Blood pathology image analysis method and system based on adaptive technology

Abstract

According to the blood pathology image analysis method and system based on the adaptive technology provided by the invention, at least two pieces of first blood pathology image information with consistent or similar directories are analyzed to obtain at least one comparison queue; analyzing at least one piece of second blood pathology image information except the at least two pieces of first blood pathology image information in the at least one comparison queue to obtain second blood pathology image information associated with the at least two pieces of first blood pathology image information; therefore, the abnormal points on the image can be accurately determined, the condition of the patient can be obtained, and medical staff can be assisted to quickly treat the patient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image analysis, in particular to a blood pathology image analysis method and system based on adaptive technology. BACKGROUND

[0002] The diagnosis of blood pathology images plays an extremely important role in clinical medicine, especially in the early screening of blood diseases and the differential diagnosis of mixed infections of complications. However, the traditional image diagnosis method often relies on experienced professionals, and such a diagnosis method has the problems of strong subjectivity and poor diagnosis consistency. In addition, the blood pathology image usually contains a large amount of complex information, and some blood diseases may be accompanied by other complications, resulting in greater difficulty in diagnosis. Especially in the case of mixed infection of multiple complications, how to effectively distinguish different diseases and improve the diagnosis accuracy has become a difficult problem to be solved in the medical field. SUMMARY

[0003] In order to improve the technical problems existing in the related art, the present application provides a blood pathology image analysis method and system based on adaptive technology.

[0004] In a first aspect, a blood pathology image analysis method based on adaptive technology is provided, the method comprising at least: acquiring a first blood pathology key feature of each of at least two first blood pathology image information; wherein the at least two first blood pathology image information have consistent or similar directories, and each of the first blood pathology key features comprises at least one abnormal region description information; comparing the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information to obtain at least one comparison queue; determining at least one second blood pathology image information existing in the at least one comparison queue in addition to the at least two first blood pathology image information, and a second blood pathology key feature of each of the second blood pathology image information in the at least one comparison queue; in response to each of the second blood pathology image information, generating a correlation relationship between the second blood pathology image information and the at least two first blood pathology image information on the premise that the number of abnormal region description information in the second blood pathology key feature of the second blood pathology image information exceeds an abnormal region description information number threshold.

[0005] In an independently implemented embodiment, the generating of the association relationship between the second blood pathology image information and the at least two first blood pathology image information on the premise that the number of abnormal area description information in the second blood pathology key feature of the second blood pathology image information exceeds a threshold value for the number of abnormal area description information includes: generating a comparison queue associated with each abnormal area description information in the second blood pathology key feature on the premise that the number of abnormal area description information in the second blood pathology key feature of the second blood pathology image information exceeds a threshold value for the number of abnormal area description information; generating the association relationship between the second blood pathology image information and the at least two first blood pathology image information on the premise that the number of comparison queues associated with the abnormal area description information in the second blood pathology key feature exceeds a first threshold.

[0006] In an independently implemented embodiment, the method further includes: on the premise that the number of the comparison queues exceeds a second threshold, generating a preset image debugging situation relationship between the at least two first blood pathology image information; determining the at least one second blood pathology image information other than the at least two first blood pathology image information present in the at least one comparison queue, and the second blood pathology key feature of each second blood pathology image information in the at least one comparison queue, including: on the premise that a preset image debugging situation relationship exists between the at least two first blood pathology image information, determining the at least one second blood pathology image information other than the at least two first blood pathology image information present in the at least one comparison queue, and the second blood pathology key feature of each second blood pathology image information in the at least one comparison queue.

[0007] In an independently implemented embodiment, the at least two first blood pathology image information includes at least one first part of blood pathology image information existing in a first catalog and at least one second part of blood pathology image information existing in a second catalog, and the preset image adjustment condition relationship includes a blood pathology image information splicing operation between the first part of blood pathology image information and the second part of blood pathology image information; and the generating of the preset image adjustment condition relationship between the at least two first blood pathology image information on the premise that the number of comparison queues exceeds a second threshold value includes: determining the number of first part of blood pathology image information and the number of second part of blood pathology image information existing in the at least one comparison queue one by one on the premise that the number of comparison queues exceeds the second threshold value; and determining the blood pathology image information splicing operation between the first part of blood pathology image information and the second part of blood pathology image information on the premise that the number of first part of blood pathology image information exceeds a first blood pathology image information number threshold value and the number of second part of blood pathology image information exceeds a second blood pathology image information number threshold value.

[0008] In an independently implemented embodiment, each of the abnormal region description information exists in an interval analysis catalog; and the comparing of the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information to obtain at least one comparison queue includes: analyzing the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information in image positions to obtain at least one image position analysis range and at least two image position repeated abnormal region description information in each of the image position analysis range; in response to each of the image position analysis range, determining an interval period analysis range based on the interval analysis catalog of each of the image position repeated abnormal region description information on the premise that the at least two image position repeated abnormal region description information in the image position analysis range meets a preset interval period requirement in an interval period, and analyzing the image position analysis range and the interval period to determine a first comparison queue.

[0009] In an independently implemented embodiment, the at least two first blood pathology image information includes at least one first part of blood pathology image information with a first catalog and at least one second part of blood pathology image information with a second catalog, the first catalog is consistent or similar to the second catalog, and each of the abnormal area description information has an image location catalog; the analysis of the abnormal area description information in the first blood pathology key feature of the at least two first blood pathology image information in the image location obtains at least one image location analysis range and at least two image location repeated abnormal area description information in each of the image location analysis range, including: taking each of the abnormal area description information in the blood pathology key feature of each of the first part of blood pathology image information with the first catalog as abnormal area description information needing to be processed; determining target abnormal area description information associated with the image location catalog of at least one of the abnormal area description information needing to be processed from the blood pathology key feature of each of the second part of blood pathology image information with the second catalog; in response to each of the target abnormal area description information, combining the image location catalog of the target abnormal area description information and the image location catalog of at least one abnormal area description information needing to be processed corresponding to the target abnormal area description information, determining at least one image location analysis range, and taking the target abnormal area description information and the at least one abnormal area description information needing to be processed as image location repeated abnormal area description information in the image location analysis range.

[0010] In an independently implemented embodiment, the at least two image location repeated abnormal area description information in the image location analysis range meets the preset interval period requirement under the premise that the interval period is analyzed, and the interval period analysis range is determined based on the interval analysis catalog of each of the image location repeated abnormal area description information, including: combining the interval analysis catalog of the at least two image location repeated abnormal area description information in the image location analysis range, determining the interval period segment between each two image location repeated abnormal area description information; under the premise that the minimum interval period segment between the image location repeated abnormal area description information belonging to the blood pathology image information with differences in the image location analysis range is less than the repeated interval period threshold, the interval period analysis range is determined based on the interval analysis catalog of each of the image location repeated abnormal area description information.

[0011] In an independently implemented embodiment, the acquiring the first blood pathology key feature of each of the at least two first blood pathology image information comprises: generating the at least two first blood pathology image information from the to-be-determined blood pathology image information cluster based on at least one catalog; wherein each of the at least two first blood pathology image information has one of the at least one catalog; and acquiring the first blood pathology key feature of each of the at least two first blood pathology image information based on a two-dimensional space set in advance; wherein the first blood pathology key feature of each of the at least two first blood pathology image information comprises at least one abnormal region description information of the first blood pathology image information in the two-dimensional space.

[0012] In the application, the two-dimensional space is understood as an xy coordinate system, in which each information of blood is displayed in a column chart, and the information with a high value is abnormal, and the abnormal information can be mined according to the abnormal value.

[0013] In an independently implemented embodiment, the method further comprises: in response to each of the second blood pathology image information, generating a contact level between the second blood pathology image information and the at least two first blood pathology image information on the premise that the second blood pathology image information is generated to have a correlation with the at least two first blood pathology image information, and combining the number of abnormal region description information in the second blood pathology key feature of the second blood pathology image information; and generating and sending a blood information abnormality description result based on the contact level between each of the second blood pathology image information and the at least two first blood pathology image information.

[0014] In a second aspect, a blood pathology image analysis system based on an adaptive technology is provided, which comprises a processor and a memory in communication with each other, and the processor is configured to read a computer program from the memory and execute the computer program to implement the method described above.

[0015] The blood pathology image analysis method and system based on the adaptive technology provided in the application can accurately determine the abnormal points on the image, and can obtain the condition of the patient, thereby assisting medical staff to quickly treat the patient. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 A flowchart of a blood pathological image analysis method based on adaptive technology provided by the embodiments of the present application.

[0018] Figure 2 A block diagram of a blood pathological image analysis device based on adaptive technology provided by the embodiments of the present application.

[0019] Figure 3 An architecture diagram of a blood pathological image analysis system based on adaptive technology provided by the embodiments of the present application. DETAILED DESCRIPTION

[0020] In order to better understand the above technical solutions, the technical solutions of the present application will be described in detail below through the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0021] Please refer to Figure 1 , which shows a blood pathological image analysis method based on adaptive technology. The method can include the technical solutions described in steps 100-400.

[0022] Step 100: obtaining a first blood pathological key feature of each of at least two first blood pathological image information; wherein the at least two first blood pathological image information have consistent or similar directories, and each of the first blood pathological key features includes at least one abnormal region description information.

[0023] Wherein, the specific operation mode of the first blood pathological key feature includes: morphological operation: using erosion operation to remove small noise points in the binary image, then performing open operation (first erosion and then inflation), separating cells without close connection, and selecting a disc-shaped structural element.

[0024] The first blood pathology key features include components: composed of plasma and blood cells. Plasma is a pale yellow liquid, mainly composed of water, also contains protein, glucose, inorganic salt, etc. Blood cells include red blood cells, white blood cells and platelets. Color: due to the presence of hemoglobin, arterial blood is rich in oxygen and appears bright red, while venous blood contains more carbon dioxide and appears dark red. pH: the pH value is usually stable between 7.35-7.45, showing weak alkalinity, which is maintained by the body's acid-base buffer system. Viscosity: more viscous than water, mainly due to the presence of macromolecular substances such as components and proteins, with a relative viscosity of about 4-5, which is important for maintaining normal blood flow and blood pressure. Fluidity: continuously circulating in the cardiovascular system, the driving force comes from the pumping action of the heart, and the structure and function of blood vessels also ensure its normal flow. Physiological function: has transport function, can transport oxygen and nutrients to tissue cells, and transport metabolic waste to excretory organs; has defense and protection function, white blood cells can phagocytose pathogens, and antibodies and other immune substances in plasma can resist diseases; also maintains internal environment homeostasis, such as transporting heat to maintain body temperature and buffering acid-base changes to maintain pH stability.

[0025] At least two first blood pathology image information in the same or similar directory in the directory represent a label set in advance by a related technical personnel, such as blood fluidity, etc.

[0026] Step 200, comparing the abnormal area description information in the first blood pathology key features of the at least two first blood pathology image information, obtaining at least one comparison queue.

[0027] The comparison content includes: cell count: through specific software or instrument, the cells in the blood image are counted. For example, using a blood cell analyzer to automatically count red blood cells, white blood cells, platelets and other cells in the blood, and then comparing the number of cells in different samples. If the white blood cell count is significantly increased, it may indicate infection or other diseases. Morphological parameter measurement: use image analysis software to measure various morphological parameters of cells, such as cell diameter, circumference, area, and nuclear-cytoplasmic ratio. Taking red blood cells as an example, the average diameter of normal red blood cells is about 7-8 microns, if the red blood cell diameter is found to deviate significantly from the normal range, it may be related to anemia and other diseases. Gray scale analysis: analyze the gray scale values of cells or tissues in the image, which can reflect the optical density and other characteristics of the cells. For example, in bone marrow smear images, blood cells at different stages of development have different gray scale values, which can help determine the maturity and abnormality of blood cells.

[0028] Step 300, determining at least one second blood pathology image information existing in the at least one comparison queue in addition to the at least two first blood pathology image information, and a second blood pathology key feature of each of the second blood pathology image information in the at least one comparison queue.

[0029] Wherein, the second blood pathology key feature is the information of the abnormal area description information in the first blood pathology key feature through the real-time situation of the patient, such as poor flow, and the reasons for poor flow include: 1, lack of exercise: if long-term lack of exercise, it is easy to cause the decrease of blood vessel elasticity, and after the increase of blood viscosity, the blood circulation may not be smooth. Pay attention to appropriate increase of exercise amount, and promote blood circulation.

[0030] 2, high blood viscosity: if the blood viscosity is high, it may not be smooth for the blood circulation in the body, and then affect the health. Especially after suffering from diabetes, it can increase the blood viscosity, which can be treated by drug treatment under the guidance of doctors, such as aspirin enteric-coated capsules, clopidogrel sulfate tablets, etc.

[0031] 3, blood volume reduction: mainly due to the decrease of blood volume in the body, caused by bleeding, unemployment and other reasons. When the amount of blood in the body decreases to a certain extent, it will exceed the metabolic capacity of the body, causing the decrease of blood perfusion flow of tissues, and blood circulation disorder. Appropriate amount of edible salt can be added in drinking water to avoid electrolyte disorder. If the symptoms of hypovolemia are serious, it needs to be treated by intravenous fluid, colloidal fluid or crystal fluid, and even plasma transfusion.

[0032] Step 400, in response to each of the second blood pathology image information, generating the second blood pathology image information and the at least two first blood pathology image information exist correlation relationship on the premise that the number of abnormal area description information in the second blood pathology key feature of the second blood pathology image information exceeds the abnormal area description information quantity threshold.

[0033] Wherein, the blood description information includes: red blood cell count: the number of red blood cells in unit volume of blood, the normal range of adult male is generally (4.0-5.5) × 10¹² / L, and the normal range of adult female is (3.5-5.0) × 10¹² / L. The change of red blood cell count can reflect anemia, polycythemia and other diseases.

[0034] White blood cell count: the white blood cell count of normal adult peripheral blood is (4.0-10.0) × 10 9 / L. Leukocytosis is common in infection, inflammation, tissue damage, etc., and reduction may be related to viral infection, blood system diseases, etc.

[0035] Platelet count: normal range is (100-300) × 10 9 / L. Abnormal platelet counts can lead to problems such as bleeding tendency or thrombosis.

[0036] Blood cell morphology: Red blood cell morphology: Normal red blood cells are biconcave discs and are relatively uniform in size. Abnormal morphologies include spherocytes, ellipsoidal cells, target cells, and sickle cells. Different abnormal morphologies can help diagnose the type of anemia.

[0037] White blood cell morphology: White blood cells include neutrophils, lymphocytes, monocytes, eosinophils, and basophils. Observing their morphology, nuclear changes, and cytoplasmic granules can help determine the presence of infections, leukemia, and other diseases. For example, a left shift in the nucleus of a neutrophil is common in acute suppurative infections.

[0038] Platelet morphology: Normal platelets are round, oval, or irregular in shape. Abnormal platelet morphology, such as giant platelets or platelet aggregation, may be associated with certain blood disorders or thrombotic diseases.

[0039] Blood biochemical indicators: Blood sugar: The normal fasting blood sugar range is 3.9 to 6.1 mmol / L, and less than 7.8 mmol / L two hours after a meal. Elevated blood sugar levels are common in diabetes, while low blood sugar levels may be associated with hypoglycemia, pancreatic islet cell tumors, and other conditions.

[0040] Blood lipids: These include total cholesterol, triglycerides, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol. Normal total cholesterol levels are generally less than 5.2 mmol / L, and triglycerides are less than 1.7 mmol / L. Dyslipidemia is a significant risk factor for cardiovascular diseases such as atherosclerosis and coronary heart disease.

[0041] Liver function indicators: such as alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin, direct bilirubin, albumin, and globulin. Normal reference values ​​for ALT and AST are generally 0 to 40 U / L, and for total bilirubin are 3.4 to 17.1 μmol / L. Abnormal liver function indicators may indicate liver diseases such as hepatitis, cirrhosis, and liver cancer.

[0042] Renal function indicators: Commonly measured include creatinine, urea nitrogen, and uric acid. The normal range for creatinine in men is 53-106 μmol / L, and in women it is 44-97 μmol / L. Elevated renal function indicators often indicate renal impairment, which can be seen in various kidney diseases.

[0043] Coagulation function indicators: Prothrombin time (PT): normal reference value is 11-13 seconds, mainly reflects the function of the extrinsic coagulation system. PT prolongation is common in vitamin K deficiency, liver disease, oral anticoagulants, etc., and shortening may be related to high blood coagulation state.

[0044] Activated partial thromboplastin time (APTT): normal range is 25-37 seconds, mainly reflecting the function of the intrinsic coagulation system. APTT prolongation is common in hemophilia, liver disease, DIC, etc., and shortening can also be seen in high blood coagulation state.

[0045] Fibrinogen: normal reference value is 2-4g / L. Fibrinogen increases in infection, inflammation, malignant tumor, etc., and decreases in DIC, primary fibrinolysis, etc.

[0046] Blood immune indicators: Immunoglobulin: including IgG, IgA, IgM, IgD and IgE. IgG normal range is 7.0-17.0g / L, IgA is 0.7-3.8g / L, and IgM is 0.4-2.3g / L. Abnormal increase or decrease of immunoglobulin can be seen in various immune diseases, infectious diseases, multiple myeloma, etc.

[0047] Complement: such as C3, C4, etc. C3 normal reference value is 0.8-1.5g / L, and C4 is 0.1-0.4g / L. Changes in complement levels are related to autoimmune diseases, infectious diseases, etc.

[0048] Blood type: human blood type system mainly includes ABO blood type system and Rh blood type system. ABO blood type is divided into A type, B type, AB type and O type, and Rh blood type is divided into Rh positive and Rh negative. Blood type identification has important significance in blood transfusion, organ transplantation, parentage identification, etc.

[0049] Therefore, the abnormal area description signal indicates that there is a problem with the above information.

[0050] Steps 100-400 are a process of dynamic analysis for each patient in the present scheme, which can analyze the patient's information in real time and save it as a sample data. Under the premise of sufficient sample data, the present scheme can learn by itself and intelligently analyze the patient's blood report.

[0051] It needs to be understood that, in the execution of the above-mentioned steps 100-200, by analyzing at least two first blood pathological image information existing in consistent or similar catalogues, obtaining at least one comparison queue, and analyzing at least one second blood pathological image information existing in the at least one comparison queue in addition to the at least two first blood pathological image information, obtaining the second blood pathological image information having a correlation with the at least two first blood pathological image information, the abnormal points on the image can be accurately determined, the condition of the patient can be obtained, and the medical staff can be assisted to quickly treat the patient.

[0052] In relation to an embodiment that can be implemented, the generation of the second blood pathological image information having a correlation with the at least two first blood pathological image information on the premise that the number of abnormal region description information in the second blood pathological key feature of the second blood pathological image information exceeds the abnormal region description information number threshold value includes: generating a comparison queue associated with each abnormal region description information in the second blood pathological key feature on the premise that the number of abnormal region description information in the second blood pathological key feature of the second blood pathological image information exceeds the abnormal region description information number threshold value; and generating the second blood pathological image information having a correlation with the at least two first blood pathological image information on the premise that the number of comparison queues associated with the abnormal region description information in the second blood pathological key feature exceeds the first threshold value.

[0053] Based on the above, the following can also be included: generating a preset image debugging condition relationship between the at least two first blood pathological image information on the premise that the number of comparison queues exceeds the second threshold value; and the determination of at least one second blood pathological image information existing in the at least one comparison queue in addition to the at least two first blood pathological image information, and the second blood pathological key feature of each second blood pathological image information in the at least one comparison queue includes: determining at least one second blood pathological image information existing in the at least one comparison queue in addition to the at least two first blood pathological image information, and the second blood pathological key feature of each second blood pathological image information in the at least one comparison queue on the premise that a preset image debugging condition relationship exists between the at least two first blood pathological image information.

[0054] In the case of a possible embodiment, the at least two first blood pathology image information includes at least one first part of blood pathology image information existing in a first catalog and at least one second part of blood pathology image information existing in a second catalog, and the preset image debugging condition relationship includes a blood pathology image information splicing operation between the first part of blood pathology image information and the second part of blood pathology image information; and the generation of the preset image debugging condition relationship between the at least two first blood pathology image information on the premise that the number of comparison queues exceeds a second threshold value includes: On the premise that the number of comparison queues exceeds a second threshold value, the number of first part of blood pathology image information and the number of second part of blood pathology image information existing in the at least one comparison queue are determined one by one; and on the premise that the number of first part of blood pathology image information exceeds a first blood pathology image information number threshold value and the number of second part of blood pathology image information exceeds a second blood pathology image information number threshold value, it is determined that there is a blood pathology image information splicing operation between the first part of blood pathology image information and the second part of blood pathology image information.

[0055] In the case of a possible embodiment, the first catalog is understood as a complete information label of blood abnormalities.

[0056] In the case of a possible embodiment, the splicing operation includes: selecting a fusion method: there are a plurality of fusion methods to choose from, such as direct splicing, weighted average fusion, multi-resolution fusion, etc. Direct splicing is to simply splice the registered images together; weighted average fusion is to perform weighted average according to the pixel values of the image overlap area to achieve smooth transition; multi-resolution fusion is to process the images at different resolutions and then merge them, which can better preserve image details.

[0057] Perform fusion: according to the selected fusion method, the registered images are fused to generate spliced images. In the fusion process, the software will handle the pixel values of the overlapping area so that the splicing looks natural and smooth.

[0058] In the case of a possible embodiment, each of the abnormal region description information exists in an interval analysis catalog; and the comparison of the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information to obtain at least one comparison queue includes: The abnormal region description information in the first blood pathology key feature of the at least two first blood pathology image information is analyzed in image positions to obtain at least one image position analysis range and at least two image position repeated abnormal region description information in each image position analysis range; in response to each image position analysis range, at least two image position repeated abnormal region description information in the image position analysis range meets a preset interval period requirement in an interval period, an interval period analysis range is determined based on an interval analysis directory of each image position repeated abnormal region description information, and the image position analysis range and the interval period are combined for analysis to determine a first comparison queue.

[0059] In relation to a possible embodiment, the at least two first blood pathology image information includes at least one first part blood pathology image information with a first directory and at least one second part blood pathology image information with a second directory, the first directory is consistent with or similar to the second directory, and each abnormal region description information has an image position directory; the analysis of the abnormal region description information in the first blood pathology key feature of the at least two first blood pathology image information in image positions to obtain at least one image position analysis range and at least two image position repeated abnormal region description information in each image position analysis range includes: taking each abnormal region description information in the blood pathology key feature of each first part blood pathology image information with the first directory as abnormal region description information to be processed; determining target abnormal region description information associated with the image position directory of at least one abnormal region description information to be processed from the blood pathology key feature of each second part blood pathology image information with the second directory; in response to each target abnormal region description information, combining the image position directory of the target abnormal region description information and the image position directory of at least one abnormal region description information to be processed corresponding to the target abnormal region description information to determine at least one image position analysis range, and taking the target abnormal region description information and the at least one abnormal region description information to be processed as image position repeated abnormal region description information in the image position analysis range.

[0060] In the second directory, the blood abnormality information label is understood as information obtained according to the current patient's condition.

[0061] In the case of the embodiment, the abnormal area description information of at least two image positions in the image position analysis range is repeated, and the interval period analysis range is determined based on the interval analysis directory of each abnormal area description information of the image position repetition under the premise that the interval period meets the preset interval period requirement. The interval period analysis range is determined by combining the interval analysis directory of the abnormal area description information of at least two image positions in the image position analysis range, and determining the interval period segment between each two abnormal area description information of the image position repetition. The interval period analysis range is determined based on the interval analysis directory of each abnormal area description information of the image position repetition under the premise that the minimum interval period segment between the abnormal area description information of the image position repetition belonging to the blood pathological image information with differences in the image position analysis range is less than the repeated interval period threshold.

[0062] In the case of the embodiment, the first blood pathological key feature of each first blood pathological image information in the at least two first blood pathological image information is obtained by: generating the at least two first blood pathological image information from the to-be-determined blood pathological image information cluster based on at least one directory, wherein each first blood pathological image information has one of the at least one directory; and obtaining the first blood pathological key feature of each first blood pathological image information in the at least two first blood pathological image information based on the previously set two-dimensional space, wherein the first blood pathological key feature of each first blood pathological image information includes at least one abnormal area description information of the first blood pathological image information in the two-dimensional space.

[0063] Based on the above, the following can also be included: in response to each second blood pathological image information, generating a contact level between the second blood pathological image information and the at least two first blood pathological image information under the premise that the second blood pathological image information is generated to have a correlation with the at least two first blood pathological image information, and combining the number of abnormal area description information in the second blood pathological key feature of the second blood pathological image information; generating and sending a blood information abnormality description result based on the contact level between each second blood pathological image information and the at least two first blood pathological image information.

[0064] The contact level here is understood as a matching level, for example, the matching level is divided into 1-10, and the matching degree is higher as the level increases. The higher the matching degree, the more accurate the blood information abnormality description result.

[0065] In the above premise, please refer to Figure 2, provide a blood pathology image analysis device 200 based on adaptive technology, applied to a blood pathology image analysis system based on dynamic learning and adaptive technology, the device comprises: An information acquisition module 210 is configured to acquire first blood pathology key features of each of at least two first blood pathology image information; wherein the at least two first blood pathology image information have consistent or similar directories, and each of the first blood pathology key features includes at least one abnormal area description information; A queue obtaining module 220 is configured to compare the abnormal area description information in the first blood pathology key features of the at least two first blood pathology image information to obtain at least one comparison queue; A feature determining module 230 is configured to determine at least one second blood pathology image information other than the at least two first blood pathology image information existing in the at least one comparison queue, and second blood pathology key features of each of the second blood pathology image information in the at least one comparison queue; A data correlation module 240 is configured to, in response to each of the second blood pathology image information, generate a correlation between the second blood pathology image information and the at least two first blood pathology image information on the premise that the number of abnormal area description information in the second blood pathology key features of the second blood pathology image information exceeds an abnormal area description information quantity threshold.

[0066] In the above premise, please refer to Figure 3 , shows a blood pathology image analysis system 300 based on adaptive technology, comprising a processor 310 and a memory 320 in communication with each other, the processor 310 is used to read computer program from the memory 320 and execute to realize the above method.

[0067] In the above premise, a computer readable storage medium is also provided, and the computer program stored thereon realizes the above method when running.

[0068] In summary, based on the above scheme, by analyzing at least two first blood pathology image information with consistent or similar directories, at least one comparison queue is obtained, and at least one second blood pathology image information other than the at least two first blood pathology image information existing in the at least one comparison queue is analyzed to obtain second blood pathology image information having a correlation with the at least two first blood pathology image information, so as to accurately determine the abnormal points on the image, obtain the patient's condition, and assist medical staff to quickly treat the patient.

[0069] It should be understood that the systems and modules thereof described above can be implemented in various ways. For example, in some embodiments, the systems and modules thereof can be implemented in hardware, software, or a combination of software and hardware. The hardware portion can be implemented with special logic, while the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art will appreciate that the above-described methods and systems can be implemented using computer-executable instructions and / or in processor control code, for example, provided on a carrier medium such as a diskette, CD or DVD-ROM, programmable memory such as read-only memory (firmware), or data carrier such as an optical or electrical signal carrier. The systems and modules thereof of the present application can be implemented not only in hardware circuitry such as very large scale integration (VLSI) or gate array, semiconductor such as logic chips, transistors, or programmable hardware devices such as field programmable gate array (FPGA), programmable logic device (PLD), etc., but also in software, for example, executed by various types of processors, and in a combination of the above-mentioned hardware circuitry and software (e.g., firmware).

[0070] It should be noted that different embodiments can produce different beneficial results, and in different embodiments, the beneficial results that can be produced can be any one or a combination of the above, or any other beneficial results that can be obtained.

[0071] The above has described the basic concepts, and it is obvious that the above detailed disclosure is only used as an example and does not limit the present application. Although it is not explicitly stated herein, those skilled in the art can make various modifications, improvements and corrections to the present application. Such modifications, improvements and corrections are suggested in the present application, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present application.

[0072] Meanwhile, specific words are used in the present application to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that the "one embodiment" or "one embodiment" or "one alternative embodiment" mentioned in different places in the specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be properly combined.

[0073] Moreover, those skilled in the art will appreciate that the aspects of the application can be practiced with a variety of computer-system configurations, including personal computers, desktop computers, laptop computer, notebook computer, netbook computers, mainframe computers, handheld computers, workstation computers, cellular telephones, WAP-enabled telephones, PDA, set-top boxes, server computers, media players, a gaming system, interactive kiosks, and the like. Any of the above devices can be a special-purpose machine or be part of an array of such machines.

[0074] Computer storage media can include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program code, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, solid state drives (SSDs) that use flash memory, phase-change memory (PCM), or other memory technology, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, optical disk storage, including compact disks and DVDs, cloud storage, or any other medium which can be used to store the desired information, and which can be accessed by an instruction execution system. Note that the computer- storage media can be integrated within a computer system or be external to the computer system.

[0075] Computer program code for carrying out operations of aspects of the present application can be written in any combination of one or more programming languages, including an object- oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, or the like, conventional procedural programming languages, such as the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network ("LAN"), a wide area network ("WAN"), or the Internet, as in the case of cloud computing, or other forms of distributed computing.

[0076] In addition, unless expressly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that meet the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0077] Similarly, it should be noted that, in order to simplify the presentation of this application and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this application sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not mean that the subject matter of this application requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single embodiment disclosed above.

[0078] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0079] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this application, as well as documents (currently or subsequently attached to this application) that limit the broadest scope of the claims of this application. It should be noted that if the descriptions, definitions, and / or use of terms in the accompanying materials of this application are inconsistent or conflicting with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0080] In the foregoing specification, specific details are given to provide an understanding of the embodiments disclosed herein. However, the embodiments herein disclosed are only examples. Other embodiments can be used without departing from the spirit and scope of the disclosure. Hence, the specification and drawings are, at best, only illustrative and exemplary. Therefore, it is understood that the breadth and scope of the disclosure should not be limited by any of the above described embodiments, but should be defined only in accordance with the following claims and their equivalents.

[0081] The above merely illustrates the embodiments of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A blood pathology image analysis method based on adaptive technology, characterized in that: The method at least comprises: Obtaining a first blood pathology key feature of each of at least two first blood pathology image information; wherein the at least two first blood pathology image information have a consistent or similar directory, and each of the first blood pathology key features includes at least one abnormal region description information; Comparing the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information to obtain at least one comparison queue; determining at least one second piece of blood pathology image information other than the at least two first pieces of blood pathology image information present in the at least one comparison queue, and a second blood pathology key feature of each piece of the second blood pathology image information in the at least one comparison queue; In response to each second blood pathology image information, on the premise that the number of abnormal area description information in the second blood pathology key feature of the second blood pathology image information exceeds the abnormal area description information number threshold, it is generated that the second blood pathology image information has an association relationship with the at least two first blood pathology image information.

2. The method according to claim 1, characterized in that The generating of an association relationship between the second blood pathology image information and the at least two first blood pathology image information, on the premise that the amount of abnormal region description information in the second blood pathology key feature of the second blood pathology image information exceeds a threshold value of the amount of abnormal region description information, includes: generating a comparison queue associated with each abnormal region description information in the second blood pathology key feature, on the premise that the number of abnormal region description information in the second blood pathology key feature exceeds a threshold value for the number of abnormal region description information; On the premise that the number of comparison queues associated with the abnormal region description information in the second blood pathology key feature exceeds a first threshold, it is generated that the second blood pathology image information has an association relationship with the at least two first blood pathology image information.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: On the premise that the number of the comparison queues exceeds a second threshold, generating a preset image debugging situation relationship between the at least two first blood pathology image information; The determining of at least one second blood pathology image information other than the at least two first blood pathology image information present in the at least one comparison queue, and the second blood pathology key feature of each second blood pathology image information in the at least one comparison queue, includes: determining, on the premise that a preset image debugging situation relationship exists between the at least two first blood pathology image information, at least one second blood pathology image information other than the at least two first blood pathology image information present in the at least one comparison queue, and the second blood pathology key feature of each second blood pathology image information in the at least one comparison queue.

4. The method according to claim 3, characterized in that The at least two first blood pathology image information include at least one first portion of blood pathology image information stored in a first directory and at least one second portion of blood pathology image information stored in a second directory, the preset image debugging situation relationship includes a blood pathology image information splicing operation between the first portion of blood pathology image information and the second portion of blood pathology image information; and generating the preset image debugging situation relationship between the at least two first blood pathology image information, on the premise that the number of comparison queues exceeds a second threshold, includes: On the premise that the number of the comparison queues exceeds a second threshold, determining one by one the number of the first portion of blood pathology image information and the second portion of blood pathology image information existing in the at least one comparison queue; On the premise that the amount of the first part of blood pathology image information exceeds a first blood pathology image information amount threshold and the amount of the second part of blood pathology image information exceeds a second blood pathology image information amount threshold, it is determined that a blood pathology image information splicing operation occurs between the first part of blood pathology image information and the second part of blood pathology image information.

5. The method according to claim 4, characterized in that: Each abnormal region description information has an interval parsing directory; the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information is compared to obtain at least one comparison queue, including: Analyzing the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information at image positions to obtain at least one image position analysis range and abnormal region description information repeated at at least two image positions in each of the image position analysis ranges; In response to each of the image position analysis ranges, on the premise that the abnormal area description information repeated in at least two image positions in the image position analysis range meets the preset interval period requirements in terms of the interval period, an interval period analysis range is determined based on the interval parsing directory of the abnormal area description information repeated in each of the image positions, and the image position analysis range and the interval period are analyzed in combination to determine the first comparison queue.

6. The method according to claim 5, characterized in that The at least two first blood pathology image information include at least one first portion of blood pathology image information stored in a first directory and at least one second portion of blood pathology image information stored in a second directory, the first directory is consistent with or similar to the second directory, and each abnormal region description information is stored in an image position directory; the abnormal region description information in the first blood pathology key features of the at least two first blood pathology image information is analyzed at image positions to obtain at least one image position analysis range and abnormal region description information repeated at at least two image positions in each of the image position analysis ranges, including: taking each abnormal region description information in each of the blood pathology key features of the first part of the blood pathology image information stored in the first directory as abnormal region description information that needs to be processed; determining, from each of the blood pathology key features of the second portion of the blood pathology image information stored in the second directory, target abnormal region description information associated with at least one image position directory of the abnormal region description information that needs to be processed; In response to each of the target abnormal area description information, combined with the image position directory of the target abnormal area description information and the image position directory of at least one abnormal area description information that needs to be processed corresponding to the target abnormal area description information, at least one image position analysis range is determined, and the target abnormal area description information and the at least one abnormal area description information that needs to be processed are both used as abnormal area description information with repeated image positions in the image position analysis range.

7. The method according to claim 6, characterized in that On the premise that the abnormal region description information repeated at at least two image positions within the image position analysis range meets a preset interval period requirement in terms of the interval period, determining an interval period analysis range based on the interval parsing directory of each of the abnormal region description information repeated at the image position includes: Determine an interval period segment between each two pieces of abnormal region description information repeated at each image position in combination with an interval parsing directory of abnormal region description information repeated at at least two image positions in the image position analysis range; On the premise that the minimum interval period segment between the repeated abnormal area description information at the image position of the blood pathology image information with differences in the image position analysis range is less than the repeated interval period threshold, an interval period analysis range is determined based on the interval parsing directory of the repeated abnormal area description information at each image position.

8. The method according to claim 1, wherein: The step of obtaining a first blood pathology key feature of each of at least two first blood pathology image information includes: Based on at least one directory, generating at least two first blood pathology image information from the pending blood pathology image information cluster; wherein each first blood pathology image information exists in one of the at least one directory; Based on a previously set two-dimensional space, a first blood pathology key feature of each of the at least two first blood pathology image information is obtained; wherein the first blood pathology key feature of each of the first blood pathology image information includes at least one abnormal area description information of the first blood pathology image information in the two-dimensional space.

9. The method according to claim 1, wherein: The method further comprises: In response to each piece of second blood pathology image information, on the premise that a correlation relationship is generated between the second blood pathology image information and the at least two pieces of first blood pathology image information, and in combination with the amount of abnormal region description information in the second blood pathology key feature of the second blood pathology image information, generating a correlation level between the second blood pathology image information and the at least two pieces of first blood pathology image information; Based on the connection level between each piece of the second blood pathology image information and the at least two pieces of the first blood pathology image information, a blood information abnormality description result is generated and sent.

10. A blood pathology image analysis system based on adaptive technology, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 9.

Images