A rapid diagnostic device for intra-abdominal hemorrhage

Abstract

The present application provides a rapid diagnostic device for intra-abdominal bleeding, including an acquisition module, a preprocessing module, a segmentation module, a feature extraction module and a processing module. The acquisition module is used to acquire a sample image of accumulated blood. The preprocessing module is electrically connected to the acquisition module. The preprocessing module is used to preprocess the sample image of accumulated blood. The segmentation module is used to segment the sample image of accumulated blood. The feature extraction module is used to extract features from the blood sample and establish a feature-time sample regression equation. The processing module is used to compare the sample regression equation with the standard regression equation of vascular blood to determine whether the extracted accumulated blood is vascular blood, thereby determining whether intra-abdominal bleeding has occurred. The present application compares the sample regression equation with the standard regression equation of vascular blood to determine whether intra-abdominal bleeding has occurred. There is no need to determine whether the blood is coagulated by the naked eye, and there is no need to wait for 5 minutes. Therefore, it is possible to quickly determine whether intra-abdominal bleeding has occurred.

Description

Technical Field

[0001] The invention relates to the field of medical technology, and in particular to a rapid diagnosis device for intra-abdominal hemorrhage. Background Art

[0002] Intra-abdominal hemorrhage is a rapid, fatal disease, and common causes include ruptured ectopic pregnancy, corpus luteum rupture, liver and spleen rupture, etc. Currently, common methods for diagnosing intra-abdominal hemorrhage in women include abdominal B-ultrasound and transvaginal posterior fornix puncture. The disadvantages of abdominal B-ultrasound are that it is time-consuming, difficult to detect when the amount of bleeding is small, and difficult to distinguish from peritoneal effusion; transvaginal posterior fornix puncture uses body position to accumulate a small amount of bleeding in the lowest physiological point of the female pelvic cavity - the uterine rectal fossa. By transvaginal posterior fornix puncture to reach this point, the abdominal blood can be directly drawn out, but during the puncture operation, it may accidentally enter the blood vessels and draw out the blood in the blood vessels, thereby mistakenly judging the vascular blood as intra-abdominal bleeding, leading to misdiagnosis.

[0003] In clinic, it is generally judged whether the blood has entered the blood vessel by mistake, because the intra-abdominal bleeding does not coagulate, while the blood in the blood vessels can coagulate. However, it takes at least 5 minutes to judge whether the blood can coagulate by naked eyes. If it is intra-abdominal bleeding, the patient's continued bleeding during this waiting time can reach 1000-2000 ml, which can cause shock or even death. Therefore, rapid diagnosis of intra-abdominal bleeding is crucial to saving patients' lives. Summary of the invention

[0004] Based on this, the main purpose of the present invention is to provide a rapid diagnostic device for intra-abdominal bleeding that can quickly determine whether intra-abdominal bleeding occurs.

[0005] To achieve the above object, the present invention provides a rapid diagnosis device for intra-abdominal bleeding, comprising:

[0006] An acquisition module, used for acquiring an image of a blood sample;

[0007] A preprocessing module, electrically connected to the acquisition module, and configured to preprocess the blood accumulation sample image to improve the quality of the blood accumulation sample image;

[0008] a segmentation module, used for performing segmentation processing on the blood accumulation sample image to segment the blood sample in the blood accumulation sample image;

[0009] A feature extraction module, used to extract features from the blood sample and establish a feature-time sample regression equation; and

[0010] The processing module is used to compare the sample regression equation with the standard regression equation of vascular blood to determine whether the extracted accumulated blood is vascular blood, thereby determining whether intra-abdominal bleeding occurs.

[0011] Preferably, the feature extraction module is used to perform multiple feature extractions on the blood sample within a preset time.

[0012] Preferably, the preset time is 5-10s.

[0013] Preferably, the rapid diagnosis device for intra-abdominal bleeding further comprises a storage tray, which is disposed adjacent to the collection module and is used for holding accumulated blood.

[0014] Preferably, the rapid diagnostic device for intra-abdominal bleeding further comprises a lighting element, which is disposed adjacent to the storage tray and is used to illuminate the accumulated blood on the storage tray.

[0015] Preferably, the feature extraction module is also used to extract features from vascular blood samples and establish a standard regression equation for vascular blood.

[0016] Preferably, the preprocessing includes contrast enhancement, brightness correction and noise removal.

[0017] Preferably, the feature extraction includes texture feature extraction, the texture feature includes contrast, and the feature extraction module is used to perform multiple contrast feature extractions on the blood sample and construct a contrast-time regression curve, and then establish a contrast-time sample regression equation based on the contrast-time regression curve.

[0018] Preferably, the texture feature further includes at least one of an average value and an entropy.

[0019] Preferably, the feature extraction further includes at least one of RGB color space feature extraction and HSV color space feature extraction, and the parameters of the HSV color space include hue, saturation and brightness.

[0020] The technical solution of the present invention has the following advantages: when it is necessary to determine whether the person to be diagnosed has intra-abdominal bleeding, the puncture needle is inserted into the abdominal cavity of the person to be diagnosed through the posterior fornix of the vagina, and the accumulated blood is extracted; then, the accumulated blood sample image is acquired by the acquisition module; then, the accumulated blood sample image is pre-processed and segmented by the pre-processing module and the segmentation module; then, the feature extraction module is used to extract features of the blood sample, and a feature-time sample regression equation is established; finally, the sample regression equation is compared with the standard regression equation of vascular blood by the processing module; if the sample regression equation is consistent with the standard regression equation of vascular blood, If the sample regression equation does not match the standard regression equation for vascular blood, it means that the accumulated blood initially drawn is vascular blood, that is, during the puncture of the posterior vaginal fornix, a blood vessel was mistakenly punctured, and vascular blood was mistakenly drawn, so it cannot be determined as intra-abdominal bleeding. Then the posterior vaginal fornix is ​​punctured again, and the above steps are repeated. If the sample regression equation does not match the standard regression equation for vascular blood, it means that the accumulated blood drawn is blood in the abdominal cavity, that is, it means that intra-abdominal bleeding has occurred. In addition, if the extracted liquid does not contain blood at all when the accumulated blood is initially drawn from the abdominal cavity, it means that intra-abdominal bleeding has not occurred, and there is no need to perform subsequent steps. The present application is different from all prior arts. It creatively establishes a characteristic-time sample regression equation for the collected accumulated blood, and compares the sample regression equation with the standard regression equation for vascular blood, so as to determine whether intra-abdominal bleeding has occurred. There is no need to judge whether the blood is coagulated by the naked eye, and there is no need to wait for 5 minutes, so that it can quickly determine whether intra-abdominal bleeding has occurred. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the devices shown in these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of a diagnostic framework of a rapid diagnostic device for intra-abdominal bleeding according to an embodiment;

[0023] Figure 2 A diagnostic flow chart of a rapid diagnostic device for intra-abdominal bleeding according to an embodiment;

[0024] Figure 3 is a con (contrast)-time curve of vascular blood in one embodiment;

[0025] Figure 4 is an R (red) histogram of vascular blood according to an embodiment;

[0026] Figure 5 is a G (green) histogram of vascular blood according to an embodiment;

[0027] Figure 6 FIG. 1 is a B (blue) histogram of vascular blood according to an embodiment;

[0028] Figure 7 is a hue histogram of an embodiment;

[0029] Figure 8 FIG. 4 is a saturation histogram of an embodiment.

[0030] Among them, 100. acquisition module; 200. pre-processing module; 300. segmentation module; 400. feature extraction module; 500. processing module; 600. storage tray; 700. lighting component; 800. knowledge base.

[0031] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes A technical solution, B technical solution, and A and B technical solutions that meet both requirements. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0034] like Figure 1-2As shown, a rapid diagnosis device for intra-abdominal bleeding includes an acquisition module 100, a pre-processing module 200, a segmentation module 300, a feature extraction module 400 and a processing module 500. The acquisition module 100 is used to acquire a blood accumulation sample image. The pre-processing module 200 is electrically connected to the acquisition module 100. The pre-processing module 200 is used to pre-process the blood accumulation sample image to improve the quality of the blood accumulation sample image. The segmentation module 300 is used to segment the blood accumulation sample image to segment out the blood sample in the blood accumulation sample image. The feature extraction module 400 is used to extract features of the blood sample and establish a feature-time sample regression equation. The processing module 500 is used to compare the sample regression equation with the standard regression equation of vascular blood to determine whether the extracted blood accumulation is vascular blood, thereby determining whether intra-abdominal bleeding occurs. Specifically, before the acquisition module 100 acquires the blood accumulation sample image, it punctures the posterior fornix of the vagina with a puncture needle to extract the blood accumulation, and then the acquisition module 100 is aligned with the blood accumulation to acquire the blood accumulation sample image.

[0035] When it is necessary to determine whether the person to be diagnosed has intra-abdominal bleeding, the puncture needle is inserted into the abdominal cavity of the person to be diagnosed through the posterior fornix of the vagina, and the accumulated blood is extracted. Then, the acquisition module 100 acquires the accumulated blood sample image, and then the pre-processing module 200 and the segmentation module 300 perform pre-processing and segmentation processing on the accumulated blood sample image. Subsequently, the feature extraction module 400 extracts features from the blood sample, and establishes a feature-time sample regression equation. Finally, the processing module 500 compares the sample regression equation with the standard regression equation of vascular blood. If the sample regression equation is consistent with the standard regression equation of vascular blood, If the sample regression equation does not match the standard regression equation for vascular blood, it means that the accumulated blood initially drawn is vascular blood, that is, during the puncture of the posterior vaginal fornix, a blood vessel was mistakenly punctured, and vascular blood was mistakenly drawn, so it cannot be judged as intra-abdominal bleeding. Then the posterior vaginal fornix is ​​punctured again, and the above steps are repeated. If the sample regression equation does not match the standard regression equation for vascular blood, it means that the accumulated blood drawn is blood in the abdominal cavity, that is, it means that intra-abdominal bleeding has occurred. In addition, if the extracted liquid does not contain blood at all when the accumulated blood is initially drawn from the abdominal cavity, it means that intra-abdominal bleeding has not occurred, and there is no need to perform subsequent steps. The present application is different from all prior arts. It creatively establishes a characteristic-time sample regression equation for the collected accumulated blood, and compares the sample regression equation with the standard regression equation for vascular blood, so as to determine whether intra-abdominal bleeding has occurred. There is no need to judge whether the blood is coagulated by the naked eye, and there is no need to wait for 5 minutes, so that it can quickly determine whether intra-abdominal bleeding has occurred.

[0036] Specifically, since vascular blood will coagulate, and the coagulation of blood is a time-varying process, the core of this application is to determine the coagulation time. After collecting the accumulated blood, a feature-time sample regression equation is established, so that it can be determined how long it will take for the accumulated blood to coagulate. If it is determined that the accumulated blood can coagulate in about five minutes, it means that the accumulated blood is vascular blood. If it is determined that the accumulated blood cannot coagulate, it means that the accumulated blood is intra-abdominal bleeding.

[0037] In this embodiment, the preprocessing module 200, the segmentation module 300, the feature extraction module 400 and the processing module 500 are in communication with each other in sequence, and information can be transmitted between them; transvaginal posterior fornix puncture is a prior art; when collecting blood accumulation sample images, the collection is performed through the collection module 100, and the collection module 100 is a camera, and the camera is a CCD camera. The lens of the camera is aimed at the blood accumulation to shoot to obtain the blood accumulation sample image.

[0038] Further, refer to Figure 1 The rapid diagnosis device for intra-abdominal hemorrhage also includes a storage tray 600. The storage tray 600 is arranged adjacent to the collection module 100. The storage tray 600 is used to hold the accumulated blood. Specifically, the storage tray 600 is used to hold the accumulated blood extracted by the puncture needle. In this embodiment, the segmentation module 300 segments the blood sample in the accumulated blood sample image, which means that the image of the blood sample is segmented separately, and other images such as the storage tray 600 are segmented and removed;.

[0039] Further, refer to Figure 1 The intra-abdominal hemorrhage rapid diagnosis device also includes an illumination component 700, which is disposed adjacent to the storage tray 600. The illumination component 700 is used to illuminate the accumulated blood on the storage tray 600 to provide suitable lighting conditions for the accumulated blood so that the accumulated blood can receive appropriate lighting, thereby ensuring that the acquisition module 100 can acquire a better quality sample image of the accumulated blood, thereby facilitating subsequent processing of the sample image of the accumulated blood. In this embodiment, the illumination component 700 is an illumination lamp.

[0040] Further, refer to Figure 1 The rapid diagnosis device for intra-abdominal bleeding also includes a knowledge base 800, which is used to store the standard regression equation of vascular blood. In this embodiment, the standard regression equation of vascular blood is established in advance, and then the standard regression equation is stored in the knowledge base 800. When needed, the processing module 500 directly compares the sample regression equation with the standard regression equation of vascular blood in the knowledge base 800. Therefore, when diagnosing intra-abdominal bleeding quickly, there is no need to temporarily spend time to establish the standard regression equation of vascular blood, which improves efficiency and saves time.

[0041] Furthermore, the feature extraction module 400 is used to perform multiple feature extractions on the blood sample within a preset time and establish a feature-time sample regression equation. Specifically, when establishing the feature-time sample regression equation, there is no need to wait for the extracted blood to coagulate or wait for too long. It only needs to wait for a short time so that the feature-time sample regression equation can be established.

[0042] Furthermore, the preset time is 5-10s. Specifically, by extracting the characteristics of blood samples within 5-10s, a reliable characteristic-time sample regression equation can be established. Therefore, the present application only needs a few seconds or tens of seconds to achieve rapid diagnosis of intra-abdominal bleeding, and there is no need to wait for 5 minutes, thereby greatly improving the diagnostic efficiency. In addition, the longer the time range for extracting the characteristics of blood samples, the more reliable the established characteristic-time sample regression equation. Therefore, for the sake of accuracy, you can choose to extract the characteristics of blood samples within a longer time, but it also takes a longer time. Considering all factors, 5-10s is a more appropriate time.

[0043] Furthermore, the feature extraction module 400 is also used to extract features from the vascular blood sample and establish a standard regression equation for the vascular blood. Specifically, the process of establishing the standard regression equation for the vascular blood is the same as the process of establishing the sample regression equation.

[0044] Specifically, when establishing the standard regression equation of vascular blood, the following steps are included: a puncture needle draws vascular blood; the acquisition module 100 acquires a vascular blood sample image; then the preprocessing module 200 preprocesses the vascular blood sample image to improve the quality of the vascular blood sample image; the segmentation module 300 segments the blood sample in the vascular blood sample image; then the feature extraction module 400 performs multiple feature extractions on the blood sample and establishes a standard regression equation, and finally stores the standard regression equation in the knowledge base 800.

[0045] Specifically, as time changes, vascular blood feature extraction is performed multiple times to establish a feature-time sample regression equation. In this embodiment, when establishing a sample regression equation, it is necessary to perform feature extraction on blood samples multiple times as time changes, so as to obtain a reliable feature-time sample regression equation.

[0046] Furthermore, the preprocessing includes contrast enhancement, brightness correction and noise elimination. Specifically, the contrast enhancement, brightness correction and noise elimination are performed to improve the quality of the blood sample image so that the blood sample image is more suitable for subsequent operations. Among them, noise elimination refers to eliminating unnecessary or redundant interference information existing in the blood sample image, such as removing various types of noise such as patchy noise and color noise in the blood sample image to enhance the visual effect of the blood sample image.

[0047] Furthermore, feature extraction includes texture feature extraction, and texture features include contrast, so that a contrast-time sample regression equation can be established, and the standard regression equation includes a contrast-time standard regression equation. Specifically, the contrast of blood is highly correlated with time, so by comparing the contrast-time standard regression equation with the contrast-time sample regression equation, it is possible to accurately determine whether the collected blood clot is vascular blood or intraperitoneal bleeding.

[0048] Furthermore, the feature extraction module 400 is used to perform multiple contrast feature extractions on the blood sample and construct a contrast-time regression curve, and then establish a contrast-time sample regression equation based on the contrast-time regression curve. Specifically, the contrast of the blood changes with time, and thus, by extracting the contrast features of the blood sample multiple times as time changes, the contrast-time sample regression equation can be established.

[0049] Furthermore, the texture feature also includes at least one of the average value and the entropy. Specifically, when establishing the feature-time sample regression equation, the contrast-time sample regression equation, the average value-time sample regression equation and the entropy-time sample regression equation can be established at the same time. Multiple regression equations are compared to make the result more reliable. In practice, only one sample regression equation can be established to compare and determine whether intra-abdominal bleeding occurs. In this embodiment, the standard regression equation includes the contrast-time standard regression equation, the average value-time standard regression equation and the entropy-time standard regression equation. Then, the above-mentioned standard regression equations are established in advance and stored in the knowledge base 800. When a standard regression equation is needed, it can be directly compared with the corresponding standard regression equation in the knowledge base 800.

[0050] The grayscale histogram of the texture area is used as a texture feature, and the image histogram is used to extract features such as mean, variance, energy and entropy to describe the texture. Let (x, y) be a point in the image. The grayscale difference between this point and the point (x+△x, y+△y) with a small distance from it is: g△(x, y) = g(x, y)-g(x+△x, y+△y), where g△ is called grayscale difference. If all possible values ​​of the grayscale difference value are assumed to have m levels, let the point (x, y) move across the entire screen, and count the number of times g△ takes each value, thus making a histogram of g△. The probability p(k) of g△'s value can be obtained from the histogram. When a smaller difference k is taken, the frequency p(k) is larger, which reflects that the texture is coarser. When the histogram is flat, it means that the texture is more delicate. Specifically, the relevant texture features are: average value: Contrast ratio: con = ∑ i i 2 p(i); Entropy: Entropy = -∑ i p(i)log2*p(i)].

[0051] Furthermore, feature extraction also includes at least one of RGB color space feature extraction and HSV color space feature extraction. The parameters of the HSV color space include hue, saturation and brightness. Specifically, the color space of blood will change significantly over time. For example, the color form of blood, namely hue, saturation and brightness, will change significantly over time. Therefore, the present application will establish a sample regression equation through RGB color space features and HSV color space features to determine whether intra-abdominal bleeding has occurred; when establishing a feature-time sample regression equation, a texture feature-time sample regression equation, an RGB color space feature-time sample regression equation and an HSV color space-time sample regression equation can be established at the same time, and multiple regression equations can be compared to make the results more reliable. In practice, one or several sample regression equations can be established according to actual needs to compare and determine whether intra-abdominal bleeding has occurred.

[0052] In this embodiment, the color space is described by a color histogram. In this application, a color histogram is first established, and then a sample regression equation is established. The color histogram serves as a color feature of an image. It describes the proportion of different colors in the entire image. The color histogram reflects the statistical characteristics of the image color distribution and is suitable for describing images that are difficult to automatically classify and images that do not require consideration of the spatial position of objects. The most commonly used color spaces are RGB color space and HSV color space.

[0053] Furthermore, the RGB color space feature-time sample regression equation includes the R (red)-time sample regression equation, the G (green)-time sample regression equation and the B (blue)-time sample regression equation, and the HSV color space-time sample regression equation includes the hue-time sample regression equation, the saturation-time sample regression equation and the lightness-time sample regression equation. Specifically, in the HSV color space, hue (H) is the basic attribute of color, which is the color name we usually say, such as red, yellow, etc.; saturation (S) refers to the purity of the color, the higher the color, the purer it is, and the lower the color, the grayer it gradually becomes, taking a value of 0-100%; lightness (V) is the brightness of the color, the higher the lightness, the brighter the color, and the lower the lightness, the darker the color.

[0054] refer to Figure 2 , the process of establishing the contrast-time standard regression equation is as follows:

[0055] The puncture needle extracts blood from the blood vessel, and then the blood vessel blood is placed on the storage tray 600; the acquisition module 100 acquires a blood vessel blood sample image; then the preprocessing module 200 preprocesses the blood vessel blood sample image to improve the quality of the blood vessel blood sample image; the segmentation module 300 segments the blood sample in the blood vessel blood sample image, and then performs multiple contrast feature extractions on the blood vessel blood sample as time changes, establishes a table as shown in Table 1, and then establishes the following table according to Table 1: Figure 3 The con (contrast)-time curve shown in the figure is used, and then a contrast-time standard regression equation is established based on the con (contrast)-time curve. Specifically, the time interval for extracting the contrast feature can be 1-10S. When establishing the contrast-time standard regression equation, a time interval of 10S can be selected to reduce the number of times the contrast feature is extracted. However, since vascular blood takes about five minutes to coagulate, a time interval of 10S is sufficient to establish a reliable contrast-time standard regression equation within five minutes.

[0056]

[0057] Table 1

[0058] According to the actual data in Table 1, the following model summary can be obtained:

[0059] Model Summary

[0060]

[0061] a. Prediction variables: (constant), time

[0062] ANOVA a

[0063]

[0064] a. Dependent variable: con

[0065] b. Prediction variables: (constant), time

[0066] coefficient a

[0067]

[0068] a. Dependent variable: con

[0069] Residual statistics a

[0070]

[0071] a. Dependent variable: con

[0072] From the model summary, we can see that R2 =0.962, indicating that 96.2% of the variation in the con (contrast) results is caused by time (time); the results of the ANOVA (analysis of variance, variance analysis) table and the coefficient table show that the regression equation is significant, F = 684.081, p < 0.0001. (P < .05, significant, indicating that the explanatory power or predictive power of the independent variable X on the dependent variable Y is positively correlated.) Therefore, it is concluded that there is a linear relationship between time and con results, and time can explain 96.2% of the variation. The regression equation is: con = 387.602-9.729time. (con contrast).

[0073] The contrast-time standard regression equation: con=387.602-9.729time is stored in the database. When it is necessary to determine whether the person to be diagnosed has intra-abdominal bleeding, the contrast-time sample regression equation is established according to the same steps, and compared with the contrast-time standard regression equation. According to whether the two are consistent, it is possible to quickly determine whether the extracted blood is vascular blood or intra-abdominal bleeding. Specifically, when establishing the contrast-time sample regression equation, it is possible to choose to extract the contrast features of the blood sample every 1S as time changes, so that the contrast features of multiple blood samples can be extracted in 5-10S, so that there is enough data to establish the contrast-time sample regression equation.

[0074] Furthermore, the process of establishing the mean-time standard regression equation and the entropy-time standard regression equation is the same as the steps of the contrast-time standard regression equation, and this application will not repeat them. Further, the process of establishing the RGB color space feature-time sample regression equation and the HSV color space-time sample regression equation is the same as the process of establishing the contrast-time standard regression equation, and this application will not repeat them.

[0075] Specifically, before establishing the RGB color space feature-time sample regression equation and the HSV color space-time sample regression equation, it is necessary to first establish the relevant histograms, where the RGB histogram of vascular blood is as follows: Figure 4-6 As shown, the hue and saturation histogram of vascular blood is as follows Figure 7-8 As shown (the brightness histogram of vascular blood is omitted in this application).

[0076] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent device transformations made using the contents of the present invention's specification and drawings, or direct / indirect applications in other related technical fields, under the inventive concept of the present invention are included in the patent protection scope of the present invention.

Claims

1. A rapid diagnostic device for intra-abdominal bleeding, characterized in that: include: An acquisition module, used for acquiring blood sample images; A preprocessing module, electrically connected to the acquisition module, and configured to preprocess the blood accumulation sample image to improve the quality of the blood accumulation sample image; a segmentation module, used for performing segmentation processing on the blood accumulation sample image to segment the blood sample in the blood accumulation sample image; A feature extraction module, used to extract features from the blood sample and establish a feature-time sample regression equation; and The processing module is used to compare the sample regression equation with the standard regression equation of vascular blood to determine whether the extracted accumulated blood is vascular blood, thereby determining whether intra-abdominal bleeding occurs.

2. The rapid diagnostic device for intra-abdominal bleeding according to claim 1, characterized in that: The feature extraction module is used to perform multiple feature extractions on the blood sample within a preset time.

3. The rapid diagnostic device for intra-abdominal bleeding according to claim 2, characterized in that: The preset time is 5-10s.

4. The rapid diagnostic device for intra-abdominal bleeding according to claim 1, characterized in that: The rapid intra-abdominal bleeding diagnosis system also includes a storage tray, which is arranged adjacent to the collection module and is used to hold accumulated blood.

5. The rapid diagnostic device for intra-abdominal bleeding according to claim 4, characterized in that: The rapid diagnosis device for intra-abdominal bleeding further comprises a lighting component, which is disposed adjacent to the storage tray and is used to illuminate the accumulated blood on the storage tray.

6. The rapid diagnosis device for intra-abdominal bleeding according to claim 1, characterized in that: The feature extraction module is also used to extract features from vascular blood samples and establish a standard regression equation for vascular blood.

7. The rapid diagnosis device for intra-abdominal bleeding according to claim 1, characterized in that: The preprocessing includes contrast enhancement, brightness correction and noise removal.

8. The rapid diagnostic device for intra-abdominal bleeding according to claim 7, characterized in that: The feature extraction includes texture feature extraction, and the texture feature includes contrast. The feature extraction module is used to perform multiple contrast feature extractions on the blood sample and construct a contrast-time regression curve, and then establish a contrast-time sample regression equation based on the contrast-time regression curve.

9. The rapid diagnostic device for intra-abdominal bleeding according to claim 8, characterized in that: The texture feature further includes at least one of a mean value and an entropy.

10. The rapid diagnosis device for intra-abdominal bleeding according to claim 7, characterized in that: The feature extraction also includes at least one of RGB color space feature extraction and HSV color space feature extraction, and the parameters of the HSV color space include hue, saturation and brightness.

Images