Sepsis prognosis method based on sublingual blood vessel image intelligent auxiliary analysis

Abstract

The invention relates to the technical field of medical images, in particular to a sepsis prognosis method based on sublingual blood vessel image intelligent auxiliary analysis, which comprises the following steps: acquiring sublingual microcirculation grayscale images at different observation moments; based on the architecture condition of the sublingual blood vessel in the sublingual microcirculation grayscale image, analyzing the grayscale rising and falling rule of similar blood vessel dilation to obtain the saliva sedimentation degree of the blood vessel structure region; the flow evaporation condition of sublingual saliva between adjacent observation moments is analyzed, and the saliva settlement degree is corrected to obtain the corrected saliva settlement degree of the sublingual microcirculation grayscale image at different observation moments; and performing prognosis auxiliary analysis on the sublingual microcirculation grayscale image according to the corrected saliva settlement degree. The development interference of saliva on sublingual blood vessels of a sepsis patient is reduced, and the sepsis prognosis analysis result is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of medical image technology, and in particular to a sepsis prognosis method based on intelligent auxiliary analysis of sublingual blood vessel images. Background Art

[0002] Sepsis is one of the major diseases that seriously threaten human health. The body's inflammatory response to infection is disordered, secondary to various serious infections, such as severe burns, surgery, pneumonia, meningitis, etc. It is necessary to accurately assess the development of the disease and deal with it in time to avoid serious complications such as respiratory attenuation and cardiac attenuation. The microcirculation process under the tongue of the patient can clearly reflect the abnormal changes in the sublingual microcirculation, which reflects the obstruction of microcirculation function in patients with sepsis. Therefore, sublingual microcirculation technology can be used to non-invasively evaluate microcirculatory blood flow, and observe changes in microcirculation perfusion through a sublingual microscope. If the microcirculation function is impaired, tissue hypoxia or organ failure may occur. Therefore, the sublingual mucosa can usually be used as a perfusion window for visceral microcirculation to evaluate the prognosis level of patients with sepsis, that is, the control effect of the disease.

[0003] During sublingual microcirculation image monitoring, the sublingual surface inevitably contains saliva, which flows as a whole on the sublingual surface. Affected by the different blood flow rates inside the blood vessels under different expansion conditions of the patient's sublingual surface, the saliva on different blood vessel surfaces under the sublingual surface reflects light differently, and the sublingual vascular area cannot be displayed well. Summary of the invention

[0004] The present invention provides a sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images to solve the existing problem that during sublingual microcirculation image monitoring, the sublingual surface inevitably contains saliva, which will flow as a whole on the sublingual surface and be affected by different blood flow rates inside the vascular conduits under different expansion conditions of the patient's sublingual surface, resulting in different reflections of light by saliva on different sublingual vascular surfaces, and the sublingual vascular area cannot be well displayed.

[0005] The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images of the present invention adopts the following technical solutions: The following steps are involved: Obtain grayscale images of sublingual microcirculation at different observation times; For a grayscale image of sublingual microcirculation at any observation time, the structure of the sublingual blood vessels in the grayscale image of sublingual microcirculation is analyzed, and a blood vessel structure area is divided from the grayscale image of sublingual microcirculation, wherein the blood vessel structure area includes a plurality of blood vessel channel areas; based on the blood vessel channel area, the grayscale rise and fall law of similar blood vessel dilation is analyzed to obtain the saliva sedimentation degree of the blood vessel structure area; The flow and evaporation of sublingual saliva between adjacent observation moments were analyzed, and the saliva sedimentation degree was corrected to obtain the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at different observation moments; The grayscale images of sublingual microcirculation were analyzed for prognosis according to the corrected salivary sedimentation.

[0006] Furthermore, the method for acquiring the blood vessel structure region is: The grayscale image of sublingual microcirculation obtains several vascular skeleton points through the trained neural network; the vascular skeleton points are expanded by window sliding to construct the vascular structure area.

[0007] Furthermore, the method for obtaining the saliva sedimentation rate is: For any vascular structure area, the similarity of the expansion of the path of the vascular channel in the vascular structure area is analyzed, and the initial vascular swelling-proximate area is divided from the vascular structure area; the extension comparison of the initial vascular swelling-proximate area in the horizontal and vertical directions is analyzed to obtain the vascular inclination of the initial vascular swelling-proximate area; the grayscale interval difference of the vascular channel in the initial vascular swelling-proximate area is analyzed to obtain the vascular saliva sedimentation degree of the initial vascular swelling-proximate area; the vascular inclination and the vascular saliva sedimentation degree are combined to obtain the saliva sedimentation degree of the vascular structure area; the saliva sedimentation degree is negatively correlated with the vascular inclination.

[0008] Furthermore, the method for obtaining the initial vascular swelling proximal region is: The channel widths of different vascular channel regions within the vascular structure region are obtained; the similarities of the channel widths between different vascular channel regions are analyzed, and the different vascular channel regions are integrated into regions similar to the initial vascular swelling.

[0009] Furthermore, the method for obtaining the blood vessel inclination is: The horizontal region length in the initial blood vessel swelling proximal region is obtained; the vertical region length in the initial blood vessel swelling proximal region is obtained; and the blood vessel inclination in the initial blood vessel swelling proximal region is obtained based on the comparison difference between the horizontal region length and the vertical region length.

[0010] Furthermore, the method for obtaining the vascular saliva sedimentation degree is: The grayscale differences between the longitudinal vascular channels in the area with similar initial vascular swelling were analyzed to obtain the vascular saliva sedimentation degree in the area with similar initial vascular swelling.

[0011] Furthermore, after calculating the saliva sedimentation rate, it also includes: The salivary sedimentation was normalized.

[0012] Furthermore, the method for obtaining the corrected saliva sedimentation rate is: Taking any observation moment as the target observation moment, the difference in saliva sedimentation before and after the target observation moment is compared to obtain the abnormal saliva dryness at the target observation moment; based on the abnormal saliva dryness, the corrected saliva sedimentation of the sublingual microcirculation grayscale image at the target observation moment is obtained.

[0013] Furthermore, the method for obtaining the abnormal dryness of saliva is: The observation moment before the target observation moment is taken as the historical observation moment, and the observation moment after the target observation moment is taken as the later observation moment. The difference in saliva sedimentation degree between the historical observation moment and the target observation moment is compared to obtain the historical saliva sedimentation difference value; the difference in saliva sedimentation degree between the target observation moment and the later observation moment is compared to obtain the later saliva sedimentation difference value; according to the historical saliva sedimentation difference value and the later saliva sedimentation difference value, the abnormal dryness of saliva at the target observation moment is obtained.

[0014] Furthermore, after calculating the corrected saliva sedimentation rate, it also includes: Normalization was performed on the corrected salivary sedimentation.

[0015] The beneficial effects of the technical solution of the present invention are as follows: by analyzing the grayscale rise and fall rules of similar vascular dilation based on the structural conditions of the sublingual blood vessels in the sublingual microcirculation grayscale image, the saliva sedimentation degree of the vascular structure area is obtained; wherein the saliva sedimentation degree is used to describe the influence of the sublingual vascular structure of the septic patient on the movement of the sublingual saliva, so that the influence on the saliva flow is more closely related to the physical state of the septic patient; then, the flow evaporation of the sublingual saliva between adjacent observation moments is analyzed, and the saliva sedimentation degree is corrected to obtain the corrected saliva of the sublingual microcirculation grayscale image at different observation moments. Sedimentation; wherein the modified saliva sedimentation is used to describe the influence of the sublingual vascular structure of sepsis patients on the movement of sublingual saliva under the comprehensive time dynamic influence, and reduce the interference of normal sublingual blood vessels and time flow on the judgment of saliva status; finally, according to the modified saliva sedimentation, the sublingual microcirculation grayscale image is subjected to prognosis auxiliary analysis; the present invention measures the modified saliva sedimentation for prognosis analysis of sepsis by analyzing the changing relationship between the sublingual vascular structure of sepsis patients and the movement state of sublingual saliva; reduces the interference of saliva on the development of sublingual blood vessels of sepsis patients, and makes the analysis result of sepsis prognosis more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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 these drawings without paying creative work.

[0017] Figure 1 This is a flowchart of the steps of the sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images of the present invention; Figure 2 Schematic diagram of the grayscale image of sublingual microcirculation of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flowchart of a method for prognosis of sepsis based on intelligent auxiliary analysis of sublingual vascular images provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Acquire grayscale images of sublingual microcirculation at different observation times.

[0022] It should be noted that during sublingual microcirculation image monitoring, the sublingual surface inevitably contains saliva, which will flow as a whole on the sublingual surface and be affected by the different blood flow rates inside the blood vessels under different expansion conditions of the patient's sublingual surface. This will cause the saliva on different blood vessel surfaces under the sublingual surface to reflect light differently, and cannot better display the sublingual vascular area.

[0023] In a specific implementation of the embodiment of the present invention, the method for obtaining the grayscale image of the sublingual microcirculation is: using a handheld live microscope (HVM) to take a number of sublingual microcirculation images, and grayscale processing each sublingual microcirculation image to obtain a sublingual microcirculation grayscale image. The grayscale processing is a well-known technology and will not be repeated in this embodiment; in addition, each sublingual microcirculation image corresponds to an observation time. Please refer to Figure 2 , is a schematic diagram of the grayscale image of sublingual microcirculation.

[0024] It is particularly noted that this embodiment is described by taking a frequency of 1 time / second and a total shooting time of 10 seconds as an example to collect sublingual microcirculation images at multiple observation times; this embodiment does not specifically limit the shooting frequency and the total shooting time, wherein the shooting frequency and the total shooting time can be determined according to the specific implementation situation.

[0025] At this point, the grayscale images of sublingual microcirculation at different observation times are obtained through the above method.

[0026] Step S002: For the sublingual microcirculation grayscale image at any observation time, analyze the structure of the sublingual blood vessels in the sublingual microcirculation grayscale image, and divide the vascular structure area from the sublingual microcirculation grayscale image, wherein the vascular structure area includes multiple vascular channel areas; based on the vascular channel area, analyze the grayscale rise and fall rules of similar blood vessel dilation to obtain the saliva sedimentation degree of the vascular structure area.

[0027] It should be noted that there are many small blood vessels with obvious branches distributed on the sublingual surface of the patient, which makes the sublingual surface form different concave and convex distributions, resulting in different obstructions for the saliva produced in the patient's mouth when it gathers under the patient's tongue. Therefore, the structure of the sublingual blood vessels in the sublingual microcirculation grayscale image can be analyzed, and the vascular structure area can be divided from the sublingual microcirculation grayscale image.

[0028] It should be further explained that when collecting grayscale images of sublingual microcirculation, the tongue will be lifted as much as possible. Under the action of natural gravity, the upper surface of the tongue is usually stained with less saliva, and the lower surface close to the tongue bed is stained with more saliva. Therefore, the upper part of the image generally has a better imaging effect, and the lower part has a poorer imaging effect due to the influence of saliva. Therefore, based on the vascular channel area, the grayscale rise and fall law of similar vascular dilation can be analyzed to obtain the saliva sedimentation degree of the vascular structure area; the greater the saliva sedimentation degree, the faster the saliva flows under the tongue in the vascular structure area, reflecting that the saliva in the vascular structure area interferes with the angiography more.

[0029] Preferably, in some implementations of the present invention, the method for acquiring the vascular structure region is: using a trained neural network to acquire a number of vascular skeleton points from the sublingual microcirculation grayscale image; and performing window sliding expansion on the vascular skeleton points to construct the vascular structure region. The specific process is as follows: The sublingual microcirculation grayscale image is input into the trained neural network to obtain the vascular skeleton points of the sublingual microcirculation grayscale image; the neural network used in this embodiment is Resnet50, and the method for obtaining the data set for training the neural network is: collecting a large number of sublingual microcirculation grayscale images, artificially marking the position of the vascular skeleton points in each sublingual microcirculation grayscale image, that is, the position of the vascular skeleton points in the sublingual microcirculation grayscale image is marked as 1, and the position of the non-vascular skeleton points is marked as 0, and this marking result is recorded as the label of each sublingual microcirculation grayscale image; collecting a large number of sublingual microcirculation grayscale images and their corresponding labels to form a data set; using the data set to train the neural network, the loss function used in the training process is the cross entropy loss function; the specific training process is a well-known content of the neural network, and this embodiment will not repeat the specific training process.

[0030] Further, taking any blood vessel skeleton point as an example, the blood vessel skeleton point is taken as the center and a preset A window of size is formed, and the image area occupied by the window is used as the local vascular skeleton area of ​​the vascular skeleton point; the local vascular skeleton areas of all vascular skeleton points are obtained; the vascular skeleton points with intersections between different local vascular skeleton areas are used as real vascular skeleton points; the local vascular skeleton area of ​​each real vascular skeleton point is used as the vascular channel area; and the union of all vascular channel areas is used as the vascular structure area. This example is described as an example, and this embodiment is not specifically limited. It may depend on the specific implementation situation.

[0031] It should be noted that each sublingual microcirculation grayscale image contains multiple vascular structure regions, and different vascular structure regions are independent regions without any intersecting regions.

[0032] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the saliva sedimentation degree is as follows: for any vascular structure region, analyze the similarity of the expansion of the path of the vascular channel in the vascular structure region, and divide the initial vascular swelling-proximate region from the vascular structure region; analyze the extension comparison of the initial vascular swelling-proximate region in the horizontal and vertical directions to obtain the vascular inclination of the initial vascular swelling-proximate region; analyze the grayscale interval difference of the vascular channel in the initial vascular swelling-proximate region to obtain the vascular saliva sedimentation degree of the initial vascular swelling-proximate region; comprehensively calculate the vascular inclination and the vascular saliva sedimentation degree to obtain the saliva sedimentation degree of the vascular structure region; the saliva sedimentation degree is negatively correlated with the vascular inclination. The specific process is as follows: It should be noted that patients with sepsis will produce a large number of inflammatory mediators in their bodies. These inflammatory mediators will damage the endothelial cells, especially the endothelial cells in the microcirculation, causing similar damage to the tissue structure of the small blood vessels under the tongue, resulting in vascular swelling of similar width. Therefore, the similar expansion of the vascular channels in the vascular structure area can be analyzed, and the initial vascular swelling areas can be divided from the vascular structure area.

[0033] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the initial vascular swelling similar area is: obtaining the channel widths of different vascular channel areas in the vascular structure area; analyzing the similarity of the channel widths between different vascular channel areas, and integrating the different vascular channel areas into the initial vascular swelling similar area. The specific process is as follows: Taking any vascular channel area in the vascular structure area as an example, the mean value of the number of pixels in all rows in the vascular channel area is taken as the channel width of the vascular channel area; the channel widths of all vascular channel areas are obtained; taking any two vascular channel areas as an example, a difference threshold is preset , if the absolute value of the difference in channel width between the two vascular channel regions is less than , then these two vascular channel regions are taken together as the initial vascular swelling close region; and several initial vascular swelling close regions are obtained. This example is described as an example, and this embodiment is not specifically limited. It may depend on the specific implementation situation.

[0034] It should be noted that when saliva settles under the patient's tongue, the vertically distributed vascular structure has the best support effect on the flow of saliva, and other vascular structures with inclined distribution will produce a certain resistance to hinder the flow of saliva. Therefore, the extension comparison of the initial vascular swelling area in the horizontal and vertical directions can be analyzed to obtain the vascular inclination of the initial vascular swelling area. The greater the vascular inclination, the greater the obstruction of the sublingual blood vessels to the saliva sedimentation.

[0035] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the blood vessel inclination is: obtaining the horizontal region length in the initial blood vessel swelling proximal region; obtaining the vertical region length in the initial blood vessel swelling proximal region; and obtaining the blood vessel inclination in the initial blood vessel swelling proximal region based on the comparison difference between the horizontal region length and the vertical region length. The specific process is as follows: Taking any initial vascular swelling proximal region as an example, the average of the channel widths of all vascular channel regions in the initial vascular swelling proximal region is taken as the horizontal region length; the average of the number of all pixel points in the column occupied by all vascular channel regions in the initial vascular swelling proximal region is taken as the vertical region length; the absolute value of the difference between the horizontal region length and the vertical region length is taken as the vascular inclination of the initial vascular swelling proximal region.

[0036] It should be noted that the greater the inclination of the blood vessels, the greater the obstacle of the sublingual blood vessels to the sedimentation of saliva.

[0037] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the vascular salivary sedimentation degree is: analyzing the grayscale difference between the longitudinal vascular channels in the initial vascular swelling-proximal region to obtain the vascular salivary sedimentation degree in the initial vascular swelling-proximal region. The specific process is as follows: The average grayscale value of all pixels in each column of all vascular channel areas in the initial vascular swelling proximity area is taken as the longitudinal vascular grayscale in each column; the cumulative sum of the absolute values ​​of the longitudinal vascular grayscale differences in different columns is taken as the vascular saliva sedimentation degree of the initial vascular swelling proximity area.

[0038] Furthermore, the ratio of the vascular saliva sedimentation degree to the vascular inclination in the area close to the initial vascular swelling is used as the regional saliva sedimentation degree in the area close to the initial vascular swelling; the normalized value of the mean of the regional saliva sedimentation degrees of all the areas close to the initial vascular swelling in the vascular structure area is used as the saliva sedimentation degree of the vascular structure area.

[0039] It is particularly noted that in this embodiment The normalization function is performed according to the specific implementation situation, and the normalization function is determined according to the specific implementation situation, which will not be described in detail in this embodiment.

[0040] It should be noted that the greater the saliva sedimentation rate, the faster the saliva flows under the tongue in the vascular structure area, which reflects that the interference of saliva in the vascular structure area on the angiography is greater.

[0041] So far, the salivary sedimentation degree of the vascular structure area is obtained by the above method.

[0042] Step S003: Analyze the flow and evaporation of sublingual saliva between adjacent observation moments, correct the saliva sedimentation degree, and obtain the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at different observation moments.

[0043] It should be noted that, in actual situations, the saliva under the patient's tongue is in a dynamic flow state, and will continue to flow and evaporate over time; and the saliva sedimentation degree obtained by analyzing the saliva flow at a single observation moment will produce different interference effects over time, so the flow and evaporation of sublingual saliva between adjacent observation moments can be analyzed, and the saliva sedimentation degree can be corrected to obtain the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at different observation moments.

[0044] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the corrected saliva sedimentation degree is: taking any observation time as the target observation time, comparing the change difference of the saliva sedimentation degree before and after the target observation time, and obtaining the abnormal saliva dryness at the target observation time; according to the abnormal saliva dryness, obtaining the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at the target observation time. The specific process is as follows: Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the abnormal dryness of saliva is: taking the observation moment before the target observation moment as the historical observation moment, taking the observation moment after the target observation moment as the later observation moment, comparing the difference in saliva sedimentation between the historical observation moment and the target observation moment, and obtaining the historical saliva sedimentation difference value; comparing the difference in saliva sedimentation between the target observation moment and the later observation moment, and obtaining the later saliva sedimentation difference value; according to the historical saliva sedimentation difference value and the later saliva sedimentation difference value, obtaining the abnormal dryness of saliva at the target observation moment.

[0045] It should be noted that if the target observation time is the first observation time, the later saliva sedimentation difference value at the target observation time is used as the abnormal saliva dryness; if the target observation time is the last observation time, the historical saliva sedimentation difference value at the target observation time is used as the abnormal saliva dryness.

[0046] Further, as an example, the corrected saliva sedimentation rate can be calculated by the following formula: ; In the formula, Indicates Corrected salivary sedimentation of the grayscale image of the sublingual microcirculation at each observation moment; Indicates Abnormal dryness of saliva at each observation moment; express Abnormal dryness of saliva at each observation moment; Indicates The mean value of salivary sedimentation in all vascular structure areas in the grayscale image of sublingual microcirculation at each observation time; Indicates taking the absolute value; represents the linear normalization function.

[0047] In particular, if If there is no observation moment before the observation moment, then calculate Not considering ; If There is no observation moment after observation moment, so calculate Not considering .

[0048] At this point, the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at different observation times is obtained through the above method.

[0049] Step S004: Perform prognostic auxiliary analysis on the sublingual microcirculation grayscale image according to the corrected saliva sedimentation degree.

[0050] Taking any observation moment as an example, the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at the observation moment is used as the grayscale weight, and the grayscale value obtained by multiplying the grayscale weight with the grayscale value of each pixel in the sublingual microcirculation grayscale image at the observation moment is used as the enhanced grayscale value of each pixel; the image composed of the enhanced grayscale values ​​of all pixels at the observation moment is used as the enhanced sublingual microcirculation image at the observation moment.

[0051] Furthermore, the length of the vascular network in the enhanced sublingual microcirculation image and the perfusion quality are analyzed to calculate the proportion of perfused blood vessels for sepsis prognosis analysis. The process of calculating the proportion of perfused blood vessels for sepsis prognosis analysis based on the length of the vascular network and the perfusion quality is a well-known technology and will not be repeated in this embodiment.

[0052] At this point, this embodiment is completed.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A sepsis prognosis method based on intelligent assisted analysis of sublingual vascular images, characterized in that: The method comprises the following steps: Obtain grayscale images of sublingual microcirculation at different observation times; For a grayscale image of sublingual microcirculation at any observation time, the structure of the sublingual blood vessels in the grayscale image of sublingual microcirculation is analyzed, and a blood vessel structure area is divided from the grayscale image of sublingual microcirculation, wherein the blood vessel structure area includes a plurality of blood vessel channel areas; based on the blood vessel channel area, the grayscale rise and fall law of similar blood vessel dilation is analyzed to obtain the saliva sedimentation degree of the blood vessel structure area; The flow and evaporation of sublingual saliva between adjacent observation moments were analyzed, and the saliva sedimentation degree was corrected to obtain the corrected saliva sedimentation degree of the sublingual microcirculation grayscale image at different observation moments; The grayscale images of sublingual microcirculation were analyzed for prognosis according to the corrected salivary sedimentation.

2. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 1, characterized in that: The method for obtaining the vascular structure region is: The grayscale image of sublingual microcirculation obtains several vascular skeleton points through the trained neural network; the vascular skeleton points are expanded by window sliding to construct the vascular structure area.

3. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 1, characterized in that: The method for obtaining the saliva sedimentation degree is: For any vascular structure area, the similarity of the expansion of the path of the vascular channel in the vascular structure area is analyzed, and the initial vascular swelling-proximate area is divided from the vascular structure area; the extension comparison of the initial vascular swelling-proximate area in the horizontal and vertical directions is analyzed to obtain the vascular inclination of the initial vascular swelling-proximate area; the grayscale interval difference of the vascular channel in the initial vascular swelling-proximate area is analyzed to obtain the vascular saliva sedimentation degree of the initial vascular swelling-proximate area; the vascular inclination and the vascular saliva sedimentation degree are combined to obtain the saliva sedimentation degree of the vascular structure area; the saliva sedimentation degree is negatively correlated with the vascular inclination.

4. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 1, characterized in that: The method for obtaining the initial vascular swelling proximal region is: The channel widths of different vascular channel regions within the vascular structure region are obtained; the similarities of the channel widths between different vascular channel regions are analyzed, and the different vascular channel regions are integrated into regions similar to the initial vascular swelling.

5. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 4, characterized in that: The method for obtaining the blood vessel inclination is: The horizontal region length in the initial blood vessel swelling proximal region is obtained; the vertical region length in the initial blood vessel swelling proximal region is obtained; and the blood vessel inclination in the initial blood vessel swelling proximal region is obtained based on the comparison difference between the horizontal region length and the vertical region length.

6. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 4, characterized in that: The method for obtaining the vascular saliva sedimentation degree is: The grayscale differences between the longitudinal vascular channels in the area with similar initial vascular swelling were analyzed to obtain the vascular saliva sedimentation degree in the area with similar initial vascular swelling.

7. According to claim 1, the method for prognosis of sepsis based on intelligent auxiliary analysis of sublingual vascular images, after calculating the saliva sedimentation degree, further comprising: The salivary sedimentation was normalized.

8. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 1, characterized in that: The method for obtaining the modified saliva sedimentation degree is: Taking any observation moment as the target observation moment, the difference in saliva sedimentation before and after the target observation moment is compared to obtain the abnormal saliva dryness at the target observation moment; based on the abnormal saliva dryness, the corrected saliva sedimentation of the sublingual microcirculation grayscale image at the target observation moment is obtained.

9. The sepsis prognosis method based on intelligent auxiliary analysis of sublingual vascular images according to claim 8, characterized in that: The method for obtaining the abnormal dryness of saliva is: The observation moment before the target observation moment is taken as the historical observation moment, and the observation moment after the target observation moment is taken as the later observation moment. The difference in saliva sedimentation degree between the historical observation moment and the target observation moment is compared to obtain the historical saliva sedimentation difference value; the difference in saliva sedimentation degree between the target observation moment and the later observation moment is compared to obtain the later saliva sedimentation difference value; according to the historical saliva sedimentation difference value and the later saliva sedimentation difference value, the abnormal dryness of saliva at the target observation moment is obtained.

10. According to claim 1, the method for prognosis of sepsis based on intelligent auxiliary analysis of sublingual vascular images, after calculating the corrected salivary sedimentation degree, further comprising: Normalization was performed on the corrected salivary sedimentation.

Images