WO2024078556A1 - 微循环图像清晰度评价方法、装置、设备及存储介质 - Google Patents

微循环图像清晰度评价方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2024078556A1
WO2024078556A1 PCT/CN2023/124143 CN2023124143W WO2024078556A1 WO 2024078556 A1 WO2024078556 A1 WO 2024078556A1 CN 2023124143 W CN2023124143 W CN 2023124143W WO 2024078556 A1 WO2024078556 A1 WO 2024078556A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
microcirculation
frame
clarity
blood vessel
Prior art date
Application number
PCT/CN2023/124143
Other languages
English (en)
French (fr)
Inventor
李宗熹
周春景
罗晓川
黄大兴
Original Assignee
广州医软智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州医软智能科技有限公司 filed Critical 广州医软智能科技有限公司
Publication of WO2024078556A1 publication Critical patent/WO2024078556A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/026—Measuring blood flow
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection

Definitions

  • the present application relates to the technical field of medical image processing, and in particular to a method, device, equipment and storage medium for evaluating the clarity of microcirculation images.
  • Microcirculation is the blood circulation in the capillaries between arterioles and venules, and is the most basic structural and functional unit in the circulatory system. Microcirculation includes the circulation of body fluids in arterioles, venules, capillary lymphatic vessels and tissue ducts. Every organ and every tissue cell in the human body needs to be provided with oxygen and nutrients by microcirculation, as well as energy transmission, information exchange, and the elimination of carbon dioxide and metabolic waste. Microcirculation reflects the physiological state and physiological changes of the human body, and studies have confirmed that inconsistencies between systemic circulation and microcirculation changes indicate organ dysfunction and poor prognosis.
  • HVM hand-held living microscope
  • the image processing method for microcirculation imaging is to manually click the collected video when the hand-held living microscope lens shakes little or is stable, and extract several single-frame images that are subjectively considered to have good quality from the collected video for analysis.
  • this method may select some images with problems such as artificial jitter and large brightness changes due to manual judgment errors, thereby affecting the quality of vascular imaging.
  • the purpose of the present application includes providing a method for evaluating the clarity of microcirculation images, which can be used to evaluate the clarity of each frame of the image when manually capturing a moving image during or after recording, filter out parts of the image with poor (unqualified) quality, and assist in improving the recognition accuracy of the vascular area and the accuracy of the calculation results.
  • the present application provides a method for evaluating the clarity of a microcirculation image, comprising the following steps:
  • the step of evaluating the clarity of the microcirculation image frame according to the statistical results includes:
  • the number of edges whose continuous edge pixel lengths in the frame of microcirculation image exceed the specified threshold does not reach the preset threshold, it means that the blood vessel density of the frame of microcirculation image is insufficient, and the frame of microcirculation image is directly determined to be unclear and abandoned.
  • the specified threshold is 70px and the preset threshold is 8.
  • the method further comprises:
  • the step of rating the clarity of the frame of microcirculation image comprises:
  • the frame of microcirculation image is rated according to the sharpness of the edge of the blood vessel region. The sharper the edge, the clearer the frame of microcirculation image.
  • the step of rating the frame of microcirculation image according to the sharpness of the edge of the blood vessel region comprises:
  • the edge of the blood vessel region is skeletonized, and the first cumulative value is obtained by accumulating pixels of the skeletonized microcirculation image.
  • the second cumulative value is obtained by accumulating pixels of the microcirculation image from which the edge of the blood vessel region has been extracted but the skeletonization has not been performed.
  • the second cumulative value is ratioed to the first cumulative value, and the sharpness is obtained according to the ratio result.
  • the frame of microcirculation image is rated according to the sharpness, wherein the closer the ratio result is to 1, the sharper the edge is.
  • the step of skeletonizing the edge of the blood vessel region includes:
  • a conversion process is performed on some pixel points at the edge of the blood vessel region in each identification frame, so that the pixel points after the conversion process are consistent with the pixel points of the background region of the blood vessel region.
  • the step of performing conversion processing on some pixel points at the edge of the blood vessel region in each of the identification frames includes:
  • the determined pixel points at the edge position are transformed.
  • the rating is divided into high-quality clarity and medium-quality clarity. If the ratio result is between 1-1.3, it is determined to be high-quality clarity, and if the ratio result is not between 1-1.3, it is determined to be medium-quality clarity.
  • the present application embodiment provides a microcirculation image clarity evaluation device, comprising:
  • An acquisition module configured to acquire a frame of microcirculation image to be evaluated for image clarity
  • An extraction module configured to extract a blood vessel region and an edge of the blood vessel region
  • a statistics module configured to count the number of edges whose continuous edge pixel length exceeds a specified threshold
  • the evaluation module is configured to evaluate the clarity of the microcirculation image frame according to the statistical results of the statistical module.
  • the device further comprises:
  • the rating module is configured to rate the clarity of the frame of microcirculation image when the number of edges whose continuous edge pixel lengths exceed a specified threshold reaches a preset threshold.
  • the rating module includes:
  • a skeletonization processing unit configured to perform skeletonization processing on the edge of the blood vessel region
  • a calculation unit configured to accumulate pixels of the skeletonized microcirculation image to obtain a first cumulative value and to accumulate pixels of the microcirculation image from which the edge of the vascular region has been extracted but the skeletonization has not been performed to obtain a second cumulative value;
  • the ratio operation unit is configured to perform a ratio operation on the second cumulative value and the first cumulative value, obtain sharpness according to the ratio result, and rate the frame of microcirculation image according to the sharpness, wherein the closer the ratio result is to 1, the sharper the edge.
  • an embodiment of the present application proposes an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the microcirculation image clarity evaluation method as described in any one of the first aspects is implemented.
  • an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the microcirculation image clarity evaluation method as described in any one of the first aspects.
  • the embodiment of the present application provides a method, device, equipment and storage medium for evaluating the clarity of microcirculation images, which evaluates and rates the clarity of microcirculation images based on the vascular density and the sharpness of the edges of the vascular regions in the microcirculation images, and can avoid the situation where only part of the image is in focus due to artificial jitter and is still judged to be clear, and the calculation efficiency is high. Based on this solution, by evaluating the clarity of each frame during or after the recording process, the part of the image with poor quality can be filtered out, which can help improve the recognition of the vascular region and improve the accuracy of the calculation results.
  • FIG1 is a flow chart of a method for evaluating the clarity of a microcirculation image provided in an embodiment of the present application
  • FIG2 is a flow chart of another implementation of a method for evaluating microcirculation image clarity provided in an embodiment of the present application
  • FIG3 is a flow chart of a method for rating a frame of microcirculation image according to the sharpness of the edge of a blood vessel region in a method for evaluating the clarity of a microcirculation image provided by an embodiment of the present application;
  • FIG4 is a diagram of blood vessels with continuous edge pixel length exceeding 70px screened out from a frame of microcirculation image provided by an embodiment of the present application. Edge schematic diagram;
  • FIG5 is a flow chart of a method for skeletonizing the edge of a blood vessel region in a method for evaluating the clarity of a microcirculation image provided in an embodiment of the present application;
  • FIG6 is a flow chart of a method for converting pixels in a method for evaluating the clarity of a microcirculation image provided in an embodiment of the present application;
  • FIG7 is a schematic diagram of the blood vessel edge after skeletonization in FIG4 ;
  • FIG8 is a schematic structural diagram of a microcirculation image clarity evaluation device provided in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of an electronic device provided in an embodiment of the present application.
  • Step S1 Acquire a frame of microcirculation image to be evaluated for image clarity.
  • microcirculation is the blood circulation in the capillaries between arterioles and venules, and is the most basic structural and functional unit in the circulatory system.
  • Microcirculation includes the circulation of body fluids in arterioles, venules, capillary lymphatic vessels and tissue ducts.
  • the microcirculation image can be obtained by manually operating a handheld live microscope to shoot a video during the monitoring process, and then intercepting it from the captured video.
  • Step S2 extracting the blood vessel region and the edge of the blood vessel region.
  • step S3 the specific method of extracting the blood vessel region and the edge of the blood vessel region belongs to the prior art, and those skilled in the art can refer to the prior art.
  • the improvement of the present application is mainly the content of step S3 and step S4.
  • Step S3 Count the number of edges whose continuous edge pixel length exceeds a specified threshold.
  • the continuous edge pixel length refers to the length of an uninterrupted edge of a blood vessel region, and in this embodiment, the number of edges whose continuous edge pixel length exceeds the specified threshold is counted mainly to determine the blood vessel density in the microcirculation image of this frame. The subsequent research on the microcirculation image with insufficient blood vessel density is of little significance.
  • Step S4 Evaluate the clarity of the microcirculation image frame according to the statistical results.
  • the method for evaluating the clarity of the microcirculation image frame according to the statistical results includes:
  • the specified threshold value may be 70px
  • the preset threshold value may be 8.
  • the specified threshold value and the preset threshold value are data obtained by the inventor based on years of experience and multiple experimental evaluations.
  • those skilled in the art may also appropriately adjust the values of the specified threshold value and the preset threshold value according to actual needs, and these adjustments are within the protection scope of this embodiment.
  • px (pixel) is the smallest point in an image, and a bitmap is made up of these points.
  • blood vessel edges with continuous edge pixel length exceeding 70px are screened out in one frame of microcirculation image.
  • the number of blood vessel edges with continuous edge pixel length exceeding 70px in this frame of microcirculation image is more than 8, so it can be confirmed that the blood vessel density in this frame of microcirculation image is sufficient, and this frame of microcirculation image can be retained for further clarity judgment.
  • the method further includes:
  • step S5 is executed: further rating the clarity of the frame of microcirculation image.
  • rating refers to further classification of image clarity.
  • the method for rating the clarity of the frame of microcirculation image includes:
  • the frame of microcirculation image is rated according to the sharpness of the edge of the blood vessel region.
  • the sharper the edge the clearer the frame of microcirculation image. Therefore, the frame of microcirculation image can be further divided into clarity according to the sharpness of the edge of the blood vessel region.
  • the method for implementing the rating of the frame of microcirculation image according to the sharpness of the edge of the blood vessel region includes:
  • Step S51 skeletonize the edge of the blood vessel region.
  • Step S52 accumulating pixels of the skeletonized microcirculation image to obtain a first accumulated value.
  • Step S53 accumulating pixels of the microcirculation image from which the edge of the vascular region has been extracted but skeletonization has not been performed to obtain a second cumulative value, performing a ratio operation on the second cumulative value and the first cumulative value, obtaining sharpness according to the ratio result, and rating the frame of microcirculation image according to the sharpness.
  • skeletonization refers to the process of removing some points from the original microcirculation image layer by layer, but still maintaining the original shape until the skeleton of the image is obtained.
  • the skeleton can be understood as the central axis of the object, for example, the skeleton of a rectangle is its central axis in the long direction, the skeleton of a square is its center point, the skeleton of a circle is its center point, the skeleton of a straight line is itself, and the skeleton of an isolated point is also itself.
  • the step of skeletonizing the edge of the blood vessel region can be implemented in the following manner:
  • Step S511 using a plurality of identification frames of set lengths to frame the edges of the blood vessel region in sequence.
  • Step S512 performing conversion processing on some pixel points at the edge of the blood vessel region in each identification frame, so that the converted pixel points are consistent with the pixel points in the background region of the blood vessel region.
  • the identification frame can be understood as a rectangular frame that can frame a part of the edge of the blood vessel area.
  • the set length can be set according to actual needs. For example, if the set length is set to be larger, the edge of a certain blood vessel area can be framed with a smaller number of identification frames. If the set length is set to be smaller, a larger number of identification frames are required to frame the edge of the same blood vessel area.
  • the edge of the blood vessel region is generally not a straight line, it is necessary to use a plurality of identification frames to frame the edge.
  • the plurality of identification frames are sequentially arranged along the edge of the blood vessel region to frame the edge.
  • the pixel points in the edge of each identification frame may be processed. Some pixel points in each identification frame may be transformed so that the transformed pixel points are consistent with the pixel points in the background region of the blood vessel region, for example, the pixel values of the pixel points are consistent. It can be understood that some pixel points in each identification frame are removed.
  • the step of performing conversion processing on some pixel points at the edge of the blood vessel region within each identification frame can be implemented in the following manner:
  • Step S5121 dividing the pixel points at the edge of the blood vessel region into a plurality of groups of pixel points in a marking direction perpendicular to the length direction of the marking frame.
  • Step S5122 Determine the pixel points in each group of pixel points that are located at the edge position in the marked direction.
  • Step S5123 transform the pixel points determined to be located at the edge position.
  • the identification frame can be understood as a rectangular frame, and the length direction of the identification frame is the direction of the longer side.
  • the identification direction perpendicular to the length direction is the width direction of the identification frame, which can be understood as the direction perpendicular to the edge of the blood vessel region.
  • each identification frame can be further divided into multiple groups of pixels from the identification direction.
  • each identification frame defines multiple pixels, and the multiple pixels are divided into multiple groups according to the identification direction, and the pixels in each group have the same coordinates in the length direction and only have coordinate differences in the identification direction.
  • the pixels at the edge position have little effect on the original shape of the blood vessel area. Therefore, some of the pixels at the edge position can be transformed, and the pixels after the transformation are consistent with the pixels in the background area, that is, some of the pixels at the edge position are removed.
  • a ratio operation is performed on the first cumulative value of the pixel point after the skeletonization process and the second cumulative value of the pixel point before the skeletonization process to obtain the sharpness.
  • the rating can be divided into high-quality clarity and medium-quality clarity. If the ratio result is between 1-1.3, the frame of microcirculation image is determined to be of high-quality clarity. If the ratio result is not between 1-1.3, the frame of microcirculation image is determined to be of medium-quality clarity.
  • FIG. 4 is the blood vessel edge image of the microcirculation image before skeletonization processing
  • FIG. 7 is the blood vessel edge image of the microcirculation image of FIG. 4 after skeletonization processing.
  • the present application evaluates and rates the clarity of microcirculation images based on the vascular density and the sharpness of the edges of the vascular regions in the microcirculation images, which can avoid the situation where only part of the image is in focus due to human jitter and is still judged to be clear, and has high computational efficiency.
  • the present application provides a method for evaluating the clarity of microcirculation images, which can filter out parts of the image with poor quality by evaluating the clarity of each frame during or after recording, thereby assisting in improving the recognition of vascular areas and improving the accuracy of calculation results.
  • the embodiment of the present application also proposes a microcirculation image clarity evaluation device.
  • Figure 8 is a structural schematic diagram of a microcirculation image clarity evaluation device provided in accordance with the embodiment of the present application, which corresponds to a microcirculation image clarity evaluation method provided in the above-mentioned embodiment of the present application. Since the microcirculation image clarity evaluation device provided in the embodiment of the present application corresponds to the microcirculation image clarity evaluation method provided in the above-mentioned embodiment of the present application, the implementation method of the above-mentioned microcirculation image clarity evaluation method is also applicable to the microcirculation image clarity evaluation device provided in the present embodiment.
  • the microcirculation image clarity evaluation device comprises:
  • An acquisition module 10 is configured to acquire a frame of microcirculation image to be evaluated for image clarity
  • An extraction module 20 configured to extract a blood vessel region and an edge of the blood vessel region
  • a statistics module 30 configured to count the number of edges whose continuous edge pixel length exceeds a specified threshold
  • An evaluation module 40 is configured to evaluate the clarity of the microcirculation image of the frame according to the statistical results of the statistical module
  • the rating module 50 is configured to rate the clarity of the frame of microcirculation image when the number of edges whose continuous edge pixel lengths exceed a specified threshold reaches a preset threshold.
  • the rating module includes:
  • a skeletonization processing unit configured to perform skeletonization processing on the edge of the blood vessel region
  • a calculation unit configured to accumulate pixels of the skeletonized microcirculation image to obtain a first accumulated value and to accumulate pixels of the microcirculation image from which the edge of the vascular region has been extracted but the skeletonization has not been performed to obtain a second accumulated value;
  • the ratio operation unit is configured to perform a ratio operation on the second cumulative value and the first cumulative value, obtain sharpness according to the ratio result, and rate the frame of microcirculation image according to the sharpness.
  • an embodiment of the present application also provides an electronic device and a computer-readable storage medium.
  • FIG9 is a schematic diagram of an electronic device provided in an embodiment of the present application.
  • the electronic device of this embodiment includes: a processor 11, a memory 12, and a computer program stored in the memory and executable on the processor 11.
  • the processor 11 executes the computer program, the steps in the above-mentioned microcirculation image clarity evaluation method embodiment are implemented.
  • the processor 11 executes the computer program, the functions of each module/unit in the above-mentioned device embodiments are implemented.
  • 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 application.
  • the one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device.
  • the electronic device may include, but is not limited to, a processor and a memory.
  • a processor and a memory.
  • the electronic device may include more or fewer components than shown in the diagram, or may combine certain components, or different components.
  • the electronic device may also include an input/output device, a network access device, a bus, etc.
  • the processor 11 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be The microprocessor or the processor may also be any conventional processor, etc.
  • the processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.
  • the memory 12 may be configured to store the computer program and/or module, and the processor implements various functions of the electronic device by running or executing the computer program and/or module stored in the memory, and calling the data stored in the memory.
  • the memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system 121, an application 122 required for at least one function (such as a sound playback function, an 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, a phone book, etc.), etc.
  • the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.
  • a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.
  • a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash
  • the module/unit integrated in the electronic device can be stored in a computer-readable storage medium.
  • the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor.
  • the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.
  • the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.
  • the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Hematology (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Image Analysis (AREA)

Abstract

本申请涉及图像处理技术领域，尤其涉及一种微循环图像清晰度评价方法、装置、设备及存储介质，一种微循环图像清晰度评价方法包括以下步骤：获取一帧待进行图像清晰度评价的微循环图像并提取血管区域及血管区域的边缘；对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；根据统计结果对该帧微循环图像清晰度进行评价。本申请基于微循环图像中的血管密度和血管区域边缘锐利度对微循环图像的清晰度进行评价和评级，可规避由于人为抖动产生的图像中只有部分对焦成功，还被判断为清晰的情况，且计算效率较高，本申请在录制过程中，或录制完成后，通过评价每帧的清晰度，过滤掉图像质量太差的部分，辅助提高血管区域的识别和提高计算结果精度。

Description

微循环图像清晰度评价方法、装置、设备及存储介质
相关申请的交叉引用
本申请要求于2022年10月13日提交中国专利局的申请号为202211253754.9、名称为“微循环图像清晰度评价方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及医学图像处理技术领域，尤其涉及一种微循环图像清晰度评价方法、装置、设备及存储介质。
背景技术
微循环是微动脉与微静脉之间毛细血管中的血液循环，是循环系统中最基层的结构和功能单位。微循环包括微动脉、微静脉、毛细淋巴管和组织管道内的体液循环。人体中每个器官、每个组织细胞均要由微循环提供氧气、养料，以及传递能量、交流信息、排除二氧化碳及代谢废物等。微循环反应人体的生理状态与生理变化，且已有研究证实体循环与微循环改变不一致预示着器官功能障碍和不良预后。
目前手持活体显微镜(Hand held living microscope，HVM)的应用实现了微循环的可视化，利用手持活体显微镜进行监测的过程中，需要人为操作手持活体显微镜进行视频拍摄，基于拍摄到的视频得到微循环血管成像图片。目前传统处理方式中，对于微循环成像的图像处理方法是在人工判断手持活体显微镜的镜头晃动小或稳定时手动点击所采集的视频，从采集的视频中截取主观上认为质量较好的几张单帧图像进行分析。但是，这种方式会因为人工的判断误差导致可能选择了人为抖动、亮度变化大等存在问题的一些图像，从而影响了血管成像的质量。
申请内容
本申请的目的包括，提供一种微循环图像清晰度评价方法，可以在录制过程中或录制完成后人工截取动图时，通过评价每帧图像的清晰度，过滤掉图像质量太差(不合格)的部分，辅助提高血管区域的识别精度和提高计算结果精度。
为实现本申请的目的，采用以下技术方案：
第一方面，本申请实施例提出一种微循环图像清晰度评价方法，包括以下步骤：
获取一帧待进行图像清晰度评价的微循环图像并提取血管区域及血管区域的边缘；
对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；
根据统计结果对该帧微循环图像清晰度进行评价。
可选地，所述根据统计结果对该帧微循环图像清晰度进行评价的步骤，包括：
如果该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量没达到预设阈值，则说明该帧微循环图像的血管密度不足够，直接判定该帧微循环图像为不清晰并放弃该帧微循环图像。
可选地，所述指定阈值为70px，所述预设阈值为8。
可选地，所述方法还包括：
若该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值，则进一步对该帧微循环图像的清晰度进行评级。
可选地，所述对该帧微循环图像的清晰度进行评级的步骤，包括：
根据血管区域的边缘的锐利度对该帧微循环图像进行评级，边缘越锐利，则代表该帧微循环图像越清晰。
可选地，所述根据血管区域的边缘的锐利度对该帧微循环图像进行评级的步骤，包括：
对血管区域的边缘进行骨骼化处理，对骨骼化处理后的微循环图像进行像素点累计得到第一累计值，对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值，将第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级，其中，比值结果越接近1，则代表边缘越锐利。
可选地，所述对血管区域的边缘进行骨骼化处理的步骤，包括：
采用多个设定长度的标识框依次框定血管区域的边缘；
针对各所述标识框内的血管区域的边缘的部分像素点进行转化处理，使得转化处理后的像素点与血管区域的背景区域的像素点一致。
可选地，所述针对各所述标识框内的血管区域的边缘的部分像素点进行转化处理的步骤，包括：
以与所述标识框的长度方向相垂直的标识方向将血管区域的边缘的像素点划分为多组像素点；
确定出各组像素点中在所述标识方向上位于边缘位置的像素点；
将确定出的位于边缘位置的像素点进行转化处理。
可选地，评级划分为高质量清晰度和中质量清晰度，若比值结果在1-1.3之间则判定为高质量清晰度，若比值结果不在1-1.3之间则判定为中质量清晰度。
第二方面，本申请实施例提出一种微循环图像清晰度评价装置，包括：
获取模块，配置成获取一帧待进行图像清晰度评价的微循环图像；
提取模块，配置成提取血管区域及血管区域的边缘；
统计模块，配置成对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；
评价模块，配置成根据统计模块的统计结果对该帧微循环图像清晰度进行评价。
可选地，所述装置还包括：
评级模块，配置成当连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值时对该帧微循环图像的清晰度进行评级。
可选地，所述评级模块包括：
骨骼化处理单元，配置成对血管区域的边缘进行骨骼化处理；
计算单元，配置成对骨骼化处理后的微循环图像进行像素点累计得到第一累计值以及对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值；
比值运算单元，配置成对第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级，其中，比值结果越接近1，则代表边缘越锐利。
第三方面，本申请实施例提出一种电子设备，包括处理器、存储器以及存储在所述存储器中且被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时实现如第一方面中任意一项所述的微循环图像清晰度评价方法。
第四方面，本申请实施例提出一种计算机可读存储介质，所述计算机可读存储介质包括存储的计算机程序，其中，在所述计算机程序运行时控制所述计算机可读存储介质所在设备执行如第一方面中任意一项所述的微循环图像清晰度评价方法。
本申请的有益效果：
本申请实施例提供一种微循环图像清晰度评价方法、装置、设备及存储介质，基于微循环图像中的血管密度和血管区域边缘锐利度对微循环图像的清晰度进行评价和评级，可规避由于人为抖动产生的图像中只有部分对焦成功，还被判断为清晰的情况，且计算效率较高。基于该方案可以在录制过程中或录制完成后，通过评价每帧的清晰度，过滤掉图像质量太差的部分，辅助提高血管区域的识别和提高计算结果精度。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种微循环图像清晰度评价方法的流程图；
图2为本申请实施例提供的一种微循环图像清晰度评价方法另一实现方式的流程图；
图3为本申请实施例提供的一种微循环图像清晰度评价方法中根据血管区域的边缘的锐利度对该帧微循环图像进行评级的方法的流程图；
图4为本申请实施例提供的从一帧微循环图像中筛选出的连续的边缘像素长度超过70px的血管 边缘示意图；
图5为本申请实施例提供的一种微循环图像清晰度评价方法中对血管区域的边缘进行骨骼化处理的方法的流程图；
图6为本申请实施例提供的一种微循环图像清晰度评价方法中对像素点进行转化处理的方法的流程图；
图7为图4骨骼化处理后的血管边缘示意图；
图8为本申请实施例提供的一种微循环图像清晰度评价装置结构示意图；
图9为本申请实施例提供的一种电子设备的示意图。
具体实施方式
以为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及它们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
请参考附图1-附图7，本申请实施例第一方面提出一种微循环图像清晰度评价方法，如图1所示，包括以下步骤：
步骤S1：获取一帧待进行图像清晰度评价的微循环图像。
其中，微循环是微动脉与微静脉之间毛细血管中的血液循环，是循环系统中最基层的结构和功能单位。微循环包括微动脉、微静脉、毛细淋巴管和组织管道内的体液循环。所述微循环图像可以通过手持活体显微镜在监测过程中人为操作手持活体显微镜进行视频拍摄，并从拍摄到的视频中截取得到。
步骤S2：提取血管区域及血管区域的边缘。
需要说明的是，提取血管区域及血管区域的边缘的具体方法属于现有技术，本领域技术人员参考现有技术即可。本申请的改进点主要是步骤S3和步骤S4的内容。
步骤S3：对连续的边缘像素长度超过指定阈值的边缘的数量进行统计。
需要说明的是，连续的边缘像素长度是指不间断的一条血管区域边缘的长度，而本实施例中对连续的边缘像素长度超过指定阈值的边缘的数量进行统计主要是为了判断该帧微循环图像中的血管密度，血管密度不足的微循环图像后续的研究意义不大。
步骤S4：根据统计结果对该帧微循环图像清晰度进行评价。
在本实施例中，根据统计结果对该帧微循环图像清晰度进行评价的实现方法包括：
如果该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量没达到预设阈值，则说明该帧微循环图像的血管密度不足够，可直接判定该帧微循环图像为不清晰并放弃该帧微循环图像。
具体地，在本实施例中，所述指定阈值可为70px，所述预设阈值可为8。所述指定阈值和所述预设阈值为发明人多年经验积累以及多次实验评估所得出的数据。当然，本领域技术人员也可以根据实际需要适当调整所述指定阈值和预设阈值的大小，而这些调整均属于本实施例的保护范围之内。
需要说明的是，px(pixel)是一张图片中最小的点，一张位图就是由这些点构成的。
如图4所示为其中一帧微循环图像中筛选出的连续的边缘像素长度超过70px的血管边缘，从图4中可以看出，该帧微循环图像中连续的边缘像素长度超过70px的血管边缘的数量是超过8条的，因此可以确认这帧微循环图像中血管密度是足够的，可以保留这帧微循环图像进行进一步的清晰度判断。
在本申请的一些实施例中，如图2所示，在步骤S4根据统计结果对该帧微循环图像清晰度进行评价之后，上述方法还包括：
若该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值，则执行步骤S5：进一步对该帧微循环图像的清晰度进行评级。
其中，评级是指对图像的清晰度进行进一步的划分。
在本实施例中，对该帧微循环图像的清晰度进行评级的实现方法包括：
根据血管区域的边缘的锐利度对该帧微循环图像进行评级，边缘越锐利，则代表该帧微循环图像越清晰。因此可以根据血管区域的边缘的锐利度对该帧微循环图像进行进一步的清晰度划分。
可选地，如图3所示，根据血管区域的边缘的锐利度对该帧微循环图像进行评级的实现方法包括：
步骤S51：对血管区域的边缘进行骨骼化处理。
步骤S52：对骨骼化处理后的微循环图像进行像素点累计得到第一累计值。
步骤S53：对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值，将第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级。
其中，比值运算(第二累计值/第一累计值)的比值结果越接近1，则代表边缘越锐利。
需要说明的是，骨骼化处理是指经过一层层的剥离，从原来的微循环图像中去掉一些点，但仍要保持原来的形状，直到得到图像的骨架的处理方式。其中，骨架可以理解为物体的中轴，例如一个长方形的骨架是它的长方向上的中轴线，正方形的骨架是它的中心点，圆的骨架是它的圆心，直线的骨架是它自身，孤立点的骨架也是自身。
本实施例中，如图5所示，对血管区域的边缘进行骨骼化处理的步骤，可以通过以下方式实现：
步骤S511：采用多个设定长度的标识框依次框定血管区域的边缘。
步骤S512：针对各标识框内的血管区域的边缘的部分像素点进行转化处理，使得转化处理后的像素点与血管区域的背景区域的像素点一致。
本实施例中，标识框可以理解为可以框定血管区域的边缘的一部分的矩形框，所述设定长度可以根据实际需求进行设定，例如，将设定长度设置得较大，对于某个血管区域的边缘则可以利用较少数量的标识框进行框定，若将设定长度设置得较小，则对于同一血管区域的边缘则需要利用较多数量的标识框进行框定。
由于血管区域的边缘一般并非呈直线，因此，需要利用多个标识框进行框定，该多个标识框沿着血管区域的边缘依次排列以对边缘进行框定。
在对血管区域的边缘进行骨骼化处理时，则可针对每一个标识框内的边缘中的像素点进行处理。可以对每个标识框内的部分像素点进行转化处理，使得转化后的像素点与血管区域的背景区域的像素点一致，例如，像素点的像素值一致。可以理解为将每个标识框内的部分像素点进行去除处理。
本实施例中，如图6所示，针对各个标识框内的血管区域的边缘的部分像素点进行转化处理的步骤，可以通过以下方式实现：
步骤S5121：以与标识框的长度方向相垂直的标识方向将血管区域的边缘的像素点划分为多组像素点。
步骤S5122：确定出各组像素点中在标识方向上位于边缘位置的像素点。
步骤S5123：将确定出的位于边缘位置的像素点进行转化处理。
本实施例中，标识框可以理解为矩形框，标识框的长度方向即为较长边所在的方向。与长度方向相垂直的标识方向即为标识框的宽度方向，可以理解为垂直于血管区域的边缘的方向。
为了更为细节化的处理，可以再将每个标识框内的像素点从标识方向划分为多组像素点。例如可以理解为每个标识框框定了多个像素点，将该多个像素点按照标识方向划分为多组，每一组中的像素点具有相同的长度方向的坐标、仅在标识方向上具有坐标差异。
对于每一组中的像素点，处于边缘位置的像素点对于血管区域的原本形状影响不大，因此，可以将处于边缘位置的部分像素点进行转化处理，而转化处理后的像素点与背景区域中的像素点保持一致，也即，将处于边缘位置的部分像素点进行去除处理。
通过以上方式完成骨骼化处理之后，将骨骼化处理后的像素点的第一累计值以及骨骼化处理前的像素点的第二累计值进行比值运算进而得到锐利度。
进一步地，评级可以划分为高质量清晰度和中质量清晰度，若比值结果在1-1.3之间则判定该帧微循环图像为高质量清晰度，若比值结果不在1-1.3之间则判定该帧微循环图像为中质量清晰度。
如图4所示为其中一帧微循环图像中筛选出的连续的边缘像素长度超过70px的血管边缘，图4是未进行骨骼化处理前的微循环图像的血管边缘图像，而图7为图4经过骨骼化处理后的微循环图像的血管边缘图像。
本申请基于微循环图像中的血管密度和血管区域边缘锐利度对微循环图像的清晰度进行评价和评级，可规避由于人为抖动产生的图像中只有部分对焦成功，还被判断为清晰的情况，且计算效率较高。
本申请提供的一种微循环图像清晰度评价方法，可以在录制过程中，或录制完成后，通过评价每帧的清晰度，过滤掉图像质量太差的部分，辅助提高血管区域的识别和提高计算结果精度。
本申请实施例还提出一种微循环图像清晰度评价装置，参见图8，是本申请实施例对应提供的一种微循环图像清晰度评价装置的结构示意图，与上述本申请实施例提供的一种微循环图像清晰度评价方法相对应，由于本申请实施例提供的一种微循环图像清晰度评价装置与上述本申请实施例提供的一种微循环图像清晰度评价方法相对应，因此在前述一种微循环图像清晰度评价方法的实施方式也适用于本实施例提供的一种微循环图像清晰度评价装置。
具体地，所述一种微循环图像清晰度评价装置包括：
获取模块10，配置成获取一帧待进行图像清晰度评价的微循环图像；
提取模块20，配置成提取血管区域及血管区域的边缘；
统计模块30，配置成对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；
评价模块40，配置成根据统计模块的统计结果对该帧微循环图像清晰度进行评价；
评级模块50，配置成当连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值时对该帧微循环图像的清晰度进行评级。
进一步地，所述评级模块包括：
骨骼化处理单元，配置成对血管区域的边缘进行骨骼化处理；
计算单元，配置成对骨骼化处理后的微循环图像进行像素点累计得到第一累计值以及对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值；
比值运算单元，配置成对第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级。
参见图9，本申请实施例还对应提供一种电子设备以及一种计算机可读存储介质。
如图9所示是本申请实施例提供的一种电子设备的示意图。该实施例的电子设备包括：处理器11、存储器12以及存储在所述存储器中并可在所述处理器11上运行的计算机程序。所述处理器11执行所述计算机程序时实现上述一种微循环图像清晰度评价方法实施例中的步骤。或者，所述处理器11执行所述计算机程序时实现上述各装置实施例中各模块/单元的功能。
示例性的，所述计算机程序可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器中，并由所述处理器11执行，以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述电子设备中的执行过程。
所述电子设备可包括，但不仅限于，处理器、存储器。本领域技术人员可以理解，所述示意图仅仅是电子设备的示例，并不构成对电子设备的限定，电子设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述电子设备还可以包括输入输出设备、网络接入设备、总线等。
所述处理器11可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是 微处理器或者该处理器也可以是任何常规的处理器等，所述处理器是所述电子设备的控制中心，利用各种接口和线路连接整个电子设备的各个部分。
所述存储器12可配置成存储所述计算机程序和/或模块，所述处理器通过运行或执行存储在所述存储器内的计算机程序和/或模块，以及调用存储在存储器内的数据，实现所述电子设备的各种功能。所述存储器可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统121、至少一个功能所需的应用程序122(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件或其他易失性固态存储器件。
其中，所述电子设备集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。
需说明的是，以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。另外，本申请提供的装置实施例附图中，模块之间的连接关系表示它们之间具有通信连接，具体可以实现为一条或多条通信总线或信号线。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (14)

  1. 一种微循环图像清晰度评价方法，其特征在于，包括以下步骤：
    获取一帧待进行图像清晰度评价的微循环图像并提取血管区域及血管区域的边缘；
    对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；
    根据统计结果对该帧微循环图像清晰度进行评价。
  2. 根据权利要求1所述的微循环图像清晰度评价方法，其特征在于，所述根据统计结果对该帧微循环图像清晰度进行评价的步骤，包括：
    如果该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量未达到预设阈值，则说明该帧微循环图像的血管密度不足够，直接判定该帧微循环图像为不清晰并放弃该帧微循环图像。
  3. 根据权利要求2所述的微循环图像清晰度评价方法，其特征在于，所述指定阈值为70px，所述预设阈值为8。
  4. 根据权利要求2所述的微循环图像清晰度评价方法，其特征在于，所述方法还包括：
    若该帧微循环图像中连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值，则进一步对该帧微循环图像的清晰度进行评级。
  5. 根据权利要求4所述的微循环图像清晰度评价方法，其特征在于，所述对该帧微循环图像的清晰度进行评级的步骤，包括：
    根据血管区域的边缘的锐利度对该帧微循环图像进行评级，边缘越锐利，则代表该帧微循环图像越清晰。
  6. 根据权利要求5所述的微循环图像清晰度评价方法，其特征在于，所述根据血管区域的边缘的锐利度对该帧微循环图像进行评级的步骤，包括：
    对血管区域的边缘进行骨骼化处理，对骨骼化处理后的微循环图像进行像素点累计得到第一累计值，对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值，将第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级，其中，比值结果越接近1，则代表边缘越锐利。
  7. 根据权利要求6所述的微循环图像清晰度评价方法，其特征在于，所述对血管区域的边缘进行骨骼化处理的步骤，包括：
    采用多个设定长度的标识框依次框定血管区域的边缘；
    针对各所述标识框内的血管区域的边缘的部分像素点进行转化处理，使得转化处理后的像素点与血管区域的背景区域的像素点一致。
  8. 根据权利要求7所述的微循环图像清晰度评价方法，其特征在于，所述针对各所述标识框内的血管区域的边缘的部分像素点进行转化处理的步骤，包括：
    以与所述标识框的长度方向相垂直的标识方向将血管区域的边缘的像素点划分为多组像素点；
    确定出各组像素点中在所述标识方向上位于边缘位置的像素点；
    将确定出的位于边缘位置的像素点进行转化处理。
  9. 根据权利要求6所述的微循环图像清晰度评价方法，其特征在于，评级划分为高质量清晰度和中质量清晰度，若比值结果在1-1.3之间则判定为高质量清晰度，若比值结果不在1-1.3之间则判定为中质量清晰度。
  10. 一种微循环图像清晰度评价装置，其特征在于，包括：
    获取模块，配置成获取一帧待进行图像清晰度评价的微循环图像；
    提取模块，配置成提取血管区域及血管区域的边缘；
    统计模块，配置成对连续的边缘像素长度超过指定阈值的边缘的数量进行统计；
    评价模块，配置成根据统计模块的统计结果对该帧微循环图像清晰度进行评价。
  11. 根据权利要求10所述的微循环图像清晰度评价装置，其特征在于，所述装置还包括：
    评级模块，配置成当连续的边缘像素长度超过指定阈值的边缘的数量达到预设阈值时对该帧微循环图像的清晰度进行评级。
  12. 根据权利要求11所述的微循环图像清晰度评价装置，其特征在于，所述评级模块包括：
    骨骼化处理单元，配置成对血管区域的边缘进行骨骼化处理；
    计算单元，配置成对骨骼化处理后的微循环图像进行像素点累计得到第一累计值以及对已提取血管区域的边缘但未进行骨骼化处理的微循环图像进行像素点累计得到第二累计值；
    比值运算单元，配置成对第二累计值与第一累计值进行比值运算，根据比值结果得到锐利度，并根据锐利度对该帧微循环图像进行评级，其中，比值结果越接近1，则代表边缘越锐利。
  13. 一种电子设备，其特征在于，包括处理器、存储器以及存储在所述存储器中且被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1至9中任意一项所述的微循环图像清晰度评价方法。
  14. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质包括存储的计算机程序，其中，在所述计算机程序运行时控制所述计算机可读存储介质所在设备执行如权利要求1至9中任意一项所述的微循环图像清晰度评价方法。
PCT/CN2023/124143 2022-10-13 2023-10-12 微循环图像清晰度评价方法、装置、设备及存储介质 WO2024078556A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211253754.9 2022-10-13
CN202211253754.9A CN115690003A (zh) 2022-10-13 2022-10-13 微循环图像清晰度评价方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024078556A1 true WO2024078556A1 (zh) 2024-04-18

Family

ID=85064840

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/124143 WO2024078556A1 (zh) 2022-10-13 2023-10-12 微循环图像清晰度评价方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115690003A (zh)
WO (1) WO2024078556A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115690003A (zh) * 2022-10-13 2023-02-03 广州医软智能科技有限公司 微循环图像清晰度评价方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100104168A1 (en) * 2007-01-11 2010-04-29 Intellectual Property Mvm B.V. Measurement of functional microcirculatory geometry and velocity distributions using automated image analysis
US20190183315A1 (en) * 2016-09-30 2019-06-20 Fujifilm Corporation Processor device, endoscope system, and method of operating processor device
CN113379702A (zh) * 2021-06-08 2021-09-10 广州医软智能科技有限公司 一种微循环图像的血管路径提取方法及装置
CN113421254A (zh) * 2021-07-20 2021-09-21 广州医软智能科技有限公司 微循环血管分支长度和直径计算方法及装置和终端设备
CN115690003A (zh) * 2022-10-13 2023-02-03 广州医软智能科技有限公司 微循环图像清晰度评价方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100104168A1 (en) * 2007-01-11 2010-04-29 Intellectual Property Mvm B.V. Measurement of functional microcirculatory geometry and velocity distributions using automated image analysis
US20190183315A1 (en) * 2016-09-30 2019-06-20 Fujifilm Corporation Processor device, endoscope system, and method of operating processor device
CN113379702A (zh) * 2021-06-08 2021-09-10 广州医软智能科技有限公司 一种微循环图像的血管路径提取方法及装置
CN113421254A (zh) * 2021-07-20 2021-09-21 广州医软智能科技有限公司 微循环血管分支长度和直径计算方法及装置和终端设备
CN115690003A (zh) * 2022-10-13 2023-02-03 广州医软智能科技有限公司 微循环图像清晰度评价方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN115690003A (zh) 2023-02-03

Similar Documents

Publication Publication Date Title
WO2024078556A1 (zh) 微循环图像清晰度评价方法、装置、设备及存储介质
WO2019223069A1 (zh) 基于直方图的虹膜图像增强方法、装置、设备及存储介质
US8180180B2 (en) Method for magnifying images and videos
CN111507994A (zh) 一种人像提取方法、人像提取装置及移动终端
CN108615236A (zh) 一种图像处理方法及电子设备
CN108765343A (zh) 图像处理的方法、装置、终端及计算机可读存储介质
CN109035138B (zh) 会议记录方法、装置、设备和存储介质
CN110176002B (zh) 一种x射线图像的病灶检测方法及终端设备
TWI310528B (en) Image edge filtering
CN110765799B (zh) 客户端扫码识别方法、装置、设备及存储介质
WO2024051429A1 (zh) 细胞扫描图像的获取方法和装置
CN108765264A (zh) 图像美颜方法、装置、设备及存储介质
CN110266946A (zh) 一种拍照效果自动优化方法、装置、存储介质及终端设备
CN110853071A (zh) 图像编辑方法及终端设备
CN116208586B (zh) 一种低延时医疗影像数据传输方法及系统
Chen et al. Human guided ground-truth generation for realistic image super-resolution
CN107277381A (zh) 摄像头对焦方法和装置
CN110838088B (zh) 一种基于深度学习的多帧降噪方法、装置及终端设备
CN106803246A (zh) 图像质量评价方法、装置及设备
CN111953888B (zh) 暗光成像方法、装置、计算机可读存储介质及终端设备
CN108876767B (zh) 一种甘蔗蔗节特征快速识别装置
CN113409375B (zh) 图像处理方法、装置以及非易失性存储介质
WO2023019681A1 (zh) 一种图像内容的提取方法、装置、终端和存储介质
TW200949759A (en) Image processing apparatus and method
CN113114934B (zh) 尿红细胞多焦距视频采集方法与系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23876756

Country of ref document: EP

Kind code of ref document: A1