Path diagram generation method, device and computer equipment

Abstract

The application relates to a path map generation method, device and computer equipment. The method comprises the following steps: acquiring a blood vessel subtraction map of a to-be-inspected part and a device subtraction map of the to-be-inspected part respectively, performing device segmentation on the device subtraction map to obtain a device segmentation result, determining a weight template corresponding to the device subtraction map according to the device segmentation result, and then fusing the device subtraction map and the blood vessel subtraction map according to the weight template to obtain a path map of the to-be-inspected part. In the method, the corresponding weight template is determined based on the device segmentation result of the device subtraction map, different weight values are configured for different regions in the device subtraction map, the subsequent fusion direction is clear, the contrast between the blood vessels and the device in the obtained path map is improved, and the clarity of the blood vessels and the device in the path map is improved.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, apparatus and computing device for generating path maps. Background Technology

[0002] A roadmap, also known as a subtraction perspective view, is typically created by overlaying a subtracted image of the blood vessels obtained after angiography with a real-time perspective view of intravascular devices (such as guidewires) onto the perspective image of the devices to produce a clear roadmap showing the movement of the devices within the blood vessel.

[0003] However, in traditional techniques, the subtraction angiography image is directly superimposed with the instrument fluoroscopic image. The resulting path map shows weak instrument imaging and poor contrast with the blood vessels, resulting in poor clarity of the blood vessels and instruments in the entire path map. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, and computer device for generating path diagrams to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for generating a path graph, comprising:

[0006] Obtain the subtraction angiogram of the blood vessels and the subtraction angiogram of the equipment at the site to be examined; perform equipment segmentation on the subtraction angiogram to obtain the equipment segmentation result;

[0007] Determine the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation results;

[0008] Based on the weighted template, the subtraction images of the equipment and blood vessels are fused to obtain the path map of the area to be examined.

[0009] In one embodiment, the equipment subtraction image is segmented to obtain the equipment segmentation result, including:

[0010] The subtraction image of the equipment is segmented based on its morphological characteristics to obtain the morphological segmentation result;

[0011] The equipment subtraction image is segmented based on the grayscale value of each pixel to obtain the grayscale segmentation result.

[0012] The equipment segmentation result is determined based on the morphological segmentation result and the grayscale segmentation result.

[0013] In one embodiment, the grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; grayscale segmentation is performed on the equipment subtraction image based on the grayscale values ​​of each pixel to obtain the grayscale segmentation result, including:

[0014] In an equipment subtraction image, the pixel region where the gray value of a pixel is less than or equal to a first gray threshold is defined as the equipment region.

[0015] In equipment subtraction images, pixel regions whose gray values ​​are greater than or equal to a second gray threshold are identified as non-equipment regions.

[0016] In an image obtained by subtraction of an instrument, the pixel region whose gray value is greater than a first gray value threshold and less than a second gray value threshold is identified as a mixed region.

[0017] In one embodiment, the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region; determining the equipment segmentation result based on the morphological segmentation result and the grayscale segmentation result includes:

[0018] Based on the morphological segmentation results, the mixed equipment region and the mixed non-equipment region in the mixed region are determined;

[0019] The equipment area in the grayscale segmentation result is defined as the first-level equipment area, the non-equipment area in the grayscale segmentation result is defined as the first-level non-equipment area, the mixed equipment area is defined as the second-level equipment area, and the mixed non-equipment area is defined as the second-level non-equipment area.

[0020] The primary equipment region, primary non-equipment region, secondary equipment region, and secondary non-equipment region in the equipment subtraction image are used as the equipment segmentation result.

[0021] In one embodiment, determining the mixed equipment region and the mixed non-equipment region within the mixed region based on the morphological segmentation results includes:

[0022] In the morphological segmentation results, a reference region matching the location of the blending region is determined;

[0023] The equipment area in the reference area is designated as the mixed equipment area, and the non-equipment area in the reference area is designated as the mixed non-equipment area.

[0024] In one embodiment, determining the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation result includes:

[0025] A weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0026] In one embodiment, the vascular subtraction image and the instrument subtraction image are fused according to a weighted template to obtain a path map of the area to be examined, including:

[0027] The weight value of each pixel in the weight template is used as the equipment weight of the corresponding pixel in the equipment subtraction image;

[0028] The difference between the equipment weight and the reference weight of each pixel in the equipment subtraction image is used as the blood vessel weight of the corresponding pixel in the blood vessel subtraction image.

[0029] The path map of the area to be examined is obtained by weighting the pixel values ​​based on the weight of the equipment, the weight of the blood vessel, the subtraction image of the equipment, and the subtraction image of the blood vessel.

[0030] In one embodiment, the method further includes, prior to fusing the angiography and the instrumentation angiography, the following:

[0031] Smooth the weight values ​​in the weight template to obtain a smoothed weight template; and / or,

[0032] Adjust the brightness and contrast values ​​of the subtraction angiography / vascular subtraction angiography.

[0033] Secondly, this application also provides a path map generation apparatus, comprising:

[0034] The image acquisition module is used to acquire the subtraction images of blood vessels and instruments in the area to be examined, respectively.

[0035] The equipment segmentation module is used to segment the equipment subtraction image to obtain the equipment segmentation result.

[0036] The weight determination module is used to determine the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation results.

[0037] The image fusion module is used to fuse the vascular subtraction image and the instrument subtraction image of the area to be examined according to the weight template to obtain the path map of the area to be examined.

[0038] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above-mentioned path diagram generation methods.

[0039] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any of the above-mentioned path graph generation methods.

[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described path graph generation methods.

[0041] The aforementioned path map generation method, apparatus, and computer equipment acquire vascular subtraction images and instrument subtraction images of the area to be examined, respectively. The instrument subtraction images are then segmented to obtain instrument segmentation results. A weight template corresponding to the instrument subtraction image is determined based on the segmentation results. Finally, the instrument subtraction images and vascular subtraction images are fused according to the weight template to obtain the path map of the area to be examined. In this method, the corresponding weight template is determined based on the instrument segmentation results of the instrument subtraction images. Different weight values ​​are assigned to different regions in the instrument subtraction images, clarifying the focus of subsequent fusion, improving the contrast between blood vessels and instruments in the obtained path map, and thus improving the clarity of blood vessels and instruments in the path map. Attached Figure Description

[0042] Figure 1 This is an internal structural diagram of a computer device in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a method for generating a path graph in one embodiment;

[0044] Figure 3 This is a flowchart illustrating the process of determining the equipment segmentation result in one embodiment;

[0045] Figure 4 This is a flowchart illustrating the process of determining grayscale segmentation results in one embodiment;

[0046] Figure 5 This is a flowchart illustrating the process of determining the equipment segmentation result in another embodiment;

[0047] Figure 6 This is a schematic diagram of the process for segmenting the mixed region in one embodiment;

[0048] Figure 7 This is a flowchart illustrating the path diagram obtained in one embodiment;

[0049] Figure 8 This is a schematic diagram of obtaining the weight template in one embodiment;

[0050] Figure 9 This is a structural block diagram of a path graph generation device in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] The path graph generation method provided in this application embodiment can be applied to, for example, Figure 1The computer device shown can be a terminal. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for generating a path graph. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0053] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0054] In one embodiment, such as Figure 2 As shown, a method for generating a path graph is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0055] S210. Obtain the vascular subtraction image and the instrument subtraction image of the area to be examined, respectively.

[0056] The blood vessels at the site of examination include medical devices. These devices are implanted within the blood vessels. For example, the device may be a guidewire, stent, or coil. A subtraction angiography (SAG) is used to indicate the blood vessels at the site of examination, and a subtraction angiography (SAG) is used to indicate the medical devices at the site of examination. The SAG and SAG images have the same specifications.

[0057] Optionally, the computer equipment can perform image scanning of the site to be examined before angiography to obtain a mask of the site, and then perform image scanning of the site to be examined after angiography to obtain a full-body image of the site. Subtraction processing is then performed on the mask and full-body images of the site to obtain a subtracted angiogram of the blood vessel. Similarly, the computer equipment can perform image scanning of the site to be examined before and after the placement of the device in the blood vessel, and perform subtraction processing on the obtained images to obtain a subtracted angiogram of the device.

[0058] Optionally, the computer device can also acquire a perspective view of the device placed on the blood vessel at the site to be examined, and use this perspective view as a device subtraction image. Alternatively, it can acquire both the perspective view of the device placed on the blood vessel and the subtraction image of the blood vessel at the site to be examined, and perform subtraction processing on the perspective view and the subtraction image of the blood vessel to obtain the device subtraction image. In this embodiment, there are no specific limitations on the methods for acquiring the subtraction images of the blood vessel and the device.

[0059] S220. Perform equipment segmentation on the equipment subtraction image to obtain the equipment segmentation result.

[0060] The equipment segmentation result is used to characterize the distribution of equipment in the equipment subtraction image. For example, the equipment segmentation result may include equipment regions and non-equipment regions in the equipment subtraction image.

[0061] Optionally, the computer device can input the equipment subtraction image into the equipment segmentation model to obtain the equipment region and non-equipment region in the equipment subtraction image, and then obtain the equipment segmentation result including the equipment region and non-equipment region in the equipment subtraction image. The equipment segmentation model is a network model trained using a large number of equipment images as training samples.

[0062] Optionally, the computer device can also segment the subtraction image of the equipment based on the morphological features of the equipment, designating the regions in the subtraction image whose morphological features match those of the equipment as equipment regions, and the remaining regions as non-equipment regions. The computer device can also segment the subtraction image of the equipment using a grayscale threshold, designating the regions in the subtraction image where the grayscale value of pixels is less than a preset grayscale threshold as equipment regions, and the remaining regions as non-equipment regions. In this embodiment, the segmentation method of the subtraction image of the equipment is not specifically limited.

[0063] S230. Determine the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation results.

[0064] The weight template includes weight values ​​for each region in the segmented equipment subtraction image, with different weight values ​​for different regions. For example, when the equipment segmentation result includes equipment regions and non-equipment regions in the equipment subtraction image, the weight template corresponding to the equipment subtraction image includes weight values ​​for the corresponding equipment regions and weight values ​​for the corresponding non-equipment regions.

[0065] It should be noted that, to highlight the equipment, the weight values ​​in the weight template are positively correlated with the proportion of equipment in the region. Typically, in the equipment segmentation result, the equipment region includes equipment, while the non-equipment region does not. That is, the proportion of equipment in the equipment region is greater than that in the non-equipment region. Therefore, the weight value of the corresponding equipment region in the weight template is greater than the weight value of the corresponding non-equipment region.

[0066] Optionally, after obtaining the equipment segmentation result of the equipment subtraction image, the computer device can determine the weight value of each region in the equipment segmentation result according to the preset correspondence between regions and weights, and form a weight template corresponding to the equipment subtraction image based on the weight values ​​of each region. For example, when the equipment segmentation result of the equipment subtraction image consists of one part being equipment regions and the other part being non-equipment regions, the computer device searches the preset correspondence between regions and weights, determines that the weight value corresponding to the equipment regions in the equipment subtraction image is 1.5, and the weight value corresponding to the non-equipment regions is 1, and obtains a weight template formed by the weight value of 1.5 for the equipment regions and the weight value of 1 for the non-equipment regions in the equipment subtraction image.

[0067] S240. Based on the weight template, fuse the instrument subtraction image and the vascular subtraction image to obtain the path map of the area to be examined.

[0068] Optionally, the weight value in the weight template corresponding to the equipment subtraction image can be greater than or equal to 1, or less than 1, and can be set according to actual needs.

[0069] For example, when the weight value in the weight template is greater than or equal to 1, the computer device can use the weight value in the corresponding weight template of the equipment subtraction image as the weight of the equipment subtraction image and use the weight value 1 as the weight of the vascular subtraction image for fusion.

[0070] For example, when the weight value in the weight template is less than 1, when fusing the device subtraction image and the vessel subtraction image, the computer device can use the weight value in the weight template corresponding to the device subtraction image as the weight of the device subtraction image, determine the weight template corresponding to the vessel subtraction image based on the weight template corresponding to the device subtraction image, and then use the weight value in the weight template corresponding to the vessel subtraction image as the weight of the vessel subtraction image for fusion. Specifically, for pixels whose positions match in the device subtraction image and the vessel subtraction image, the sum of the weight value of that pixel in the weight template corresponding to the device subtraction image and the weight value in the weight template corresponding to the vessel subtraction image is 1.

[0071] Optionally, the computer device can perform weighted fusion of matching regions in the instrument subtraction image and the vascular subtraction image according to the weight template of the instrument subtraction image to obtain a path map of the site to be examined. For example, taking the path map G of the site to be examined as an example, the instrument subtraction image E includes the instrument region E1 (corresponding to the weight value α in the weight template) and the non-instrument region E2 (corresponding to the weight value β in the weight template), and the vascular subtraction image B includes the region B1 that matches E1 and the region B2 that matches E2, where G = (αE1 + B1) + (βE2 + B2), α ≥ 1, β ≥ 1.

[0072] In this embodiment, a computer device acquires a vascular subtraction image and an instrument subtraction image of the area to be examined. The instrument subtraction image is then segmented to obtain an instrument segmentation result. A weight template corresponding to the instrument subtraction image is determined based on the segmentation result. Subsequently, the instrument subtraction image and the vascular subtraction image are fused according to the weight template to obtain a path map of the area to be examined. The blood vessels in the area to be examined include instruments. In the above method, a corresponding weight template is determined based on the instrument segmentation result of the instrument subtraction image. Different weight values ​​are assigned to different regions in the instrument subtraction image, clarifying the focus of subsequent fusion, improving the contrast between blood vessels and instruments in the obtained path map, and thus improving the clarity of blood vessels and instruments in the path map.

[0073] In practical applications, the equipment segmentation result of the subtraction image can be determined based on the morphological characteristics of the equipment and the grayscale values ​​of the pixels in the equipment subtraction image. Based on this, in one embodiment, such as... Figure 3 As shown, in step S220 above, the equipment subtraction image is segmented to obtain the equipment segmentation result, including:

[0074] S310. Segment the subtraction image of the equipment according to its morphological characteristics to obtain the morphological segmentation result.

[0075] Optionally, the computer device can also segment the subtraction image of the equipment based on its morphological features, designating the regions in the subtraction image whose morphological features match those of the equipment as equipment regions, and the remaining regions as non-equipment regions, to obtain a morphological segmentation result that includes both equipment and non-equipment regions in the subtraction image. For example, taking a tubular device as an example, the computer device can segment the subtraction image of the equipment based on its tubular features, determining the regions in the subtraction image that match the tubular features as equipment regions, and determining the remaining regions in the subtraction image or regions that do not match the tubular features as non-equipment regions.

[0076] S320. Segment the equipment subtraction image according to the grayscale value of each pixel in the equipment subtraction image to obtain the grayscale segmentation result.

[0077] In an image, the grayscale value of a pixel represents its brightness. A higher grayscale value indicates a brighter pixel, while a lower grayscale value indicates a darker pixel. In an image with subtraction, pixels in the equipment area are darker than pixels in the non-equipment area; therefore, the grayscale value of pixels in the equipment area is lower than that of pixels in the non-equipment area.

[0078] Optionally, the grayscale segmentation result may include only the equipment region and non-equipment region in the equipment subtraction image, or it may include the equipment region, non-equipment region, and a mixed region in the equipment subtraction image. The mixed region is the transition area between the equipment region and the non-equipment region. The number of regions in the grayscale segmentation result is affected by the number of preset grayscale thresholds; the more preset grayscale thresholds, the more regions in the grayscale segmentation result. For example, when a single preset grayscale threshold is included, the grayscale segmentation result may include the equipment region and non-equipment region; when two preset grayscale thresholds are included, the grayscale segmentation result may include the equipment region, non-equipment region, and a mixed region.

[0079] Optionally, when a single preset grayscale threshold is included, the computer device can acquire the grayscale value of each pixel in the equipment subtraction image, and for each pixel, compare the corresponding grayscale value with the preset grayscale threshold to determine whether the pixel is a pixel in the equipment region, so as to obtain a shape segmentation result including the equipment region and non-equipment regions in the equipment subtraction image. Specifically, regions in the equipment subtraction image where the grayscale value of pixels is less than or equal to the preset grayscale threshold can be identified as equipment regions, and the remaining regions in the equipment subtraction image or regions where the grayscale value of pixels is greater than the preset grayscale value can be identified as non-equipment regions.

[0080] S330. Determine the equipment segmentation result based on the morphological segmentation result and the grayscale segmentation result.

[0081] The morphological segmentation result and the grayscale segmentation result may be the same or different.

[0082] Optionally, the computer device can determine the equipment segmentation result of the equipment subtraction image based on the morphological segmentation result and the grayscale segmentation result. Specifically, the computer device can compare the morphological segmentation result and the grayscale segmentation result, determine the segmentation result with finer granularity, and update the segmentation result with coarser granularity based on the finer granularity result to obtain the aforementioned equipment segmentation result.

[0083] Optionally, the number of regions segmented in the segmentation result can be used to characterize the segmentation granularity. The more regions segmented, the finer the segmentation granularity; conversely, the fewer regions segmented, the coarser the segmentation granularity. For example, if the number of regions segmented in the morphological segmentation result is greater than the number of regions segmented in the grayscale segmentation result, the computer device can update the grayscale segmentation result with the morphological segmentation result to obtain the equipment segmentation result; if the number of regions segmented in the grayscale segmentation result is greater than the number of regions segmented in the morphological segmentation result, the computer device can update the morphological segmentation result with the grayscale segmentation result to obtain the equipment segmentation result.

[0084] In this embodiment, the computer device segments the subtraction image of the equipment based on its morphological features to obtain a morphological segmentation result, and then segments the subtraction image based on the grayscale values ​​of each pixel in the subtraction image to obtain a grayscale segmentation result. Finally, the equipment segmentation result is determined based on both the morphological and grayscale segmentation results. In this method, the subtraction image is segmented based on both the morphological features of the equipment and the grayscale values ​​of the pixels in the subtraction image, achieving segmentation in different dimensions. The resulting segmentation results are then comprehensively determined, improving the diversity and fineness of the equipment segmentation results. This correspondingly increases the contrast between different regions in the obtained path image, thus improving the display effect.

[0085] Typically, grayscale segmentation results include the equipment region, non-equipment region, and mixed region in the equipment subtraction image. Based on this, in one embodiment, such as... Figure 4 As shown, in step S320 above, the equipment subtraction image is segmented based on the grayscale values ​​of each pixel to obtain the grayscale segmentation result, including:

[0086] S410. In the equipment subtraction image, the pixel region where the gray value of a pixel is less than or equal to a first gray value threshold is determined as the equipment region.

[0087] In the subtraction image of the equipment, the brightness of the equipment region, the blended region, and the non-equipment region increases sequentially. Correspondingly, the gray value of pixels in the equipment region is lower than that of pixels in the blended region, and the gray value of pixels in the blended region is lower than that of pixels in the non-equipment region.

[0088] Optionally, the computer device can acquire the grayscale value of each pixel in the subtraction image of the equipment, and for each pixel, compare the grayscale value of the pixel with a first preset grayscale threshold to determine that the pixel region formed by pixels in the subtraction image of the equipment whose grayscale value is less than or equal to the first grayscale threshold is the equipment region.

[0089] S420. In the subtraction image of the equipment, the pixel region where the gray value of the pixel is greater than or equal to the second gray value threshold is determined as the non-equipment region.

[0090] Optionally, the computer device can acquire the grayscale value of each pixel in the subtraction image of the equipment, and for each pixel, compare the grayscale value of the pixel with a second preset grayscale threshold to determine that the pixel area formed by pixels with grayscale values ​​greater than or equal to the second grayscale threshold in the subtraction image of the equipment is a non-equipment area.

[0091] S430. In the subtraction image of the equipment, the pixel region where the gray value of the pixel is greater than the first gray value threshold and less than the second gray value threshold is determined as the mixed region.

[0092] Optionally, the computer device can acquire the grayscale value of each pixel in the subtraction image of the equipment, and for each pixel, compare the grayscale value of the pixel with a first preset grayscale value and a second preset grayscale threshold to determine that the pixel region formed by pixels in the subtraction image of the equipment whose grayscale value is greater than the first grayscale threshold and less than the second grayscale threshold is a mixed region.

[0093] In this embodiment, the computer device, in an equipment subtraction image, determines that pixel regions with gray values ​​less than or equal to a first gray value threshold are equipment regions, pixel regions with gray values ​​greater than or equal to a second gray value threshold are non-equipment regions, and pixel regions with gray values ​​greater than the first gray value threshold and less than the second gray value threshold are mixed regions. In this method, based on the brightness relationships of different regions in the equipment subtraction image, the first and second gray value thresholds are used to segment the equipment subtraction image into equipment regions, non-equipment regions, and mixed regions, thereby improving the granularity of equipment subtraction image segmentation.

[0094] The equipment segmentation result includes a primary equipment area, a primary non-equipment area, a secondary equipment area, and a secondary non-equipment area. Therefore, in one embodiment, as... Figure 5 As shown, the above-mentioned S330, determining the equipment segmentation result based on the morphological segmentation result and the grayscale segmentation result, includes:

[0095] S510. Based on the morphological segmentation results, determine the mixed equipment region and the mixed non-equipment region in the mixed region.

[0096] Among them, the mixed equipment area represents the area in the mixed area where equipment accounts for a large proportion, and the mixed non-equipment area represents the area in the mixed area where non-equipment accounts for a large proportion.

[0097] When the subtraction image of the instrument includes an instrument region and a non-instrument region in the morphological segmentation result, and the grayscale segmentation result includes an instrument region, a non-instrument region, and a mixed region, the mixed region in the grayscale segmentation result is characterized as including part of the instrument region and / or part of the non-instrument region in the morphological segmentation result.

[0098] Optionally, the computer device can acquire the equipment region A1' that matches the position of equipment region A1 in the equipment subtraction image and the morphological segmentation result, and the non-equipment region A2' that matches the position of non-equipment region A2 in the morphological segmentation result. Simultaneously, it can acquire the mixed region B3' in the equipment subtraction image that matches the position of mixed region B3 in the grayscale segmentation result, so as to divide B3' into a mixed equipment region and a mixed non-equipment region based on A1', A2', and B3'. Specifically, the overlapping area between A1' and B3' in the equipment subtraction image is determined as the mixed equipment region A13', and the overlapping area between A2' and B3' in the equipment subtraction image is determined as the mixed non-equipment region A23'.

[0099] S520, Define the equipment area in the grayscale segmentation result as the first-level equipment area, define the non-equipment area in the grayscale segmentation result as the first-level non-equipment area, define the mixed equipment area as the second-level equipment area, and define the mixed non-equipment area as the second-level non-equipment area.

[0100] The proportion of equipment in the primary equipment area, secondary equipment area, primary non-equipment area, and secondary non-equipment area is different. Furthermore, the proportion of equipment in the primary equipment area is greater than that in the secondary equipment area, the proportion of equipment in the secondary equipment area is greater than that in the secondary non-equipment area, and the proportion of equipment in the secondary non-equipment area is greater than that in the primary non-equipment area.

[0101] Optionally, the computer device can determine the material region in the grayscale segmentation result as the first-level material region in the material subtraction image, determine the non-material region in the grayscale segmentation result as the first-level non-material region in the material subtraction image, determine the mixed material region in the mixed region of the grayscale segmentation result as the second-level material region, and determine the mixed non-material region in the mixed region of the grayscale segmentation result as the second-level non-material region.

[0102] S530. The first-level equipment region, the first-level non-equipment region, the second-level equipment region, and the second-level non-equipment region in the equipment subtraction image are taken as the equipment segmentation result.

[0103] Optionally, the computer device can directly divide the primary equipment region, primary non-equipment region, secondary equipment region, and secondary non-equipment region in the equipment subtraction image into the equipment segmentation result of the equipment subtraction image.

[0104] In an optional embodiment, when the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region, S230, determining the weight template corresponding to the equipment subtraction image based on the equipment segmentation result, includes:

[0105] The weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0106] Optionally, after obtaining the equipment segmentation results, the computer equipment can determine the weight values ​​of each region in the equipment segmentation results according to the preset correspondence between regions and weights, determine the first weight value corresponding to the first-level equipment region, the second weight value corresponding to the second-level equipment region, the third weight value corresponding to the second-level non-equipment region, and the fourth weight value of the first-level non-equipment region, and generate a weight template for the equipment subtraction image based on the first weight value of the first-level equipment region, the second weight value of the second-level equipment region, the third weight value of the second-level non-equipment region, and the fourth weight value of the first-level non-equipment region.

[0107] Optionally, to highlight the equipment, the first weight value is greater than the second weight value, which is greater than the third weight value, which is greater than the fourth weight value.

[0108] In this embodiment, the computer device determines the mixed equipment region and mixed non-equipment region within the mixed region based on the morphological segmentation result. The equipment region in the morphological segmentation result is defined as the primary equipment region, the non-equipment region as the primary non-equipment region, the mixed equipment region as the secondary equipment region, and the mixed non-equipment region as the secondary non-equipment region. Then, the primary equipment region, primary non-equipment region, secondary equipment region, and secondary non-equipment region in the equipment subtraction image are used as the equipment segmentation result. Based on this, a weight template for the equipment subtraction image can be generated according to the first weight value of the primary equipment region, the second weight value of the secondary equipment region, the third weight value of the secondary non-equipment region, and the fourth weight value of the primary non-equipment region. In the above method, the equipment segmentation result, including the primary equipment region, primary non-equipment region, secondary equipment region, and secondary non-equipment region, is obtained based on the morphological segmentation result and the grayscale segmentation result. This improves the segmentation granularity of the equipment subtraction image, correspondingly increases the contrast between regions in the obtained path map, and consequently improves the display efficiency.

[0109] To simplify the processing, in one embodiment, such as Figure 6 As shown, S510 above, determining the mixed equipment region and mixed non-equipment region in the mixed region based on the morphological segmentation result, includes:

[0110] S610. Determine the reference region that matches the position of the blending region in the morphological segmentation results.

[0111] Optionally, the computer device may determine a region in the morphological segmentation result that matches the location of the blended region and use that region as a reference region.

[0112] S620. The equipment area in the reference area is taken as the mixed equipment area, and the non-equipment area in the reference area is taken as the mixed non-equipment area.

[0113] Optionally, after the computer device obtains the reference region in the morphological segmentation result, it takes the instrument region in the reference region as the mixed instrument region and the non-instrument region in the reference region as the mixed non-instrument region.

[0114] In this embodiment, the computer device directly determines a reference region that matches the position of the mixed region in the morphological segmentation result, and then uses the equipment region in the reference region as the mixed equipment region and the non-equipment region in the reference region as the mixed non-equipment region. This method simplifies the process of determining the mixed equipment region and the mixed non-equipment region, saves processing time, improves processing efficiency, and correspondingly improves the efficiency of path map generation.

[0115] The fusion process of vascular subtraction images and instrument subtraction images is essentially a pixel value weighting process. Based on this, in one embodiment, such as... Figure 7 As shown, in step S240 above, the instrument subtraction image and the vessel subtraction image are fused according to the weight template to obtain a path map of the area to be examined, including:

[0116] S710. Use the weight values ​​of each pixel in the weight template as the equipment weights of the corresponding pixels in the equipment subtraction image.

[0117] In the weight template, different regions correspond to different weight values, while all pixels in the same region correspond to the same weight value.

[0118] Optionally, the computer device can determine the weight values ​​of pixels in each region of the weighted target, and the weight values ​​of pixels at corresponding positions in the subtractive plot of the material, denoted as the material weight. For example, such as... Figure 8 As shown, the weight template includes a primary equipment region Q1, a primary non-equipment region F1, a secondary equipment region Q2, and a secondary non-equipment region F2. Each pixel in Q1 corresponds to a weight value of 0.7, each pixel in F1 corresponds to a weight value of 0.2, each pixel in Q2 corresponds to a weight value of 0.5, and each pixel in F2 corresponds to a weight value of 0.3. Accordingly, in the equipment subtraction image, 0.7 is the equipment weight of each pixel in Q1, 0.2 is the equipment weight of each pixel in F1, 0.5 is the equipment weight of each pixel in Q2, and 0.3 is the equipment weight of each pixel in F2.

[0119] S720. The difference between the equipment weight and the reference weight of each pixel in the equipment subtraction image is used as the blood vessel weight of the corresponding pixel in the blood vessel subtraction image.

[0120] The reference weight is 1. Typically, the weight values ​​in the weight template are less than 1, meaning the equipment weight is less than 1. The sum of the equipment weight and vessel weight of pixels whose positions match in the equipment subtraction image and vessel subtraction image is the reference weight, which is 1.

[0121] Optionally, after obtaining the equipment weights of each pixel in the equipment subtraction image, the computer device can calculate the difference between the equipment weights and reference weights of each pixel in the equipment subtraction image as the weights of the corresponding pixels in the blood vessel subtraction image, denoted as the blood vessel weights. Continuing the example above, based on the equipment weights of each pixel in the equipment subtraction image and the reference weight 1, it can be calculated that in the blood vessel subtraction image, each pixel in Q1 corresponds to a blood vessel weight of 0.3, each pixel in F1 corresponds to a blood vessel weight of 0.8, each pixel in Q2 corresponds to a blood vessel weight of 0.5, and each pixel in F2 corresponds to a blood vessel weight of 0.7.

[0122] Optionally, before fusing the instrument subtraction image and the vascular subtraction image, the computer device can also smooth the weight values ​​in the weight template to obtain a smoothed weight template. This reduces the deviation between corresponding weight values ​​in adjacent areas of the weight template, resulting in a smooth transition between adjacent areas in the final path map, thereby improving the display effect of the obtained path map.

[0123] Optionally, before fusing the instrument subtraction image and the vessel subtraction image, the computer device can also adjust the brightness and contrast values ​​of the instrument subtraction image / vessel subtraction image. For example, to reduce fusion interference, the computer device can adjust the brightness and contrast values ​​of the instrument subtraction image / vessel subtraction image to make them the same. For instance, the computer device can acquire the brightness and contrast value of the instrument subtraction image and adjust the overall pixel grayscale of the vessel subtraction image accordingly, so that the brightness and contrast value of the vessel subtraction image reaches the target, i.e., is the same as the brightness and contrast value of the instrument subtraction image. Alternatively, the computer device can acquire the brightness and contrast value of the vessel subtraction image and adjust the overall pixel grayscale of the instrument subtraction image accordingly, so that the brightness and contrast value of the instrument subtraction image reaches the target, i.e., is the same as the brightness and contrast value of the vessel subtraction image.

[0124] S730: Pixel values ​​are weighted according to the equipment weight, blood vessel weight, equipment subtraction image, and blood vessel subtraction image to obtain the path map of the area to be examined.

[0125] Optionally, after obtaining the instrument subtraction image and the blood vessel subtraction image, as well as the instrument weight of each pixel in the instrument subtraction image and the blood vessel weight of each pixel in the blood vessel subtraction image, the computer device can use the instrument weight as the weight value of each pixel in the instrument subtraction image and the blood vessel weight as the weight value of each pixel in the blood vessel subtraction image, and perform a weighted summation of the pixel values ​​of the pixels with matching positions in the instrument subtraction image and the blood vessel subtraction image to obtain the path map of the area to be examined.

[0126] In this embodiment, the computer device uses the weight values ​​of each pixel in the weight template as the device weights of the corresponding pixels in the device subtraction image, and uses the difference between the device weights of each pixel in the device subtraction image and the reference weights as the vessel weights of the corresponding pixels in the vessel subtraction image. Based on the device weights, vessel weights, device subtraction images, and vessel subtraction images, pixel values ​​are weighted to obtain a path map of the area to be examined. In the above method, the device subtraction image and the vessel subtraction image are fused by weighted summation of pixel values, and the weights of the corresponding pixels are used as fusion constraints to achieve a fusion process that meets the requirements, improving the contrast between vessels and devices in the obtained path map, thereby improving the clarity of vessels and devices in the path map.

[0127] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0128] Based on the same inventive concept, this application also provides a path graph generation apparatus for implementing the path graph generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations of one or more path graph generation apparatus embodiments provided below can be found in the limitations of the path graph generation method described above, and will not be repeated here.

[0129] In one embodiment, such as Figure 9 As shown, a path map generation device is provided, comprising: an image acquisition module 901, an equipment segmentation module 902, a weight determination module 903, and an image fusion module 904, wherein:

[0130] The image acquisition module 901 is used to acquire the subtraction image of blood vessels and the subtraction image of instruments in the area to be examined, respectively.

[0131] The equipment segmentation module 902 is used to segment the equipment subtraction image to obtain the equipment segmentation result;

[0132] The weight determination module 903 is used to determine the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation results;

[0133] The image fusion module 904 is used to fuse the vascular subtraction image and the instrument subtraction image of the area to be examined according to the weight template to obtain the path map of the area to be examined.

[0134] In one embodiment, the equipment segmentation module 902 includes:

[0135] The morphology segmentation submodule is used to segment the subtraction image of the equipment based on its morphological characteristics to obtain the morphology segmentation result.

[0136] The grayscale segmentation submodule is used to segment the equipment subtraction image based on the grayscale values ​​of each pixel in the equipment subtraction image to obtain the grayscale segmentation result;

[0137] The result determination submodule is used to determine the equipment segmentation result based on the morphological segmentation result and the grayscale segmentation result.

[0138] In one embodiment, the grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; the grayscale segmentation submodule includes:

[0139] The equipment unit is used to determine the pixel region in the equipment subtraction image where the gray value of the pixel is less than or equal to a first gray threshold as the equipment region.

[0140] Non-equipment unit, used to determine the non-equipment region in an equipment subtraction image where the gray value of a pixel is greater than or equal to a second gray threshold;

[0141] The mixing unit is used to determine, in the subtraction image of the equipment, the pixel region where the gray value of the pixel is greater than a first gray value threshold and less than a second gray value threshold as the mixing region.

[0142] In one embodiment, the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region; the result determination submodule includes:

[0143] The hybrid partitioning unit is used to determine the hybrid equipment region and the hybrid non-equipment region in the hybrid region based on the morphological segmentation results.

[0144] The region classification unit is used to determine the equipment region in the grayscale segmentation result as the first-level equipment region, the non-equipment region in the grayscale segmentation result as the first-level non-equipment region, the mixed equipment region as the second-level equipment region, and the mixed non-equipment region as the second-level non-equipment region.

[0145] The result determination unit is used to take the primary equipment region, primary non-equipment region, secondary equipment region, and secondary non-equipment region in the equipment subtraction image as the equipment segmentation result.

[0146] In one embodiment, the hybrid partitioning unit includes:

[0147] Reference sub-units are used to determine reference regions that match the location of the blended regions in the morphological segmentation results;

[0148] The partition sub-unit is used to treat the equipment area in the reference area as a mixed equipment area and the non-equipment area in the reference area as a mixed non-equipment area.

[0149] In one embodiment, the weight determination module 903 is specifically used for:

[0150] A weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0151] In one embodiment, the image fusion module 904 includes:

[0152] The equipment weighting module is used to use the weight values ​​of each pixel in the weighting template as the equipment weights of the corresponding pixels in the equipment subtraction image.

[0153] The vessel weight module is used to take the difference between the equipment weight and the reference weight of each pixel in the equipment subtraction image as the vessel weight of the corresponding pixel in the vessel subtraction image.

[0154] The weighted fusion module is used to weight pixel values ​​based on the equipment weight, blood vessel weight, equipment subtraction image, and blood vessel subtraction image to obtain a path map of the area to be examined.

[0155] In one embodiment, the above-described apparatus further includes:

[0156] The smoothing module is used to smooth the weight values ​​in the weight template to obtain a smoothed weight template; and / or,

[0157] The contrast adjustment module is used to adjust the brightness and contrast values ​​of the subtraction angiography / vascular subtraction angiography.

[0158] Each module in the aforementioned path diagram generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0159] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0160] Obtain the vascular subtraction image and the instrument subtraction image of the area to be examined, respectively; perform instrument segmentation on the instrument subtraction image to obtain the instrument segmentation result; determine the weight template corresponding to the instrument subtraction image based on the instrument segmentation result; and fuse the instrument subtraction image and the vascular subtraction image according to the weight template to obtain the path map of the area to be examined.

[0161] In one embodiment, the processor further performs the following steps when executing the computer program:

[0162] The subtraction image of the equipment is segmented based on its morphological characteristics to obtain a morphological segmentation result; the subtraction image of the equipment is segmented based on the grayscale values ​​of each pixel in the subtraction image to obtain a grayscale segmentation result; the equipment segmentation result is determined based on the morphological segmentation result and the grayscale segmentation result.

[0163] In one embodiment, the grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; the processor also performs the following steps when executing the computer program:

[0164] In an equipment subtraction image, pixel regions with gray values ​​less than or equal to a first gray threshold are defined as equipment regions; pixel regions with gray values ​​greater than or equal to a second gray threshold are defined as non-equipment regions; and pixel regions with gray values ​​greater than the first gray threshold and less than the second gray threshold are defined as mixed regions.

[0165] In one embodiment, the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region; the processor, when executing the computer program, also performs the following steps:

[0166] Based on the morphological segmentation results, the mixed equipment region and mixed non-equipment region in the mixed region are determined; the equipment region in the grayscale segmentation results is determined as the first-level equipment region, the non-equipment region in the grayscale segmentation results is determined as the first-level non-equipment region, the mixed equipment region is determined as the second-level equipment region, and the mixed non-equipment region is determined as the second-level non-equipment region; the first-level equipment region, the first-level non-equipment region, the second-level equipment region, and the second-level non-equipment region in the equipment subtraction image are taken as the equipment segmentation results.

[0167] In one embodiment, the processor further performs the following steps when executing the computer program:

[0168] In the morphological segmentation results, a reference region matching the position of the mixed region is determined; the equipment region in the reference region is taken as the mixed equipment region, and the non-equipment region in the reference region is taken as the mixed non-equipment region.

[0169] In one embodiment, the processor further performs the following steps when executing the computer program:

[0170] A weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0171] In one embodiment, the processor further performs the following steps when executing the computer program:

[0172] The weight values ​​of each pixel in the weight template are used as the equipment weights of the corresponding pixels in the equipment subtraction image; the difference between the equipment weights and the reference weights of each pixel in the equipment subtraction image is used as the vascular weights of the corresponding pixels in the vascular subtraction image; the pixel values ​​are weighted according to the equipment weights, vascular weights, equipment subtraction images, and vascular subtraction images to obtain the path map of the area to be examined.

[0173] In one embodiment, the processor further performs the following steps when executing the computer program:

[0174] Smooth the weight values ​​in the weight template to obtain a smoothed weight template; and / or adjust the brightness and contrast values ​​of the instrument subtraction image / vascular subtraction image.

[0175] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0176] Obtain the vascular subtraction image and the instrument subtraction image of the area to be examined, respectively; perform instrument segmentation on the instrument subtraction image to obtain the instrument segmentation result; determine the weight template corresponding to the instrument subtraction image based on the instrument segmentation result; and fuse the instrument subtraction image and the vascular subtraction image according to the weight template to obtain the path map of the area to be examined.

[0177] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0178] The subtraction image of the equipment is segmented based on its morphological characteristics to obtain a morphological segmentation result; the subtraction image of the equipment is segmented based on the grayscale values ​​of each pixel in the subtraction image to obtain a grayscale segmentation result; the equipment segmentation result is determined based on the morphological segmentation result and the grayscale segmentation result.

[0179] In one embodiment, the grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; when the computer program is executed by the processor, it also performs the following steps:

[0180] In an equipment subtraction image, pixel regions with gray values ​​less than or equal to a first gray threshold are defined as equipment regions; pixel regions with gray values ​​greater than or equal to a second gray threshold are defined as non-equipment regions; and pixel regions with gray values ​​greater than the first gray threshold and less than the second gray threshold are defined as mixed regions.

[0181] In one embodiment, the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region; when the computer program is executed by the processor, it also performs the following steps:

[0182] Based on the morphological segmentation results, the mixed equipment region and mixed non-equipment region in the mixed region are determined; the equipment region in the grayscale segmentation results is determined as the first-level equipment region, the non-equipment region in the grayscale segmentation results is determined as the first-level non-equipment region, the mixed equipment region is determined as the second-level equipment region, and the mixed non-equipment region is determined as the second-level non-equipment region; the first-level equipment region, the first-level non-equipment region, the second-level equipment region, and the second-level non-equipment region in the equipment subtraction image are taken as the equipment segmentation results.

[0183] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0184] In the morphological segmentation results, a reference region matching the position of the mixed region is determined; the equipment region in the reference region is taken as the mixed equipment region, and the non-equipment region in the reference region is taken as the mixed non-equipment region.

[0185] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0186] A weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0187] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0188] The weight values ​​of each pixel in the weight template are used as the equipment weights of the corresponding pixels in the equipment subtraction image; the difference between the equipment weights and the reference weights of each pixel in the equipment subtraction image is used as the vascular weights of the corresponding pixels in the vascular subtraction image; the pixel values ​​are weighted according to the equipment weights, vascular weights, equipment subtraction images, and vascular subtraction images to obtain the path map of the area to be examined.

[0189] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0190] Smooth the weight values ​​in the weight template to obtain a smoothed weight template; and / or adjust the brightness and contrast values ​​of the instrument subtraction image / vascular subtraction image.

[0191] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0192] Obtain the vascular subtraction image and the instrument subtraction image of the area to be examined, respectively; perform instrument segmentation on the instrument subtraction image to obtain the instrument segmentation result; determine the weight template corresponding to the instrument subtraction image based on the instrument segmentation result; and fuse the instrument subtraction image and the vascular subtraction image according to the weight template to obtain the path map of the area to be examined.

[0193] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0194] The subtraction image of the equipment is segmented based on its morphological characteristics to obtain a morphological segmentation result; the subtraction image of the equipment is segmented based on the grayscale values ​​of each pixel in the subtraction image to obtain a grayscale segmentation result; the equipment segmentation result is determined based on the morphological segmentation result and the grayscale segmentation result.

[0195] In one embodiment, the grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; when the computer program is executed by the processor, it also performs the following steps:

[0196] In an equipment subtraction image, pixel regions with gray values ​​less than or equal to a first gray threshold are defined as equipment regions; pixel regions with gray values ​​greater than or equal to a second gray threshold are defined as non-equipment regions; and pixel regions with gray values ​​greater than the first gray threshold and less than the second gray threshold are defined as mixed regions.

[0197] In one embodiment, the equipment segmentation result includes a primary equipment region, a primary non-equipment region, a secondary equipment region, and a secondary non-equipment region; when the computer program is executed by the processor, it also performs the following steps:

[0198] Based on the morphological segmentation results, the mixed equipment region and mixed non-equipment region in the mixed region are determined; the equipment region in the grayscale segmentation results is determined as the first-level equipment region, the non-equipment region in the grayscale segmentation results is determined as the first-level non-equipment region, the mixed equipment region is determined as the second-level equipment region, and the mixed non-equipment region is determined as the second-level non-equipment region; the first-level equipment region, the first-level non-equipment region, the second-level equipment region, and the second-level non-equipment region in the equipment subtraction image are taken as the equipment segmentation results.

[0199] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0200] In the morphological segmentation results, a reference region matching the position of the mixed region is determined; the equipment region in the reference region is taken as the mixed equipment region, and the non-equipment region in the reference region is taken as the mixed non-equipment region.

[0201] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0202] A weight template for the subtraction image of the equipment is generated based on the first weight value of the primary equipment area, the second weight value of the secondary equipment area, the third weight value of the secondary non-equipment area, and the fourth weight value of the primary non-equipment area.

[0203] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0204] The weight values ​​of each pixel in the weight template are used as the equipment weights of the corresponding pixels in the equipment subtraction image; the difference between the equipment weights and the reference weights of each pixel in the equipment subtraction image is used as the vascular weights of the corresponding pixels in the vascular subtraction image; the pixel values ​​are weighted according to the equipment weights, vascular weights, equipment subtraction images, and vascular subtraction images to obtain the path map of the area to be examined.

[0205] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0206] Smooth the weight values ​​in the weight template to obtain a smoothed weight template; and / or adjust the brightness and contrast values ​​of the instrument subtraction image / vascular subtraction image.

[0207] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0208] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0209] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating a path graph, characterized in that, The method includes: A vascular subtraction image and an instrument subtraction image of the area to be examined are acquired respectively. Instrument segmentation is performed on the instrument subtraction image to obtain an instrument segmentation result. The instrument segmentation result is determined by: identifying a mixed instrument region and a mixed non-instrument region within the mixed region based on the morphological segmentation result; defining the instrument region in the grayscale segmentation result as a primary instrument region, the non-instrument region in the grayscale segmentation result as a primary non-instrument region, the mixed instrument region as a secondary instrument region, and the mixed non-instrument region as a secondary non-instrument region; the primary instrument region, the primary non-instrument region, the secondary instrument region, and the secondary non-instrument region in the instrument subtraction image are used as the instrument segmentation result; wherein, in the instrument subtraction image, pixel regions with grayscale values ​​greater than a first grayscale threshold and less than a second grayscale threshold are identified as the mixed region. The weight template corresponding to the subtraction image of the equipment is determined based on the equipment segmentation result; wherein, the weight template is generated based on the first weight value of the primary equipment region, the second weight value of the secondary equipment region, the third weight value of the secondary non-equipment region, and the fourth weight value of the primary non-equipment region; the weight value of each region in the weight template is positively correlated with the proportion of equipment in the region; According to the weighted template, the subtraction image of the equipment and the subtraction image of the blood vessels are fused by weighted summation of pixel values ​​to obtain a path map of the area to be examined, so as to enhance the contrast between blood vessels and equipment in the path map.

2. The method according to claim 1, characterized in that, The process of segmenting the equipment subtraction image to obtain the equipment segmentation result includes: The subtraction image of the equipment is segmented based on its morphological characteristics to obtain the morphological segmentation result; The subtraction image of the equipment is segmented based on the grayscale value of each pixel to obtain the grayscale segmentation result; The equipment segmentation result is determined based on the morphological segmentation result and the grayscale segmentation result.

3. The method according to claim 2, characterized in that, The grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; the grayscale segmentation of the equipment subtraction image based on the grayscale values ​​of each pixel in the equipment subtraction image to obtain the grayscale segmentation result includes: In the equipment subtraction image, the pixel region where the gray value of a pixel is less than or equal to a first gray value threshold is defined as the equipment region. In the subtraction image of the equipment, the pixel region where the gray value of a pixel is greater than or equal to the second gray threshold is determined to be the non-equipment region; In the subtraction image of the equipment, the pixel region whose gray value is greater than the first gray value threshold and less than the second gray value threshold is determined as the mixing region.

4. The method according to claim 1, characterized in that, The step of determining the mixed equipment region and the mixed non-equipment region in the mixed region based on the morphological segmentation result includes: In the morphological segmentation results, a reference region matching the position of the mixed region is determined; The equipment area in the reference area is taken as the mixed equipment area, and the non-equipment area in the reference area is taken as the mixed non-equipment area.

5. The method according to any one of claims 1-4, characterized in that, The step of fusing the vascular subtraction image and the instrument subtraction image according to the weight template to obtain the path map of the area to be examined includes: The weight value of each pixel in the weight template is used as the equipment weight of the corresponding pixel in the equipment subtraction image; The difference between the device weight and the reference weight of each pixel in the device subtraction image is used as the vascular weight of the corresponding pixel in the vascular subtraction image. The path map of the area to be examined is obtained by weighting the pixel values ​​based on the weight of the equipment, the weight of the blood vessel, the subtraction image of the equipment, and the subtraction image of the blood vessel.

6. The method according to any one of claims 1-4, characterized in that, Before fusing the vascular subtraction image and the device subtraction image, the method further includes: The weight values ​​in the weight template are smoothed to obtain a smoothed weight template; and / or, Adjust the brightness and contrast values ​​of the subtraction angiography of the equipment / the subtraction angiography of the blood vessels.

7. A path map generation apparatus, characterized in that, The device includes: The image acquisition module is used to acquire the subtraction angiogram of blood vessels and the subtraction angiogram of the equipment at the site to be examined, respectively. The equipment segmentation module is used to segment the equipment subtraction image to obtain equipment segmentation results. Determining the equipment segmentation results includes: identifying a mixed equipment region and a mixed non-equipment region within the mixed region based on the morphological segmentation results; defining the equipment region in the grayscale segmentation results as a primary equipment region, the non-equipment region in the grayscale segmentation results as a primary non-equipment region, the mixed equipment region as a secondary equipment region, and the mixed non-equipment region as a secondary non-equipment region; using the primary equipment region, the primary non-equipment region, the secondary equipment region, and the secondary non-equipment region in the equipment subtraction image as the equipment segmentation result; wherein, in the equipment subtraction image, pixel regions with grayscale values ​​greater than a first grayscale threshold and less than a second grayscale threshold are identified as the mixed region. The weight determination module is used to determine the weight template corresponding to the subtraction image of the equipment based on the equipment segmentation result; wherein, the weight template is generated based on the first weight value of the primary equipment region, the second weight value of the secondary equipment region, the third weight value of the secondary non-equipment region, and the fourth weight value of the primary non-equipment region; the weight value of each region in the weight template is positively correlated with the proportion of equipment in the region; The image fusion module is used to fuse the subtraction image of blood vessels and the subtraction image of equipment in the area to be examined by weighted summation of pixel values ​​according to the weight template, so as to obtain a path map of the area to be examined, thereby enhancing the contrast between blood vessels and equipment in the path map.

8. The apparatus according to claim 7, characterized in that, The equipment segmentation module includes: The morphology segmentation submodule is used to segment the subtraction image of the equipment based on its morphological characteristics to obtain the morphology segmentation result. The grayscale segmentation submodule is used to segment the equipment subtraction image based on the grayscale values ​​of each pixel in the equipment subtraction image to obtain the grayscale segmentation result; The result determination submodule is used to determine the equipment segmentation result based on the morphological segmentation result and the grayscale segmentation result.

9. The apparatus according to claim 8, characterized in that, The grayscale segmentation result includes the equipment region, non-equipment region, and mixed region in the equipment subtraction image; The grayscale segmentation submodule includes: The equipment unit is used to determine the pixel region in the equipment subtraction image where the gray value of a pixel is less than or equal to a first gray threshold. Non-equipment unit, used to determine the non-equipment region in the equipment subtraction image where the gray value of a pixel is greater than or equal to a second gray threshold; The mixing unit is used to determine, in the equipment subtraction image, the pixel region where the gray value of a pixel is greater than a first gray value threshold and less than a second gray value threshold as the mixing region.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

Images