Blood sampling method and system
By monitoring the blood images in the blood collection tube in real time and analyzing the liquid surface line, and identifying blood pixels using the HSV color space and European distance threshold, the precise control problem in existing blood collection technology is solved, and the precise control and difference elimination of blood collection volume is achieved.
Patent Information
- Application Number
- CN202411286160.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-06
AI Technical Summary
The existing blood collection technology is difficult to achieve precise control, resulting in the problem of differences in blood collection volume and the dependence of professional skills level on manual judgment.
By monitoring the blood images in the blood collection tube in real time, analyzing the blood surface line, and stopping the collection when the preset scale is reached, blood pixels are identified using the HSV color space and European distance thresholds, and blood images are constructed and noise-reduced to determine the liquid surface Wire.
Accurate control of blood collection volume is achieved, the impact of the difference in vacuum between the zone and blood collection vessels is eliminated, and the accuracy of blood collection is improved.
Smart Images

Figure CN119073985A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of blood collection, and more specifically, to a blood collection method and system. Background Art
[0002] In the current blood collection system, the blood collection components play a key role. They include a blood collection tube fixing unit for fixing the blood collection tube, and a blood collection needle fixing unit for fixing the blood collection needle. The blood collection needle fixing unit moves toward the blood collection tube fixing unit, prompting the blood collection needle to pierce the cap of the blood collection tube, and blood collection begins with the help of the negative pressure of the blood collection tube. After blood collection is completed, the blood collection needle fixing unit moves away from the blood collection tube fixing unit to guide the blood collection needle out of the cap of the blood collection tube.
[0003] There are currently two main methods of blood collection. One is passive blood collection based on the vacuum degree of the blood collection tube until the tube can no longer absorb blood. The other is to rely on the naked eye to judge the amount of blood collected, thereby manually terminating the blood collection action. However, the passive blood collection method based on the vacuum degree of the blood collection tube has obvious defects. Since the vacuum degree of each blood collection tube is different and is affected by factors such as altitude, the amount of blood that can be collected by each blood collection tube is different, which easily leads to excessive or insufficient blood collection. The method of manually judging the amount of blood collected and terminating the blood collection action is limited by the level of manual professional skills, and it is difficult to achieve precise control of the amount of blood collected.
[0004] Therefore, how to draw blood accurately is a difficult problem that needs to be solved urgently in the field of blood collection technology. Summary of the invention
[0005] In view of the above problems, the present application provides a blood sampling method and system to improve the accuracy of blood sampling.
[0006] In order to achieve the above objectives, the specific plan is proposed as follows:
[0007] A blood sampling method, comprising:
[0008] During the process of collecting blood into the blood collection tube, real-time monitoring of the blood image in the blood collection tube;
[0009] Analyzing the blood image to obtain the blood level in the blood collection tube;
[0010] When the blood liquid level reaches the preset scale line of the blood collection tube, the blood collection is stopped.
[0011] Optionally, the blood image is an RGB color image;
[0012] The step of analyzing the blood image to obtain the blood level line in the blood collection tube includes:
[0013] Convert each pixel of the blood image from RGB value to HSV three-dimensional value;
[0014] For each pixel of the blood image, based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template, the HSV Euclidean distance of the pixel is calculated, and if the HSV Euclidean distance of the pixel is greater than a preset Euclidean distance threshold, the pixel is determined to be a blood pixel;
[0015] constructing a blood image according to each blood pixel;
[0016] Performing noise reduction processing on the blood image to obtain a noise-reduced blood image;
[0017] Acquire the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image;
[0018] A circumscribed rectangle of the blood outer contour is constructed, and the upper top edge of the circumscribed rectangle in the vertical direction is determined to be the blood level line in the blood collection tube.
[0019] Optionally, performing noise reduction processing on the blood image to obtain a noise-reduced blood image includes:
[0020] Based on a preset grayscale threshold, roughly screening out a blood area from the blood image;
[0021] determining a rough outer contour of the blood region;
[0022] The noise points within the rough outer contour are filled to obtain a denoised blood image.
[0023] Optionally, the process of determining the HSV three-dimensional value of the blood template includes:
[0024] Acquire a plurality of sample blood images, and extract each sample blood pixel in each sample blood image;
[0025] For each blood pixel of the sample, extract the HSV three-dimensional value of the blood pixel of the sample;
[0026] The blood template HSV three-dimensional value is determined according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
[0027] A blood collection system includes a blood collection component, an image collection module, a judgment processing module and a control processing module;
[0028] The image acquisition module is used to monitor the blood image in the blood collection tube in real time during the process of the blood collection component collecting blood into the blood collection tube;
[0029] The judgment processing module is used to analyze the blood image to obtain the blood level in the blood collection tube, so as to judge whether the blood level reaches the preset scale line of the blood collection tube;
[0030] The control processing module is used to control the blood collection component to stop collecting the blood when the blood liquid level reaches the preset scale line.
[0031] Optionally, the judgment processing module includes:
[0032] A color conversion module, used for converting each pixel of the blood image from an RGB value to an HSV three-dimensional value;
[0033] a blood pixel determination module, configured to calculate, for each pixel of the blood image, the HSV Euclidean distance of the pixel based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template, and determine that the pixel is a blood pixel if the HSV Euclidean distance of the pixel is greater than a preset Euclidean distance threshold;
[0034] A blood image construction module, used for constructing a blood image according to each blood pixel;
[0035] A noise reduction processing module, used for performing noise reduction processing on the blood image to obtain a noise-reduced blood image;
[0036] A blood outer contour extraction module, used for obtaining the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image;
[0037] The blood liquid level determination module is used to construct a circumscribed rectangle of the blood outer contour and determine the upper top edge of the circumscribed rectangle in the vertical direction as the blood liquid level in the blood collection tube.
[0038] Optionally, the noise reduction processing module includes:
[0039] A first noise reduction processing submodule, configured to roughly screen out a blood area from the blood image based on a preset grayscale threshold;
[0040] A second noise reduction processing submodule is used to determine a rough outer contour of the blood area;
[0041] The third noise reduction processing submodule is used to fill the noise points within the rough outer contour to obtain a noise-reduced blood image.
[0042] Optionally, the blood collection system further includes:
[0043] A sample blood image acquisition module, used for acquiring a plurality of sample blood images and extracting each sample blood pixel in each sample blood image;
[0044] A sample pixel HSV three-dimensional value extraction module, used for extracting the HSV three-dimensional value of each sample blood pixel;
[0045] The blood template HSV three-dimensional value determination module is used to determine the blood template HSV three-dimensional value according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
[0046] Optionally, the blood collection assembly includes a blood collection tube fixing unit and a blood collection needle fixing unit, and the blood collection needle fixing unit includes a blood collection needle;
[0047] The blood collection tube fixing unit is used to fix the blood collection tube;
[0048] The blood collection needle fixing unit is used to be driven by the control processing module to approach the blood collection tube fixing unit when the blood collection system receives a blood collection instruction, so as to guide the blood collection needle to pierce the cap of the blood collection tube and collect blood under the negative pressure of the blood collection tube.
[0049] Optionally, the image acquisition module includes a high-precision module camera, a high-definition lens, a customized shadowless light source and an image acquisition card.
[0050] By means of the above technical solution, the present application monitors the blood image in the blood collection tube in real time during the process of collecting blood into the blood collection tube, analyzes the blood image to obtain the blood level in the blood collection tube, and stops collecting blood when the blood level reaches the preset scale line of the blood collection tube. It can be seen that since the preset scale line is defined according to local environmental factors, collecting blood to the preset scale line can eliminate the defects of different differences in different zones and different vacuum degrees of the blood collection tube, and can accurately control the blood collection volume by monitoring the blood collection process, thereby achieving accurate blood collection. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0052] Figure 1 A schematic diagram of a flow chart of a blood sampling method provided in an embodiment of the present application;
[0053] Figure 2 A schematic diagram of converting a blood RGB image into an HSV image provided in an embodiment of the present application;
[0054] Figure 3A schematic diagram of constructing a blood image based on an HSV image provided in an embodiment of the present application;
[0055] Figure 4 A schematic diagram of denoising a blood image provided in an embodiment of the present application;
[0056] Figure 5 A schematic diagram of extracting the outer contour of a blood denoised image provided in an embodiment of the present application;
[0057] Figure 6 A schematic diagram of a liquid level line extraction of a blood contour image provided in an embodiment of the present application;
[0058] Figure 7 A schematic diagram of the module structure of a system for implementing blood sampling provided in an embodiment of the present application. DETAILED DESCRIPTION
[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0060] The present application scheme can be implemented based on a terminal with data processing capabilities, and the terminal can be a blood collection system. The waste disposal system can include a blood collection component, an image acquisition module, a judgment processing module, and a control processing module. Among them, the blood collection component can be used to collect blood, the image acquisition module can be used to monitor the blood level change image of the blood collection tube in real time during the blood collection process, the judgment processing module can be used to judge in real time whether the blood level reaches the preset scale line on the blood collection tube, and the control processing module can control whether the blood collection component collects blood.
[0061] Next, combine Figure 1 The blood collection method of the present application may include the following steps:
[0062] Step S110: During the process of collecting blood into the blood collection tube, the blood image in the blood collection tube is monitored in real time.
[0063] Specifically, monitoring and obtaining blood images can be achieved by an image acquisition module, wherein the image acquisition module may include a high-precision module camera, a high-definition lens, a customized shadowless light source, and an image acquisition card. The lens of the image acquisition module can be pre-aligned with the blood collection tube. When the blood collection component starts to collect blood, the image acquisition module starts to work and records the blood collection tube to obtain a large number of images.
[0064] The blood collection assembly may include a blood collection tube fixing unit and a blood collection needle fixing unit. The blood collection needle fixing unit may include a blood collection needle.
[0065] The blood collection tube fixing unit can be used to fix the blood collection tube. When the blood collection system receives a blood collection instruction, the blood collection needle fixing unit can be driven by the control processing module to approach the blood collection tube fixing unit to guide the blood collection needle to pierce the cap of the blood collection tube and collect blood under the negative pressure of the blood collection tube.
[0066] Step S120: Analyze the blood image to obtain the blood level in the blood collection tube.
[0067] Specifically, the judgment processing module can analyze the blood image to obtain the blood level in the blood collection tube, and judge whether the blood level reaches the preset scale line of the blood collection tube. The judgment processing module can immediately analyze each blood image to obtain the real-time blood level, and compare the height of the real-time blood level with the height of the preset scale line to judge whether the blood level reaches the preset scale line.
[0068] Step S130: When the blood level reaches the preset scale line of the blood collection tube, stop collecting blood.
[0069] Specifically, if the judgment processing module determines that the blood liquid level has reached the preset scale line, it can send a signal to the control processing module to stop collecting blood. The control processing module can then control the blood collection component to immediately stop blood collection to ensure that the current amount of collected blood just reaches the preset scale line of the blood collection tube, thereby achieving accurate blood collection.
[0070] The blood collection method provided in this embodiment monitors the blood image in the blood collection tube in real time during the process of collecting blood into the blood collection tube, analyzes the blood image to obtain the blood level in the blood collection tube, and stops collecting blood when the blood level reaches the preset scale line of the blood collection tube. It can be seen that since the preset scale line is defined according to local environmental factors, collecting blood to the preset scale line can eliminate the differences in different regions and the defects of different vacuum degrees of the blood collection tube, and can accurately control the blood collection volume by monitoring the blood collection process, thereby achieving accurate blood collection.
[0071] In some embodiments of the present application, the above step S120, the process of analyzing the blood image to obtain the blood level line in the blood collection tube, is further introduced. The blood image mentioned in the above embodiment may be an RGB color image. Based on this, the process may include:
[0072] S1201, convert each pixel of the blood image from RGB value to HSV three-dimensional value.
[0073] It is understandable that the RGB model is the most commonly used color space for color images and is often used for color display and image processing. The RGB model is composed of three primary colors, and the three components of the RGB color space are all closely related to brightness, that is, as long as the brightness changes, the three components will change accordingly. RGB images obtained in the natural environment are easily affected by natural light, occlusion, shadows, etc., that is, they are sensitive to brightness and cannot intuitively express the color of objects. HSV (Hue, Saturation, Value) is a color space created based on the intuitive characteristics of colors, also known as the Hexcone Model, with parameters of hue (H), saturation (S), and value (V). Therefore, compared with the RGB model, the HSV model is more in line with the way of describing colors, and thus more accurate results can be obtained by analyzing blood information through the HSV model.
[0074] Among them, the formula for converting the RGB model to the HSV model is as follows:
[0075] Let r, g, and b be the coordinates of the colors red, green, and blue respectively, and their values are between 0 and 1. Calculate the maximum value max = max(r, g, b), and the minimum value min = min(r, g, b).
[0076] Calculate the hue H:
[0077] If max = min, then H = 0;
[0078] If max = r and g ≥ b, then ;
[0079] If max = r and g < b, then ;
[0080] If max = g, then ;
[0081] If max = b, then ;
[0082] Calculate the saturation S:
[0083] If max = 0, then S = 0, rounded ;
[0084] Calculate the value V:
[0085] V = max
[0086] Specifically, according to the formula, the blood color can be converted from RGB to HSV, or the cvtColor function in opencv can be called, and the mode is selected as COLOR_RGB2HSV, both of which can achieve color conversion.
[0087] For example Figure 2 , Figure 2 The left side is the RGB color image, which is obtained after color conversion Figure 2 HSV image on the right.
[0088] S1202. For each pixel of the blood image, the HSV Euclidean distance of the pixel is calculated based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template. If the HSV Euclidean distance of the pixel is less than the preset Euclidean distance threshold, the pixel is determined to be a blood pixel.
[0089] Specifically, the three-dimensional value of the blood template HSV is , the HSV three-dimensional value of the pixel is , then the HSV Euclidean distance of the pixel is:
[0090]
[0091] Furthermore, the HSV Euclidean distance is compared with a preset Euclidean distance threshold to determine whether the pixel is blood.
[0092] Examples include Figure 3 When it is judged to be a blood pixel, the pixel is filled with white, otherwise it is filled with black as the background.
[0093] S1203: Construct a blood image based on each blood pixel.
[0094] Specifically, an image composed of white blood pixel dots is a blood image.
[0095] S1204: Perform noise reduction processing on the blood image to obtain a noise-reduced blood image.
[0096] Specifically, the noise reduction process may include:
[0097] S12041. Based on a preset grayscale threshold, roughly filter out the blood area from the blood image.
[0098] S12042. Determine the rough outer contour of the blood area.
[0099] S12043. Fill the noise points within the rough outer contour to obtain a denoised blood image.
[0100] Examples include Figure 4 ,Since the white area represents blood information, all the black points in the white area can be filled with white to achieve the effect of removing noise.
[0101] S1205 , obtaining the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image.
[0102] Examples include Figure 5 , Figure 5 The red line outside the white area on the right is the outer contour of the blood.
[0103] Specifically, all contour information in the blood denoised image can be extracted by using the findContours function, with the search mode set to RETR_EXTERNAL and the contour approximation method set to CHAIN_APPROX_NONE. The contourArea function is used to obtain the areas of all contours, and after area screening, the optimal contour is determined to be the blood outer contour.
[0104] S1206: construct a circumscribed rectangle of the blood outer contour, and determine that the upper edge of the circumscribed rectangle in the vertical direction is the blood level line in the blood collection tube.
[0105] Examples include Figure 6 , Figure 6 The green line on top of the white area on the right is the blood level.
[0106] Specifically, the boundingRect function is called from the blood outer contour point set information to obtain the contour circumscribed rectangle. The locLiquidLine function is used to locate the edge of the circumscribed rectangle with the minimum Y value as the liquid surface line L1, and the maximum Y value as the reference line L0.
[0107] The blood sampling method provided in this embodiment performs color conversion, blood pixel recognition, blood image reconstruction, denoising, contour extraction and liquid level extraction on the color RGB blood image, so that the blood level of the blood sampling tube in the image is more accurately recognized.
[0108] In some embodiments of the present application, the determination process of the HSV three-dimensional value of the blood template mentioned in the above embodiment is introduced, and the determination process may include:
[0109] S1. Acquire multiple sample blood images, and extract each sample blood pixel in each sample blood image.
[0110] S2. For each blood pixel of the sample, extract the HSV three-dimensional value of the blood pixel of the sample.
[0111] S3. Determine the HSV three-dimensional value of the blood template according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
[0112] It is understandable that the preparation of the blood template requires multiple sample blood image data to obtain the standard HSV three-dimensional value of the blood pixel. When the pixel is judged as blood, its HSV three-dimensional value can be compared with the standard HSV three-dimensional value, and the Euclidean distance can be calculated to obtain the difference between it and the standard HSV three-dimensional value. If the difference is too large, it can be judged as a non-blood pixel. If the difference is within the preset Euclidean distance threshold, it can be judged as a blood pixel.
[0113] The following is a description of a system for implementing blood collection provided in an embodiment of the present application. The system for implementing blood collection described below and the method for implementing blood collection described above can be referenced to each other.
[0114] See also Figure 7 , Figure 7 A schematic diagram of the structure of a system for implementing blood sampling disclosed in an embodiment of the present application.
[0115] like Figure 7 As shown, the system may include: a blood collection component 10, an image collection module 11, a judgment processing module 12 and a control processing module 13;
[0116] The image acquisition module 11 is used to monitor the blood image in the blood collection tube in real time during the process of the blood collection component 10 collecting blood into the blood collection tube;
[0117] The judgment processing module 12 is used to analyze the blood image to obtain the blood level in the blood collection tube, so as to judge whether the blood level reaches the preset scale line of the blood collection tube;
[0118] The control processing module 13 is used to control the blood collection component 10 to stop collecting the blood when the blood liquid level reaches the preset scale line.
[0119] Optionally, the judgment processing module includes:
[0120] A color conversion module, used for converting each pixel of the blood image from an RGB value to an HSV three-dimensional value;
[0121] a blood pixel determination module, configured to calculate, for each pixel of the blood image, the HSV Euclidean distance of the pixel based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template, and determine that the pixel is a blood pixel if the HSV Euclidean distance of the pixel is greater than a preset Euclidean distance threshold;
[0122] A blood image construction module, used for constructing a blood image according to each blood pixel;
[0123] A noise reduction processing module, used for performing noise reduction processing on the blood image to obtain a noise-reduced blood image;
[0124] A blood outer contour extraction module, used for obtaining the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image;
[0125] The blood liquid level determination module is used to construct a circumscribed rectangle of the blood outer contour and determine the upper top edge of the circumscribed rectangle in the vertical direction as the blood liquid level in the blood collection tube.
[0126] Optionally, the noise reduction processing module includes:
[0127] A first noise reduction processing submodule, configured to roughly screen out a blood area from the blood image based on a preset grayscale threshold;
[0128] A second noise reduction processing submodule is used to determine a rough outer contour of the blood area;
[0129] The third noise reduction processing submodule is used to fill the noise points within the rough outer contour to obtain a noise-reduced blood image.
[0130] Optionally, the blood collection system further includes:
[0131] A sample blood image acquisition module, used for acquiring a plurality of sample blood images and extracting each sample blood pixel in each sample blood image;
[0132] A sample pixel HSV three-dimensional value extraction module, used for extracting the HSV three-dimensional value of each sample blood pixel;
[0133] The blood template HSV three-dimensional value determination module is used to determine the blood template HSV three-dimensional value according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
[0134] Optionally, the blood collection assembly includes a blood collection tube fixing unit and a blood collection needle fixing unit, and the blood collection needle fixing unit includes a blood collection needle;
[0135] The blood collection tube fixing unit is used to fix the blood collection tube;
[0136] The blood collection needle fixing unit is used to be driven by the control processing module to approach the blood collection tube fixing unit when the blood collection system receives a blood collection instruction, so as to guide the blood collection needle to pierce the cap of the blood collection tube and collect blood under the negative pressure of the blood collection tube.
[0137] Optionally, the image acquisition module includes a high-precision module camera, a high-definition lens, a customized shadowless light source and an image acquisition card.
[0138] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0139] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.
[0140] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A blood sampling method, characterized in that: include: During the process of collecting blood into the blood collection tube, real-time monitoring of the blood image in the blood collection tube; Analyzing the blood image to obtain the blood level in the blood collection tube; When the blood liquid level reaches the preset scale line of the blood collection tube, the blood collection is stopped.
2. The blood sampling method according to claim 1, characterized in that: The blood image is an RGB color image; The step of analyzing the blood image to obtain the blood level line in the blood collection tube includes: Convert each pixel of the blood image from RGB value to HSV three-dimensional value; For each pixel of the blood image, based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template, the HSV Euclidean distance of the pixel is calculated, and if the HSV Euclidean distance of the pixel is greater than a preset Euclidean distance threshold, the pixel is determined to be a blood pixel; constructing a blood image according to each blood pixel; Performing noise reduction processing on the blood image to obtain a noise-reduced blood image; Acquire the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image; A circumscribed rectangle of the blood outer contour is constructed, and the upper top edge of the circumscribed rectangle in the vertical direction is determined to be the blood level line in the blood collection tube.
3. The method according to claim 2, characterized in that Performing noise reduction processing on the blood image to obtain a noise-reduced blood image includes: Based on a preset grayscale threshold, roughly screening out a blood area from the blood image; determining a rough outer contour of the blood region; The noise points within the rough outer contour are filled to obtain a denoised blood image.
4. The method according to claim 2, characterized in that: The process of determining the HSV three-dimensional value of the blood template includes: Acquire a plurality of sample blood images, and extract each sample blood pixel in each sample blood image; For each blood pixel of the sample, extract the HSV three-dimensional value of the blood pixel of the sample; The blood template HSV three-dimensional value is determined according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
5. A blood sampling system, characterized in that: It includes a blood collection component, an image collection module, a judgment processing module and a control processing module; The image acquisition module is used to monitor the blood image in the blood collection tube in real time during the process of the blood collection component collecting blood into the blood collection tube; The judgment processing module is used to analyze the blood image to obtain the blood level in the blood collection tube, so as to judge whether the blood level reaches the preset scale line of the blood collection tube; The control processing module is used to control the blood collection component to stop collecting the blood when the blood liquid level reaches the preset scale line.
6. The blood sampling system according to claim 5, characterized in that: The judgment processing module includes: A color conversion module, used for converting each pixel of the blood image from an RGB value to an HSV three-dimensional value; a blood pixel determination module, configured to calculate, for each pixel of the blood image, the HSV Euclidean distance of the pixel based on the HSV three-dimensional value of the pixel and the predetermined HSV three-dimensional value of the blood template, and determine that the pixel is a blood pixel if the HSV Euclidean distance of the pixel is greater than a preset Euclidean distance threshold; A blood image construction module, used for constructing a blood image according to each blood pixel; A noise reduction processing module, used for performing noise reduction processing on the blood image to obtain a noise-reduced blood image; A blood outer contour extraction module, used for obtaining the blood outer contour in the denoised blood image by extracting the blood connected domain in the denoised blood image; The blood liquid level determination module is used to construct a circumscribed rectangle of the blood outer contour and determine the upper top edge of the circumscribed rectangle in the vertical direction as the blood liquid level in the blood collection tube.
7. The blood sampling system according to claim 6, characterized in that: The noise reduction processing module comprises: A first noise reduction processing submodule, configured to roughly screen out a blood area from the blood image based on a preset grayscale threshold; A second noise reduction processing submodule is used to determine a rough outer contour of the blood area; The third noise reduction processing submodule is used to fill the noise points within the rough outer contour to obtain a noise-reduced blood image.
8. The blood sampling system according to claim 5, characterized in that: Also includes: A sample blood image acquisition module, used for acquiring a plurality of sample blood images and extracting each sample blood pixel in each sample blood image; A sample pixel HSV three-dimensional value extraction module, used for extracting the HSV three-dimensional value of each sample blood pixel; The blood template HSV three-dimensional value determination module is used to determine the blood template HSV three-dimensional value according to the HSV three-dimensional value of each sample blood pixel of each sample blood image.
9. The blood sampling system according to claim 5, characterized in that: The blood collection assembly comprises a blood collection tube fixing unit and a blood collection needle fixing unit, and the blood collection needle fixing unit comprises a blood collection needle; The blood collection tube fixing unit is used to fix the blood collection tube; The blood collection needle fixing unit is used to be driven by the control processing module to approach the blood collection tube fixing unit when the blood collection system receives a blood collection instruction, so as to guide the blood collection needle to pierce the cap of the blood collection tube and collect blood under the negative pressure of the blood collection tube.
10. The blood sampling system according to claim 5, characterized in that: The image acquisition module includes a high-precision module camera, a high-definition lens, a customized shadowless light source and an image acquisition card.
Citation Information
Patent Citations
Agglutination intensity interpretation method and device and blood type analyzer
CN115201464A
Retina hemorrhage area identification method and system
CN116665259A
Sample feeder
CN117031059A
Blood collection device and blood collection system
CN210961997U
Analyzer
JP2012159318A
Cited By
Blood collection device, blood collection method, and blood collection system
WO2026053590A1
