[0105] In a possible implementation, the first determining unit 11 includes:

[0106] The first acquisition subunit is used to acquire a tomographic image of the myocardium in a human body coordinate system.

[0107] The rotation subunit is used to perform coordinate system rotation on the tomographic image of the myocardium in the human body coordinate system to obtain a rotated tomographic image.

[0108] The interpolation subunit is used to perform bilinear interpolation on the rotated tomographic image to obtain a tomographic image of the myocardium in a cardiac axis coordinate system.

[0109] In a possible implementation, the second determining unit 13 includes:

[0110] The second acquisition subunit is used to acquire the pixel size of the multiple frames of horizontal long-axis images, the pixel size of the multiple frames of vertical long-axis images, and the inter-slice spacing of the multiple frames of short-axis images.

[0111] The first calculation subunit is used to calculate the first frame interval in the short axis direction based on the layer spacing of the multiple frames of short axis images, the pixel size of the multiple frames of horizontal long axis images and the ellipse major axis radius of the multiple frames of horizontal long axis images.

[0112] The second calculation subunit is used to calculate a second frame interval in the short axis direction based on the layer spacing of the multiple frames of short axis images, the pixel size of the multiple frames of vertical long axis images and the ellipse major axis radius of the multiple frames of vertical long axis images.

[0113] The first determining subunit is configured to select a frame interval with a larger range between the first frame interval in the short-axis direction and the second frame interval in the short-axis direction as a candidate frame interval in the short-axis direction.

[0114] The second determination subunit is used to determine the target frame interval in the short axis direction from the candidate frame intervals in the short axis direction based on the circular radius of the multi-frame short axis images and the multi-frame ellipse center.

[0115] In a possible implementation, the second determining subunit includes:

[0116] The first screening subunit is used to screen out a starting frame in the short-axis direction from the candidate frame interval in the short-axis direction, wherein the vertex of the circular radius of the short-axis image corresponding to the starting frame in the short-axis direction is the apex of the heart.

[0117] The second screening subunit is used to screen out an end frame in the short axis direction from the candidate frame interval in the short axis direction, and the ellipse center corresponding to the end frame in the short axis direction is the heart bottom.

[0118] The third determining subunit is used to determine a target frame interval in the short-axis direction based on a start frame in the short-axis direction and an end frame in the short-axis direction.

[0119] In a possible implementation, the third determining unit 14 for determining the multi-frame rings and the multi-frame myocardial regions based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval includes:

[0120] The detection subunit is used to detect the short-axis image corresponding to the target frame interval to obtain the center and radius of the outer circle of multiple frames.

[0121] The combining subunit is used to calculate the ring width of each frame in the target frame interval based on the number of frames in the target frame interval and the maximum outer circle radius, and based on the ring width of each frame, combine the corresponding centers of the multi-frame outer circles and the multi-frame outer circle radii to obtain the multi-frame circular ring, and the centers of the multi-frame outer circles of the multi-frame circular ring coincide.

[0122] The division subunit is used to divide the short-axis image corresponding to the target frame interval to obtain the multi-frame myocardial area.

[0123] In a possible implementation, the bull's-eye image of the myocardium includes a plurality of segments, and the device further includes:

[0124] A calculation unit is used to calculate the standardized uptake value of each of the segments and the average standardized uptake value of the bull's eye image.

[0125] A fifth determination unit is used to calculate, for each segment, a percentage of the standardized uptake value of the segment to the average standardized uptake value of the bull's-eye image, and use the percentage as the score of the segment.

[0126] The present application also provides an electronic device in an embodiment. Fig.10 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Fig.10 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0127] like Fig.10 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 to a random access memory (RAM) 1003. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0128] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a memory card, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Fig.10 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0129] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any method for generating a bull's eye image provided in an embodiment of the present application.

[0130] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any method for generating a bull's eye image provided in an embodiment of the present application.

[0131] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0132] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0133] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0134] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The 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. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for generating a bull's eye graph, characterized in that: include: Determine a tomographic image of the myocardium in a cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes multiple frames of horizontal long axis images, multiple frames of vertical long axis images, and multiple frames of short axis images; Identify the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images, and the multi-frame short-axis images to obtain a multi-frame ellipse center, an ellipse long-axis radius of the multi-frame horizontal long-axis images, an ellipse long-axis radius of the multi-frame vertical long-axis images, and a circular radius of the multi-frame short-axis images; Determining a target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center; Based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, a multi-frame annulus and a multi-frame myocardial region are determined, and the multi-frame myocardial region is scaled to the corresponding annulus of each frame to obtain a multi-frame myocardial annulus; Determine the target frame myocardial ring, project the other frame myocardial rings onto the target frame myocardial ring, and convert the projected image into polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings in the multiple frame myocardial rings except the target frame myocardial ring.

2. The method for generating a bull's eye graph according to claim 1, characterized in that: Determining a tomographic image of the myocardium in a cardiac axis coordinate system comprises: Acquire a tomographic image of the myocardium in a human coordinate system; Performing coordinate system rotation on the tomographic image of the myocardium in the human body coordinate system to obtain a rotated tomographic image; Bilinear interpolation is performed on the rotated tomographic image to obtain a tomographic image of the myocardium in a cardiac axis coordinate system.

3. The method for generating a bull's eye diagram according to claim 1, characterized in that: The determining of the target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center comprises: Acquire the pixel size of the multiple frames of horizontal long-axis images, the pixel size of the multiple frames of vertical long-axis images, and the inter-slice spacing of the multiple frames of short-axis images; Based on the inter-layer spacing of the multiple-frame short-axis images, the pixel size of the multiple-frame horizontal long-axis images, and the radius of the ellipse major axis of the multiple-frame horizontal long-axis images, a first frame interval in the short-axis direction is calculated; Based on the inter-layer spacing of the multiple frames of short-axis images, the pixel size of the multiple frames of vertical long-axis images, and the radius of the ellipse major axis of the multiple frames of vertical long-axis images, a second frame interval in the short-axis direction is calculated; taking a frame interval with a larger range between the first frame interval in the short-axis direction and the second frame interval in the short-axis direction as a candidate frame interval in the short-axis direction; Based on the circular radius of the multi-frame short-axis images and the center of the multi-frame ellipse, a target frame section in the short-axis direction is determined from the candidate frame sections in the short-axis direction.

4. The method for generating a bull's eye graph according to claim 1, characterized in that: The determining, based on the circular radius of the multi-frame short-axis images and the multi-frame ellipse center, of a target frame interval in the short-axis direction from candidate frame intervals in the short-axis direction comprises: Filtering out a starting frame in the short-axis direction from the candidate frame intervals in the short-axis direction, wherein the vertex of the circular radius of the short-axis image corresponding to the starting frame in the short-axis direction is the apex of the heart; Filtering out an end frame in the direction of the short axis from the candidate frame intervals in the direction of the short axis, wherein the center of the ellipse corresponding to the end frame in the direction of the short axis is the heart bottom; Based on the start frame in the short-axis direction and the end frame in the short-axis direction, a target frame section in the short-axis direction is determined.

5. The method for generating a bull's eye diagram according to claim 4, characterized in that: The determining of the multi-frame annulus and the multi-frame myocardial region based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval includes: Detecting the short-axis image corresponding to the target frame interval to obtain the center and radius of the outer circles of multiple frames; Based on the acquired number of frames of the target frame interval and the maximum outer circle radius, the ring width of each frame in the target frame interval is calculated, and based on the ring width of each frame, the corresponding centers of the outer circles of multiple frames and the radii of the outer circles of multiple frames are combined to obtain the multi-frame circular ring, wherein the centers of the outer circles of multiple frames of the multi-frame circular ring coincide with each other; The short-axis image corresponding to the target frame interval is divided to obtain the multi-frame myocardial area.

6. The method for generating a bull's eye diagram according to claim 5, characterized in that: The bull's-eye image of the myocardium includes a plurality of segments, and the method further includes: calculating the standardized uptake value of each of the segments and the average standardized uptake value of the bull's eye image; For each segment, the percentage of the standardized uptake value of the segment to the average standardized uptake value of the bull's-eye graph was calculated, and the percentage was used as the score of the segment.

7. A device for generating a bull's eye diagram, characterized in that: include: A first determining unit is used to determine a tomographic image of the myocardium in a cardiac axis coordinate system, wherein the tomographic image of the myocardium in the cardiac axis coordinate system includes a plurality of frames of horizontal long axis images, a plurality of frames of vertical long axis images, and a plurality of frames of short axis images; an identification unit, used for identifying the multi-frame horizontal long-axis images, the multi-frame vertical long-axis images and the multi-frame short-axis images, and obtaining the multi-frame ellipse center, the ellipse long-axis radius of the multi-frame horizontal long-axis images, the ellipse long-axis radius of the multi-frame vertical long-axis images and the circular radius of the multi-frame short-axis images; A second determining unit is used to determine a target frame interval in the short axis direction based on the ellipse major axis radius of the multi-frame horizontal long axis image, the ellipse major axis radius of the multi-frame vertical long axis image, the circular radius of the multi-frame short axis image and the multi-frame ellipse center; A third determination unit is used to determine the multi-frame annulus and the multi-frame myocardial region based on the acquired frame number of the target frame interval and the short-axis image corresponding to the target frame interval, and scale the multi-frame myocardial region to the corresponding annulus of each frame to obtain the multi-frame myocardial annulus; The fourth determination unit is used to determine the target frame myocardial ring, project the other frame myocardial rings onto the target frame myocardial ring, and convert the image obtained after projection into polar coordinates to obtain a bull's eye image of the myocardium, the center of the outer circle corresponding to the target frame myocardial ring is the apex, and the other frame myocardial rings are the multiple frame myocardial rings among the multiple frame myocardial rings except the target frame myocardial ring.

8. A computer program product, characterized in that It comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the method for generating a bull's eye diagram as claimed in any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the method for generating a bull's eye image as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the method for generating a bull's eye image as described in any one of claims 1 to 6.

Images