Image processing method and device and medical imaging equipment

Abstract

The invention discloses an image processing method and device and medical imaging equipment, and relates to the technical field of image processing. After the medical imaging equipment acquires the original image of the scanned part, the region of interest can be extracted from the original image, and under the condition that the spinal artery exists in the region of interest, the target image, marked with the spinal artery and the opening of the spinal artery, of the scanned part is automatically displayed. Compared with a mode that a doctor recognizes the spinal artery by observing and analyzing a DSA image of the chest with naked eyes, the method provided by the invention has the advantages that on one hand, the spinal artery and the opening of the spinal artery can be quickly determined from the original image, and the recognition efficiency of the spinal artery is effectively improved; and on the other hand, the phenomena of misrecognition and missed recognition can be reduced to a certain extent, so that the recognition accuracy of the spinal artery can be improved. In addition, a doctor does not need to recognize the spinal artery, so that the operation of the doctor can be simplified.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an image processing method and device, and medical imaging equipment. Background Art

[0002] Patients with severe lung diseases (such as tuberculosis or bronchiectasis) may experience life-threatening symptoms of massive hemoptysis when their condition worsens. At this time, doctors need to promptly perform surgery to treat the blood vessels supplying the bleeding lesions to control the bleeding. In addition, during the operation, doctors also need to identify the patient's spinal artery and perform protective occlusion of the spinal artery to avoid paralysis of the patient's lower limbs due to accidental embolism of the spinal artery. Therefore, accurate identification of the spinal artery is crucial.

[0003] Currently, doctors can identify the spinal artery from the digital subtraction angiography (DSA) image of the chest by visually observing and analyzing the DSA image of the chest based on their own experience. However, the efficiency of doctors identifying the spinal artery by visually observing the DSA image is low. Summary of the invention

[0004] The present invention provides an image processing method and device, and medical imaging equipment, which can solve the problem of low efficiency in the related art that doctors identify spinal arteries by observing DSA images of the chest with naked eyes. The technical solution is as follows:

[0005] In one aspect, an image processing method is provided, the method comprising:

[0006] Acquire the original image of the scanned part;

[0007] Extracting a region of interest containing blood vessels from the original image;

[0008] When the spinal artery exists in the region of interest, a target image of the scanning site is displayed, and the spinal artery and the opening of the spinal artery are marked in the target image.

[0009] Optionally, the intercostal bronchial arteries and radicular arteries are also marked in the target image.

[0010] Optionally, display a target image of the scanned area, including:

[0011] The region of interest is input into the vascular category segmentation model to obtain an intermediate vascular image output by the vascular category segmentation model, where the intermediate vascular image is marked with spinal arteries, intercostal bronchial arteries and radicular arteries;

[0012] The junction of the intercostal bronchial artery and the radicular artery was determined as the location of the opening of the spinal artery;

[0013] Based on the position of the opening and the intermediate vascular image, a target image is acquired and displayed; the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the intermediate vascular image, or the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the original image.

[0014] Optionally, the original image is a digital subtraction angiography image; the target image showing the scanned part includes:

[0015] In the case that the spinal artery exists in multiple frames of continuous digital subtraction angiography images, multiple frames of target images of the scanned part are displayed, and each frame of the target image is obtained from one frame of digital subtraction angiography image having the spinal artery.

[0016] Optionally, extract the region of interest from the original image, including:

[0017] The original image is input into the vascular tree segmentation model to obtain the region of interest output by the vascular tree segmentation model; alternatively, target detection is performed on the original image to determine the position of each blood vessel, and the region of interest is extracted from the original image based on the position of blood vessels with diameters greater than a diameter threshold among multiple blood vessels.

[0018] Optionally, before displaying the target image of the scanned part, the method further includes:

[0019] Based on the region of interest, a recognition result of a spinal artery in the region of interest is determined, where the recognition result includes: the spinal artery exists in the region of interest and the spinal artery does not exist.

[0020] Optionally, based on the region of interest, determining the identification result of the spinal artery in the region of interest includes:

[0021] The region of interest is input into the spinal artery recognition model to obtain a recognition result of the spinal artery in the region of interest output by the spinal artery recognition model.

[0022] Optionally, the target image is also marked with a recommended occlusion position, which is used to place a device for occluding the spinal artery.

[0023] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the image processing method described in the above aspects is implemented.

[0024] In another aspect, a medical imaging device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the image processing method described in the above aspect is implemented.

[0025] In another aspect, an image processing device is provided, which is applied to a control device comprising:

[0026] An acquisition module, used for acquiring an original image of the scanned part;

[0027] An extraction module, used for extracting a region of interest containing blood vessels from an original image;

[0028] The display module is used for displaying a target image of the scanning site when a spinal artery exists in the region of interest, wherein the target image is marked with the spinal artery and the opening of the spinal artery.

[0029] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0030] The present invention provides an image processing method and apparatus, and a medical imaging device. After the medical imaging device acquires the original image of the scanned part, it can extract the region of interest from the original image, and when the spinal artery exists in the region of interest, it automatically displays the target image of the scanned part marked with the spinal artery and the opening of the spinal artery. Compared with the method in which doctors observe and analyze chest DSA images with the naked eye to identify the spinal artery, the method provided by the present invention can, on the one hand, quickly determine the spinal artery and the opening of the spinal artery from the original image, effectively improving the recognition efficiency of the spinal artery; on the other hand, it can reduce the phenomenon of misidentification and missed identification to a certain extent, thereby improving the recognition accuracy of the spinal artery. In addition, since there is no need for doctors to identify the spinal artery, the doctor's operation can be simplified.

[0031] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a flow chart of an image processing method provided by an embodiment of the present invention;

[0033] Figure 2 is a flow chart of another image processing method provided by an embodiment of the present invention;

[0034] Figure 3 is a schematic diagram of a target image and an auxiliary image provided by an embodiment of the present invention;

[0035] Figure 4 is a schematic diagram of another target image and an auxiliary image provided by an embodiment of the present invention;

[0036] Figure 5 is a structural schematic diagram of a medical imaging device provided by an embodiment of the present invention;

[0037] Figure 6It is a block diagram of an image processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0039] Patients with severe lung diseases (such as tuberculosis or bronchiectasis) may experience life-threatening symptoms of massive hemoptysis when their condition worsens. At this time, doctors need to promptly perform surgery to treat the blood vessels supplying the bleeding lesions to control the bleeding. In addition, during the operation, doctors also need to identify the patient's spinal artery and perform protective occlusion of the spinal artery to avoid paralysis of the patient's lower limbs due to accidental embolism of the spinal artery. Therefore, accurate identification of the spinal artery is crucial.

[0040] At present, DSA equipment can obtain and display a two-dimensional DSA image of a patient's chest. Doctors can observe and analyze the DSA image with the naked eye to identify the patient's spinal artery. However, the efficiency of doctors identifying the spinal artery by observing and analyzing the DSA image with the naked eye is low, and there may be problems of misidentification and missed identification of the spinal artery during the identification process, resulting in low accuracy in identifying the spinal artery.

[0041] Figure 1 is a flowchart of an image processing method provided by an embodiment of the present invention, and the method is applied to a medical imaging device. Optionally, the medical imaging device may be a DSA device and a computed tomography (CT) device. Figure 1 , the method comprising:

[0042] Step 101: Acquire an original image of the scanned part.

[0043] The scanning part may include: a chest of a scanning object. The scanning object may be a human body, a phantom or other animal body.

[0044] In an embodiment of the present invention, the original image may be a DSA image. At this time, the medical imaging device may first obtain a mask image of the scanned part and an angiography image. Afterwards, the medical imaging device may subtract the mask image from the angiography image to obtain a DSA image of the scanned part. The mask image is obtained by the medical imaging device scanning the scanned part before the contrast agent is injected into the scanned object. The angiography image is obtained by the medical imaging device scanning the scanned part after the contrast agent is injected into the scanned object. The DSA image of the scanned part may be a two-dimensional image.

[0045] Alternatively, the medical imaging device can obtain a CT image of the scanned part and segment the CT image (such as threshold segmentation) to obtain the original image of the scanned part. The CT image can be an image containing a contrast agent, an image without a contrast agent, or a subtraction image obtained based on an image containing a contrast agent and an image without a contrast agent.

[0046] Step 102: extracting a region of interest from the original image.

[0047] The region of interest may be a region in the original image that contains a blood vessel. For example, the center of the region of interest may be a blood vessel whose diameter is greater than a diameter threshold (ie, a thicker blood vessel).

[0048] In an embodiment of the present invention, the medical imaging device may perform target detection on the original image to determine the location of each blood vessel, and then extract the region of interest from the original image based on the location of the blood vessels with diameters greater than a diameter threshold among the multiple blood vessels. The diameter threshold may be pre-stored in the medical imaging device.

[0049] Alternatively, the medical imaging device may pre-store a vascular tree segmentation model. The medical imaging device may input the original image into the vascular tree segmentation model to obtain a region of interest output by the vascular tree segmentation model.

[0050] Step 103: When a spinal artery exists in the region of interest, a target image of the scanned part is displayed.

[0051] The medical imaging device can detect whether a spinal artery exists in the region of interest. If the medical imaging device determines that a spinal artery exists in the region of interest, a target image of the scanned portion can be acquired and displayed. The target image is marked with the spinal artery and the opening of the spinal artery. Thus, the position of the spinal artery and the position of the opening can be identified.

[0052] The position of the opening is used for the doctor to determine the occlusion position, which is the position for placing a device for occluding the spinal artery to perform protective occlusion on the spinal artery.

[0053] In summary, an embodiment of the present invention provides an image processing method. After the medical imaging device obtains the original image of the scanned part, it can extract the region of interest from the original image, and when the spinal artery exists in the region of interest, it automatically displays the target image of the scanned part marked with the spinal artery and the opening of the spinal artery. Compared with the method of doctors identifying the spinal artery by naked eye observation, the method provided by the embodiment of the present invention can, on the one hand, quickly determine the spinal artery and the opening of the spinal artery from the original image, effectively improving the recognition efficiency of the spinal artery; on the other hand, it can reduce the phenomenon of misidentification and missed identification to a certain extent, thereby improving the recognition accuracy of the spinal artery. In addition, since there is no need for doctors to identify the spinal artery, the doctor's operation can be simplified.

[0054] The present invention takes the original image as a DSA image as an example to exemplarily illustrate the image processing method provided by the present invention, and the method can be applied to medical imaging equipment. Figure 2 , the method may include:

[0055] Step 201: Acquire an original image of the scanned part.

[0056] The medical imaging device may first obtain a mask image of the scanned part and an angiography image. Afterwards, the medical imaging device may subtract the mask image from the angiography image to obtain a DSA image of the scanned part. The mask image is obtained by the medical imaging device scanning the scanned part before a contrast agent is injected into the scanned object. The angiography image is obtained by the medical imaging device scanning the scanned part after a contrast agent is injected into the scanned object. The scanned part may be the chest of the scanned object.

[0057] Step 202: Input the original image into the vascular tree segmentation model to obtain the region of interest output by the vascular tree segmentation model.

[0058] The medical imaging device may pre-store a vascular tree segmentation model. After obtaining an original image of the scanned part, the medical imaging device may input the original image into the vascular tree segmentation model to obtain a region of interest output by the vascular tree segmentation model.

[0059] In an embodiment of the present invention, before the medical imaging device inputs the original image into the vascular tree segmentation model, it can first obtain a vascular tree segmentation dataset, and perform model training based on the vascular tree segmentation dataset to obtain a vascular tree segmentation model. Optionally, the vascular tree segmentation model can be a U-Net neural network.

[0060] The vascular tree segmentation data set may include: a plurality of sample vascular images, and a plurality of labeled vascular images corresponding to the plurality of sample vascular images. Each of the plurality of labeled vascular images is marked with a sample region of interest. Each labeled vascular image may be obtained by manually marking the sample region of interest in a sample vascular image.

[0061] In an embodiment of the present invention, the medical imaging device may divide the vascular tree segmentation data set into a first training set and a first test set. Then, based on the first training set, the medical imaging device may adjust the parameters of the first initial model to minimize the first loss function to train the model, and determine the first initial model after training as the vascular tree segmentation model. Afterwards, the medical imaging device may use the first test set to evaluate the performance of the vascular tree segmentation model, and tune the vascular tree segmentation model based on the evaluation result to further improve the performance of the vascular tree segmentation model. The first initial model may be pre-stored in the medical imaging device.

[0062] Optionally, the ratio of the first training set to the first test set may be 4:1. The first loss function may include: a cross entropy loss function and / or a dice loss function. For example, the first loss function may be a weighted sum of a cross entropy loss function and a dice loss function, that is, the first loss value of the vascular tree segmentation model may be a weighted sum of a loss value of a cross entropy loss function and a loss value of a dice loss function. The weight of the cross entropy loss function and the weight of the dice loss function may be pre-stored. For example, the ratio of the weight of the cross entropy loss function to the weight of the dice loss function may be 0.5:1.

[0063] Step 203: Based on the region of interest, determine the recognition result of the spinal artery in the region of interest.

[0064] The recognition result includes: the spinal artery exists in the region of interest and the spinal artery does not exist.

[0065] In the embodiment of the present invention, the medical imaging device may perform target detection on the region of interest to determine the recognition result of the spinal artery in the region of interest.

[0066] Alternatively, a spinal artery recognition model is stored in the medical imaging device. The medical imaging device can input the region of interest into the spinal artery recognition model to obtain the recognition result of the spinal artery in the region of interest output by the spinal artery recognition model. Optionally, the spinal artery recognition model can output a target probability, which can characterize the recognition result of the spinal artery in the region of interest. For example, the target probability can be 1 or 0. If the target probability is 1, it means that the recognition result is that the spinal artery exists in the region of interest; if the target probability is 0, it means that the recognition result is that the spinal artery does not exist in the region of interest.

[0067] In an embodiment of the present invention, before the medical imaging device inputs the region of interest into the spinal artery recognition model, it can obtain a spinal artery recognition dataset, and perform model training based on the spinal artery recognition dataset to obtain a spinal artery recognition model. Optionally, the spinal artery recognition model can be a densely connected convolutional network (DenseNet).

[0068] The spinal artery recognition data set may include: multiple first sample regions of interest, and multiple label recognition results corresponding to the multiple first sample regions of interest. Each first sample region of interest may be obtained by extracting a region of interest from a sample blood vessel image by a medical imaging device. The region of interest may include an image of a blood vessel. Each label recognition result may be obtained by manually marking the recognition result of the spinal artery in a first sample region of interest.

[0069] In an embodiment of the present invention, the medical imaging device may divide the spinal artery recognition data set into a second training set and a second test set. Then, based on the second training set, the medical imaging device may adjust the parameters of the second initial model to minimize the second loss function to train the model, and determine the second initial model after training as the spinal artery recognition model. Afterwards, the medical imaging device may use the second test set to evaluate the performance of the spinal artery recognition model, and optimize the spinal artery recognition model based on the evaluation result to further improve the performance of the spinal artery recognition model. The second initial model may be pre-stored in the medical imaging device.

[0070] Optionally, the ratio of the second training set to the second test set may be 4: 1. The second loss function may be a cross entropy loss function.

[0071] Step 204: When a spinal artery exists in the region of interest, a target image of the scanned area is displayed.

[0072] The target image is marked with a spinal artery and an opening of the spinal artery. Thus, the position of the spinal artery and the position of the opening can be identified. The position of the opening is used for doctors to determine the blocking position, which is the position for placing a device for blocking the spinal artery to perform protective blocking on the spinal artery.

[0073] In the embodiment of the present invention, the size of the target image may be equal to the size of the original image. In this case, the target image may be an image obtained after marking at least the spinal artery and the opening of the spinal artery in the original image. Alternatively, the size of the target image may be equal to the size of the region of interest. In this case, the target image may be obtained after marking at least the spinal artery and the opening in the region of interest.

[0074] Optionally, the target image may also be marked with intercostal bronchial arteries and root arteries. In addition, when the size of the target image is equal to the size of the original image, the target image may also be marked with a region of interest. For ease of distinction, the region of interest in the original image is referred to as a first region of interest, and the region of interest in the target image is referred to as a second region of interest. The position of the first region of interest in the original image is the same as the position of the second region of interest in the target image. Compared with the first region of interest, the second region of interest is marked with the spinal artery, the opening of the spinal artery, the intercostal bronchial artery and the root artery.

[0075] Taking the target image marked with the spinal artery, the opening of the spinal artery, the intercostal bronchial artery and the root artery as an example, referring to the following steps C1 to C3, the process of displaying the target image of the scanned part by the medical imaging device is exemplarily described. The process may include:

[0076] Step C1: input the region of interest into the blood vessel classification segmentation model to obtain an intermediate blood vessel image output by the blood vessel classification segmentation model.

[0077] Among them, the middle blood vessel image is labeled with spinal artery, intercostal bronchial artery and root artery. Medical imaging equipment can pre-store blood vessel category segmentation models.

[0078] Optionally, before the medical imaging device inputs the region of interest into the vascular classification segmentation model, it can obtain a vascular classification segmentation dataset and perform model training based on the vascular classification segmentation dataset to obtain a vascular classification segmentation model. Optionally, the vascular classification segmentation model can be a U-Net neural network.

[0079] The blood vessel category segmentation data set may include: multiple second sample regions of interest and multiple labeled blood vessel categories corresponding to the multiple second sample regions of interest. The medical imaging device may determine multiple labeled identification results of the spinal artery in the spinal artery identification data set as the second sample regions of interest. Each labeled blood vessel category may be obtained by manually marking different types of blood vessels in a second sample region of interest. The different types of blood vessels include: intercostal bronchial arteries, root arteries, and spinal arteries.

[0080] In an embodiment of the present invention, the medical imaging device may divide the blood vessel classification segmentation data set into a third training set and a third test set. Then, the medical imaging device may adjust the parameters of the third initial model based on the third training set to minimize the third loss function to train the model, and determine the third initial model after training as the blood vessel classification segmentation model. Afterwards, the medical imaging device may use the third test set to evaluate the performance of the blood vessel classification segmentation model, and optimize the blood vessel classification segmentation model based on the evaluation result to further improve the performance of the blood vessel classification segmentation model. The third initial model may be pre-stored in the medical imaging device.

[0081] Optionally, the ratio of the third training set to the third test set may be 4:1. The third loss function may include: a cross entropy loss function and / or a dice loss function. For example, the third loss function may be a weighted sum of the cross entropy loss function and the dice loss function. That is, the third loss value of the blood vessel category segmentation model may be a weighted sum of the loss value of the cross entropy loss function and the loss value of the dice loss function. The weight of the cross entropy loss function and the weight of the dice loss function may be pre-stored. For example, the ratio of the weight of the cross entropy loss function to the weight of the dice loss function may be 0.5:1.

[0082] Step C2: determine the junction of the intercostal bronchial artery and the root artery as the opening of the spinal artery.

[0083] After the medical imaging device identifies the intercostal bronchial artery and the root artery, the intersection position of the intercostal bronchial artery and the root artery can be determined, and then the intersection position is determined as the position of the opening of the spinal artery.

[0084] Step C3: acquiring and displaying a target image based on the position of the opening and the intermediate blood vessel image.

[0085] In the embodiment of the present invention, when the size of the target image is equal to the size of the region of interest, the medical imaging device can directly mark the opening in the intermediate blood vessel image based on the position of the opening, thereby obtaining the target image. That is, the target image is an image obtained after marking at least the opening of the spinal artery and the spinal artery in the intermediate blood vessel image.

[0086] In the case where the size of the target image is equal to the size of the original image, the medical imaging device can acquire the target image based on the position of the opening, the intermediate blood vessel image and the original image. Specifically, the medical imaging device first marks the opening in the intermediate blood vessel image to obtain the intermediate blood vessel image marked with the opening. The size of the intermediate blood vessel image is equal to the size of the region of interest. Then, the medical imaging device can replace the region of interest in the original image with the intermediate blood vessel image marked with the opening, thereby obtaining the target image. That is, at this time, the target image can be regarded as an image obtained after marking at least the opening of the spinal artery and the spinal artery in the original image.

[0087] Optionally, the medical imaging device marks the opening in the form of a detection frame in the intermediate blood vessel image, thereby obtaining a target image.

[0088] In an embodiment of the present invention, after the medical imaging device acquires the target image, the target image and the original image can be displayed simultaneously for comparison and viewing by the doctor. The target image and the original image can be displayed on one display screen, or can be displayed on multiple display screens (such as two) respectively.

[0089] Furthermore, when displaying the target image, the medical imaging device may also display the auxiliary image. It is understood that when the size of the target image is equal to the size of the region of interest, see Figure 3 , the auxiliary image can be the original image with the region of interest marked. In the case where the size of the target image is equal to the size of the original image, see Figure 4 The auxiliary image may be a partial magnified image of the second region of interest in the target image. In this way, the doctor can more intuitively see the details of the content marked in the second region of interest (such as the spinal artery and the opening, etc.), thereby improving the accuracy of the doctor's operation.

[0090] Please continue to see Figure 3 and Figure 4 , Figure 3 and Figure 4 In the present invention, spinal artery opening identification refers to the opening of the spinal artery, and spinal artery segmentation refers to the spinal artery. Figure 3 The region of interest in the vessel tree is identified as the first region of interest.

[0091] Optionally, the target image may also be marked with a recommended occlusion position, which is used to place a device for occluding the spinal artery.

[0092] Since the target image can also be marked with recommended occlusion positions for the doctor's reference, the doctor's work efficiency can be effectively improved compared to the doctor directly judging the recommended occlusion positions based on experience.

[0093] Optionally, the process of the medical imaging device acquiring the original image of the scanned part may include: acquiring a DSA image sequence of the scanned part, the DSA image sequence including multiple frames of DSA images. The medical imaging device can detect whether there is a spinal artery in each frame of the DSA image. In the case where the spinal artery exists in multiple consecutive frames of DSA images, the medical imaging device can determine that the spinal artery exists in the DSA image sequence, and then display multiple frames of target images. Each frame of the target image is obtained based on a frame of DSA image with a spinal artery. In this way, the probability of misjudgment of the medical imaging device can be effectively reduced, the accuracy of the medical imaging device in identifying the spinal artery can be improved, and the reliability of the medical imaging device can be improved.

[0094] Patients with severe lung diseases (such as tuberculosis or bronchiectasis) may experience life-threatening symptoms of massive hemoptysis when their condition worsens. At this time, doctors need to promptly perform surgery to treat the blood vessels supplying the bleeding lesions to control the bleeding. In addition, during the operation, doctors also need to identify the patient's spinal artery and perform protective occlusion of the spinal artery to avoid paralysis of the patient's lower limbs due to accidental embolism of the spinal artery. Therefore, accurate identification of the spinal artery is crucial.

[0095] In the related art, cone beam computed tomography (CBCT) equipment can acquire and display three-dimensional CBCT images of the patient's chest for doctors to view and identify the spinal arteries. However, although the three-dimensional CBCT images can include richer vascular information compared to the two-dimensional DSA images, doctors still need to identify the spinal arteries through naked eye observation and analysis. There are still problems with low efficiency of the spinal artery identification method and misidentification and missed identification of the spinal artery. Moreover, when using the CBCT device to acquire a three-dimensional CBCT image of the patient's chest, the patient needs to be angiographically imaged at a large angle, which increases the patient's radiation dose. In addition, since the CBCT device takes a long time to reconstruct the CBCT image, the operation time is long, which in turn leads to low efficiency of the operation.

[0096] Based on this, the image processing method provided by the embodiment of the present invention can improve the efficiency and accuracy of spinal artery identification because it does not require the doctor to identify it through naked eye observation. In addition, since it is not necessary to identify the spinal artery based on CBCT images, it can avoid increasing the radiation dose of the scanned object, and can reduce the operation time, improve the operation efficiency, and improve the fluency of the operation process.

[0097] It is understandable that the order of the steps of the image processing method provided by the embodiment of the present invention can be appropriately adjusted, and the steps can be increased or decreased accordingly according to the situation. For example, step 201 can be deleted according to the situation. Any technician familiar with the technical field can easily think of a method of variation within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention, so it will not be repeated.

[0098] In summary, an embodiment of the present invention provides an image processing method. After the medical imaging device obtains the original image of the scanned part, it can extract the region of interest from the original image, and when the spinal artery exists in the region of interest, it automatically displays the target image of the scanned part marked with the spinal artery and the opening of the spinal artery. Compared with the way in which doctors observe and analyze chest DSA images with the naked eye to identify the spinal artery, the method provided by the embodiment of the present invention can, on the one hand, quickly determine the spinal artery and the opening of the spinal artery from the original image, effectively improving the recognition efficiency of the spinal artery; on the other hand, it can reduce the phenomenon of misidentification and missed identification to a certain extent, thereby improving the recognition accuracy of the spinal artery. In addition, since there is no need for doctors to identify the spinal artery, the doctor's operation can be simplified.

[0099] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned image processing method is implemented. Figure 1 or Figure 2 The image processing method shown.

[0100] Figure 5 is a schematic diagram of the structure of a medical imaging device provided by an embodiment of the present invention, such as Figure 5 As shown, the medical imaging device 50 may include a memory 501, a processor 502, and a computer program stored in the memory 501 and executable on the processor 502. When the processor 502 executes the computer program, the image processing method shown in the above embodiment is implemented. Figure 1 or Figure 2 The image processing method shown.

[0101] Figure 6 is a block diagram of an image processing device provided by an embodiment of the present invention, such as Figure 6 As shown, the control device 60 includes:

[0102] The acquisition module 601 is used to acquire the original image of the scanned part.

[0103] The extraction module 602 is used to extract a region of interest including blood vessels from the original image.

[0104] The display module 603 is used to: when there is a spinal artery in the region of interest, display a target image of the scanned part, where the target image is marked with the spinal artery and the opening of the spinal artery.

[0105] Optionally, the intercostal bronchial arteries and radicular arteries are also marked in the target image.

[0106] Optionally, the display module 603 may be used to: input the region of interest into the vascular category segmentation model to obtain an intermediate vascular image output by the vascular category segmentation model, wherein the intermediate vascular image is marked with spinal arteries, intercostal bronchial arteries, and radicular arteries;

[0107] The junction of the intercostal bronchial artery and the radicular artery was determined as the location of the opening of the spinal artery;

[0108] Based on the position of the opening and the intermediate vascular image, a target image is acquired and displayed; the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the intermediate vascular image, or the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the original image.

[0109] Optionally, the original image is a digital subtraction angiography image; the display module 603 can be used to:

[0110] In the case that the spinal artery exists in multiple frames of continuous digital subtraction angiography images, multiple frames of target images of the scanned part are displayed, and each frame of the target image is obtained from one frame of digital subtraction angiography image having the spinal artery.

[0111] Optionally, the extraction module 602 may be used to:

[0112] The original image is input into the vascular tree segmentation model to obtain the region of interest output by the vascular tree segmentation model; alternatively, target detection is performed on the original image to determine the position of each blood vessel, and the region of interest is extracted from the original image based on the position of blood vessels with diameters greater than a diameter threshold among multiple blood vessels.

[0113] Optional, reference Figure 6 The control device 60 may further include an identification module 604, which may be used to determine an identification result of a spinal artery in the region of interest based on the region of interest before displaying a target image of the scanned portion, the identification result including: the presence or absence of a spinal artery in the region of interest.

[0114] Optionally, the identification module 604 may be used to:

[0115] The region of interest is input into the spinal artery recognition model to obtain a recognition result of the spinal artery in the region of interest output by the spinal artery recognition model.

[0116] Optionally, the target image is also marked with a recommended occlusion position, which is used to place a device for occluding the spinal artery.

[0117] In summary, an embodiment of the present invention provides an image processing device. After the medical imaging device obtains the original image of the scanned part, it can extract the region of interest from the original image, and when the spinal artery exists in the region of interest, it automatically displays the target image of the scanned part marked with the spinal artery and the opening of the spinal artery. Compared with the way in which doctors observe and analyze chest DSA images with the naked eye to identify the spinal artery, the device provided by the embodiment of the present invention can, on the one hand, quickly determine the spinal artery and the opening of the spinal artery from the original image, effectively improving the recognition efficiency of the spinal artery; on the other hand, it can reduce the phenomenon of misidentification and missed identification to a certain extent, thereby improving the recognition accuracy of the spinal artery. In addition, since there is no need for a doctor to identify the spinal artery, the doctor's operation can be simplified.

[0118] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0119] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0120] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0121] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0122] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0123] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.

[0124] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0125] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An image processing method, characterized in that: The method comprises: Acquire the original image of the scanned part; extracting a region of interest containing a blood vessel from the original image; When a spinal artery exists in the region of interest, a target image of the scanning region is displayed, wherein the spinal artery and the opening of the spinal artery are marked on the target image.

2. The method according to claim 1, characterized in that The target image also includes intercostal bronchial arteries and radicular arteries marked.

3. The method according to claim 2, characterized in that Displaying a target image of the scanned part includes: Inputting the region of interest into a blood vessel classification segmentation model to obtain an intermediate blood vessel image output by the blood vessel classification segmentation model, wherein the intermediate blood vessel image is marked with the spinal artery, the intercostal bronchial artery, and the radicular artery; Determine the junction of the intercostal bronchial artery and the root artery as the opening of the spinal artery; Based on the position of the opening and the intermediate blood vessel image, a target image is acquired and displayed; the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the intermediate blood vessel image, or the target image is an image obtained after at least the opening of the spinal artery and the spinal artery are marked in the original image.

4. The method according to any one of claims 1 to 3, characterized in that: The original image is a digital subtraction angiography image; the target image showing the scanned part includes: When a spinal artery exists in a plurality of consecutive frames of the digital subtraction angiography images, a plurality of frames of target images of the scanned part are displayed, each frame of the target image being obtained from a frame of the digital subtraction angiography image having the spinal artery.

5. The method according to any one of claims 1 to 3, characterized in that: Extracting a region of interest from the original image includes: Inputting the original image into a vascular tree segmentation model to obtain a region of interest output by the vascular tree segmentation model; Alternatively, target detection is performed on the original image to determine the position of each blood vessel, and a region of interest is extracted from the original image based on the position of a blood vessel having a diameter greater than a diameter threshold among the multiple blood vessels.

6. The method according to any one of claims 1 to 3, characterized in that: Before displaying the target image of the scanned part, the method further includes: Based on the region of interest, a recognition result of a spinal artery in the region of interest is determined, the recognition result comprising: the spinal artery exists in the region of interest and the spinal artery does not exist.

7. The method according to claim 6, characterized in that Determining, based on the region of interest, an identification result of a spinal artery in the region of interest, comprising: The region of interest is input into a spinal artery recognition model to obtain a recognition result of the spinal artery in the region of interest output by the spinal artery recognition model.

8. The method according to any one of claims 1 to 3, characterized in that: The target image is also marked with a recommended occlusion position, where the recommended occlusion position is used to place a device for occluding the spinal artery.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the image processing method according to any one of claims 1 to 8 is implemented.

10. A medical imaging device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the image processing method according to any one of claims 1 to 8 is implemented.

11. An image processing device, characterized in that: The device comprises: An acquisition module, used for acquiring an original image of the scanned part; An extraction module, used for extracting a region of interest from the original image; The display module is used for displaying a target image of the scanning part when a spinal artery exists in the region of interest, wherein the target image is marked with the spinal artery and the opening of the spinal artery.

Images