Image analysis method, apparatus and computer device

Abstract

The application relates to an image analysis method, device and computer equipment. The method comprises the following steps: acquiring a blood vessel image to be processed, performing identification processing on the blood vessel image to be processed, determining a target tissue region image and a reference region of interest image, acquiring a first enhancement intensity of the target tissue region image and a second enhancement intensity of the reference region of interest image, and determining the reinforcement degree of the target tissue by the first enhancement intensity and the second enhancement intensity. The method can identify the target tissue region and the reference region of interest in the blood vessel first, and then calculate the reinforcement degree of the target tissue by the target tissue region and the reference region of interest, thereby avoiding the intervention process by medical staff according to experience, and the accuracy of the determined reinforcement degree of the plaque can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical technical field, in particular to an image analysis method and device and computer equipment. BACKGROUND

[0002] Stroke, also known as apoplexy or cerebrovascular accident, is an acute cerebrovascular disease, including ischemic stroke and hemorrhagic stroke. Generally, the incidence of ischemic stroke is higher than that of hemorrhagic stroke. In ischemic stroke patients, plaques can reflect the level of inflammatory activity, and the degree of plaque enhancement is related to acute vascular events. Significant plaque enhancement indicates unstable plaques. Unstable plaques are prone to acute cardiovascular events. Therefore, the degree of plaque enhancement is an important indicator for intracranial plaque evaluation and the most important parameter for plaque qualitative evaluation.

[0003] In the traditional technology, clinical medical staff observe images and evaluate the relative enhancement of plaques based on clinical experience, which leads to low accuracy of the evaluated plaque enhancement degree. SUMMARY

[0004] Therefore, it is necessary to provide an image analysis method, device and computer equipment to solve the above technical problems.

[0005] An image analysis method, the method comprising:

[0006] obtaining a to-be-processed blood vessel image;

[0007] performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image;

[0008] obtaining a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image;

[0009] determining a target tissue enhancement degree by using the first enhancement degree and the second enhancement degree.

[0010] In one embodiment, the method comprises:

[0011] determining the first enhancement degree of the target tissue region image according to an intensity feature value of the target tissue region image before enhancement and an intensity feature value of the target tissue region image after enhancement;

[0012] determining the second enhancement degree of the reference region of interest image according to an intensity feature value of the reference region of interest image before enhancement and an intensity feature value of the reference region of interest image after enhancement.

[0013] In one of the embodiments, the target tissue region image comprises a tube wall region image and a plaque region image; the identifying processing of the to-be-processed blood vessel image to determine the target tissue region image comprises:

[0014] the tube wall identification of the to-be-processed blood vessel image to obtain the tube wall region image;

[0015] the plaque identification of the tube wall region image to obtain the plaque region image.

[0016] In one of the embodiments, the identifying processing of the to-be-processed blood vessel image to determine the reference region of interest image comprises:

[0017] the image registration of the to-be-processed blood vessel image and the template image to determine the reference region of interest image.

[0018] In one of the embodiments, the identifying processing of the to-be-processed blood vessel image to determine the reference region of interest image comprises:

[0019] inputting the to-be-processed blood vessel image into a segmentation network model to obtain the reference region of interest image.

[0020] In one of the embodiments, the identifying processing of the to-be-processed blood vessel image to determine the reference region of interest image comprises:

[0021] obtaining a delineation instruction; the delineation instruction comprises position information of the reference region of interest;

[0022] determining the reference region of interest image corresponding to the to-be-processed blood vessel image according to the position information of the reference region of interest.

[0023] In one of the embodiments, the to-be-processed blood vessel image comprises a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement; the method further comprises:

[0024] obtaining a blood vessel image before enhancement and a blood vessel image after enhancement;

[0025] taking any blood vessel image in the blood vessel image before enhancement as a reference, performing image registration on other blood vessel images before enhancement and the blood vessel image after enhancement to obtain the to-be-processed blood vessel image before enhancement and the to-be-processed blood vessel image after enhancement.

[0026] In one of the embodiments, the determination of the intensification degree of the target tissue through the first enhancement intensity and the second enhancement intensity comprises:

[0027] multiplying the first enhancement intensity by the second enhancement intensity to obtain the intensification degree of the target tissue.

[0028] In one of the embodiments, the method further comprises:

[0029] generating a target tissue report by the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image and the enhancement degree of the target tissue.

[0030] An image analysis device, the device comprising:

[0031] a blood vessel image acquisition module configured to acquire a to-be-processed blood vessel image;

[0032] a recognition processing module configured to perform recognition processing on the to-be-processed blood vessel image, to determine a target tissue region image and a reference region of interest image;

[0033] an enhancement degree acquisition module configured to acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image;

[0034] an enhancement degree acquisition module configured to acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image;

[0035] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0036] acquiring a to-be-processed blood vessel image;

[0037] performing recognition processing on the to-be-processed blood vessel image, to determine a target tissue region image and a reference region of interest image;

[0038] acquiring a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image;

[0039] acquiring a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image;

[0040] The image analysis method, device and computer device described above, the computer device can acquire a to-be-processed blood vessel image, perform recognition processing on the to-be-processed blood vessel image, determine a target tissue region image and a reference region of interest image, acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image, and determine an enhancement degree of the target tissue by the first enhancement degree and the second enhancement degree; the method can first identify a target tissue region and a reference region of interest in a blood vessel, and then calculate the enhancement degree of the target tissue by the target tissue region and the reference region of interest, thereby avoiding the process of intervention by medical staff based on experience, so as to improve the accuracy of the determined plaque enhancement degree. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 Flowchart of a method for determining image intensities in an embodiment;

[0042] Figure 2 Flowchart of a method for determining image intensities in an embodiment;

[0043] Figure 3 Flowchart of a method for determining image intensities in an embodiment;

[0044] Figure 4 Flowchart of a method for determining image intensities in an embodiment;

[0045] Figure 5 Flowchart of a method for determining image intensities in an embodiment;

[0046] Figure 6 Layout interface display of different tissue region images before and after enhancement in another embodiment;

[0047] Figure 7 Display interface display of a target tissue report in another embodiment;

[0048] Figure 8 Block diagram of an image analysis device in an embodiment;

[0049] Figure 9 Internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0050] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0051] The image analysis method provided in the application can be applied to a reinforcement degree analysis system. Optionally, the reinforcement degree analysis system comprises a computer device and an image acquisition device, and the computer device and the image acquisition device can be in communication connection, which can be Wi-Fi, mobile network or Bluetooth connection, etc. The image acquisition device can be an electronic computed tomography system, a computed radiography system, a magnetic resonance acquisition device or a direct digital radiography system, etc. The computer device can be various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, but is not limited to these. The embodiment can quantitatively analyze the plaque of intracranial arteries, carotid arteries and aortas, etc. and determine the reinforcement degree of the plaque, so that medical staff can identify the unstable characteristics such as the fibrous cap, hemorrhage, calcification, lipid core and inflammation of the vulnerable plaque according to the reinforcement degree of the plaque, thereby diagnosing cardiovascular diseases. Meanwhile, the embodiment can quantitatively analyze other regions of interest in the blood vessels and determine the reinforcement degree of the tissues in the other regions of interest.

[0052] In one embodiment, as shown in Figure 1 An image analysis method is provided, which is described by taking the computer device as an example and comprises the following steps:

[0053] S100, acquiring a to-be-processed blood vessel image.

[0054] Specifically, the medical imaging device can acquire the to-be-extracted data of the target tissue part of the subject after the subject is perfused with a drug, and send the to-be-extracted data to the computer device. Then, the computer device extracts the blood vessel data corresponding to the blood vessels from the to-be-extracted data, and then reconstructs the blood vessel data to obtain a three-dimensional blood vessel image, and further pre-processes the blood vessel image to obtain a to-be-processed blood vessel image.

[0055] S200, performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image.

[0056] Specifically, the medical imaging device can perform identification processing on different tissue regions in the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image. The to-be-extracted data can include blood vessel data of the blood vessels, and can also include data corresponding to the tissues around the blood vessels. The pre-processing can be rotation, translation, correction, cutting and the like. In the embodiment, the to-be-processed blood vessel image can be an image without segmented plaque, and the to-be-processed blood vessel image can be a two-dimensional blood vessel image.

[0057] It should be noted that the method for extracting the blood vessel data from the to-be-extracted data can be a method for inputting the to-be-extracted data into a blood vessel extraction model to obtain the blood vessel data, and the blood vessel extraction model can be a region convolution network model, a fast region convolution network model, a multi-class single-stick detector, or the like. The blood vessel extraction model can be a pre-trained network model.

[0058] It can be understood that the target tissue site can be any tissue site of the subject, which can be a head, a neck, an arm, a back, or the like. The blood vessel image can be a three-dimensional magnetic resonance blood vessel image. The blood vessels can be divided into arterial blood vessels, venous blood vessels, and capillary blood vessels, and the target tissues corresponding to each type of blood vessel can be a tube wall, a plaque, a smooth muscle, a nerve fiber, or the like in the blood vessel. The method of the identification processing can be an artificial intelligence identification method, or a drawing instruction of a target tissue region contour drawn by an interest region drawing tool of a reinforcement degree analysis system or an additional ITK-SNAP software, and then a method of completing the identification processing.

[0059] S300, obtaining a first enhancement degree of the target tissue region image and a second enhancement degree of the reference interest region image.

[0060] Specifically, the computer device can perform arithmetic operation processing, analysis processing, comparison processing, and / or image sharpening processing, or the like on the target tissue region image and the reference interest region image, and calculate the first enhancement degree of the target tissue region image and the second enhancement degree of the reference interest region image. The enhancement degree can also be understood as a contrast.

[0061] The target tissue region and the reference interest region can be two separate tissue regions in the blood vessel, or adjacent tissue regions in the blood vessel, which are not limited in this embodiment.

[0062] S400, determining the reinforcement degree of the target tissue by the first enhancement degree and the second enhancement degree.

[0063] Specifically, the computer device can perform arithmetic operation processing, analysis processing, comparison processing, and / or image sharpening processing, or the like on the target tissue region image and the reference interest region image, and calculate the first enhancement degree of the target tissue region image and the second enhancement degree of the reference interest region image. The enhancement degree can also be understood as a contrast.

[0064] The step of determining the reinforcement degree of the target tissue by the first enhancement degree and the second enhancement degree in S400 can include: taking the quotient of the first enhancement degree and the second enhancement degree to obtain the reinforcement degree of the target tissue.

[0065] In this embodiment, the reinforcement degree of the target tissue can be represented by a reinforcement degree quantization value.

[0066] In the image analysis method, the computer device can acquire a to-be-processed blood vessel image, perform recognition processing on the to-be-processed blood vessel image, determine a target tissue region image and a reference region of interest image, acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image, and determine the enhancement degree of the target tissue by using the first enhancement degree and the second enhancement degree. The method can first recognize the target tissue region and the reference region of interest in the blood vessel, and then calculate the enhancement degree of the target tissue by using the target tissue region and the reference region of interest. The method avoids the process of intervention by the medical staff based on experience, thereby improving the accuracy of the determined plaque enhancement degree and shortening the determination time of the plaque enhancement degree. Meanwhile, the method does not need the process of intervention by the medical staff based on experience, thereby reducing the requirement for the experience of the medical staff and further reducing the cost of human resources. In addition, the method can quantitatively analyze the target tissue by using a computer program, which is beneficial to improving the accuracy and efficiency of the target tissue enhancement degree and has very important clinical application significance.

[0067] As one of the embodiments, as shown in Figure 2 The step of acquiring the first enhancement degree of the target tissue region image and the second enhancement degree of the reference region of interest image in S300 can be implemented by the following steps:

[0068] S310, determining the first enhancement degree of the target tissue region image according to the intensity feature value of the target tissue region image before enhancement and the intensity feature value of the target tissue region image after enhancement.

[0069] Specifically, the target tissue region image can include a target tissue region image before enhancement and a target tissue region image after enhancement. The target tissue region image before enhancement can be understood as a target tissue region image corresponding to the target tissue part of the subject before the drug is perfused, and the target tissue region image after enhancement can be understood as a target tissue region image corresponding to the target tissue part of the subject after the drug is perfused. In this embodiment, the purpose of perfusing the drug to the target tissue part is to make the target tissue part have obvious distinguishing features before and after the drug is perfused, so as to facilitate the subsequent identification of the target tissue of the target tissue part.

[0070] It should be noted that the intensity feature value of the target tissue region image can be understood as the feature value of all pixels of the target tissue region image. The intensity feature value of the target tissue region image can be the maximum pixel value in all pixels of the target tissue region image, the minimum pixel value in all pixels of the target tissue region image, the average pixel value of all pixels of the target tissue region image, the variance of all pixels of the target tissue region image, and / or the standard deviation of all pixels of the target tissue region image, and the like.

[0071] Further, the computer device can perform arithmetic operation processing and / or comparison processing, etc. on the intensity feature value of the target tissue region image before enhancement and the intensity feature value of the target tissue region image after enhancement to obtain the first enhancement degree of the target tissue region image.

[0072] S320, determining the second enhancement degree of the reference region of interest image according to the intensity feature value of the reference region of interest image before enhancement and the intensity feature value of the reference region of interest image after enhancement.

[0073] It can be understood that, similar to the method of determining the first enhancement degree of the target tissue region image, the computer device can perform arithmetic operation processing and / or comparison processing, etc. on the intensity feature value of the reference region of interest image before enhancement and the intensity feature value of the reference region of interest image after enhancement to obtain the second enhancement degree of the reference region of interest image.

[0074] The intensity feature value of the reference region of interest image can be understood as the feature value of all pixels of the reference region of interest image, which can be the maximum pixel value in all pixels of the target tissue region image, the minimum pixel value in all pixels, the average pixel value of all pixels, the variance of all pixels, and / or the standard deviation of all pixels, etc.

[0075] In the embodiment, the intensity feature value can be the mean value of the image. Specifically, the computer device can divide the mean value of the target tissue region image after enhancement by the mean value of the target tissue region image before enhancement to obtain the first enhancement degree of the target tissue region image; and divide the mean value of the reference region of interest image after enhancement by the mean value of the reference region of interest image before enhancement to obtain the second enhancement degree of the reference region of interest image.

[0076] The image analysis method can first determine the first enhancement degree of the target tissue region image and the second enhancement degree of the reference region of interest image, and then further calculate the reinforcement degree of the target tissue through the first enhancement degree and the second enhancement degree, so as to improve the accuracy of the determined plaque reinforcement degree, and the processing method can shorten the determination time of the plaque reinforcement degree.

[0077] As one of the embodiments, the target tissue region image includes a pipe wall region image and a plaque region image; as shown in the following figure, Figure 3 The step of identifying the to-be-processed blood vessel image in S200 to determine the target tissue region image can be implemented by the following steps:

[0078] S210, identifying the to-be-processed blood vessel image to obtain a pipe wall region image.

[0079] Specifically, the computer device can identify the tube wall region of the blood vessel in the to-be-processed blood vessel image to obtain a tube wall region image. The tube wall region identification method can be an artificial intelligence identification method, or a drawing instruction of a tube wall region contour drawn by an interested region drawing tool of the reinforcement degree analysis system or additional ITK-SNAP software, and then a method of completing tube wall region identification processing. The artificial intelligence identification method can be a method of inputting the to-be-processed blood vessel image into a tube wall identification network model to obtain the tube wall region image. The tube wall identification network model can be a region convolution network model, a fast region convolution network model, a multi-classification single rod detector, or the like. The tube wall identification network model can be a pre-trained network model.

[0080] In S220, a plaque region image is obtained by identifying the plaque region on the tube wall in the tube wall region image.

[0081] Further, the computer device can identify the plaque region on the tube wall in the obtained tube wall region image to obtain a plaque region image. The plaque region identification method can be an artificial intelligence identification method, or a drawing instruction of a plaque region contour drawn by an interested region drawing tool of the reinforcement degree analysis system or additional ITK-SNAP software, and then a method of completing plaque region identification processing. The artificial intelligence identification method can be a method of inputting the tube wall region image into a plaque identification network model to obtain the plaque region image. The plaque identification network model can be a region convolution network model, a fast region convolution network model, a multi-classification single rod detector, or the like. The plaque identification network model can be a pre-trained network model.

[0082] Meanwhile, the computer device can also identify other interested regions on the tube wall in the tube wall region image to obtain other interested region images. The other interested regions can be other regions in the blood vessel region except the tube wall region and the plaque region. The other interested region identification method can also be an artificial intelligence identification method, or a drawing instruction of an other interested region contour drawn by an interested region drawing tool of the reinforcement degree analysis system or additional ITK-SNAP software, and then a method of completing other interested region identification processing. In this embodiment, the other interested regions in the tube wall can be different from the reference interested regions.

[0083] The above image analysis method can obtain the tube wall region image, the plaque region image, and the reference interested region image, and then quickly calculate the reinforcement degree of the target tissue based on the tube wall region image and the plaque region image. Moreover, the method avoids the process of intervention by medical personnel based on experience, thereby improving the accuracy of determining the plaque reinforcement degree and shortening the determination time of the plaque reinforcement degree.

[0084] As one of the embodiments, the step of determining the reference region of interest image by recognizing the to-be-processed blood vessel image in S200 can be implemented by the following steps: determining the reference region of interest image by image registration between the to-be-processed blood vessel image and the template image.

[0085] Specifically, the template image can be an image corresponding to a reference region of interest tissue predefined in advance, or an image corresponding to a preset tissue with a more prominent feature before and after perfusion of a drug. The size of the template image can be the same as that of the to-be-processed blood vessel image. The template image can include the reference region of interest tissue image or the preset tissue image and a background image, or only the reference region of interest tissue image or the preset tissue image. The preset tissue with a more prominent feature before and after perfusion of a drug can be smooth muscle, sarcoplasm, nerve fiber, or the like. The background image is an invalid image filled after the reference region of interest tissue image or the preset tissue image, and is only used to fill the reference region of interest tissue image or the preset tissue image into an image with the same size as the to-be-processed blood vessel image.

[0086] It can be understood that the computer device can perform image registration between the template image and the to-be-processed blood vessel image to obtain the reference region of interest image in the to-be-processed blood vessel image.

[0087] In this embodiment, since the pituitary stalk tissue exhibits a more prominent feature before and after perfusion of a drug, the preset tissue with a more prominent feature before and after perfusion of a drug can be the pituitary stalk. Generally, the pituitary stalk exists on the wall of the blood vessel, and the tissue structure of the wall is similar to that of the pituitary stalk. First, a pituitary stalk region image can be segmented from the to-be-processed blood vessel image, and then the pituitary stalk region image is used as a template image to perform image registration to obtain the reference region of interest image in the to-be-processed blood vessel image. Alternatively, a standardized pituitary stalk region image can be directly used as a template image to perform image registration to obtain the reference region of interest image in the to-be-processed blood vessel image. The image registration in this step can be understood as a process of mapping the pituitary stalk region in the pituitary stalk region image to the to-be-processed blood vessel image.

[0088] Alternatively, the step of determining the reference region of interest image by recognizing the to-be-processed blood vessel image in S200 can also be implemented by the following steps: inputting the to-be-processed blood vessel image into a segmentation network model to obtain the reference region of interest image.

[0089] It should be noted that the aforementioned segmentation network model can be a fully convolutional network model, a fast convolutional network model, an accelerated region convolutional network model, a masked region convolutional network model, etc., or a combination of these network models. The computer device can train the initial segmentation network model using a vascular image training set to obtain a pre-trained segmentation network model. Specifically, the computer device can input vascular images from the vascular image training set into the initial segmentation network model to obtain a predicted region of interest (ROI) image. A loss function is used to calculate the prediction error between the predicted ROI image and the standard ROI image, and the initial network parameters in the initial segmentation network model are updated based on the prediction error value. This training process is iterated until the prediction error value meets a preset error threshold or the number of iterations reaches a preset threshold, resulting in a pre-trained segmentation network model. The aforementioned vascular image training set can be a collection of vascular images from different subjects, and the aforementioned standard ROI image can be an idealized ROI image.

[0090] The vascular images in the aforementioned vascular image training set can include plaque images and non-plaque images. Optionally, the aforementioned loss function can be a mean squared error function, a binary classification cross-entropy function, a sparse binary classification cross-entropy loss function, etc., and there is no limitation on this.

[0091] At the same time, such as Figure 4 As shown, the step of identifying and processing the blood vessel image to be processed and determining the reference region of interest image in S200 above can also be achieved through the following steps:

[0092] S230, Obtain the drawing instruction; the drawing instruction includes the location information of the reference area of ​​interest.

[0093] Understandably, medical staff can trigger the enhancement analysis control via mouse, keyboard, or voice input. The computer device can then automatically open the region of interest (ROI) delineation tool or ITK-SNAP software. Based on the parameter settings interface of the ROI delineation tool or ITK-SNAP software, the delineation parameters can be set, and the device will automatically delineate the contours of other ROI regions in the vascular image to be processed. At this point, the computer device can receive the delineation instructions. The delineation parameters can be the location information of the reference ROI.

[0094] S240. Based on the location information of the reference region of interest, determine the reference region of interest image corresponding to the blood vessel image to be processed.

[0095] Specifically, the computer device can extract the reference region of interest image from the to-be-processed blood vessel image according to the acquired position information of the reference region of interest, and filter out images of other regions. In addition, the reference region of interest can be determined according to actual clinical needs, and in addition to the pituitary stalk region, it can also be a muscle region, a muscle fiber region, a cerebrospinal fluid region, and the like.

[0096] In this embodiment, the reference region of interest image can be determined by any one of the above three methods, thereby improving the flexibility of determining the reference region of interest image.

[0097] The above image analysis method can obtain the reference region of interest image, and then quickly calculate the enhancement degree of the target tissue based on the target tissue region image and the reference region of interest image. In addition, the method avoids the process of intervention by medical staff according to experience, thereby improving the accuracy of determining the plaque enhancement degree and shortening the determination time of the plaque enhancement degree. At the same time, the method can determine the reference region of interest image by multiple methods, thereby improving the flexibility of determining the reference region of interest image.

[0098] As one of the embodiments, the to-be-processed blood vessel image includes a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement; before performing S200, the method can further include: Figure 5 As shown in the above S200, the method can further include:

[0099] S500, acquiring a blood vessel image before enhancement and a blood vessel image after enhancement.

[0100] Specifically, the medical imaging device can collect first to-be-extracted data of a target tissue part of a subject before being perfused with a drug, and send the first to-be-extracted data to the computer device. Then the computer device extracts first blood vessel data corresponding to the blood vessels from the first to-be-extracted data, and then reconstructs the first blood vessel data to obtain a first blood vessel image. At the same time, the first blood vessel image needs to be processed to obtain a two-dimensional blood vessel image before enhancement. At the same time, the medical imaging device can collect second to-be-extracted data of a target tissue part of a subject after being perfused with a drug, and send the second to-be-extracted data to the computer device. Then the computer device extracts second blood vessel data corresponding to the blood vessels from the second to-be-extracted data, and then reconstructs the second blood vessel data to obtain a second blood vessel image. At the same time, the second blood vessel image needs to be processed to obtain a two-dimensional blood vessel image after enhancement.

[0101] The computer device can perform skeletonization processing on the first blood vessel image to obtain a first blood vessel center line, and then cut the three-dimensional first blood vessel image according to the first blood vessel center line to obtain a two-dimensional image corresponding to a cross section of the blood vessel, that is, a two-dimensional pre-enhancement blood vessel image. Meanwhile, the computer device can perform skeletonization processing on the second blood vessel image to obtain a second blood vessel center line, and then cut the three-dimensional second blood vessel image according to the second blood vessel center line to obtain a two-dimensional image corresponding to a cross section of the blood vessel, that is, a two-dimensional post-enhancement blood vessel image.

[0102] It should be noted that the pre-enhancement blood vessel image can include a pre-enhancement black blood vessel image and / or a pre-enhancement bright blood vessel image, and the post-enhancement blood vessel image can include a post-enhancement black blood vessel image and / or a post-enhancement bright blood vessel image, wherein the pre-enhancement blood vessel image corresponds to the post-enhancement blood vessel image, but in this embodiment, the pre-enhancement blood vessel image includes a pre-enhancement black blood vessel image, and therefore the post-enhancement blood vessel image includes a post-enhancement black blood vessel image.

[0103] S600, taking any blood vessel image in the pre-enhancement blood vessel image as a reference, performing image registration on the other pre-enhancement blood vessel images and the post-enhancement blood vessel images to obtain a pre-enhancement blood vessel image to be processed and a post-enhancement blood vessel image to be processed.

[0104] Specifically, each time the blood vessel data of the target tissue part is collected, the subject may have a motion displacement, and the body position of the subject is slightly different each time the blood vessel data is collected, which will cause the blood vessel data collected each time to be different. Therefore, the pre-enhancement blood vessel images and the post-enhancement blood vessel images collected need to be motion corrected to correct motion artifacts to obtain corresponding blood vessel images under the same body position.

[0105] The motion correction process can be understood as selecting any one of the pre-enhancement blood vessel images as a reference image, and then the computer device can perform image registration on the other pre-enhancement blood vessel images and the post-enhancement blood vessel images through the reference image to obtain a pre-enhancement blood vessel image to be processed and a post-enhancement blood vessel image to be processed.

[0106] Meanwhile, the pre-enhancement blood vessel image to be processed and the post-enhancement blood vessel image to be processed can be displayed simultaneously on the display interface of the computer device for medical staff to conveniently view, and the local display mode of these images on the display interface can be arbitrary and is not limited. In addition, the pre-enhancement blood vessel image to be processed and the post-enhancement blood vessel image to be processed can be displayed in turn on the display interface of the computer device through mouse sliding, that is, only one pre-enhancement blood vessel image to be processed or one post-enhancement blood vessel image to be processed can be displayed on the display interface each time, and then other blood vessel images to be processed can be viewed through mouse sliding.

[0107] Exemplary, Figure 6 Fig. 1 is a layout interface display diagram of different tissue region images before and after enhancement. Figure 6 The first column and the third column in the table represent the identification of the to-be-processed blood vessel images before and after enhancement, the second column and the third column respectively display five to-be-processed blood vessel images before enhancement and five to-be-processed blood vessel images after enhancement corresponding to the cross sections 1-5, and the fourth column displays intermediate calculation parameters involved in the process of calculating the enhancement degree of the target tissue. The specific parameters are shown in Table 1. In Table 1, the mean value of the reference region of interest image before enhancement is represented as R0, the mean value of the reference region of interest image after enhancement is represented as R1, the mean value of the wall region image before enhancement is represented as W0, the mean value of the wall region image after enhancement is represented as W1, the mean value of the plaque region image before enhancement is represented as P0, the mean value of the plaque region image after enhancement is represented as P1, the mean value of the other region of interest image before enhancement is represented as R, and the mean value of the other region of interest image after enhancement is represented as R1. The enhancement and the enhancement degree calculated further through these mean values are shown in Table 1. ef ef1 The mean value of the reference region of interest image after enhancement is represented as R1, the mean value of the wall region image after enhancement is represented as W1, the mean value of the plaque region image after enhancement is represented as P1, and the mean value of the other region of interest image after enhancement is represented as R1. The enhancement and the enhancement degree calculated further through these mean values are shown in Table 1.

[0108] Table 1

[0109]

[0110] Further, the embodiment can further determine whether the enhancement degree of the target tissue belongs to obvious enhancement, mild enhancement or no enhancement according to the enhancement degree of the target tissue. Specifically, the computer device can determine that the enhancement degree of the target tissue belongs to obvious enhancement when the enhancement degree of the target tissue is greater than or equal to the enhancement degree of the reference region of interest tissue, determine that the enhancement degree of the target tissue belongs to mild enhancement when the enhancement degree of the target tissue is less than the enhancement degree of the reference region of interest tissue, and determine that the enhancement degree of the target tissue is no enhancement when the enhancement degree of the target tissue is approximately equal to the enhancement degree of the target tissue before enhancement.

[0111] The image analysis method can obtain the blood vessel images before and after enhancement of the subject in the same body position through image registration, and further determine the enhancement degree of the target tissue through the blood vessel images before and after enhancement, so as to avoid the inaccuracy of the enhancement degree of the target tissue due to the influence of motion artifacts, and improve the accuracy of the determined enhancement degree of the target tissue. At the same time, the method avoids the process of intervention by medical staff according to experience, so as to greatly improve the accuracy of the determined plaque enhancement degree and shorten the determination time of the plaque enhancement degree.

[0112] ​As one of the embodiments, after the step S400, the image analysis method can further include: generating a target tissue report by the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the enhancement degree of the target tissue.

[0113] Specifically, the computer device can display the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the enhancement degree of the target tissue on the same interface at the same time to generate a structured target tissue report. The to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the enhancement degree of the target tissue can be arranged in any layout in the target tissue report as long as they are not overlapped. The target tissue report can be an electronic report, and can also be a paper report exported from the electronic report.

[0114] Meanwhile, the computer device can calculate the intensity feature values corresponding to the to-be-processed blood vessel image, the target tissue region image, and the reference region of interest image respectively, and then display the intensity feature values in the target tissue report at the same time. The target tissue report can also display other related parameters of the target tissue. Figure 7 As the wall is in the lumen, the target tissue report also has related parameters of the lumen.

[0115] The image analysis method can generate a target tissue report by the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the enhancement degree of the target tissue, so that medical staff can intuitively obtain the enhancement degree of the target tissue from the target tissue report, and can comprehensively analyze the health impact of the plaque on the subject by combining the to-be-processed blood vessel image, the target tissue region image, and the reference region of interest image in the target tissue report. Meanwhile, when the medical staff lacks clinical experience, the target tissue report can also be taken to other departments to consult multiple medical experts to diagnose the health status of the subject, thereby improving the accuracy of cardiovascular disease diagnosis.

[0116] In order to facilitate the understanding of those skilled in the art, the image analysis method provided by the present application is introduced by taking the computer device as an execution subject. Specifically, the method includes:

[0117] (1) obtaining a blood vessel image before enhancement and a blood vessel image after enhancement.

[0118] (2) taking any blood vessel image in the blood vessel image before enhancement as a reference, performing image registration on the other blood vessel images before enhancement and the blood vessel images after enhancement to obtain a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement.

[0119] (3) performing tube wall recognition on the to-be-processed blood vessel image to obtain a tube wall region image.

[0120] (4) performing plaque recognition on the tube wall region image to obtain a plaque region image.

[0121] (5) performing image registration on the to-be-processed blood vessel image and the template image to determine a reference region of interest image; or inputting the to-be-processed blood vessel image into a segmentation network model to obtain the reference region of interest image; or obtaining a delineation instruction, the delineation instruction including position information of the reference region of interest, and determining a reference region of interest image corresponding to the to-be-processed blood vessel image according to the position information of the reference region of interest.

[0122] (6) determining a first enhancement degree of the target tissue region image according to an intensity feature value of the target tissue region image before enhancement and an intensity feature value of the target tissue region image after enhancement, the target tissue region image including the tube wall region image and the plaque region image.

[0123] (7) determining a second enhancement degree of the reference region of interest image according to an intensity feature value of the reference region of interest image before enhancement and an intensity feature value of the reference region of interest image after enhancement.

[0124] (8) obtaining a reinforcement degree of the target tissue by taking the first enhancement degree and the second enhancement degree as quotient.

[0125] (9) generating a target tissue report by the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the reinforcement degree of the target tissue.

[0126] The execution processes of (1) to (9) above can refer to the descriptions of the above embodiments for details, and have similar implementation principles and technical effects, which will not be described here again.

[0127] It should be understood that, although Figures 1-5 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in sequence according to the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, Figures 1-5 at least part of the steps in the flowchart can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or steps or stages in other steps.

[0128] In one embodiment, as Figure 8As shown, an image analysis device is provided, comprising a blood vessel image acquisition module 11, an identification processing module 12, an enhancement intensity acquisition module 13 and an intensification degree acquisition module 14, wherein:

[0129] The blood vessel image acquisition module 11 is configured to acquire a blood vessel image to be processed.

[0130] The identification processing module 12 is configured to perform identification processing on the blood vessel image to be processed to determine a target tissue region image and a reference region of interest image.

[0131] The enhancement intensity acquisition module 13 is configured to acquire a first enhancement intensity of the target tissue region image and a second enhancement intensity of the reference region of interest image.

[0132] The intensification degree acquisition module 14 is configured to determine the intensification degree of the target tissue by the first enhancement intensity and the second enhancement intensity.

[0133] The image analysis device provided in the embodiment can execute the method embodiments described above, and has similar implementation principles and technical effects, which will not be described here again.

[0134] In one of the embodiments, the enhancement intensity acquisition module 13 comprises a first enhancement intensity determination unit and a second enhancement intensity determination unit, wherein:

[0135] The first enhancement intensity determination unit is configured to determine the first enhancement intensity of the target tissue region image according to the intensity feature value of the target tissue region image before enhancement and the intensity feature value of the target tissue region image after enhancement.

[0136] The second enhancement intensity determination unit is configured to determine the second enhancement intensity of the reference region of interest image according to the intensity feature value of the reference region of interest image before enhancement and the intensity feature value of the reference region of interest image after enhancement.

[0137] The image analysis device provided in the embodiment can execute the method embodiments described above, and has similar implementation principles and technical effects, which will not be described here again.

[0138] In one of the embodiments, the target tissue region image comprises a pipe wall region image and a plaque region image; the identification processing module 12 comprises a pipe wall identification unit and a plaque identification unit, wherein:

[0139] The pipe wall identification unit is configured to perform pipe wall identification on the blood vessel image to be processed to acquire the pipe wall region image.

[0140] The plaque identification unit is configured to perform plaque identification on the pipe wall region image to acquire the plaque region image.

[0141] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0142] In one of the embodiments, the identification processing module 12 comprises an image registration unit, wherein:

[0143] The image registration unit is configured to perform image registration on the to-be-processed blood vessel image and the template image, and determine the reference region of interest image.

[0144] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0145] In one of the embodiments, the identification processing module 12 further comprises a first region of interest determination unit, wherein:

[0146] The first region of interest determination unit is configured to input the to-be-processed blood vessel image into the segmentation network model to obtain the reference region of interest image.

[0147] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0148] In one of the embodiments, the identification processing module 12 further comprises a delineation instruction acquisition unit and a second region of interest determination unit, wherein:

[0149] The delineation instruction acquisition unit is configured to acquire a delineation instruction, and the delineation instruction comprises position information of the reference region of interest.

[0150] The second region of interest determination unit is configured to determine the reference region of interest image corresponding to the to-be-processed blood vessel image according to the position information of the reference region of interest.

[0151] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0152] In one of the embodiments, the to-be-processed blood vessel image comprises a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement; and the image analysis apparatus further comprises a blood vessel image acquisition module and an image registration module, wherein:

[0153] The blood vessel image acquisition module is configured to acquire the blood vessel image before enhancement and the blood vessel image after enhancement.

[0154] The image registration module is configured to take any blood vessel image in the blood vessel image before enhancement as a reference, perform image registration on the other blood vessel images before enhancement and the blood vessel image after enhancement, and obtain the to-be-processed blood vessel image before enhancement and the to-be-processed blood vessel image after enhancement.

[0155] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0156] In one of the embodiments, the enhancement degree acquisition module 14 is specifically configured to multiply the first enhancement degree and the second enhancement degree to obtain the enhancement degree of the target tissue.

[0157] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0158] In one of the embodiments, the image analysis apparatus further includes a report generation module, wherein:

[0159] The report generation module is configured to generate a target tissue report by using the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image and the enhancement degree of the target tissue.

[0160] The image analysis apparatus provided in the embodiment can execute the method embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0161] The specific limitations of the image analysis apparatus can refer to the limitations of the image analysis method described above, which will not be described here again. Each module in the image analysis apparatus described above can be realized by software, hardware and a combination thereof in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in the form of software, so as to call and execute the operations corresponding to each module by the processor.

[0162] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 9 The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store a to-be-processed blood vessel image. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an image analysis method.

[0163] Those skilled in the art can understand that, Figure 9The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0164] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0165] obtaining a to-be-processed blood vessel image;

[0166] performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image;

[0167] obtaining a first enhancement intensity of the target tissue region image and a second enhancement intensity of the reference region of interest image;

[0168] determining a strengthening degree of the target tissue by the first enhancement intensity and the second enhancement intensity.

[0169] In one embodiment, a readable storage medium is provided, storing a computer program, and the computer program implements the following steps when executed by a processor:

[0170] obtaining a to-be-processed blood vessel image;

[0171] performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image;

[0172] obtaining a first enhancement intensity of the target tissue region image and a second enhancement intensity of the reference region of interest image;

[0173] determining a strengthening degree of the target tissue by the first enhancement intensity and the second enhancement intensity.

[0174] In one embodiment, a computer program product is provided, comprising a computer program, and the computer program implements the following steps when executed by a processor:

[0175] obtaining a to-be-processed blood vessel image;

[0176] performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image;

[0177] obtaining a first enhancement intensity of the target tissue region image and a second enhancement intensity of the reference region of interest image;

[0178] determining a strengthening degree of the target tissue by the first enhancement intensity and the second enhancement intensity.

[0179] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0180] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of each technical feature in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0181] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An image analysis method characterized by, The method comprises: acquiring a to-be-processed blood vessel image; the to-be-processed blood vessel image comprises a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement; performing identification processing on the to-be-processed blood vessel image to determine a target tissue region image and a reference region of interest image; acquiring a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image; determining a reinforcement degree of the target tissue by using the first enhancement degree and the second enhancement degree; the reinforcement degree is used to represent a lesion degree of the target tissue; performing identification processing on the to-be-processed blood vessel image to determine the reference region of interest image, comprising: performing image registration by using the to-be-processed blood vessel image and a template image to determine the reference region of interest image; the template image is a pituitary stalk region image or a standardized pituitary stalk region image, and the pituitary stalk region image is an image segmented from the to-be-processed blood vessel image.

2. The method of claim 1, wherein, The acquiring of the first enhancement degree of the target tissue region image and the second enhancement degree of the reference region of interest image comprises: determining the first enhancement degree of the target tissue region image according to an intensity feature value of the target tissue region image before enhancement and an intensity feature value of the target tissue region image after enhancement; determining the second enhancement degree of the reference region of interest image according to an intensity feature value of the reference region of interest image before enhancement and an intensity feature value of the reference region of interest image after enhancement.

3. The method according to claim 1 or 2, characterized in that, The target tissue region image comprises a pipe wall region image and a plaque region image; the performing of the identification processing on the to-be-processed blood vessel image to determine the target tissue region image comprises: performing pipe wall identification on the to-be-processed blood vessel image to acquire the pipe wall region image; performing plaque identification on the pipe wall region image to acquire the plaque region image.

4. The method according to claim 1 or 2, characterized in that, The performing of the identification processing on the to-be-processed blood vessel image to determine the reference region of interest image comprises: performing image registration by using the to-be-processed blood vessel image and a template image to determine the reference region of interest image; and preferably, the performing of the identification processing on the to-be-processed blood vessel image to determine the reference region of interest image comprises: inputting the to-be-processed blood vessel image into a segmentation network model to obtain the reference region of interest image.

5. The method according to claim 1 or 2, characterized in that, The performing of the identification processing on the to-be-processed blood vessel image to determine the reference region of interest image comprises: acquiring a delineation instruction; the delineation instruction comprises position information of the reference region of interest; determining a reference region of interest image corresponding to the to-be-processed blood vessel image according to the position information of the reference region of interest.

6. The method of claim 1 or 2, wherein, The method further comprises: performing image registration on other blood vessel images before enhancement and blood vessel images after enhancement with any blood vessel image in the blood vessel images before enhancement as a reference to obtain the to-be-processed blood vessel image before enhancement and the to-be-processed blood vessel image after enhancement.

7. The method according to claim 1 or 2, characterized in that, The determining of the reinforcement degree of the target tissue by using the first enhancement degree and the second enhancement degree comprises: performing multiplication on the first enhancement degree and the second enhancement degree to obtain the reinforcement degree of the target tissue.

8. The method of claim 1, wherein, The method further comprises: A target tissue report is generated by the to-be-processed blood vessel image, the target tissue region image, the reference region of interest image, and the enhancement degree of the target tissue.

9. An image analysis apparatus characterized by comprising: The device comprises: a blood vessel image acquisition module, configured to acquire a to-be-processed blood vessel image; the to-be-processed blood vessel image comprises a to-be-processed blood vessel image before enhancement and a to-be-processed blood vessel image after enhancement; a recognition processing module, configured to perform recognition processing on the to-be-processed blood vessel image, and determine a target tissue region image and a reference region of interest image; an enhancement degree acquisition module, configured to acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image; an enhancement degree acquisition module, configured to acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image; an enhancement degree acquisition module, configured to acquire a first enhancement degree of the target tissue region image and a second enhancement degree of the reference region of interest image; the enhancement degree is used to represent the lesion degree of the target tissue; 10.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-9. performing recognition processing on the to-be-processed blood vessel image, and determining the reference region of interest image, comprises: performing image registration on the to-be-processed blood vessel image and a template image to determine the reference region of interest image; the template image is a pituitary stalk region image or a standardized pituitary stalk region image, and the pituitary stalk region image is an image segmented from the to-be-processed blood vessel image. The processor executes the computer program to realize the steps of the method in any one of claims 1-8.

Images