Microcirculation image blood vessel region extraction method and device, equipment and storage medium

Abstract

This invention relates to the field of medical image processing technology, and particularly to a method, apparatus, device, and storage medium for extracting vascular regions from microcirculation images. A method for extracting vascular regions from microcirculation images includes the following steps: Step S1: Obtaining vascular regions from several consecutive frames of original images in a microcirculation video and caching them in a vascular sequence; Step S2: Merging the vascular regions from several frames of original images in the vascular sequence to obtain the final vascular region. This invention, by inputting a microcirculation video with minimal jitter, obtains several vascular regions from the original image sequence and then merges them into the final vascular region. This can, to a certain extent, correct the inaccuracies of single-frame calculations, and minimize or balance data errors caused by incomplete or excessive deformation of vascular regions due to flow or jitter. The resulting vascular extraction is more complete and accurate, and the obtained results are more scientifically reliable and objective.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method, apparatus, device, and storage medium for extracting vascular regions from microcirculation images. Background Technology

[0002] Microcirculation is the blood circulation within the capillaries between arterioles and venules, and it is the most basic structural and functional unit of the circulatory system. It includes the circulation of body fluids within arterioles, venules, lymphatic capillaries, and tissue channels. Every organ and every tissue cell in the human body relies on microcirculation to receive oxygen and nutrients, transfer energy, exchange information, and remove carbon dioxide and metabolic waste. Microcirculation reflects the physiological state and changes in the human body, and studies have confirmed that inconsistencies between systemic circulation and microcirculation indicate organ dysfunction and poor prognosis.

[0003] The invention of handheld live microscopes (HVMs) has enabled the visualization of microcirculation. During monitoring, the handheld microscope requires manual operation to capture videos and obtain microcirculatory vascular images. Current image processing methods for microcirculation images involve manually capturing video when the lens is stable and the shaking is minimal. A few subjectively considered good single-frame images are then extracted for analysis, and these manually selected images are used to extract microcirculatory vessels for microcirculation data calculation. However, because the analysis is done frame-by-frame, there is no comparison with the overall video image. This makes it impossible to calibrate for deviations caused by visual observation during acquisition or extraction, as well as data errors caused by the flow of fluid within the microcirculation, thus posing a significant risk of data error. Summary of the Invention

[0004] The purpose of this invention is to provide a method for extracting blood vessel regions from microcirculation images. By inputting a microcirculation video with minimal jitter, the inaccuracy of single-frame calculation can be corrected to a certain extent, resulting in more complete and accurate blood vessel extraction. The results obtained are more scientifically reliable and objective.

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] In a first aspect, the present invention proposes a method for extracting vascular regions from microcirculation images, comprising the following steps:

[0007] Step S1: Obtain the vascular region from several consecutive frames of raw images in the microcirculation video and cache them in the vascular sequence;

[0008] Step S2: Merge the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region.

[0009] A further improvement is that, after step S2, the method further includes:

[0010] Step S3: Render the final blood vessel region onto a black and white binary image, calculate the centerline set of the black and white binary image, and obtain the radius and length of all centerlines based on the centerline set.

[0011] A further improvement is that the specific method for acquiring the vascular region of several consecutive frames of original images in the microcirculation video and caching it into the vascular sequence in step S1 includes:

[0012] Step S10: Extract a frame of original image from the microcirculation video as the current frame original image, and initialize the blood vessel sequence size to 0;

[0013] Step S11: Determine whether the extracted original image of the current frame is clear. If yes, proceed to step S12. If no, clear the blood vessel sequence, reset the blood vessel sequence size to 0, and extract the next frame original image as the current frame original image and re-execute step S11.

[0014] Step S12: Obtain the blood vessel region of the original image of the current frame and cache it in the blood vessel sequence, incrementing the blood vessel sequence size by 1;

[0015] Step S13: Determine whether the size of the blood vessel sequence has reached the preset threshold. If it has, proceed to step S2. If it has not, retrieve the next frame of the original image as the current frame of the original image and return to step S11.

[0016] A further improvement is that the specific method for obtaining the blood vessel region of the original image of the current frame and caching it to the blood vessel sequence in step S12 includes:

[0017] Step S120: Perform mean filtering on the extracted original image of the current frame to obtain a mean-blurred image;

[0018] Step S121: Use the extracted original image of the current frame and the corresponding mean blurred image to perform dynamic threshold segmentation to obtain the blood vessel region of the original image of the current frame and cache it to the blood vessel sequence.

[0019] A further improvement is that the preset threshold is half the size of the original image sequence of the micro-circulation video.

[0020] A further improvement is that the dynamic threshold segmentation process includes setting two main parameters: the first parameter is either a higher or lower grayscale, and the second parameter is the grayscale segmentation threshold.

[0021] A further improvement is that the first parameter is a lower gray level, the gray level segmentation threshold is X, and the gray level of the original image of the current frame is subtracted pixel by pixel from the gray level of the corresponding mean blurred image to extract the relatively prominent low gray level pixel region where the gray level difference between the original image of the current frame and the corresponding mean blurred image is between [-X, 0).

[0022] Secondly, the present invention provides a microcirculation image vascular region extraction device, the device comprising:

[0023] The acquisition module is used to acquire the vascular region of several consecutive frames of raw images in the microcirculation video and cache them into the vascular sequence;

[0024] The merging module is used to merge the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region.

[0025] Thirdly, the present invention provides an electronic device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement a method for extracting blood vessel regions from microcirculation images as described in any one of the first aspects.

[0026] Fourthly, the present invention provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform a method for extracting blood vessel regions from microcirculation images as described in any one of the first aspects.

[0027] The beneficial effects of this invention are:

[0028] This invention provides a method for extracting blood vessel regions from microcirculation images. By inputting a microcirculation video with minimal jitter, several blood vessel regions in the original image sequence are obtained and then merged into a final blood vessel region. This method can, to some extent, correct the inaccuracy of single-frame calculations and eliminate or balance data errors caused by incomplete or excessive deformation of blood vessel regions due to flow or jitter as much as possible. The extracted blood vessels are more complete and accurate, and the results obtained are more scientifically reliable and objective. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1This is an overall flowchart of a method for extracting blood vessel regions from microcirculation images according to the present invention;

[0031] Figure 2 This is a flowchart illustrating the specific method of the present invention for acquiring the vascular region of several consecutive frames of original images in microcirculation video and caching it into a vascular sequence.

[0032] Figure 3 This is a flowchart illustrating the specific method of obtaining the vascular region of the original image of the current frame and caching it into a vascular sequence according to the present invention.

[0033] Figure 4 This is a schematic diagram of a single frame of the original image in the micro-loop video of this invention;

[0034] Figure 5 For the present invention Figure 4 A schematic diagram of the image after mean filtering;

[0035] Figure 6 This is an image showing the effect of vascular region extraction in this invention;

[0036] Figure 7 This is a structural diagram of a microcirculation image vascular region extraction device according to the present invention;

[0037] Figure 8 This is a schematic diagram of an electronic device according to the present invention. Detailed Implementation

[0038] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0040] Please refer to the attached document. Figure 1 -Appendix Figure 8 ,like Figure 1 As shown, the first aspect of this invention proposes a method for extracting blood vessel regions from microcirculation images, comprising the following steps:

[0041] Step S1: Input the original microcirculation video, traverse its image sequence, obtain the vascular region of several consecutive frames of original images in the microcirculation video and cache it into the vascular sequence;

[0042] Microcirculation, specifically the blood circulation within the capillaries between arterioles and venules, is the most basic structural and functional unit of the circulatory system. It includes the circulation of body fluids within arterioles, venules, lymphatic capillaries, and tissue channels. The microcirculation video can be captured manually using a handheld in vivo microscope during monitoring.

[0043] In microcirculation images, red blood cells can be observed as independent, low-grayscale continuous regions by the naked eye, while other liquids or backgrounds are generally non-prominent high-grayscale regions. Therefore, during processing, the relatively low-grayscale and relatively independent pixel regions resolved from the image can be considered as red blood cells.

[0044] Step S2: Merge the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region.

[0045] It should be noted that merging the vascular regions of several frames of the original images in the vascular sequence to obtain the final vascular region can eliminate and balance the data errors caused by incomplete or excessive deformation of the vascular region due to flow or jitter as much as possible.

[0046] In some embodiments, step S2 is followed by:

[0047] Step S3: Render the final blood vessel region onto a black and white binary image, calculate the centerline set of the black and white binary image, and obtain the radius and length of all centerlines based on the centerline set.

[0048] It should be noted that by merging the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region through the aforementioned steps S1 and S2, the accuracy of subsequent calculations of the vascular region can be improved. For example, the final vascular region can be rendered into a black and white binary image, the center line set of the black and white binary image can be calculated, and the radius and length of all center lines can be obtained based on the center line set.

[0049] In this embodiment, as Figure 2 As shown, the specific method for acquiring the vascular region of several consecutive frames of original images in the microcirculation video and caching it into the vascular sequence in step S1 includes:

[0050] Step S10: Extract a frame of original image from the microcirculation video as the current frame original image, and initialize the blood vessel sequence size to 0;

[0051] Step S11: Determine whether the extracted original image of the current frame is clear. If yes, proceed to step S12. If no, clear the blood vessel sequence, reset the blood vessel sequence size to 0, and extract the next frame original image as the current frame original image and re-execute step S11.

[0052] Step S12: Obtain the blood vessel region of the original image of the current frame and cache it in the blood vessel sequence, incrementing the blood vessel sequence size by 1;

[0053] Step S13: Determine whether the size of the blood vessel sequence has reached the preset threshold. If it has, stop traversing the image sequence and execute step S2. If it has not, take the next frame of the original image as the current frame of the original image and return to step S11.

[0054] It should be noted that image sharpness is an important indicator of image quality. The method used in this invention to determine whether the extracted original image of the current frame is sharp can employ the Brenner gradient function. The Brenner gradient function is the simplest gradient evaluation function; it simply calculates the square of the gray-level difference between two adjacent pixels. Of course, those skilled in the art can choose other sharpness evaluation methods according to actual needs.

[0055] In this invention, the purpose of determining whether the size of the blood vessel sequence has reached a preset threshold is to execute step S2 if it has, and to retrieve the next frame of the original image as the current frame of the original image and return to step S11 if it has not. This is to obtain enough blood vessel regions from consecutive frames of the original image, merge the blood vessel regions from multiple frames of the original image into a single region, and further improve the accuracy of the final blood vessel region.

[0056] Clearing the vascular sequence refers to clearing the vascular region from the multiple frames of original images accumulated in the vascular sequence.

[0057] Furthermore, in this embodiment, the specific method for obtaining the vascular region of the original image of the current frame and caching it to the vascular sequence in step S12 includes:

[0058] Step S120: Perform mean filtering on the extracted original image of the current frame to obtain a mean-blurred image;

[0059] It should be noted that mean filtering refers to making the gray level of all pixels within a matrix the average value. Assuming the original image I has dimensions (w, h), and given a matrix M of dimensions (x, y), where x is greater than 0 and less than w, and y is greater than 0 and less than h, a matrix M is generated. Starting from the origin (0, 0) at the top left corner of I, the matrix is ​​traversed pixel by pixel from left to right and from top to bottom. At each step, all pixels within M are set to the average gray level of M.

[0060] Mean filtering can make the gray levels of each pixel in a mean-blurred image more similar, thus reducing the overall contrast of the image. When some areas of the original image in the current frame are more sharp, the corresponding parts in the mean-blurred image obtained after mean filtering will be weakened.

[0061] Step S121: Use the extracted original image of the current frame and the corresponding mean blurred image to perform dynamic threshold segmentation to obtain the blood vessel region of the original image of the current frame and cache it to the blood vessel sequence.

[0062] like Figure 4 The image shown is a schematic diagram of a single frame of the original image in the micro-loop video of this invention. Figure 5 For the present invention Figure 4 A schematic diagram of the image after mean filtering. Figure 6 This is an image showing the effect of extracting the blood vessel region according to the present invention.

[0063] In this embodiment, the preset threshold is half the size of the original image sequence of the micro-circulation video.

[0064] The dynamic threshold segmentation process includes setting two main parameters: the first parameter is either a higher grayscale 'light' or a lower grayscale 'dark', and the second parameter is the grayscale segmentation threshold.

[0065] In this embodiment, assuming the first parameter is a lower grayscale 'dark', the grayscale segmentation threshold is X, and the value of X is 5, by subtracting the grayscale of each pixel from the original image of the current frame and the corresponding mean blurred image, the relatively prominent low grayscale pixel region with a grayscale difference between the original image of the current frame and the corresponding mean blurred image in the range of [-5, 0) can be identified.

[0066] A second aspect of this invention provides a device for extracting blood vessel regions from microcirculation images, see [link to relevant documentation]. Figure 7This is a schematic diagram of a microcirculation image vascular region extraction device provided in an embodiment of the present invention, which corresponds to the microcirculation image vascular region extraction method provided in the above embodiment of the present invention. Since the microcirculation image vascular region extraction device provided in this embodiment corresponds to the microcirculation image vascular region extraction method provided in the above embodiment of the present invention, the implementation method of the aforementioned microcirculation image vascular region extraction method is also applicable to the microcirculation image vascular region extraction device provided in this embodiment.

[0067] Specifically, such as Figure 7 As shown, a microcirculation image vascular region extraction device includes:

[0068] The acquisition module 100 is used to acquire the vascular region of several consecutive frames of raw images in the microcirculation video and cache it into the vascular sequence;

[0069] The merging module 200 is used to merge the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region.

[0070] Furthermore, the acquisition module specifically includes:

[0071] The image acquisition unit is used to extract a frame of original image from the microcirculation video as the original image of the current frame and initialize the blood vessel sequence size to 0;

[0072] The sharpness determination unit is used to determine whether the extracted original image of the current frame is clear. If it is, it is sent to the blood vessel region acquisition unit for processing. If not, the blood vessel sequence is cleared, the blood vessel sequence size is reset to 0, and the next frame original image is extracted as the current frame original image and sent back to the sharpness determination unit for processing.

[0073] Blood vessel region acquisition unit: Acquires the blood vessel region of the original image of the current frame and caches it in the blood vessel sequence, incrementing the blood vessel sequence size by 1;

[0074] The second judgment unit is used to determine whether the size of the blood vessel sequence has reached a preset threshold. If it has, the traversal of the image sequence is stopped and the image is handed over to the merging module for processing. If it has not reached the threshold, the next frame of the original image is taken out as the original image of the current frame and handed over to the sharpness judgment unit for processing.

[0075] Specifically, the vascular region acquisition unit includes:

[0076] The mean filtering processing subunit is used to perform mean filtering processing on the extracted original image of the current frame to obtain a mean blurred image;

[0077] The dynamic threshold segmentation processing subunit is used to perform dynamic threshold segmentation processing on the extracted original image of the current frame and the corresponding mean blurred image to obtain the blood vessel region of the original image of the current frame;

[0078] The cache subunit is used to cache the vascular region to the vascular sequence.

[0079] See Figure 8 The present invention also provides an electronic device and a computer-readable storage medium.

[0080] like Figure 8 The diagram illustrates an electronic device according to an embodiment of the present invention. This electronic device includes a processor 11, a memory 12, and a computer program stored in the memory and executable on the processor 11. When the processor 11 executes the computer program, it implements the steps described in the embodiment of the microcirculation image vascular region extraction method. Alternatively, when the processor 11 executes the computer program, it implements the functions of each module / unit in the above-described device embodiments.

[0081] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor 11 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0082] The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the schematic diagram is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0083] The processor 11 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0084] The memory 12 can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system 121, at least one application program 122 required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0085] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0086] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for extracting vascular regions from microcirculation images, characterized in that, Includes the following steps: Step S1: Obtain the vascular region from several consecutive frames of raw images in the microcirculation video and cache it in the vascular sequence. Specific methods include: Step S10: Extract a frame of original image from the microcirculation video as the current frame original image, and initialize the blood vessel sequence size to 0; Step S11: Determine whether the extracted original image of the current frame is clear. If yes, proceed to step S12. If no, clear the blood vessel sequence, reset the blood vessel sequence size to 0, and extract the next frame original image as the current frame original image and re-execute step S11. Step S12: Obtain the blood vessel region of the original image of the current frame and cache it to the blood vessel sequence, including: Step S120: Perform mean filtering on the extracted original image of the current frame to obtain a mean blurred image; the mean filtering process makes the gray level of each pixel in the mean blurred image similar, reducing the overall contrast of the image. When the sharpness of some areas in the original image of the current frame is relatively prominent, the corresponding part in the mean blurred image obtained after mean filtering will be weakened. Step S121: Use the extracted original image of the current frame and the corresponding mean blurred image to perform dynamic threshold segmentation to obtain the blood vessel region of the original image of the current frame and cache it to the blood vessel sequence, and increment the blood vessel sequence size by 1; The dynamic threshold segmentation process includes: setting two main parameters, the first parameter being a lower gray level and the second parameter being a gray level segmentation threshold, wherein the gray level segmentation threshold is X; subtracting the gray level of each pixel from the original image of the current frame and the corresponding mean blurred image; and parsing out the relatively prominent low gray level pixel regions where the gray level difference between the original image of the current frame and the corresponding mean blurred image is between [-X, 0). Step S13: Determine whether the size of the blood vessel sequence has reached the preset threshold. If it has, proceed to step S2. If it has not, retrieve the next frame of the original image as the current frame of the original image and return to step S11. Step S2: Merge the vascular regions of several frames of original images in the vascular sequence into a single region to obtain the final vascular region.

2. The method for extracting blood vessel regions from microcirculation images according to claim 1, characterized in that, The process following step S2 also includes: Step S3: Render the final blood vessel region onto a black and white binary image, calculate the centerline set of the black and white binary image, and obtain the radius and length of all centerlines based on the centerline set.

3. The method for extracting blood vessel regions from microcirculation images according to claim 1, characterized in that, The preset threshold is half the size of the original image sequence of the micro-circulation video.

4. A device for extracting vascular regions from microcirculation images, characterized in that, A method for extracting blood vessel regions from microcirculation images according to any one of claims 1-3 includes: The acquisition module is used to acquire the vascular region of several consecutive frames of raw images in the microcirculation video and cache them into the vascular sequence; The merging module is used to merge the vascular regions of several frames of original images in the vascular sequence to obtain the final vascular region.

5. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements a method for extracting blood vessel regions from microcirculation images as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform a method for extracting blood vessel regions from microcirculation images as described in any one of claims 1 to 3.

Images