Microvascular detection method and electronic equipment

Abstract

The invention discloses a capillary detection method and electronic equipment, and the method comprises the steps: obtaining a to-be-detected first super-resolution image which comprises a capillary; determining a first detection area in the first super-resolution image; determining an information entropy corresponding to the first detection area according to the target blood vessel parameter corresponding to the first detection area; and generating a capillary detection result of the first super-resolution image according to the information entropy. According to the microvessel detection method, the information entropy calculation is performed on the target blood vessel parameters of the detection area in the super-resolution image, and the microvessel detection result is generated according to the calculated information entropy, so that the information entropy calculation can be performed based on the blood vessel parameters in the super-resolution image with higher resolution; richer and more real blood vessel structures and hemodynamic information in the microvessels can be extracted, so that the accuracy of detecting the complexity of the microvessels can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical detection, and in particular, to a microvessel detection method and an electronic device. BACKGROUND

[0002] The complexity of microvessels has important value for early diagnosis and treatment of various diseases. At present, the complexity of microvessels is usually detected and determined based on conventional ultrasound contrast technology and blood flow Doppler imaging technology. However, due to the limitation of the diffraction limit, the conventional ultrasound imaging technology has limited ability to display microvessels, resulting in low accuracy of detecting the complexity of microvessels. SUMMARY

[0003] The present application provides a microvessel detection method and an electronic device, which solves the problem of low accuracy of detecting the complexity of microvessels in the related art.

[0004] In a first aspect, the present application provides a microvessel detection method, which includes: obtaining a first super-resolution image to be detected, the first super-resolution image including microvessels; determining a first detection region in the first super-resolution image; determining information entropy corresponding to the first detection region according to a target blood vessel parameter of the first detection region; and generating a microvessel detection result of the first super-resolution image according to the information entropy.

[0005] In a second aspect, the present application further provides a microvessel detection method, which includes:

[0006] obtaining a super-resolution image to be detected, the super-resolution image including microvessels; determining information entropy corresponding to the super-resolution image according to a blood vessel parameter of the super-resolution image; and generating a microvessel detection result of the super-resolution image according to the information entropy.

[0007] In a third aspect, the present application further provides a microvessel detection method, which includes:

[0008] displaying a first super-resolution image to be detected in a microvessel detection interface, the first super-resolution image including microvessels; determining a target region in the first super-resolution image in response to a region determination instruction; determining information entropy corresponding to the target region according to a target blood vessel parameter of the target region; generating a first microvessel detection result of the first super-resolution image according to the information entropy; and outputting the first microvessel detection result in the microvessel detection interface.

[0009] Fourthly, this application also provides an electronic device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the above-described microvascular detection method when executing the computer program.

[0010] This application provides a method and electronic device for detecting microvessels. By calculating the information entropy of the target blood vessel parameters in the detection area of ​​a super-resolution image, and generating microvessel detection results based on the calculated information entropy, since super-resolution images have super-resolution characteristics and information entropy is used to describe the amount of information carried by an image, calculating information entropy based on blood vessel parameters in a higher-resolution super-resolution image can extract richer and more realistic vascular structure and hemodynamic information in microvessels, thereby improving the accuracy of detecting the complexity of microvessels. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0013] Figure 2 This is a schematic flowchart of a microvascular detection method provided in an embodiment of this application;

[0014] Figure 3 This is a schematic diagram of a super-resolution image processing procedure provided in an embodiment of this application;

[0015] Figure 4 This is a blood flow direction diagram of a microvessel provided in an embodiment of this application;

[0016] Figure 5 This is a microvascular blood flow velocity diagram provided in an embodiment of this application;

[0017] Figure 6 This is a blood flow density map of a microvessel provided in an embodiment of this application;

[0018] Figure 7 This is a schematic flowchart of another microvascular detection method provided in the embodiments of this application;

[0019] Figure 8 This is a schematic flowchart of another microvascular detection method provided in the embodiments of this application;

[0020] Figure 9 is a schematic flowchart of a sub-step of determining information entropy provided by an embodiment of the present application;

[0021] Figure 10 is a schematic diagram of a super-resolution image provided by an embodiment of the present application;

[0022] Figure 11 is a schematic diagram of another super-resolution image provided by an embodiment of the present application;

[0023] Figure 12 is a schematic flowchart of another microvessel detection method provided by an embodiment of the present application;

[0024] Figure 13 is a schematic diagram of a microvessel detection interface provided by an embodiment of the present application;

[0025] Figure 14 is a schematic diagram of image mode switching provided by an embodiment of the present application;

[0026] Figure 15 is a schematic diagram of determining sub-entropy values of a plurality of regions of interest provided by an embodiment of the present application;

[0027] Figure 16 is a schematic diagram of determining sub-entropy values corresponding to a plurality of blood vessel parameters provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0029] The flowcharts shown in the drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order can be changed according to the actual situation.

[0030] It should be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0031] It should also be understood that the term "and / or" as used herein in the specification and in the claims, unless otherwise specified, means any combination of one or more of the associated listed items. It should also be understood that, in the specification and the appended claims, the terms "comprise", "comprising", "comprises" and "comprising" or "include", "including", "includes" and "including" are used in their open-ended, non-limiting sense, and thus should be interpreted as specifying the presence of stated features or components but not precluding the presence of additional features or components.

[0032] It should be noted that the blockage, obstruction and lesion of microcirculation are precursors of many diseases, and observing the complexity of microvessels is beneficial to early diagnosis of diseases. Microvessels are mainly composed of capillaries, microarteries and microveins, among which capillaries are in the epidermis layer and are an important part of blood microcirculation, with the smallest diameter of about 6-9 μm; microarteries and microveins are in the dermis layer and are connected to the arteries and veins in the lower epidermis layer, with a diameter of about 10-100 μm. Microcirculation refers to the blood circulation between microarteries and microveins in the vascular network, which is both the terminal part of the circulatory system and an important component of organs. Under normal circumstances, the blood flow of microcirculation is adapted to the metabolic level of human tissues and organs, and maintains normal life activities and metabolism of the human body. When the metabolism and function of tissues and organs are abnormal, the microcirculation will change to a certain extent, so the microcirculation is closely related to the occurrence and development of diseases, and has important physiological, pathological, pharmacological and clinical significance, and has important value for early diagnosis and treatment of various diseases.

[0033] At present, the related technology usually observes the blood vessel shape perfusion structure and the degree of disorder of blood flow direction to determine the complexity of blood vessels, or uses the bending degree of blood vessels to measure the structural complexity of blood vessels based on conventional ultrasound contrast technology and blood flow Doppler imaging technology. Due to the limitation of the diffraction limit of the conventional ultrasound imaging technology, the ability to display the details of the blood vessel structure is limited, resulting in low accuracy of detecting the complexity of microvessels.

[0034] Therefore, an embodiment of the present application provides a microvessel detection method and an electronic device, which performs information entropy calculation on a target blood vessel parameter of a detection region in a super-resolution image, and generates a microvessel detection result according to the calculated information entropy. Since the super-resolution image can break through the diffraction limit of traditional ultrasound imaging and has the characteristic of super-resolution, and the information entropy is used to describe the amount of information carried by the image, the information entropy calculation based on the blood vessel parameter in the super-resolution image with higher resolution can extract more abundant and more real blood vessel structure and hemodynamics information in the microvessel, thereby improving the accuracy of detecting the complexity of microvessels. The following will explain in detail how to detect microvessels.

[0035] Please refer to Figure 1 , Figure 1Fig. 1 is a structural schematic diagram of an electronic device 100 provided by an embodiment of the present application. The electronic device 100 can include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 can be connected through a bus, which can be an Inter-integrated Circuit (I2C) bus or any applicable bus.

[0036] For example, the electronic device 100 can be a server, a terminal or a super-resolution imaging device. The server can be a standalone server or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be an electronic device such as a smartphone, a tablet computer, a notebook computer or a desktop computer. The super-resolution imaging device refers to a medical device that detects microvessels in human tissues based on super-resolution contrast imaging technology and generates super-resolution images corresponding to the microvessels.

[0037] The memory 1002 can include a storage medium and an internal memory. The storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, can cause the processor 1001 to perform the microvessel detection method described in any embodiment.

[0038] The processor 1001 is configured to provide computing and control capabilities to support the operation of the entire electronic device 100.

[0039] The processor 1001 can be a Central Processing Unit (CPU). The processor can also be a general-purpose processor, a Digital Signal Processor (DSP), an application specific integrated circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. The general-purpose processor can be a microprocessor or any conventional processor.

[0040] In one embodiment, the processor 1001 is configured to run a computer program stored in the memory 1002 to perform the following steps:

[0041] Obtaining a first super-resolution image to be detected, the first super-resolution image comprising microvessels; determining a first detection region in the first super-resolution image; determining information entropy corresponding to the first detection region according to a target blood vessel parameter of the first detection region; and generating a microvessel detection result of the first super-resolution image according to the information entropy.

[0042] In one embodiment, the processor 1001 is configured to implement the following when determining the first detection region in the first super-resolution image:

[0043] Determining the first detection region in the first super-resolution image according to a region determination operation of a user.

[0044] In one embodiment, the target blood vessel parameter corresponding to the first detection region is of multiple types; and the processor 1001 is configured to implement the following when determining the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region:

[0045] According to a target blood vessel parameter, a first sub-entropy value corresponding to the target blood vessel parameter is obtained; and the information entropy corresponding to the first detection region is determined according to the first sub-entropy values corresponding to the multiple target blood vessel parameters.

[0046] In one embodiment, the target blood vessel parameter comprises a preset parameter value of each pixel in the first detection region; and the processor 1001 is configured to implement the following when determining the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region:

[0047] Determining a probability of each blood flow direction value in all blood flow direction values of the first detection region; and determining the information entropy according to the probability corresponding to each blood flow direction value based on an information entropy calculation formula.

[0048] In one embodiment, the processor 1001 is further configured to implement the following:

[0049] Obtaining a second super-resolution image, the second super-resolution image being obtained by performing image mode switching on the first super-resolution image; determining a second detection region in the second super-resolution image according to a boundary of the first detection region; and generating a microvessel detection result of the second super-resolution image according to a target blood vessel parameter corresponding to the second detection region.

[0050] In one embodiment, the processor 1001 is further configured to implement the following:

[0051] Obtaining a super-resolution image to be detected, the super-resolution image comprising microvessels; determining information entropy corresponding to the super-resolution image according to a blood vessel parameter of the super-resolution image; and generating a microvessel detection result of the super-resolution image according to the information entropy.

[0052] In one embodiment, the processor 1001 is configured to implement the following when implementing the blood vessel parameter according to the super-resolution image, and determining the information entropy corresponding to the super-resolution image:

[0053] determining at least one region of interest in the super-resolution image, and obtaining a blood vessel parameter of the at least one region of interest; determining a second sub-entropy value of the at least one region of interest according to the blood vessel parameter of the at least one region of interest; and determining the information entropy of the super-resolution image according to the second sub-entropy value of the at least one region of interest.

[0054] In one embodiment, the processor 1001 is further configured to implement the following:

[0055] displaying a first super-resolution image to be detected in a microvessel detection interface, the first super-resolution image including microvessels; determining a target detection region in the first super-resolution image in response to a region determination instruction; determining an information entropy corresponding to the target detection region according to a target blood vessel parameter of the target detection region; generating a first microvessel detection result of the first super-resolution image according to the information entropy; and outputting the first microvessel detection result in the microvessel detection interface.

[0056] In one embodiment, the processor 1001 is further configured to implement the following:

[0057] displaying a second super-resolution image and a second microvessel detection result of the second super-resolution image in the microvessel detection interface according to a switching operation on an image mode switching control in the microvessel detection interface, the second super-resolution image being obtained by image mode switching of the first super-resolution image.

[0058] In one embodiment, the processor 1001 is further configured to implement the following after outputting the first microvessel detection result in the microvessel detection interface:

[0059] saving the first super-resolution image and the first microvessel detection result according to a triggering operation on a save control in the microvessel detection interface; and / or exporting the first super-resolution image and the first microvessel detection result according to a triggering operation on an export control in the microvessel detection interface.

[0060] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the case of no conflict, the embodiments described below and the features in the embodiments can be combined with each other. Please refer to Figure 2 , Figure 2 is a schematic flowchart of a microvessel detection method provided by an embodiment of the present application. As Figure 2 shown, the microvessel detection method includes steps S101 to S104.

[0061] Step S101, obtaining a first super-resolution image to be detected, the first super-resolution image including microvessels.

[0062] It should be noted that normal microvessels have good forked branches and ordered structure, and compared with abnormal microvessels, for example, tumor vessels lack ordered hierarchical structure, and present the characteristics of expansion, cystic and uneven diameter in spatial distribution, chaotic blood flow direction, reduced blood flow velocity, and lower overall perfusion rate than normal tissues. Therefore, the embodiments of the present application can accurately detect the complexity of microvessels by quantitatively analyzing the morphological (microbubble density) and kinetic (blood flow direction, blood flow velocity) parameters of microvessels, and can be used for lesion nature identification, lesion progression monitoring or efficacy quantitative evaluation, etc.

[0063] Due to the diffraction limit of ultrasound, the ability of conventional clinical ultrasound contrast to display microvessel structure details is limited. Super-resolution contrast-enhanced ultrasound (SR-CEUS) is a new imaging method with ultra-high spatial resolution. The embodiments of the present application use the principle of fluorescence microscopic positioning technology in optical super-resolution imaging to construct a blood vessel image with a spatial scale of microns by positioning and tracking the motion trajectory of isolated microbubbles. The super-resolution image processing process will be described in detail below.

[0064] Please refer to Figure 3 , Figure 3 is a schematic diagram of a super-resolution image processing process provided by the embodiments of the present application. As Figure 3 indicated, the super-resolution image processing process can include data acquisition, microbubble detection, microbubble separation, microbubble positioning, microbubble tracking, and image reconstruction.

[0065] Among them, data acquisition refers to acquiring original images with ultra-high frame rate based on high frame rate imaging technology (such as plane wave imaging, wide beam imaging, etc.).

[0066] Microbubble detection refers to extracting microbubble signals from the original images to separate microbubbles and tissue signals. Currently, there are mainly the following three categories of microbubble scattering signal detection methods, the first category is based on the nonlinear scattering characteristics of microbubbles, such as pulse inversion, contrast pulse sequence (CPS), ultraharmonic, etc., the second category is based on the inter-frame difference caused by microbubble dissolution or rupture, such as differential imaging (DI), etc., and the third category is based on the flow characteristics of microbubbles, such as singular value decomposition (SVD) spatial filtering, etc.

[0067] Microbubble separation refers to processing microbubble signals by using band-pass filters of different frequencies, so that spatially overlapping microbubbles can be distinguished in the frequency domain; or dividing microbubble signals into multiple subsets based on microbubble speed to reduce microbubble concentration, thereby achieving microbubble separation.

[0068] Microbubble positioning refers to using the centroid method to obtain the precise positioning of each microbubble by point spread function deconvolution.

[0069] Microbubble tracking refers to further tracking the trajectory of microbubbles flowing with blood after obtaining the precise positioning of each microbubble, thereby improving the fault tolerance of microbubble extraction and positioning processing through multi-frame pairing and tracking.

[0070] Image reconstruction refers to drawing a microvessel image with a "microscopic" effect by positioning and tracking the position of the microbubble centroid flowing in the microvessel, and then accumulating and superimposing over a period of time, thereby breaking through the original ultrasonic wave diffraction limit and achieving microvessel and blood flow information with a resolution of microns, so as to realize ultrahigh-resolution imaging of microvessels.

[0071] In the embodiments of the present application, microvessel morphological imaging (for example, blood flow density map) can be generated based on the accumulation of microbubble points; and the inter-frame displacement size of the microbubble represents the speed of the microbubble motion, after obtaining the precise positioning of each microbubble, the moving trajectory of the microbubble in multiple frames of data is continuously tracked, and the moving speed and direction of the microbubble are estimated according to the microbubble motion trajectory, so as to generate microvessel kinetic imaging (for example, blood flow velocity map, blood flow direction map).

[0072] Please refer to Figures 4-6 , Figure 4 is a blood flow direction map of a microvessel provided by the embodiments of the present application, Figure 5 is a blood flow velocity map of a microvessel provided by the embodiments of the present application, Figure 6 is a blood flow density map of a microvessel provided by the embodiments of the present application. The blood flow direction map is used to indicate the blood flow direction of the microvessel, the blood flow velocity map is used to indicate the blood flow velocity of the microvessel, and the blood flow density map is used to indicate the microbubble density of the microvessel.

[0073] It should be noted that when the complexity of the microvessel in the super-resolution image needs to be detected, the user can upload or select one or more super-resolution images on the microvessel detection interface of the electronic device.

[0074] For example, the user-uploaded super-resolution image can be determined as a first super-resolution image to be detected, or multiple super-resolution images can be loaded from a local database or a local disk, and the first super-resolution image to be detected can be determined according to the selection operation of the user. The first super-resolution image includes a microvessel.

[0075] Step S102, determining a first detection region in the first super-resolution image.

[0076] For example, after obtaining the first super-resolution image to be detected, the first detection region in the first super-resolution image can be determined.

[0077] In some embodiments, determining the first detection region in the first super-resolution image can include determining the first detection region in the first super-resolution image according to a region determination operation of a user.

[0078] For example, the region of interest in the first super-resolution image can be determined according to the region determination operation of the user, and the region of interest is determined as the first detection region.

[0079] It should be noted that the user can delineate the region of interest in the first super-resolution image according to actual needs. The delineation type of the region of interest can include, but is not limited to, a trace, a circle, an ellipse, a rectangle, and the like.

[0080] The above embodiment can effectively improve the efficiency of microvessel detection by determining the first detection region in the first super-resolution image, and subsequently detecting the microvessels in the first detection region, without detecting the microvessels in the entire first super-resolution image. At the same time, the user can select the detection region of interest according to actual needs, which facilitates the user to view the microvessel detection results in different regions of the first super-resolution image, and meets different scene requirements.

[0081] Step S103, determining information entropy corresponding to the first detection region according to a target blood vessel parameter of the first detection region.

[0082] After determining the first detection region in the first super-resolution image, the information entropy corresponding to the first detection region can be determined according to the target blood vessel parameter of the first detection region.

[0083] It should be noted that in the embodiments of the present application, the type of the target blood vessel parameter of the first detection region can include one or more, for example, the type of the target blood vessel parameter can include at least one of blood flow direction, blood flow velocity, or blood vessel microbubble density. The target blood vessel parameter corresponding to the first detection region includes a preset parameter value of each pixel in the first detection region. The preset parameter value refers to the parameter value of the blood vessel parameter, for example, the blood flow direction value, the blood flow velocity value, or the blood vessel microbubble density value.

[0084] In some embodiments, the target blood vessel parameter corresponding to the first detection region includes at least one of the blood flow direction value of each pixel in the first detection region, the blood flow velocity value of each pixel in the first detection region, and the blood vessel microbubble density value of each pixel in the first detection region.

[0085] For example, the target blood vessel parameter corresponding to the first detection region can include a blood flow direction value of each pixel in the first detection region. For another example, the target blood vessel parameter corresponding to the first detection region can include a blood flow direction value and a blood flow speed value of each pixel in the first detection region. For another example, the target blood vessel parameter corresponding to the first detection region can include a blood flow direction value, a blood flow speed value and a blood vessel microbubble density value of each pixel in the first detection region.

[0086] In the embodiments of the present application, the target blood vessel parameter corresponding to the first detection region can include three parameter values of a blood flow direction value, a blood flow speed value and a blood vessel microbubble density value of each pixel in the first detection region by default. The type of the target blood vessel parameter corresponding to the first detection region can also be determined according to a selection operation of a user, and the type of the target blood vessel parameter can also be determined according to an image mode of the first super-resolution image, in which case the type of the target blood vessel parameter is one type.

[0087] For example, the information entropy corresponding to the first detection region can be determined according to the target blood vessel parameter of the first detection region. The information entropy is an image measurement method for describing the amount of information carried by an image, and the calculation formula of the information entropy is as follows:

[0088]

[0089] In formula (1), n is the total number of pixels, x i is the gray value of the i th pixel, and p(x i ) is the proportion of the number of pixels with the gray value x i to the total number of pixels in the image.

[0090] In the embodiments of the present application, since the super-resolution image contains rich blood vessel parameters, the information entropy is used to describe the amount of information carried by the image, and therefore the complexity of the microvessels can be evaluated by calculating the information entropy corresponding to the super-resolution image based on the information entropy principle. The greater the information entropy, the higher the complexity of the microvessels, that is, the more chaotic the content of the microvessels; the smaller the information entropy, the lower the complexity of the microvessels, that is, the more ordered the content of the microvessels.

[0091] In some embodiments, the type of the target blood vessel parameter of the first detection region is determined according to an image mode of the first super-resolution image, in which different image modes correspond to different types of target blood vessel parameters.

[0092] It should be noted that the image mode of the first super-resolution image can include but is not limited to a blood flow direction map, a blood flow speed map or a blood flow density map.

[0093] Exemplarily, when the image mode of the first super-resolution image is a blood flow direction map, the type of the target blood vessel parameter corresponding to the first detection region is blood flow direction; when the image mode of the first super-resolution image is a blood flow velocity map, the type of the target blood vessel parameter corresponding to the first detection region is blood flow velocity; and when the image mode of the first super-resolution image is a blood flow density map, the type of the target blood vessel parameter corresponding to the first detection region is blood vessel microbubble density.

[0094] According to the above embodiment, by determining the type of the target blood vessel parameter of the first detection region according to the image mode of the first super-resolution image, the target blood vessel parameter can be automatically determined according to the image mode of the first super-resolution image without manual selection of the type of the target blood vessel parameter by the user.

[0095] In the following, the determination of the information entropy of the first detection region will be described by taking the type of the target blood vessel parameter corresponding to the first detection region as blood flow direction, blood flow velocity, and blood vessel microbubble density, respectively.

[0096] In some embodiments, the determination of the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region can include: determining the probability of each blood flow direction value in all pixel blood flow direction values in the first detection region; and determining the information entropy according to the probability corresponding to each blood flow direction value based on an information entropy calculation formula.

[0097] Exemplarily, when the type of the target blood vessel parameter is blood flow direction, the information entropy can be calculated by the above information entropy calculation formula (1), in which case, x i is the blood flow direction value of the i-th pixel, p(x i ) is the probability of the blood flow direction value x i in all pixel blood flow direction values in the first detection region, and H(X) is the information entropy corresponding to the first detection region.

[0098] According to the above embodiment, by determining the probability of each blood flow direction value in all pixel blood flow direction values in the first detection region and determining the information entropy according to the probability corresponding to each blood flow direction value based on the information entropy calculation formula, the information entropy can be used to reflect the disorder degree of the blood flow direction of the microvessel.

[0099] In other embodiments, the determination of the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region can further include: determining the probability of each blood flow velocity value in all pixel blood flow velocity values in the first detection region; and determining the information entropy according to the probability corresponding to each blood flow velocity value based on the information entropy calculation formula.

[0100] Exemplarily, when the type of the target blood vessel parameter is blood flow velocity, the information entropy can be calculated by the above information entropy calculation formula (1), in which case, x iLet p(x) be the blood flow velocity value of the i-th pixel. i (x) represents the blood flow velocity value. i The probability of blood flow velocity values ​​among all pixels in the first detection region, H(X) is the information entropy corresponding to the first detection region.

[0101] In the above embodiments, by determining the probability of each blood flow velocity value among all pixel blood flow velocity values ​​in the first detection area, and determining the information entropy based on the probability corresponding to each blood flow velocity value according to the information entropy calculation formula, it is possible to use information entropy to reflect the degree of disorder of blood flow velocity in microvessels.

[0102] In other embodiments, determining the information entropy corresponding to the first detection area based on the target blood vessel parameters of the first detection area may further include: determining the probability of each blood vessel microbubble density value among all pixel blood vessel microbubble density values ​​in the first detection area; and determining the information entropy based on the information entropy calculation formula and the information entropy corresponding to each blood vessel microbubble density value.

[0103] For example, when the target vascular parameter is blood flow density, the information entropy can be calculated using the above information entropy calculation formula (1). In this case, x i Let p(x) be the vascular microbubble density value of the i-th pixel. i (x) represents the vascular microbubble density value. i The probability of the blood vessel microbubble density values ​​among all pixels in the first detection region, H(X) is the information entropy corresponding to the first detection region.

[0104] In the above embodiments, by determining the probability of each vascular microbubble density value among all pixel vascular microbubble density values ​​in the first detection area, and based on the information entropy calculation formula, the information entropy corresponding to each vascular microbubble density value can be used to reflect the degree of disorder of vascular microbubble density in microvessels.

[0105] In this embodiment, in addition to determining the information entropy corresponding to the first detection region based on one target blood vessel parameter, the information entropy corresponding to the first detection region can also be determined based on multiple target blood vessel parameters.

[0106] In some embodiments, determining the information entropy corresponding to the first detection region based on the target blood vessel parameters corresponding to the first detection region includes: calculating the information entropy based on a target blood vessel parameter to obtain a first sub-entropy value corresponding to the target blood vessel parameter; and determining the information entropy corresponding to the first detection region based on the first sub-entropy values ​​corresponding to each of the multiple target blood vessel parameters.

[0107] For example, when the types of the target vessel parameters corresponding to the first detection region include blood flow direction and blood flow velocity, the information entropy can be calculated according to the blood flow direction values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow direction, and the information entropy can be calculated according to the blood flow velocity values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow velocity. Then, the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity are determined as the information entropy corresponding to the first detection region. The calculation processes of the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity can be referred to the detailed description of the above embodiments, and will not be described here.

[0108] For example, when the types of the target vessel parameters corresponding to the first detection region include blood flow direction and blood flow velocity, the information entropy can be calculated according to the blood flow direction values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow direction, and the information entropy can be calculated according to the blood flow velocity values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow velocity. Then, the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity are determined as the information entropy corresponding to the first detection region. The calculation processes of the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity can be referred to the detailed description of the above embodiments, and will not be described here.

[0109] For example, when the types of the target vessel parameters corresponding to the first detection region include blood flow direction and blood flow velocity, the information entropy can be calculated according to the blood flow direction values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow direction, and the information entropy can be calculated according to the blood flow velocity values of the pixels in the first detection region to obtain the first sub-entropy value corresponding to the blood flow velocity. Then, the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity are determined as the information entropy corresponding to the first detection region. The calculation processes of the first sub-entropy value corresponding to the blood flow direction and the first sub-entropy value corresponding to the blood flow velocity can be referred to the detailed description of the above embodiments, and will not be described here.

[0110] The above embodiments can realize the generation of the information entropy corresponding to multiple target vessel parameters at the same time by calculating the first sub-entropy value corresponding to each type of target vessel parameter respectively and determining the information entropy corresponding to the first detection region according to the first sub-entropy values corresponding to the multiple target vessel parameters respectively, so as to facilitate the user to compare the complexity of the microvessels under different target vessel parameters.

[0111] In step S104, the microvessel detection result of the first super-resolution image is generated according to the information entropy.

[0112] In some embodiments, after the information entropy corresponding to the first detection region is determined according to the target vessel parameters of the first detection region, the microvessel detection result of the first super-resolution image can be generated according to the information entropy.

[0113] Exemplarily, the information entropy can be taken as the microvessel detection result of the first super-resolution image, that is, the microvessel detection result includes the information entropy. For example, when the type of the target blood vessel parameter in the first detection region is the blood flow direction, the information entropy corresponding to the blood flow direction in the first detection region can be determined as the microvessel detection result. For another example, when the type of the target blood vessel parameter in the first detection region is the blood flow direction and the blood flow velocity, the sub-entropy value corresponding to the blood flow direction and the sub-entropy value corresponding to the blood flow velocity in the first detection region can be determined as the microvessel detection result.

[0114] Exemplarily, the complexity level of the microvessel can be determined according to the information entropy, and the complexity level is taken as the microvessel detection result of the first super-resolution image. Wherein, the greater the information entropy is, the higher the complexity level of the microvessel corresponding to the information entropy is. For example, when the information entropy is greater than or equal to a first threshold value, it is determined that the complexity level of the microvessel corresponding to the information entropy is level three; when the information entropy is greater than or equal to a second threshold value and less than the first threshold value, it is determined that the complexity level of the microvessel corresponding to the information entropy is level two; when the information entropy is less than the first threshold value, it is determined that the complexity level of the microvessel corresponding to the information entropy is level one. Wherein, the first threshold value is greater than the second threshold value, and the first threshold value and the second threshold value can be set according to actual conditions, and the specific numerical value is not limited herein.

[0115] In the above embodiments, the target blood vessel parameter of the detection region in the super-resolution image is calculated by information entropy, and the microvessel detection result is generated according to the calculated information entropy. Since the super-resolution image has the characteristic of super-resolution, and the information entropy is used to describe the amount of information carried by the image, the blood vessel parameter in the super-resolution image with higher resolution is calculated by information entropy, so that more abundant and more real blood vessel structure and hemodynamic information in the microvessel can be extracted, thereby the accuracy of detecting the complexity of the microvessel can be improved.

[0116] Please refer to Figure 7 , Figure 7 is a schematic flowchart of another microvessel detection method provided by the embodiments of the present application. As shown in Figure 7 , the method can include the following steps S105 to S107.

[0117] In step S105, a second super-resolution image is acquired, and the second super-resolution image is obtained by image mode switching of the first super-resolution image.

[0118] In the embodiments of the present application, the first super-resolution image of the current microvessel detection interface on the electronic device can also be subjected to image mode switching according to the image mode switching operation of the user, to obtain the second super-resolution image, and to generate the microvessel detection result of the second super-resolution image.

[0119] For example, when the image mode of the first super-resolution image is the blood flow direction map, if it is detected that the user switches the blood flow direction map to the blood flow velocity map, a super-resolution image with the image mode of the blood flow velocity map can be acquired as the second super-resolution image. For another example, when the image mode of the first super-resolution image is the blood flow direction map, if it is detected that the user switches the blood flow direction map to the blood flow density map, a super-resolution image with the image mode of the blood flow density map can be acquired as the second super-resolution image.

[0120] In step S106, a second detection region is determined in the second super-resolution image according to the boundary of the first detection region.

[0121] For example, the first detection region in the first super-resolution image can be taken as the second detection region in the second super-resolution image.

[0122] By taking the first detection region in the first super-resolution image as the second detection region in the second super-resolution image, the original detection region can be retained when the image mode is switched, and there is no need to delineate the detection region in the second super-resolution image again.

[0123] In step S107, a microvessel detection result of the second super-resolution image is generated according to the target blood vessel parameter corresponding to the second detection region.

[0124] For example, after the second detection region is determined in the second super-resolution image, a microvessel detection result of the second super-resolution image can be generated according to the target blood vessel parameter corresponding to the second detection region. The specific process of generating the microvessel detection result of the second super-resolution image according to the target blood vessel parameter corresponding to the second detection region can refer to the detailed description of determining the information entropy of the first detection region according to the target blood vessel parameter of the first detection region and generating the microvessel detection result of the first super-resolution image according to the information entropy in the above embodiment, and the specific process is not described herein.

[0125] The above embodiment can flexibly switch the super-resolution image according to the image mode switching operation of the user by switching the image mode of the first super-resolution image and determining the microvessel detection result of the second super-resolution image after the image mode is switched, which facilitates the user to view the microvessel detection result of the super-resolution image in different image modes.

[0126] Please refer to Figure 8 , Figure 8is a schematic flowchart of another microvessel detection method provided in the embodiments of the present application. As shown in Figure 8 may include the following steps S201 to S203.

[0127] Step S201, obtaining a super-resolution image to be detected, the super-resolution image including microvessels.

[0128] For example, the super-resolution image uploaded by a user can be determined as the super-resolution image to be detected, or a plurality of super-resolution images are loaded from a local database or a local disk, and the super-resolution image to be detected is determined according to a selection operation of the user. The super-resolution image includes microvessels.

[0129] Step S202, determining information entropy corresponding to the super-resolution image according to a blood vessel parameter of the super-resolution image.

[0130] In the embodiments of the present application, the information entropy corresponding to the super-resolution image can be determined according to the blood vessel parameter of the entire super-resolution image. Moreover, the information entropy corresponding to the super-resolution image can be determined according to one or more blood vessel parameters of the super-resolution image.

[0131] In some embodiments, the type of the blood vessel parameter corresponding to the super-resolution image is determined according to an image mode of the super-resolution image, wherein the type of the blood vessel parameter corresponding to each of different image modes is at least partially different.

[0132] For example, the image mode of the first super-resolution image can include but is not limited to a blood flow direction map, a blood flow velocity map or a blood flow density map. The type of the blood vessel parameter corresponding to each of different image modes can include one or more, wherein the type of the blood vessel parameter can include blood flow direction, blood flow velocity and blood vessel microbubble density.

[0133] For example, when the image mode of the super-resolution image is a blood flow direction map, the type of the blood vessel parameter corresponding to the super-resolution image is blood flow direction; when the image mode of the super-resolution image is a blood flow velocity map, the type of the blood vessel parameter corresponding to the super-resolution image is blood flow velocity; and when the image mode of the super-resolution image is a blood flow density map, the type of the blood vessel parameter corresponding to the super-resolution image is blood vessel microbubble density.

[0134] In some embodiments, the blood vessel parameter corresponding to each image mode includes at least one of the following: a blood flow direction value of each pixel in the super-resolution image, a blood flow velocity value of each pixel in the super-resolution image, and a blood vessel microbubble density value of each pixel in the super-resolution image.

[0135] For example, for the blood flow direction map, the blood vessel parameters corresponding to the blood flow direction map can include blood flow direction values of each pixel in the super-resolution image. For example, for the blood flow velocity map, the blood vessel parameters corresponding to the blood flow velocity map can include blood flow direction values and blood flow velocity values of each pixel in the super-resolution image. For example, for the blood flow velocity map, the blood vessel parameters corresponding to the blood flow velocity map can include blood flow direction values, blood flow velocity values and blood vessel micro-bubble density values of each pixel in the super-resolution image.

[0136] In at least one embodiment, when determining the information entropy corresponding to the super-resolution image according to the blood vessel parameters of the super-resolution image, if the type of the blood vessel parameters of the super-resolution image is one, for example, the blood flow direction, the probability of each blood flow direction value in all blood flow direction values of the super-resolution image is determined, and the information entropy corresponding to the super-resolution image is determined according to the probability corresponding to each blood flow direction value based on the information entropy calculation formula. The specific process of calculating the information entropy according to the blood flow direction can be referred to the detailed description of the above embodiments, which will not be repeated here.

[0137] In at least one embodiment, when determining the information entropy corresponding to the super-resolution image according to the blood vessel parameters of the super-resolution image, if the type of the blood vessel parameters of the super-resolution image is two, for example, the blood flow direction and the blood flow velocity, the information entropy is calculated according to the blood flow direction to obtain the sub-entropy value corresponding to the blood flow direction, and the information entropy is calculated according to the blood flow velocity to obtain the sub-entropy value corresponding to the blood flow velocity, and the information entropy corresponding to the super-resolution image is determined according to the sub-entropy value corresponding to the blood flow direction and the sub-entropy value corresponding to the blood flow velocity. The specific process of calculating the information entropy according to the blood flow direction and calculating the information entropy according to the blood flow velocity can be referred to the detailed description of the above embodiments, which will not be repeated here.

[0138] In step S203, the microvessel detection result of the super-resolution image is generated according to the information entropy.

[0139] In some embodiments, after determining the information entropy corresponding to the super-resolution image according to the blood vessel parameters of the super-resolution image, the microvessel detection result of the super-resolution image can be generated according to the information entropy.

[0140] For example, the information entropy can be taken as the microvessel detection result of the super-resolution image, that is, the microvessel detection result includes the information entropy. For example, when the type of the blood vessel parameters of the super-resolution image is the blood flow direction, the information entropy corresponding to the blood flow direction of the super-resolution image can be determined as the microvessel detection result. For example, when the type of the blood vessel parameters of the super-resolution image is the blood flow direction and the blood flow velocity, the sub-entropy value corresponding to the blood flow direction and the sub-entropy value corresponding to the blood flow velocity can be determined as the microvessel detection result of the super-resolution image.

[0141] The above embodiment calculates the information entropy of the blood vessel parameters of the super-resolution image, and generates the microvessel detection result according to the calculated information entropy. Since the super-resolution image has the super-resolution characteristic, and the information entropy is used to describe the information amount carried by the image, the information entropy calculation based on the blood vessel parameters in the super-resolution image with higher resolution can extract more abundant and more real blood vessel structure and hemodynamics information in the microvessel, thereby improving the accuracy of detecting the complexity of the microvessel.

[0142] Referring to Figure 9 , Figure 9 is a schematic flowchart of a sub-step of determining information entropy provided by an embodiment of the present application. As shown in Figure 9 , step S202 can further include the following steps S2021 to S2023.

[0143] Step S2021, determining at least one region of interest in the super-resolution image, and obtaining the blood vessel parameters of the at least one region of interest.

[0144] In the embodiment of the present application, in addition to determining the information entropy corresponding to the super-resolution image according to the blood vessel parameters of the entire super-resolution image, the information entropy corresponding to the super-resolution image can also be determined according to the blood vessel parameters in one or more detection regions in the super-resolution image.

[0145] For example, at least one region of interest in the super-resolution image can be determined according to the region determination operation of the user. The drawing type of the region of interest can include, but is not limited to, tracing, circle, ellipse, rectangle, etc.

[0146] Referring to Figure 10 , Figure 10 is a schematic diagram of a super-resolution image provided by an embodiment of the present application. As shown in Figure 10 , when the image mode of the super-resolution image is a blood flow direction map, the A region of interest in the super-resolution image can be determined according to the region determination operation of the user.

[0147] Referring to Figure 11 , Figure 11 is another schematic diagram of a super-resolution image provided by an embodiment of the present application. As shown in Figure 11 , when the image mode of the super-resolution image is a blood flow velocity map, the A region of interest and the B region of interest in the super-resolution image can be determined according to the region determination operation of the user.

[0148] In some embodiments, the type of the blood vessel parameters of the at least one region of interest is the same as the type of the blood vessel parameters of the other at least one region of interest.

[0149] For example, as Figure 11As shown, the type of the vascular parameter of the A region of interest can be blood flow velocity, and the type of the vascular parameter of the B region of interest can also be blood flow velocity.

[0150] In the above embodiment, by setting the type of the vascular parameter of the at least one region of interest to be the same as the type of the vascular parameter of the other at least one region of interest, the sub-entropy values of the same type of vascular parameter in different regions of interest can be obtained by subsequently calculating the sub-entropy values according to the vascular parameters of each region of interest, so as to facilitate the user to compare the complexity of the microvessels in the same type of vascular parameter in different regions of interest.

[0151] In other embodiments, the type of the vascular parameter of the at least one region of interest is different from the type of the vascular parameter of the other at least one region of interest.

[0152] For example, as shown in FIG. 6, the type of the vascular parameter of the A region of interest can be blood flow velocity, and the type of the vascular parameter of the B region of interest can be blood flow direction. Figure 11 For example, as shown in FIG. 6, the type of the vascular parameter of the A region of interest can be blood flow velocity, and the type of the vascular parameter of the B region of interest can be blood flow direction.

[0153] In the above embodiment, by setting the type of the vascular parameter of the at least one region of interest to be different from the type of the vascular parameter of the other at least one region of interest, the sub-entropy values corresponding to the super-resolution image in different regions of interest and different vascular parameters can be obtained by subsequently calculating the sub-entropy values according to the vascular parameters of each region of interest, so as to facilitate the user to simultaneously view the complexity of the microvessels in different regions of interest and different vascular parameters.

[0154] In step S2022, a second sub-entropy value of the at least one region of interest is determined according to the vascular parameter of the at least one region of interest.

[0155] For example, as shown in FIG. 6, the type of the vascular parameter of the A region of interest can be blood flow velocity, and the type of the vascular parameter of the B region of interest can be blood flow direction. Figure 11 For example, as shown in FIG. 6, when the type of the vascular parameter of the A region of interest is blood flow velocity, and the type of the vascular parameter of the B region of interest is blood flow direction, the second sub-entropy value of the A region of interest can be obtained by calculating the information entropy according to the blood flow velocity of the A region of interest, and the second sub-entropy value of the B region of interest can be obtained by calculating the information entropy according to the blood flow direction of the B region of interest. The specific process of calculating the information entropy according to the blood flow direction and calculating the information entropy according to the blood flow velocity can be referred to the detailed description of the above embodiment, which will not be repeated here.

[0156] In step S2023, the information entropy of the super-resolution image is determined according to the second sub-entropy value of the at least one region of interest.

[0157] Exemplarily, after the second sub-entropy value of the at least one region of interest is determined according to the blood vessel parameter of the at least one region of interest, the information entropy of the super-resolution image can be determined according to the second sub-entropy value of the at least one region of interest. For example, the information entropy of the super-resolution image can be generated according to the second sub-entropy value of the A region of interest and the second sub-entropy value of the B region of interest.

[0158] According to the above embodiment, by determining the at least one region of interest in the super-resolution image and performing information entropy calculation according to the blood vessel parameter of the at least one region of interest, the sub-entropy value corresponding to the at least one region of interest can be obtained, which facilitates the user to simultaneously view and compare the complexity of the microvessels in the multiple regions of interest in the super-resolution image.

[0159] Please refer to Figure 12 , Figure 12 is a schematic flowchart of another microvessel detection method provided by the embodiment of the present application. As shown in Figure 12 , the method can include the following steps S301 to S305.

[0160] Step S301, display a first super-resolution image to be detected in a microvessel detection interface, the first super-resolution image including microvessels.

[0161] Exemplarily, the super-resolution image uploaded by the user in the microvessel detection interface can be determined as the first super-resolution image to be detected, or multiple frames of super-resolution images can be loaded from a local database or a local disk to the microvessel detection interface, and the first super-resolution image to be detected can be determined according to the selection operation of the user. The first super-resolution image includes microvessels.

[0162] Please refer to Figure 13 , Figure 13 is a schematic diagram of a microvessel detection interface provided by the embodiment of the present application. As shown in Figure 13 , the microvessel detection interface is used to display a super-resolution image to be detected and display a microvessel detection result corresponding to the super-resolution image. The microvessel detection interface can include an upload control 110, an image mode switching control 120, a save control 130, and an export control 140, and the like. The upload control 110 is used for the user to upload the super-resolution image to be detected, the image mode switching control 120 is used for the user to switch the super-resolution image in different image modes, the save control 130 is used for the user to save the detected super-resolution image and the microvessel detection result corresponding to the super-resolution image, and the export control 140 is used for the user to export the detected super-resolution image and the microvessel detection result corresponding to the super-resolution image. The positions of the upload control 110, the image mode switching control 120, the save control 130, and the export control 140 on the microvessel detection interface can be set according to the actual situation, which is not limited herein.

[0163] Step S302, in response to the region determination instruction, determining a target detection region in the first super-resolution image.

[0164] For example, after displaying the first super-resolution image to be detected in the microvessel detection interface, the target detection region in the first super-resolution image can be determined in response to the region determination instruction of the user. The target detection region can be one or more regions of interest in the first super-resolution image.

[0165] It should be noted that in the embodiments of the present application, the user can draw at least one region of interest in the first super-resolution image according to actual needs.

[0166] In the above embodiments, the target detection region in the first super-resolution image is determined in response to the region determination instruction, and the information entropy corresponding to the target detection region can be determined according to the target blood vessel parameters of the target detection region.

[0167] Step S303, determining the information entropy corresponding to the target detection region according to the target blood vessel parameters of the target detection region.

[0168] It should be noted that in the embodiments of the present application, the types of target blood vessel parameters of the target detection region can include one or more, for example, the types of target blood vessel parameters can include at least one of blood flow direction, blood flow velocity or blood vessel microbubble density. Correspondingly, the target blood vessel parameters of the target detection region include at least one of the blood flow direction value of each pixel in the target detection region, the blood flow velocity value of each pixel in the target detection region, and the blood vessel microbubble density value of each pixel in the target detection region.

[0169] In some embodiments, when the type of target blood vessel parameters of the target detection region is one, the information entropy of the target detection region can be calculated according to the target blood vessel parameters; when the type of target blood vessel parameters of the target detection region is multiple, the information entropy of the target detection region can be calculated according to one target blood vessel parameter to obtain a sub-entropy value corresponding to the target blood vessel parameter, and the information entropy of the target detection region can be determined according to the sub-entropy values corresponding to the multiple target blood vessel parameters. The specific process of calculating the information entropy according to one or more target blood vessel parameters can be referred to the detailed description of the above embodiments, and the specific process is not described here.

[0170] Step S304, generating the first microvessel detection result of the first super-resolution image according to the information entropy.

[0171] After determining the information entropy corresponding to the target detection region according to the target blood vessel parameters of the target detection region, the first microvessel detection result of the first super-resolution image can be generated according to the information entropy.

[0172] Exemplarily, the information entropy can be taken as the first microvessel detection result of the first super-resolution image, i.e., the microvessel detection result includes the information entropy. For example, when the type of the target vessel parameter in the target detection region is the blood flow direction, the information entropy corresponding to the blood flow direction in the target detection region can be determined as the first microvessel detection result. For another example, when the type of the target vessel parameter in the target detection region is the blood flow direction and the blood flow velocity, the sub-entropy value corresponding to the blood flow direction and the sub-entropy value corresponding to the blood flow velocity in the target detection region can be determined as the first microvessel detection result.

[0173] In step S305, the first microvessel detection result is output on the microvessel detection interface.

[0174] Exemplarily, after the first microvessel detection result of the first super-resolution image is generated according to the information entropy, the first microvessel detection result can be displayed on the microvessel detection interface, so as to enable the user to more intuitively and quickly obtain the complexity of the microvessel.

[0175] In the above embodiments, the target vessel parameter of the target detection region in the super-resolution image is calculated by the information entropy, and the microvessel detection result is generated according to the calculated information entropy. Since the super-resolution image has the super-resolution characteristic, and the information entropy is used to describe the amount of information carried by the image, the blood vessel parameter in the super-resolution image with higher resolution is calculated by the information entropy, so that more abundant and more real blood vessel structure and blood flow dynamics information in the microvessel can be extracted, thereby the accuracy of detecting the complexity of the microvessel can be improved.

[0176] In some embodiments, the microvessel detection method provided by the embodiments of the present application can further include: according to the switching operation of the image mode switching control on the microvessel detection interface, displaying a second super-resolution image and a second microvessel detection result of the second super-resolution image on the microvessel detection interface, the second super-resolution image being obtained by image mode switching of the first super-resolution image.

[0177] Please refer to Figure 14 , Figure 14 is a schematic diagram of image mode switching provided by the embodiments of the present application. As Figure 14As shown, when the image mode currently displayed by the microvessel detection interface is the blood flow direction map, if a switching operation of the user is detected to switch the image mode to the blood flow velocity map, a second super-resolution image with the image mode as the blood flow velocity map is acquired, and the second super-resolution image is displayed on the microvessel detection interface. At the same time, the information entropy is calculated according to the target blood vessel parameters of the target detection area in the second super-resolution image, the second microvessel detection result of the second super-resolution image is obtained, and the second microvessel detection result is displayed on the microvessel detection interface. The target detection area in the second super-resolution image is the same as the target detection area in the first super-resolution image.

[0178] The above embodiment, by displaying the second super-resolution image and the second microvessel detection result of the second super-resolution image on the microvessel detection interface according to the switching operation of the image mode switching control on the microvessel detection interface, can facilitate the user to view the complexity of the microvessels in the super-resolution image of different image modes according to actual needs.

[0179] In some embodiments, after the first microvessel detection result is output on the microvessel detection interface, the method can further include: saving the first super-resolution image and the first microvessel detection result according to a triggering operation of a save control on the microvessel detection interface; and / or exporting the first super-resolution image and the first microvessel detection result according to a triggering operation of an export control on the microvessel detection interface.

[0180] For example, as shown in FIG. 1, the microvessel detection interface 100 can include a save control 130 and an export control 140. Figure 13 As shown, when a triggering operation of the user on the save control 130 of the microvessel detection interface is detected, the first super-resolution image and the first microvessel detection result are saved. When a triggering operation of the user on the export control 140 of the microvessel detection interface is detected, the first super-resolution image and the first microvessel detection result are exported.

[0181] The above embodiment, by saving and exporting the first super-resolution image and the first microvessel detection result, facilitates the user to further identify the lesion properties, monitor the lesion progression, or quantitatively evaluate the curative effect according to the complexity of the microvessels subsequently.

[0182] For example, as shown in FIG. 1, the microvessel detection interface 100 can include a save control 130 and an export control 140. Figure 15 , Figure 15 is a schematic diagram of determining a sub-entropy value of a plurality of regions of interest provided by an embodiment of the present application. As shown in FIG. 2, the sub-entropy value of the region of interest can be determined according to the following formula: Figure 15As shown, when the user draws an A region of interest and a B region of interest in the super-resolution image, the information entropy can be calculated according to the blood vessel parameters of the A region of interest and the blood vessel parameters of the B region of interest respectively, to obtain a sub-entropy value of the A region of interest and a sub-entropy value of the B region of interest. The blood vessel parameters of the A region of interest and the blood vessel parameters of the B region of interest can be the same or different. By determining the corresponding sub-entropy values of the super-resolution image in different regions of interest, the user can conveniently view the complexity of the microvessels in different regions of interest.

[0183] Please refer to Figure 16 , Figure 16 is a schematic diagram of determining sub-entropy values corresponding to a plurality of blood vessel parameters provided by the embodiment of the present application. As shown Figure 16 , when the current image mode of the super-resolution image is a blood vessel direction map, the information entropy can be calculated according to the blood flow direction, the blood flow velocity, and the blood vessel microbubble density in the region of interest respectively, to obtain the sub-entropy values corresponding to the blood flow direction, the blood flow velocity, and the blood vessel microbubble density respectively. By determining the sub-entropy values corresponding to a plurality of blood vessel parameters of the super-resolution image in the region of interest, the user can conveniently compare the complexity of the microvessels in different blood vessel parameters.

[0184] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements shall be encompassed within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for detecting microvessels, characterized by, The detection method comprises: obtaining a first super-resolution image to be detected, the first super-resolution image comprising microvessels; determining a first detection region in the first super-resolution image; determining information entropy corresponding to the first detection region according to a target blood vessel parameter of the first detection region; generating a microvessel detection result of the first super-resolution image according to the information entropy.

2. The method of detecting microvessels according to claim 1, wherein The determination of the first detection region in the first super-resolution image comprises: determining the first detection region in the first super-resolution image according to a region determination operation of a user.

3. The method of detecting microvessels according to claim 1, wherein The target blood vessel parameter corresponding to the first detection region comprises at least one of a blood flow direction value of each pixel in the first detection region, a blood flow velocity value of each pixel in the first detection region, and a blood vessel microbubble density value of each pixel in the first detection region.

4. The method of detecting microvessels according to any one of claims 1, wherein The type of the target blood vessel parameter of the first detection region is determined according to an image mode of the first super-resolution image; wherein the types of the target blood vessel parameters corresponding to different image modes are different.

5. The method of detecting microvessels according to claim 4, wherein When the image mode of the first super-resolution image is a blood flow direction map, the type of the target blood vessel parameter corresponding to the first detection region is a blood flow direction. When the image mode of the first super-resolution image is a blood flow velocity map, the type of the target blood vessel parameter corresponding to the first detection region is a blood flow velocity. When the image mode of the first super-resolution image is a blood flow density map, the type of the target blood vessel parameter corresponding to the first detection region is a blood vessel microbubble density.

6. The method of detecting microvessels according to claim 3, wherein The type of the target blood vessel parameter corresponding to the first detection region is multiple; The determination of the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region comprises: performing information entropy calculation according to one of the target blood vessel parameters to obtain a first sub-entropy value corresponding to the target blood vessel parameter; determining the information entropy corresponding to the first detection region according to the first sub-entropy values corresponding to the multiple target blood vessel parameters.

7. The method of detecting microvessels according to claim 3, wherein The target blood vessel parameter comprises a preset parameter value of each pixel in the first detection region. The determination of the information entropy corresponding to the first detection region according to the target blood vessel parameter of the first detection region comprises: determining a probability of each blood flow direction value in all blood flow direction values of pixels in the first detection region; determining the information entropy according to the probability corresponding to each blood flow direction value based on an information entropy calculation formula.

8. The method of detecting microvessels according to any one of claims 1 to 7, wherein, The method further comprises: obtaining a second super-resolution image, the second super-resolution image being obtained by image mode switching of the first super-resolution image; determining a second detection region in the second super-resolution image according to a boundary of the first detection region; generating a microvessel detection result of the second super-resolution image according to a target blood vessel parameter corresponding to the second detection region.

9. A method for detecting microvessels, characterized by, The detection method comprises: obtaining a super-resolution image to be detected, the super-resolution image comprising microvessels; determining information entropy corresponding to the super-resolution image according to a blood vessel parameter of the super-resolution image; generating a microvessel detection result of the super-resolution image according to the information entropy.

10. The method of detecting microvessels according to claim 9, wherein a type of the blood vessel parameter corresponding to the super-resolution image is determined according to an image mode of the super-resolution image, wherein the type of the blood vessel parameter corresponding to each of the different image modes is at least partially different; and / or the blood vessel parameter corresponding to each of the image modes comprises at least one of a blood flow direction value of each pixel in the super-resolution image, a blood flow velocity value of each pixel in the super-resolution image, and a blood microbubble density value of each pixel in the super-resolution image.

11. The method of detecting microvessels according to claim 9, wherein the information entropy corresponding to the super-resolution image is determined according to the blood vessel parameter of the super-resolution image, and the determining further comprises: at least one region of interest in the super-resolution image is determined, and a blood vessel parameter of the at least one region of interest is obtained; a second sub-entropy value of the at least one region of interest is determined according to the blood vessel parameter of the at least one region of interest; the information entropy of the super-resolution image is determined according to the second sub-entropy value of the at least one region of interest.

12. The method of detecting microvessels according to claim 11, wherein, the type of the blood vessel parameter of the at least one region of interest is the same as that of at least one other region of interest; and / or the type of the blood vessel parameter of the at least one region of interest is different from that of at least one other region of interest.

13. A method of detecting microvessels, characterized by, The detection method comprises: displaying a first super-resolution image to be detected in a microvessel detection interface, the first super-resolution image comprising microvessels; in response to a region determination instruction, determining a target detection region in the first super-resolution image; determining an information entropy corresponding to the target detection region according to a target blood vessel parameter of the target detection region; generating a first microvessel detection result of the first super-resolution image according to the information entropy; outputting the first microvessel detection result in the microvessel detection interface.

14. The method of detecting microvessels according to claim 13, wherein The method further comprises: in response to a switching operation on an image mode switching control in the microvessel detection interface, displaying a second super-resolution image and a second microvessel detection result of the second super-resolution image in the microvessel detection interface, the second super-resolution image being obtained by image mode switching of the first super-resolution image.

15. The method for detecting microvessels according to claim 13, characterized in that, After outputting the first microvessel detection result in the microvessel detection interface, the method further comprises: in response to a triggering operation on a save control in the microvessel detection interface, saving the first super-resolution image and the first microvessel detection result; and / or in response to a triggering operation on an export control in the microvessel detection interface, exporting the first super-resolution image and the first microvessel detection result.

16. An electronic device, comprising: The electronic device comprises a memory and a processor; the memory is configured to store a computer program; the processor is configured to execute the computer program and implement the following when executing the computer program: the microvessel detection method of any one of claims 1 to 8; or the microvessel detection method of any one of claims 9 to 12; or the microvessel detection method of any one of claims 13 to 15.

Images