Contrast image analysis method and device

Abstract

The present invention provides a contrast image analysis method and device, belonging to the technical field of contrast image processing. The contrast image analysis method of the present invention obtains an image of a target blood vessel area after blood flows back to the target blood vessel, obtains a first development image after previous image processing, and compares the clarity with a second development image obtained in a conventional development process, and then selects a higher-definition image to obtain a final target blood vessel contrast image, thereby reducing the impact of low contrast of the development image caused by dynamic changes in blood and contrast agents, and can obtain the clearest and most accurate target blood vessel contrast image.

Description

Technical Field

[0001] The present invention relates to the technical field of contrast image processing, and in particular to a contrast image analysis method and device. Background Art

[0002] Carbon dioxide angiography is a medical imaging technique used to visualize the internal structure of blood vessels. This process is done by injecting carbon dioxide gas into the patient's vascular system. When the carbon dioxide is injected, it temporarily empties a section of blood vessels of blood. The x-ray device can capture an image of the blood vessels because carbon dioxide and human tissue absorb x-rays differently. This difference allows the structures within the blood vessels to be clearly seen. The carbon dioxide then quickly dissolves in the blood and circulates through the blood into the respiratory system, where it is exhaled. This way, the effects of carbon dioxide on the body are very short-lived and do not remain in the body. The main advantages of this process are that it provides clear images of blood vessels and that carbon dioxide is safer than traditional contrast agents, especially for patients who are allergic to iodine-based contrast agents.

[0003] Existing carbon dioxide angiography mainly obtains the angiography image of the blood vessel by subtracting the image obtained after the carbon dioxide contrast agent empties the blood in the target blood vessel from the basic image. However, since the blood vessel is sensitive to parameters such as the amount of carbon dioxide injection, injection pressure, and injection speed, the dynamic changes of blood and contrast agent will lead to low clarity of the developed image, and a clear angiography image may not be obtained after the angiography operation. Summary of the invention

[0004] The present invention provides an angiography image analysis method and device, which are used to solve the defect of low clarity of angiography images in the prior art and achieve the effect of obtaining clearer angiography images.

[0005] The present invention provides a method for analyzing angiographic images, comprising:

[0006] acquiring a first image, wherein the first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel;

[0007] Acquire a second image, wherein the second image is an image of the target blood vessel region after the carbon dioxide contrast agent is injected into the target blood vessel region and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent;

[0008] acquiring a third image, wherein the third image is an image of the target blood vessel region after blood flows back into the target blood vessel;

[0009] comparing the clarity of the target blood vessel in a first developed image with the clarity of the target blood vessel in a second developed image; the first developed image is determined based on the third image and the second image; the second developed image is determined based on the second image and the first image;

[0010] In a case where the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image, a target blood vessel angiography image of the target blood vessel region is determined based on the first developed image.

[0011] According to a contrast image analysis method provided by the present invention, the clarity of the target blood vessel is determined by:

[0012] Performing target segmentation on the image containing the target blood vessel, and identifying the target blood vessel area and the background area respectively;

[0013] Based on the target blood vessel area and the background area, determining the contrast of the target blood vessel area relative to the background area and the edge clarity of the target blood vessel;

[0014] The definition of the target blood vessel is determined based on the signal-to-noise ratio of the target blood vessel region, the contrast of the target blood vessel region relative to the background region, and the edge definition of the target blood vessel.

[0015] According to a method for analyzing angiography images provided by the present invention, determining a target blood vessel angiography image of the target blood vessel region based on the first development image includes:

[0016] comparing a blood vessel contour of a target blood vessel in the first developed image with a blood vessel contour of the target blood vessel in the second developed image;

[0017] When there is a deviation between the blood vessel contour of the target blood vessel in the first developed image and the blood vessel contour of the target blood vessel in the second developed image, correcting the first developed image based on the second developed image;

[0018] The corrected first development image is determined as the target angiography image.

[0019] According to a contrast image analysis method provided by the present invention, the first developed image is corrected based on the second developed image, comprising:

[0020] Based on the second developed image, identifying a first target position of the target blood vessel in the first developed image; the first target position is a position where the morphology of the target blood vessel is deformed; the deformation includes at least one of bending, stretching and twisting;

[0021] Based on the image of the target blood vessel at the first target position in the second developed image, the first target position of the target blood vessel in the first developed image is corrected to obtain a corrected first developed image.

[0022] According to a contrast image analysis method provided by the present invention, the first developed image is corrected based on the second developed image, comprising:

[0023] Based on the second developed image, identifying a second target position of the target blood vessel in the first developed image; the second target position is a position where dense carbon dioxide contrast agent remains in the target blood vessel;

[0024] Based on the image of the target blood vessel at the second target position in the second developed image, the second target position of the target blood vessel in the first developed image is corrected to obtain a corrected first developed image.

[0025] According to a contrast image analysis method provided by the present invention, the first image, the second image and the third image are all captured by using a high frame rate DSA device.

[0026] The present invention also provides a radiographic image analysis device, comprising:

[0027] A first acquisition module is used to acquire a first image, where the first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel;

[0028] A second acquisition module is used to acquire a second image, wherein the second image is an image of the target blood vessel region after the carbon dioxide contrast agent is injected into the target blood vessel region and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent;

[0029] A third acquisition module, used for acquiring a third image, wherein the third image is an image of the target blood vessel area after blood flows back to the target blood vessel;

[0030] a comparison module, configured to compare the clarity of the target blood vessel in a first developed image with the clarity of the target blood vessel in a second developed image; the first developed image is determined based on the third image and the second image; the second developed image is determined based on the second image and the first image;

[0031] A processing module is used to determine a target blood vessel angiography image of the target blood vessel region based on the first developed image when the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image.

[0032] The present invention also provides a DSA development device, comprising: an X-ray generator, an imaging auxiliary device, an image generator and a processing system;

[0033] The X-ray generator is used to generate X-rays, the imaging auxiliary device is used to adjust the position of the imaged object, and the image generator is used to capture image data formed after the X-rays generated by the X-ray generator pass through the imaged object;

[0034] The processing system is used to control the operation of the X-ray generator, the imaging auxiliary device, and the image generator, and to process and analyze the acquired image data; the processing system includes an image processor and a memory, the memory stores a computer program, and when the image processor executes the computer program, the angiography image analysis method as described in any one of claims 1 to 6 is implemented.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned angiography image analysis methods is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the angiography image analysis method as described above is implemented.

[0037] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned angiography image analysis methods.

[0038] The angiography image analysis method and device provided by the present invention obtain an image of the target blood vessel area after blood flows back to the target blood vessel, obtain a first development image after processing with the previous image, and compare the clarity with the second development image obtained in the conventional development process, and then select a higher-definition image to obtain the final target blood vessel angiography image, reduce the impact of low clarity of the development image caused by dynamic changes in blood and contrast agent, and can obtain the clearest and most accurate target blood vessel angiography image. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1It is one of the flow charts of the angiographic image analysis method provided by the present invention;

[0041] Figure 2 This is the second flow chart of the angiographic image analysis method provided by the present invention;

[0042] Figure 3 It is a structural schematic diagram of the angiography image analysis device provided by the present invention;

[0043] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Combine the following Figure 1-Figure 4 The angiographic image analysis method and device of the present invention are described.

[0046] like Figure 1 As shown, the angiography image analysis method according to the embodiment of the present invention mainly includes step 110 , step 120 , step 130 , step 140 and step 150 .

[0047] Step 110: Acquire a first image.

[0048] The first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel.

[0049] Step 120: Acquire a second image.

[0050] The second image is an image of the target blood vessel region after the carbon dioxide contrast agent is injected into the target blood vessel region and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent.

[0051] Step 130: Acquire a third image.

[0052] The third image is an image of the target blood vessel region after blood flows back into the target blood vessel.

[0053] It is understood that vascular images may be captured by equipping the device with a digital subtraction angiography (DSA) device or other suitable imaging devices.

[0054] Before carbon dioxide is injected into the target blood vessel, the DSA device is used to capture the basic image and the first image of the target blood vessel. This image captures the blood vessel structure when it is filled with blood, but the carbon dioxide contrast agent has not yet been injected, so the clear blood vessel structure cannot be directly observed.

[0055] After the carbon dioxide is injected, the carbon dioxide contrast agent quickly diffuses in the blood vessels and replaces the blood, clearly showing the lumen of the blood vessels. Immediately after the carbon dioxide contrast agent is injected, the DSA device is used to capture a second image, which reflects the vascular structure after the carbon dioxide replaces the blood.

[0056] After the carbon dioxide contrast agent has completed contrast, blood will naturally return to the target blood vessel area. This process usually completes very quickly, so a third image after this process needs to be taken quickly.

[0057] After the blood flows back to the target blood vessel, a third image is taken again using DSA. The third image shows the state of the blood vessel after the blood is refilled.

[0058] It should be noted that the first image, the second image and the third image are all captured by using a DSA device with a high frame rate.

[0059] High-frame-rate DSA devices can capture images at a speed of tens to hundreds of frames per second, which enables DSA devices to record the rapid flow of blood and carbon dioxide contrast agents in blood vessels and provide continuous dynamic image sequences.

[0060] In other words, by using a high frame rate DSA device, the first image, the second image, and the third image may each include a plurality of continuous image sequences, thus providing abundant basic images for obtaining accurate development images.

[0061] In addition, high frame rates can significantly reduce image blur and artifacts caused by micro-movements such as heartbeats, thereby improving image clarity and accuracy.

[0062] Step 140 : Compare the clarity of the target blood vessel in the first developed image with the clarity of the target blood vessel in the second developed image.

[0063] The first developed image is determined based on the third image and the second image; the second developed image is determined based on the second image and the first image.

[0064] Subtraction techniques in DSA can highlight the distribution of contrast agents in blood vessels by subtracting one image from another. Typically, a background image (the base image without contrast agent) is compared and subtracted from a foreground image (the image after contrast agent injection).

[0065] Through image processing software, the information in the background image (such as bones, soft tissue, etc.) is subtracted, leaving only the contrast agent image in the foreground image. This processing can eliminate unnecessary background interference and make blood vessel imaging clearer.

[0066] In this embodiment, the first developed image is obtained by performing a subtraction operation on the third image and the second image. The subtraction operation refers to subtracting the pixel values ​​of one image from another image. Specifically, the pixel values ​​in the third image may be subtracted from the pixel values ​​in the second image.

[0067] The third image shows the state after the blood flows back to the target blood vessel, while the second image shows the state when the blood vessel is filled with carbon dioxide contrast agent. Through subtraction, the structure of the blood vessel after the blood flows back can be highlighted. This subtraction process makes the blood vessel structure present a higher contrast, and the inner wall of the blood vessel, possible lesions or narrow areas can be more clearly displayed.

[0068] The second developed image may be obtained by performing a subtraction operation on the second image and the first image, or by subtracting a pixel value in the first image from a pixel value in the second image.

[0069] The first image represents the basal state when blood fills the blood vessels, while the second image represents the state inside the blood vessels after the carbon dioxide contrast agent replaces the blood.

[0070] It should be noted that after the blood flows back to the target blood vessel, a relatively clearer first development image of the target blood vessel can be obtained by acquiring a suitable third image and performing a subtraction operation with the previous image.

[0071] Although in actual operation, the clarity of the first developed image is higher, there are also some situations where the clarity of the first developed image is relatively poor.

[0072] Since it is difficult to determine the speed at which blood flows back after carbon dioxide gas is discharged from the blood vessels, the third image taken by the DSA device in actual practice may not be a photo taken just after the blood has returned. The blood may not have completely returned, or the blood may have returned too quickly, and the carbon dioxide in the tissues around the target blood vessel area may also dissipate quickly. This will also make it impossible for the first development image obtained after subtracting the third image from the previous second image to show the clear structure of the target blood vessel.

[0073] Therefore, it is necessary to compare the clarity of the target blood vessel in the first developed image with the clarity of the target blood vessel in the second developed image, and then select the image with higher clarity to obtain the target blood vessel angiography image.

[0074] It can be understood that the sharpness of an image is evaluated by calculating the sum of the gradient amplitudes in the entire image. Regions with larger gradients generally indicate richer details of the image, and thus images with richer details are regarded as images with higher clarity.

[0075] The energy of the local area of ​​the image (usually the sum of the squares of the grayscale changes) can also be analyzed to evaluate the texture and edge clarity of the image, and to distinguish images with clearer details. The image can also be converted to the frequency domain for analysis. Images with higher clarity usually have higher high-frequency components. By comparing the high-frequency components of the first developed image and the second developed image, it can be determined which image has higher clarity.

[0076] In some embodiments, the definition of the target vessel is determined in the following manner.

[0077] The image containing the target blood vessel may be segmented to identify the target blood vessel region and the background region, respectively, and then based on the target blood vessel region and the background region, the contrast of the target blood vessel region relative to the background region and the edge clarity of the target blood vessel may be determined.

[0078] Finally, the definition of the target vessel is determined based on the signal-to-noise ratio of the target vessel region, the contrast of the target vessel region relative to the background region, and the edge definition of the target vessel.

[0079] It is understandable that the acquired image may be preprocessed first, including grayscale conversion, denoising processing (such as Gaussian filtering), etc., to reduce image noise and enhance visibility of the target blood vessel.

[0080] The target blood vessel region and the background region are separated in the image using a target segmentation algorithm, such as the Otsu threshold method, region growing method, K-means clustering or convolutional neural network (CNN). The result after segmentation is usually a binary image, in which the blood vessel region is marked as foreground (such as 1) and the background region is marked as background (such as 0).

[0081] Contrast is usually defined as the grayscale value difference between the target blood vessel region and the background region. The contrast can be obtained by calculating the average grayscale value of all pixels in the target blood vessel region and the average grayscale value of the background region.

[0082] On this basis, edge detection algorithms, such as Sobel operator and Canny edge detection, are further used to identify the edges of target blood vessels.

[0083] The result of edge detection is usually an image that emphasizes areas with fast grayscale changes in the image, which usually correspond to the edges of blood vessels. In the edge image, the gradient amplitude (i.e., the speed of grayscale change) of edge pixels is calculated. The average gradient amplitude or the peak value of the edge can be used as a measure of edge clarity. A higher gradient amplitude indicates a sharper edge and higher blood vessel clarity.

[0084] The signal-to-noise ratio indicates the ratio of the signal (i.e. the useful information of the target vascular region) to the noise (background or random noise). The signal intensity is usually taken as the average grayscale value of the target vascular region. The noise intensity can be represented by the standard deviation of the background region. A higher signal-to-noise ratio means that the difference between the target vascular region and the background region is more obvious, and the image clarity is higher.

[0085] In some embodiments, the above three indicators (contrast, edge clarity, and signal-to-noise ratio) can be normalized so that they can be compared on the same scale, and a weight can be assigned to each indicator, which can be determined based on experience, application scenarios, or through experiments.

[0086] Finally, the clarity of the target blood vessel is determined based on the comprehensive score. If necessary, a threshold can be set to determine whether the image has reached the clarity required for diagnosis.

[0087] Step 150 : when the definition of the target blood vessel in the first developed image is greater than the definition of the target blood vessel in the second developed image, determine a target blood vessel angiography image of the target blood vessel region based on the first developed image.

[0088] It can be understood that, when the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image, the first developed image can be directly determined as the target blood vessel angiography image of the target blood vessel region.

[0089] Of course, if there are defects in the first developed image, the first developed image can be corrected to obtain the final target angiography image.

[0090] According to an angiography image analysis method provided by an embodiment of the present invention, an image of a target blood vessel area after blood flows back to the target blood vessel is obtained, a first development image after processing with the previous image is obtained, and the clarity is compared with the second development image obtained by the conventional development process, and then a higher-definition image is selected to obtain the final target blood vessel angiography image, thereby reducing the impact of low clarity of the development image caused by dynamic changes in blood and contrast agent, and being able to obtain the clearest and most accurate target blood vessel angiography image.

[0091] In some embodiments, Figure 2As shown, step 150: determining a target blood vessel angiography image of a target blood vessel region based on the first development image, includes steps 151, 152 and 153.

[0092] Step 151 : Compare the blood vessel contour of the target blood vessel in the first developed image with the blood vessel contour of the target blood vessel in the second developed image.

[0093] Step 152 : When there is a deviation between the blood vessel contour of the target blood vessel in the first developed image and the blood vessel contour of the target blood vessel in the second developed image, correct the first developed image based on the second developed image.

[0094] Step 153: determine the corrected first development image as the target angiography image.

[0095] An edge detection algorithm, such as Canny edge detection or Sobel operator, may be used to extract the contour of the target blood vessel in the first development image and the second development image.

[0096] The continuous contour line in the edge detection result can be extracted to obtain the outer edge of the target blood vessel.

[0097] Perform image registration (such as affine transformation or rigid transformation) on the first developed image and the second developed image to ensure that the two images are aligned in space. Compare the contours of blood vessels in the two registered images. Shape matching algorithms, such as Hausdorff distance, ICP algorithm, etc., can be used to evaluate the deviation between the two.

[0098] The Hausdorff distance is a distance that measures the maximum deviation between two sets of points (here, two blood vessel contours). It can quantify the maximum deviation between two contours. The contour of the target blood vessel can be extracted from the first development image and the second development image, and the contour point set can be represented as two point sets A and B.

[0099] The unidirectional Hausdorff distance from point set A to point set B can be calculated based on the Euclidean distance, and then the distance from point set B to point set A can be calculated. The final Hausdorff distance is the maximum value of these two unidirectional distances. The larger the Hausdorff distance, the greater the deviation between the two contours. By calculating the Hausdorff distance, the degree of match between the two contours is evaluated. If the distance is large, it means that the contour in the first developed image needs to be corrected.

[0100] The ICP algorithm is a method for registering two point sets. It gradually reduces the deviation between two contours by iteratively finding the closest point pair.

[0101] The deviation between the target blood vessel contour in the first developed image and the contour in the second developed image is calculated based on the contour comparison result of step 151. The deviation can be measured by the point-to-point distance, angle difference or deformation degree of the contour line.

[0102] The first developed image may be subjected to an appropriate geometric transformation (such as translation, rotation, scaling) to make its blood vessel contour more consistent with the contour of the second developed image. The transformation may be determined by minimizing the difference between the two contours.

[0103] If the deviation is mainly concentrated in a specific area, local correction can be performed in that area. Deformable models (such as thin plate spline deformation) can be used to achieve local fine-tuning.

[0104] If there is still a slight deviation after correction, it may be necessary to fuse the corrected first development image and the second development image to obtain a final high-quality target angiography image.

[0105] The clarity of the corrected first developed image is re-evaluated (such as the aforementioned contrast, edge clarity, and signal-to-noise ratio analysis) to ensure that the quality of the corrected image is higher than or equal to that of the second developed image.

[0106] If the clarity of the corrected first development image meets or exceeds the expected standard, it can be directly determined as the target angiography image.

[0107] Through the above steps, the vascular contours of the two developed images can be accurately compared and corrected, thereby obtaining a higher quality and more accurate target vascular angiography image, which is suitable for scenarios requiring high-precision vascular imaging and facilitates more accurate detection of lesions such as vascular stenosis and aneurysms.

[0108] In some embodiments, correcting the first developed image based on the second developed image also includes: identifying a first target position of the target blood vessel in the first developed image based on the second developed image; the first target position is the position where the morphology of the target blood vessel is deformed; the deformation includes at least one of bending, stretching and twisting; based on the image of the target blood vessel at the first target position in the second developed image, correcting the first target position of the target blood vessel in the first developed image to obtain a corrected first developed image.

[0109] During angiography, the subject will experience a certain amount of pain or other physical discomfort after the injection of carbon dioxide contrast agent. If the patient's body moves or twists, it will affect the target blood vessels at the angiography location.

[0110] Blood vessels may deform in different states, such as bending, stretching or twisting, which may cause inconsistencies in the shape and position of blood vessels in different images. Especially in areas with obvious deformation, the target blood vessel shape in the first image may deviate from the actual situation, affecting the accuracy of the image and subsequent analysis.

[0111] When the second development image is acquired, the carbon dioxide contrast agent has just been injected into the blood vessel, and the reaction of the injected object is small. Based on the information in the second development image, the first target position where the blood vessel morphology in the first development image is deformed can be identified. This position is usually the part where the blood vessel is bent, stretched or twisted. By analyzing the blood vessel morphology at this position in the second development image, more accurate morphological information can be obtained. Then, this information is used to correct the blood vessel morphology at the corresponding position in the first development image to make it more realistic and accurate. Finally, the corrected first development image is obtained to ensure that the blood vessel morphology in the image is more in line with the actual situation, thereby improving the diagnostic value and reliability of the image.

[0112] In some embodiments, correcting the first developed image based on the second developed image includes: identifying a second target position of the target blood vessel in the first developed image based on the second developed image; the second target position is a position where dense carbon dioxide contrast agent residues exist in the target blood vessel; based on an image of the target blood vessel at the second target position in the second developed image, correcting the second target position of the target blood vessel in the first developed image to obtain a corrected first developed image.

[0113] During carbon dioxide angiography, the carbon dioxide contrast agent may not be uniformly dispersed and distributed in the blood vessels, and dense carbon dioxide residue may exist in certain parts of the blood vessels. This residue may affect the clarity and accuracy of the image, resulting in incomplete or blurred display of the target blood vessels in the first image.

[0114] In order to improve the accuracy of the image, it is necessary to correct the first developed image based on the second developed image. Specifically, the second target position where the carbon dioxide residue in the first developed image is dense is first identified in the second developed image. These positions are usually caused by the incomplete dissipation or emptying of the contrast agent. Then, the blood vessels at the corresponding positions in the first developed image are corrected using the clearer and more complete vascular image information of these positions in the second developed image.

[0115] Through correction, the image error caused by residual contrast agent can be reduced, and finally a more accurate and clear corrected first development image can be obtained, ensuring that the diagnostic effect of angiography is more reliable.

[0116] The contrast image analysis device provided by the present invention is described below. The contrast image analysis device described below and the contrast image analysis method described above can be referenced to each other.

[0117] like Figure 3 As shown, the angiography image analysis device according to the embodiment of the present invention mainly includes a first acquisition module 310 , a second acquisition module 320 , a third acquisition module 330 , a comparison module 340 and a processing module 350 .

[0118] The first acquisition module 310 is used to acquire a first image, where the first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel;

[0119] The second acquisition module 320 is used to acquire a second image, which is an image of the target blood vessel area after the carbon dioxide contrast agent is injected into the target blood vessel area and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent;

[0120] The third acquisition module 330 is used to acquire a third image, where the third image is an image of the target blood vessel area after blood flows back to the target blood vessel;

[0121] The comparison module 340 is used to compare the clarity of the target blood vessel in the first development image with the clarity of the target blood vessel in the second development image; the first development image is determined based on the third image and the second image; the second development image is determined based on the second image and the first image;

[0122] The processing module 350 is configured to determine a target blood vessel angiography image of the target blood vessel region based on the first development image when the clarity of the target blood vessel in the first development image is greater than the clarity of the target blood vessel in the second development image.

[0123] According to an embodiment of the present invention, an angiography image analysis device is provided. By acquiring an image of a target blood vessel region after blood flows back to the target blood vessel, a first development image after processing with a previous image is obtained, and the clarity is compared with a second development image obtained by a conventional development process, and then a higher-definition image is selected to obtain a final target blood vessel angiography image, thereby reducing the impact of low clarity of the development image caused by dynamic changes in blood and contrast agent, and being able to obtain the clearest and most accurate target blood vessel angiography image.

[0124] The embodiment of the present invention further provides a DSA developing device, which includes: an X-ray generator, an imaging auxiliary device, an image generator, and a processing system. The X-ray generator is used to generate X-rays, the imaging auxiliary device is used to adjust the position of the imaged object, and the image generator is used to capture image data formed after the X-rays generated by the X-ray generator pass through the imaged object.

[0125] The processing system is used to control the operation of the X-ray generator, the imaging auxiliary device, and the image generator, and to process and analyze the acquired image data; the processing system includes an image processor and a memory, the memory stores a computer program, and the image processor implements the above-mentioned angiography image analysis method when executing the computer program, the method comprising: acquiring a first image, the first image is an image of the target blood vessel before the carbon dioxide contrast agent is injected into the target blood vessel; acquiring a second image, the second image is an image of the target blood vessel area after the carbon dioxide contrast agent is injected into the target blood vessel area and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; acquiring a third image, the third image is an image of the target blood vessel area after the blood flows back to the target blood vessel; comparing the clarity of the target blood vessel in the first development image with the clarity of the target blood vessel in the second development image; the first development image is determined based on the third image and the second image; the second development image is determined based on the second image and the first image; when the clarity of the target blood vessel in the first development image is greater than the clarity of the target blood vessel in the second development image, determining the target blood vessel angiography image of the target blood vessel area based on the first development image.

[0126] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute the angiography image analysis method, which includes: acquiring a first image, the first image is an image of the target blood vessel before the carbon dioxide contrast agent is injected into the target blood vessel; acquiring a second image, the second image is an image of the target blood vessel area after the carbon dioxide contrast agent is injected into the target blood vessel area and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; acquiring a third image, the third image is an image of the target blood vessel area after the blood flows back into the target blood vessel; comparing the clarity of the target blood vessel in the first development image with the clarity of the target blood vessel in the second development image; the first development image is determined based on the third image and the second image; the second development image is determined based on the second image and the first image; when the clarity of the target blood vessel in the first development image is greater than the clarity of the target blood vessel in the second development image, determining the target blood vessel angiography image of the target blood vessel area based on the first development image.

[0127] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0128] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the angiography image analysis method provided by the above methods, which includes: acquiring a first image, the first image is an image of the target blood vessel before the carbon dioxide contrast agent is injected into the target blood vessel; acquiring a second image, the second image is an image of the target blood vessel area after the carbon dioxide contrast agent is injected into the target blood vessel area and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; acquiring a third image, the third image is an image of the target blood vessel area after the blood flows back to the target blood vessel; comparing the clarity of the target blood vessel in the first development image with the clarity of the target blood vessel in the second development image; the first development image is determined based on the third image and the second image; the second development image is determined based on the second image and the first image; when the clarity of the target blood vessel in the first development image is greater than the clarity of the target blood vessel in the second development image, determining the target blood vessel angiography image of the target blood vessel area based on the first development image.

[0129] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the angiography image analysis method provided by the above-mentioned methods, the method comprising: acquiring a first image, the first image being an image of the target blood vessel before the carbon dioxide contrast agent is injected into the target blood vessel; acquiring a second image, the second image being an image of the target blood vessel area after the carbon dioxide contrast agent is injected into the target blood vessel area and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; acquiring a third image, the third image being an image of the target blood vessel area after the blood flows back into the target blood vessel; comparing the clarity of the target blood vessel in the first developed image with the clarity of the target blood vessel in the second developed image; the first developed image is determined based on the third image and the second image; the second developed image is determined based on the second image and the first image; when the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image, determining the target blood vessel angiography image of the target blood vessel area based on the first developed image.

[0130] The device embodiments described above are merely illustrative, 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 on 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. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing angiographic images, It is characterized in that include: Acquiring a first image, wherein the first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel; Acquire a second image, wherein the second image is an image of the target blood vessel region after the carbon dioxide contrast agent is injected into the target blood vessel region and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; acquiring a third image, wherein the third image is an image of the target blood vessel region after blood flows back into the target blood vessel; comparing the clarity of the target blood vessel in a first developed image with the clarity of the target blood vessel in a second developed image; the first developed image is obtained by performing a subtraction operation on the third image and the second image; and the second developed image is obtained by performing a subtraction operation on the second image and the first image; In a case where the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image, a target blood vessel angiography image of the target blood vessel region is determined based on the first developed image.

2. The contrast image analysis method according to claim 1, It is characterized in that The clarity of the target blood vessel is determined by: Performing target segmentation on the image containing the target blood vessel, and identifying the target blood vessel area and the background area respectively; Based on the target blood vessel area and the background area, determining the contrast of the target blood vessel area relative to the background area and the edge clarity of the target blood vessel; The definition of the target blood vessel is determined based on the signal-to-noise ratio of the target blood vessel region, the contrast of the target blood vessel region relative to the background region, and the edge definition of the target blood vessel.

3. The contrast image analysis method according to claim 1, It is characterized in that The step of determining a target angiography image of the target blood vessel region based on the first development image comprises: comparing a blood vessel contour of a target blood vessel in the first developed image with a blood vessel contour of the target blood vessel in the second developed image; When there is a deviation between the blood vessel contour of the target blood vessel in the first developed image and the blood vessel contour of the target blood vessel in the second developed image, correcting the first developed image based on the second developed image; The corrected first development image is determined as the target angiography image.

4. The contrast image analysis method according to claim 3, It is characterized in that The correcting the first developed image based on the second developed image includes: Based on the second developed image, identifying a first target position of the target blood vessel in the first developed image; the first target position is a position where the morphology of the target blood vessel is deformed; the deformation includes at least one of bending, stretching and twisting; Based on the image of the target blood vessel at the first target position in the second developed image, the first target position of the target blood vessel in the first developed image is corrected to obtain a corrected first developed image.

5. The contrast image analysis method according to claim 3, It is characterized in that The correcting the first developed image based on the second developed image includes: Based on the second developed image, identifying a second target position of the target blood vessel in the first developed image; the second target position is a position where dense carbon dioxide contrast agent remains in the target blood vessel; Based on the image of the target blood vessel at the second target position in the second developed image, the second target position of the target blood vessel in the first developed image is corrected to obtain a corrected first developed image.

6. The contrast image analysis method according to claim 1, It is characterized in that The first image, the second image, and the third image are all captured using a DSA device with a high frame rate.

7. A radiographic image analysis device, It is characterized in that include: A first acquisition module is used to acquire a first image, where the first image is an image of the target blood vessel before a carbon dioxide contrast agent is injected into the target blood vessel; A second acquisition module is used to acquire a second image, wherein the second image is an image of the target blood vessel region after the carbon dioxide contrast agent is injected into the target blood vessel region and the blood in the target blood vessel is emptied by the carbon dioxide contrast agent; A third acquisition module, used for acquiring a third image, wherein the third image is an image of the target blood vessel area after blood flows back to the target blood vessel; a comparison module, configured to compare the clarity of the target blood vessel in a first developed image with the clarity of the target blood vessel in a second developed image; the first developed image is obtained by performing a subtraction operation on the third image and the second image; the second developed image is obtained by performing a subtraction operation on the second image and the first image; A processing module is used to determine a target blood vessel angiography image of the target blood vessel region based on the first developed image when the clarity of the target blood vessel in the first developed image is greater than the clarity of the target blood vessel in the second developed image.

8. A DSA developing device, It is characterized in that include: X-ray generators, imaging aids, image generators, and processing systems; The X-ray generator is used to generate X-rays, the imaging auxiliary device is used to adjust the position of the imaged object, and the image generator is used to capture image data formed after the X-rays generated by the X-ray generator pass through the imaged object; The processing system is used to control the operation of the X-ray generator, the imaging auxiliary device, and the image generator, and to process and analyze the acquired image data; the processing system includes an image processor and a memory, the memory stores a computer program, and when the image processor executes the computer program, the angiography image analysis method as described in any one of claims 1 to 6 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, It is characterized in that When the processor executes the program, the contrast image analysis method according to any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the contrast image analysis method according to any one of claims 1 to 6 is implemented.

Images