CN116046643A - Auxiliary diagnostic information providing device and blood analysis system - Google Patents
Auxiliary diagnostic information providing device and blood analysis system Download PDFInfo
- Publication number
- CN116046643A CN116046643A CN202310323347.9A CN202310323347A CN116046643A CN 116046643 A CN116046643 A CN 116046643A CN 202310323347 A CN202310323347 A CN 202310323347A CN 116046643 A CN116046643 A CN 116046643A
- Authority
- CN
- China
- Prior art keywords
- sample
- image
- sample analysis
- analysis image
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004159 blood analysis Methods 0.000 title claims abstract description 13
- 239000000523 sample Substances 0.000 claims abstract description 359
- 238000004458 analytical method Methods 0.000 claims abstract description 264
- 230000002159 abnormal effect Effects 0.000 claims abstract description 158
- 238000003745 diagnosis Methods 0.000 claims abstract description 152
- 238000001514 detection method Methods 0.000 claims abstract description 112
- 239000012472 biological sample Substances 0.000 claims abstract description 80
- 230000005856 abnormality Effects 0.000 claims abstract description 78
- 230000004913 activation Effects 0.000 claims abstract description 33
- 239000013074 reference sample Substances 0.000 claims description 92
- 238000010586 diagram Methods 0.000 claims description 56
- 210000004369 blood Anatomy 0.000 claims description 27
- 239000008280 blood Substances 0.000 claims description 27
- 210000000601 blood cell Anatomy 0.000 claims description 21
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 239000007788 liquid Substances 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 4
- 230000028993 immune response Effects 0.000 claims description 3
- 210000004027 cell Anatomy 0.000 description 27
- 238000000034 method Methods 0.000 description 14
- 238000000605 extraction Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 210000003743 erythrocyte Anatomy 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 4
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 210000000265 leukocyte Anatomy 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 239000008103 glucose Substances 0.000 description 3
- 210000004698 lymphocyte Anatomy 0.000 description 3
- 102000039446 nucleic acids Human genes 0.000 description 3
- 108020004707 nucleic acids Proteins 0.000 description 3
- 150000007523 nucleic acids Chemical class 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 208000010110 spontaneous platelet aggregation Diseases 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 102000009027 Albumins Human genes 0.000 description 2
- 108010088751 Albumins Proteins 0.000 description 2
- 102000002260 Alkaline Phosphatase Human genes 0.000 description 2
- 108020004774 Alkaline Phosphatase Proteins 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 108010023302 HDL Cholesterol Proteins 0.000 description 2
- 108010028554 LDL Cholesterol Proteins 0.000 description 2
- 208000002693 Multiple Abnormalities Diseases 0.000 description 2
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 description 2
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 description 2
- 210000003651 basophil Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000012000 cholesterol Nutrition 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000002526 effect on cardiovascular system Effects 0.000 description 2
- 210000003714 granulocyte Anatomy 0.000 description 2
- 230000001900 immune effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000003924 normoblast Anatomy 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 description 2
- 229940116269 uric acid Drugs 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 description 1
- 108010082126 Alanine transaminase Proteins 0.000 description 1
- 206010003445 Ascites Diseases 0.000 description 1
- 108010003415 Aspartate Aminotransferases Proteins 0.000 description 1
- 102000004625 Aspartate Aminotransferases Human genes 0.000 description 1
- 208000027205 Congenital disease Diseases 0.000 description 1
- 238000008789 Direct Bilirubin Methods 0.000 description 1
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 206010048612 Hydrothorax Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000008050 Total Bilirubin Reagent Methods 0.000 description 1
- PNNCWTXUWKENPE-UHFFFAOYSA-N [N].NC(N)=O Chemical compound [N].NC(N)=O PNNCWTXUWKENPE-UHFFFAOYSA-N 0.000 description 1
- 238000000149 argon plasma sintering Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012742 biochemical analysis Methods 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 229940109239 creatinine Drugs 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002124 endocrine Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003979 eosinophil Anatomy 0.000 description 1
- 238000000684 flow cytometry Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000007850 fluorescent dye Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003018 immunoassay Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000386 microscopy Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000000440 neutrophil Anatomy 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 210000004180 plasmocyte Anatomy 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000007261 regionalization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 210000001995 reticulocyte Anatomy 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 238000000790 scattering method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 210000001179 synovial fluid Anatomy 0.000 description 1
- 210000001685 thyroid gland Anatomy 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/00584—Control arrangements for automatic analysers
- G01N35/00594—Quality control, including calibration or testing of components of the analyser
- G01N35/00712—Automatic status testing, e.g. at start-up or periodic
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1026—Recognising analyser failures, e.g. bubbles; Quality control for particle analysers
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Dispersion Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The application provides an auxiliary diagnostic information providing device and blood analysis system, the auxiliary diagnostic information providing device includes: the acquisition module is used for acquiring sample detection data obtained by detection analysis of a biological sample of an object to be detected; the first abnormal recognition module is used for obtaining first abnormal characteristic information representing abnormal characteristics in the sample analysis image according to the sample analysis image; a second abnormality identification module for obtaining second abnormality characteristic information characterizing abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter; and the output module is used for outputting an auxiliary diagnosis report comprising auxiliary diagnosis category information, an activation graph and a sample analysis image carrying a positioning mark. The auxiliary diagnosis report provides an activation graph and a sample analysis image with a positioning mark, so that a doctor can quickly grasp the diagnosis basis of the currently obtained auxiliary diagnosis type information to judge the reliability of the current auxiliary diagnosis type information.
Description
Technical Field
The present application relates to the field of medical assistance, and more particularly, to an assistance diagnosis information providing apparatus and a blood analysis system.
Background
In the field of medical diagnosis, it is very common practice to collect biological samples such as blood, urine, saliva, etc. of a patient and perform detection analysis to obtain sample detection data, which can provide a doctor with a judgment that the patient may have a certain disease.
At present, sample detection data obtained by detecting and analyzing biological samples is mainly completed by doctors according to experience and learning. On one hand, the utilization of sample detection data is very limited by personal experience and learning of doctors, and important information is easy to appear and cannot be effectively identified and utilized; on the other hand, the identification of a large amount of sample detection data can take up much time and effort from a doctor, severely affecting diagnosis efficiency.
With the improvement of the technological and informationized degree of the medical industry, in recent years, an auxiliary diagnosis application system based on computer intelligent assistance starts to develop gradually, and analysis and identification are performed on sample detection data through the auxiliary diagnosis application system so as to identify abnormal information in the sample detection data and provide the abnormal information for doctors, so that the doctors are assisted in making diagnosis decisions. However, in the scheme of the auxiliary diagnostic application system which is currently known to be adopted, a doctor often cannot know how to determine whether the auxiliary diagnostic application system obtains abnormal information, so that the doctor has great trouble on whether to adopt the identification information provided by the auxiliary diagnostic application system, and practical application and development of the auxiliary diagnostic technology are greatly limited.
Disclosure of Invention
In order to solve the technical problems, the application provides an accurate and efficient auxiliary diagnosis information providing device and a blood analysis system, which can be beneficial to effectively verifying auxiliary diagnosis results.
In a first aspect of an embodiment of the present application, there is provided an auxiliary diagnostic information providing apparatus including:
the acquisition module is used for acquiring sample detection data obtained by detection analysis of a biological sample of an object to be detected; the sample detection data comprises a sample analysis image and sample detection parameters;
the first abnormal recognition module is used for obtaining first abnormal characteristic information representing abnormal characteristics in the sample analysis image according to the sample analysis image;
a second abnormality identification module for obtaining second abnormality characteristic information characterizing abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter;
the output module is used for outputting an auxiliary diagnosis report according to the sample analysis image, the first abnormal characteristic information and the second abnormal characteristic information, and the auxiliary diagnosis report comprises:
auxiliary diagnostic category information;
an activation map for highlighting a diagnostic basis of the first abnormal feature information, the activation map being superimposed by a thermodynamic diagram obtained based on a feature map of the sample analysis image and the biological sample analysis image; wherein the thermodynamic diagram characterizes the degree of decision impact of each unit region of the sample analysis image on determining the first anomaly characteristic information;
The sample analysis image carries a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image.
In a second aspect of the embodiments of the present application, there is provided an auxiliary diagnostic information providing apparatus, including:
the acquisition module is used for acquiring sample detection data obtained by detection analysis of a biological sample of an object to be detected; the sample detection data comprises a sample analysis image and sample detection parameters;
the first abnormal recognition module is used for obtaining first abnormal characteristic information representing abnormal characteristics in the sample analysis image according to the sample analysis image;
a second abnormality identification module for obtaining second abnormality characteristic information characterizing abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter;
the output module is used for outputting an auxiliary diagnosis report according to the sample analysis image, the first abnormal characteristic information and the second abnormal characteristic information, and the auxiliary diagnosis report comprises:
auxiliary diagnostic category information;
the sample analysis image carrying a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image;
A target reference sample image matched with the sample analysis image, wherein the target reference sample image is a reference image with similarity meeting a preset condition with the sample analysis image in a sample analysis image library; the sample analysis image library comprises sample analysis images of historical diagnosis cases confirmed by microscopic examination, and the positioning marks in the target reference sample image are used for highlighting the positions of the diagnosis basis for obtaining the first abnormal characteristic information.
In a third aspect of embodiments of the present application, there is provided a blood analysis system comprising:
the sampling assembly is used for collecting and distributing a biological sample of an object to be detected, wherein the biological sample is a blood sample;
the reaction component is used for processing the biological sample to form a liquid to be tested;
the driving assembly is used for driving a liquid path between the sampling assembly and the reaction assembly;
the detection component is used for classifying and counting blood cells contained in the liquid to be detected to obtain sample detection data containing sample detection parameters and sample analysis images;
the auxiliary diagnostic information providing apparatus as described in any one of the embodiments of the present application is configured to output an auxiliary diagnostic report based on the sample detection data.
In the above embodiment, the auxiliary diagnosis information providing apparatus obtains first abnormal feature information characterizing abnormal features in the sample analysis image by analyzing and recognizing the sample analysis image, and obtains second abnormal feature information characterizing abnormal parameter values in the biological sample determined based on the sample detection parameters, and outputs an auxiliary diagnosis report according to the sample analysis image, the first abnormal feature information, and the second abnormal feature information, wherein the auxiliary diagnosis report includes auxiliary diagnosis category information, a sample analysis image showing the position of the first abnormal feature information through a positioning mark, and a target reference sample image obtained by highlighting an activation image/a history diagnosis example of diagnostic basis of the first abnormal feature information obtained based on the sample analysis image, so that a user can obtain not only the auxiliary diagnosis category information determined by comprehensive multi-aspect information but also the accuracy and efficiency of the auxiliary diagnosis result through the auxiliary diagnosis report; moreover, through the activation image/the target reference sample image confirmed by microscopic examination output in the auxiliary diagnosis report, the sample analysis image carrying the positioning mark is convenient for doctors to rapidly verify the accuracy of the current auxiliary diagnosis type information so as to judge the reliability of the current auxiliary diagnosis type information, thereby considering whether the current auxiliary diagnosis type information is adopted.
The blood analysis system provided in the above embodiment has the same technical concept as the corresponding embodiments of the auxiliary diagnostic information providing apparatuses, so as to have the same technical effects, and will not be described herein.
Drawings
FIG. 1 is an alternative application scenario diagram of an auxiliary diagnostic information providing apparatus according to an embodiment of the present application;
FIG. 2 is an alternative application scenario diagram of an auxiliary diagnostic information providing apparatus according to another embodiment of the present application;
FIG. 3 is a schematic diagram of an auxiliary diagnostic information providing apparatus according to an embodiment;
FIG. 4 is a schematic diagram of an interface for providing auxiliary diagnostic reports according to an embodiment;
FIG. 5 is a schematic diagram showing a structure of an auxiliary diagnostic information providing apparatus according to another embodiment;
fig. 6 is a schematic structural diagram of a blood analysis system according to an embodiment.
Detailed Description
The technical scheme of the application is further elaborated below by referring to the drawings in the specification and the specific embodiments.
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 application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the implementations of the present application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In the following description, reference is made to the expression "some embodiments" which describe a subset of the possible embodiments, but it should be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
In the following description, the terms "first," second, "and the like are used merely to distinguish similar objects and do not represent a particular ordering of the objects, it being understood that the terms" first, "" second, "and third," if allowed, may be interchanged with a particular order or precedence, to enable embodiments of the present application described herein to be implemented in other than those illustrated or described herein.
Referring to fig. 1, an optional application scenario diagram of an auxiliary diagnostic information providing apparatus according to an embodiment of the present application is shown, where the auxiliary diagnostic information providing apparatus 11 may refer to a computer program product, such as various application programs, based on a computer program flow, for implementing an auxiliary diagnostic function; and may also refer to auxiliary diagnostic devices such as various types of intelligent devices having storage and computing capabilities loaded with a corresponding computer program product to perform auxiliary diagnostic functions.
In practical application, the auxiliary diagnostic information providing apparatus 11 refers to an auxiliary diagnostic device loaded with a corresponding computer program product, and may be a physically independent smart device or may be integrated with a known smart device; as shown in fig. 1, the auxiliary diagnostic information providing apparatus 11 is a smart device, such as a smart phone, a personal computer, a medical diagnostic instrument, a cloud server, or the like, which is physically separated from the sample analyzer 21; referring to fig. 2, the auxiliary diagnostic information providing device 11 is integrated with a sample analyzer 21, such as a sample analyzer loaded with a corresponding computer program product.
The auxiliary diagnostic information providing apparatus 11 may be provided in communication with an output interface of an application system for performing detection analysis on a sample in the sample analyzer 21 for acquiring sample detection data obtained after the detection analysis is performed on a biological sample of an object to be detected from the sample analyzer 21. The sample analyzer 21 may refer to a device for performing intelligent detection analysis on a collected biological sample. The biological sample may be a sample which is taken from the body of the subject to be detected and contains various biological cell information or other biological information, such as a blood sample, a urine sample, other body fluid (hydrothorax and ascites, cerebrospinal fluid, serosal cavity effusion, synovial fluid) sample, etc., and the biological cell type may be at least one of the group consisting of neutrophils, lymphocytes, monospheres, eosinophils and basophils; but also immature granulocytes, tumor cells, lymphoblasts, plasma cells, atypical lymphocytes, pre-erythroblasts, basal erythrocytes and polychromatic erythrocytes, orthochromatic erythrocytes, pre-megablasts, basal megablasts, polychromatic megacytes and nucleated erythrocytes selected from the group consisting of orthochromatic megaerythrocytes and megakaryospheres.
The auxiliary diagnosis information providing apparatus 11 obtains sample detection data obtained by detecting and analyzing the biological sample by the sample analyzer 21, and can determine abnormal characteristics of the biological sample by combining clinical information of an object to be detected, the sample detection data and a case database formed according to a history diagnosis record, and output an auxiliary diagnosis report according to the recognized abnormal characteristics of the biological sample, wherein the auxiliary diagnosis report provides auxiliary diagnosis category information determined based on the abnormal characteristics in the biological sample and a diagnosis basis for obtaining the auxiliary diagnosis category information. Therefore, a user can more intuitively know the condition of a possible existing or potential disease of an object to be detected by checking the auxiliary diagnosis report, and for the condition that the abnormality exists, an accurate auxiliary diagnosis result can be obtained by knowing a diagnosis basis provided in the auxiliary diagnosis report without depending on the personal experience level of a checking doctor, so that the checking efficiency can be improved, the detection result is more accurate, the diagnosis conclusion is more interpretable, the detection result can be converted into a descriptive auxiliary diagnosis report according to a sample detection image and sample detection parameters obtained by a sample analyzer, the workload of screening detection data by the auxiliary checking doctor is reduced, and the grading diagnosis policy can be matched better by means of the result in the auxiliary diagnosis report.
Alternatively, in determining the auxiliary diagnostic information providing apparatus 11, various data of the subject to be detected, such as clinical information data showing individual difference conditions of the subject to be detected, including sex, age, medical history, etc., may be comprehensively considered. The utilization of clinical information data by the auxiliary diagnostic information providing apparatus 11 may be embodied in a plurality of stages: one stage is sample detection data obtained by the sample analyzer 21 in the process of detecting and analyzing the biological sample of the object to be detected, wherein the sample analyzer 21 takes clinical information data of the object to be detected into consideration to calibrate the obtained sample detection data; the other stage is that the auxiliary diagnostic information providing apparatus 11 directly acquires clinical information data of the object to be detected, and further comprehensively considers the clinical information data of the object to be detected to calibrate the acquired auxiliary diagnostic category information in determining the auxiliary diagnostic category information based on the sample analysis image, the identified first abnormal feature information and the second abnormal feature information. In some embodiments, the auxiliary diagnostic information providing device 11 is set to use clinical information data of the object to be tested, including the second stage, where the auxiliary diagnostic information providing device 11 is in communication connection with a test information system (Laboratory Information System, LIS), and the test information system generally includes application terminals disposed at different positions of a diagnosis guiding table, a clinical laboratory, etc. of the hospital, and may be used to receive test data, enter and store patient test information, and assist the hospital in information management. The auxiliary diagnostic information providing apparatus 11 may obtain clinical information data of a specified category of the object to be detected directly from the inspection information system.
In order to facilitate understanding of the technical implementation of the auxiliary diagnostic information providing apparatus 11 provided in the embodiment of the present application, in the description of the present application, a specific example will be mainly described in detail taking a biological sample as a blood sample, and the sample analyzer 21 refers to a blood cell analyzer. The known blood cell analyzer is a typical application of flow cytometry, the impedance channel for cell counting uses the coulter electrical impedance principle, the colorimetric principle is used for hemoglobin concentration measurement, and the optical channel of the blood cell analyzer for higher end such as white blood cell classification, reticulocyte identification, nucleated red blood cell identification, basophil identification, low-value platelet identification, primitive cell identification and the like uses a laser scattering method and a nucleic acid fluorescent staining technique, and the aim of the above techniques is to convert biological characteristics such as the size of blood cells, the complexity of cell contents, the nucleic acid content and the like into electric pulse signals which can be raw data collected by the blood cell analyzer, and the collected electric pulse signals are analyzed to output sample analysis images and numerical sample detection parameters which characterize blood cell characteristics. However, it should be noted that, although the description of the embodiments of the present application describes sample detection data as detection analysis data of a blood sample, it should not be construed as limiting the scope of the present application. For example, in other embodiments, the sample analyzer 21 may be a biochemical analyzer, where the biological sample to be analyzed is different according to different detection requirements, such as for liver function detection, and the biochemical analyzer analyzes glutamic pyruvic transaminase (ALT/GPT), glutamic oxaloacetic transaminase (AST/GOT) alkaline phosphatase (ALP) total bilirubin (t.bil) direct bilirubin (d.bil), total Protein (TP), albumin (ALB) in the biological sample to be detected. For kidney function detection, a biochemical analyzer detects urea nitrogen (BUN), creatinine (Cre), carbon dioxide binding force (CO 2), uric Acid (UA) in a biological sample of a subject to be detected. For example, for blood lipid detection, the biochemical analyzer analyzes total Cholesterol (CHO), triglyceride (TG), high density lipoprotein cholesterol (HDL-C), and low density lipoprotein cholesterol (LDL-C) in a biological sample of a subject. For blood glucose testing, a biochemical analyzer analyzes Glucose (GLU) in a biological sample. In addition, in other embodiments, the sample analyzer 21 may be an immune analyzer, and is configured to analyze tumor markers, thyroid function related features, reproduction/endocrine related features, cardiovascular type related features, and/or congenital disease related features in a biological sample to obtain corresponding sample detection data. In other further embodiments, the sample detection data of the object to be detected may be from a plurality of different sample analyzers 21, such as the blood cell analyzer, the biochemical analyzer, and the immunological analyzer. Accordingly, the sample detection data acquired by the auxiliary diagnostic information providing apparatus 11 may include one or more of blood cell analysis data, biochemical analysis data, and immunological analysis data.
Referring to fig. 3, a schematic structural diagram of an auxiliary diagnostic information providing apparatus according to an embodiment of the present application includes an obtaining module 111, a first abnormality identifying module 112, a second abnormality identifying module 113 and an output module 114a.
The acquiring module 111 is configured to acquire sample detection data obtained by performing detection analysis on a biological sample of an object to be detected; the sample detection data includes a sample analysis image and a sample detection parameter.
The object to be detected refers to the person to whom the biological sample belongs, and takes the biological sample as a blood sample of a human body as an example, and the object to be detected generally refers to a patient who provides the blood sample. The sample detection data is corresponding analysis data obtained by counting and detecting various biological samples containing biological cell information or other biological information. The sample analysis image is image type detection data which is obtained by counting, detecting and analyzing the biological sample by a sample analyzer and can characterize the characteristics of the biological sample. Specifically, the sample analysis image may be a graph obtained by analyzing a pulse signal detected by a sample, or may be a data matrix obtained by analyzing a pulse signal, and the data matrix may be displayed on the instrument interface in a visual graph manner. The sample detection parameter is numerical detection data which is obtained after the sample analyzer detects and analyzes the biological sample and can characterize the characteristics of the biological sample. The biological sample characteristic can be a healthy characteristic or an unhealthy characteristic of different types of cells corresponding to the biological sample, such as abnormal cell type, cell number characteristic, cell size characteristic, cell composition proportion characteristic, cell content characteristic, nucleic acid content characteristic and the like in the biological sample. The sample detection data obtained by detecting and analyzing the biological sample of the object to be detected may be a sample detection data obtained by detecting and analyzing the biological sample of the object to be detected by a sample analyzer, which is communicatively connected to the sample analyzer.
Optionally, the acquiring module 111 is further configured to acquire clinical information data of the object to be detected. The auxiliary diagnosis information providing device can be set to provide an information input interface for man-machine interaction operation, and a user inputs corresponding information in each configuration item of the information input interface to obtain clinical information data of an object to be detected; alternatively, the auxiliary diagnostic information providing apparatus may be provided in communication with a test information system from which clinical information data of each object to be detected is imported. The auxiliary diagnosis information providing device is used for identifying abnormal characteristics in the biological sample by comprehensively considering clinical information data and sample detection data through obtaining the clinical information data of the object to be detected, and analyzing sample analysis images by comprehensively considering attribute information such as age, sex, medical history and the like of the object to be detected in the process of obtaining auxiliary diagnosis type information, so that more accurate auxiliary diagnosis results can be obtained under the condition of considering individual differences of different objects to be detected.
The first anomaly identification module 112 is configured to obtain first anomaly characteristic information that characterizes an anomaly characteristic in the sample analysis image according to the sample analysis image.
The abnormal characteristics refer to image characteristics capable of reflecting unhealthy states of objects to be detected in a sample analysis image. Such as PLT histogram in sample detection data for blood samples, the abnormal feature refers to an image feature in the PLT histogram that can reflect abnormal distribution of the number of platelets of different sizes in blood of an object to be detected. The first abnormal feature information is result information outputted by the pointer to the recognition result of the abnormal feature in the recognized sample analysis image. The type of the result information output in response to the recognition result of the abnormal feature in the sample analysis image may be various depending on the image recognition algorithm used. In this embodiment of the present application, the first abnormal feature information includes at least a category of abnormal features in the sample analysis image, such as presence of small red blood cell interference, small number of platelets, and the like.
The second abnormality identification module 113 is configured to obtain second abnormality characteristic information that characterizes abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter.
The second abnormal characteristic information is mainly obtained in two forms, namely, the auxiliary diagnosis information providing device obtains sample detection parameters from a third party, and the parameter value is abnormal through comprehensively considering clinical information data of an object to be detected and the sample detection parameters and comparing the clinical information data with a corresponding standard parameter table; secondly, the clinical information data and the sample detection parameters of the object to be detected are comprehensively considered by a third party, the parameter value abnormality is determined by comparing the clinical information data and the sample detection parameters with the corresponding standard parameter table, and the auxiliary diagnosis information providing device can directly obtain the identification result of the parameter value abnormality from the third party. The third party refers to a logic body which is relatively independent from the auxiliary diagnosis information providing apparatus, and can be a sample analyzer, a test information system and the like.
It should be noted that, based on the form of the second abnormal characteristic information that characterizes the abnormality of the parameter value in the biological sample and is determined by the sample detection parameter, a plurality of forms may be set according to the requirements of different types of users to read. For example, for a patient user, a more readable form is typically one in which a parameter value is above or below a standard parameter; what is more desirable for the physician user is the value of a certain parameter and the corresponding standard parameter value.
The output module 114a is configured to output an auxiliary diagnostic report according to the sample analysis image, the first abnormal feature information, and the second abnormal feature information, where the auxiliary diagnostic report includes: auxiliary diagnostic category information; an activation map for highlighting a diagnostic basis of the first abnormal feature information, the activation map being superimposed by a thermodynamic diagram obtained based on a feature map of the sample analysis image and the sample analysis image; wherein the thermodynamic diagram characterizes the degree of decision impact of each unit region of the sample analysis image on determining the first anomaly characteristic information; the sample analysis image carries a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image.
The auxiliary diagnosis report can be set into various forms such as a simplified form, a detailed form and the like, a plurality of display partitions can be set according to different contents to be displayed in the auxiliary diagnosis report, and in the embodiment, the auxiliary diagnosis report at least comprises an analysis display area for displaying auxiliary diagnosis category information in a targeted manner and an image display area for displaying an activation image and a sample analysis image carrying a positioning mark in a targeted manner. Referring to fig. 4, an interface diagram of an auxiliary diagnostic report according to an embodiment is shown. The auxiliary diagnosis type information refers to conclusion information of the unhealthy type of the current object to be detected, which is obtained by the auxiliary diagnosis information providing device according to the obtained sample detection data, the first abnormal characteristic information and the second abnormal characteristic information, and whether the unhealthy state exists in the object to be detected, which is determined after comprehensive analysis. The auxiliary diagnosis information providing device obtains auxiliary diagnosis category information based on the sample analysis image, the first abnormal feature information and the second abnormal feature information, and may be: the auxiliary diagnosis information providing apparatus obtains auxiliary diagnosis category information by inputting the sample analysis image, the first abnormality feature information, and the second abnormality feature information into a diagnosis database constructed based on the history diagnosis examples, and by a correspondence between the diagnosis category and the condition provided in the diagnosis database. Optionally, the auxiliary diagnosis category information further comprises diagnosis and treatment suggestions corresponding to the currently obtained conclusion information of the unhealthy type.
The thermodynamic diagram can be a characteristic diagram obtained by a characteristic extraction network in a neural network model, the weight value of each channel of the characteristic diagram output to a classification output layer by the characteristic extraction network is calculated, a machine vision visualization algorithm is adopted to carry out linear weighted summation on the image characteristics output by each channel based on the weight value, and the image displayed correspondingly according to the linear weighted summation result, namely, the neural network model outputs the image of the region concerned corresponding to the classification result. In an alternative specific example, the machine vision visualization algorithm refers to a Grad-CAM algorithm, and by utilizing the characteristic that the back propagation between adjacent network layers in the neural network model reaches training learning, different types of neural network models (such as a deep convolutional neural network VGG and a residual neural network ResNet) can be compatible without retraining to obtain a thermodynamic diagram; in this embodiment, the Grad-CAM algorithm calculates the weight value of each channel of the feature map by using the back-propagation gradient of the classified Convolutional Neural Network (CNN), as shown in equation one below:
In the formula one, c represents the category, yc is the value of logits corresponding to the category (i.e., the value that has not passed through the classified output layer (Softmax layer)), a represents the feature map (image feature output by the feature extraction network), k represents the channel of the feature map, ij represents the abscissa and ordinate of the feature map, and Z represents the size (i.e., length by width) of the feature map. The Grad-CAM algorithm is equivalent to the process of obtaining the thermodynamic diagram based on the input image, namely solving the average value of gradients on the feature map of the input image, realizing global average pooling operation, obtaining weights and then linearly weighting and fusing channels of the feature map together to obtain the thermodynamic diagram, wherein the thermodynamic diagram is represented by the following formula II:
In the second formula, grad-CAM adds a linear weighting (Relu function) to the fused thermodynamic diagram, and only the region with positive effect on the category c is reserved, so that the image of the region concerned of the neural network model output corresponding to the classification result is obtained. The activation graph is obtained by superposing the thermodynamic diagram and the sample analysis image, so that the activation graph can more intuitively display the importance degree of different areas for obtaining the first abnormal characteristic information in the sample analysis graph, the neural network model can be fully utilized to conduct identification analysis on the sample analysis image to compensate deviation caused by personal differences of doctors, more image characteristics which are indistinguishable by human eyes can be fully utilized to achieve improvement of identification accuracy and identification precision, and more importantly, the basis of the first abnormal characteristic information obtained by the neural network model based on the sample analysis image can be obtained and presented in an auxiliary diagnosis report in a visual mode.
The sample analysis image carrying the positioning mark shows the position of the first abnormal characteristic information in the sample analysis image correspondingly through the positioning mark, so that the important focused region of the sample analysis image is mastered according to the image region defined by the positioning mark, and the accuracy of the first abnormal characteristic information obtained at present is also convenient to judge quickly.
In this embodiment of the present application, the sample analysis image refers to an image formed by counting and detecting cells in a biological sample taken from an object to be detected, and according to the different counting and detecting principles adopted, the obtained image is capable of representing the variation of electrical parameters or optical parameters of cell differences in the biological sample, and identifying different cell types, obtaining cell counts, distribution conditions and other cell characteristics through the cell differences. The sample analysis image is different from cell imaging images representing the forms of substances such as a cell form image, a cardiovascular image, a human tissue image and the like obtained by a camera, a microscope and an endoscope, and the cell imaging images are still analog representation data of biological samples; in the embodiment of the application, the sample analysis image is used for detecting and analyzing the biological sample, so that quantitative characterization results which can more accurately characterize cell characteristics such as cell differences, quantity and distribution conditions in the biological sample can be obtained, the conversion of the biological sample characterization from analog to digital is completed, and the sample analysis image can carry digitized biological sample characteristic information. The auxiliary diagnosis information providing device takes the sample analysis image as the input for determining the first abnormal characteristic information, and can mine abnormal characteristics which cannot be identified only by the cell imaging image in the biological sample, so that the accuracy and the reference value of an auxiliary diagnosis result are effectively improved. In the auxiliary diagnostic information providing apparatus, the first abnormality characteristic information obtained by the first abnormality identifying module may identify an abnormality of a biological sample characteristic in the sample analysis image that is not obtainable from the cell imaging image; based on an activation graph obtained by superposing the thermodynamic diagram and the sample analysis image, the influence degree of each image area in the sample analysis image on the recognition result of the abnormal condition of the obtained biological sample characteristics can be represented, and information which is difficult to distinguish by human eyes and is intelligently extracted by a computer can be converted into a visual result. The auxiliary diagnosis report is used for displaying auxiliary diagnosis category information of the biological sample, an activation graph and a sample analysis image carrying a positioning mark, so that biological sample characteristics corresponding to abnormal characteristic information, such as cell types, forms and quantity distribution conditions in the biological sample, can be rapidly positioned, and the reliability of the currently obtained auxiliary diagnosis category information is analyzed and judged according to the characterization condition of the decision influence degree of the activation graph.
In the above embodiment, the auxiliary diagnosis information providing apparatus obtains the first abnormal feature information characterizing the abnormal feature in the sample analysis image by analyzing and identifying the sample analysis image, and obtains the second abnormal feature information characterizing the abnormal parameter value in the biological sample determined based on the sample detection parameter, and outputs the auxiliary diagnosis report according to the sample analysis image, the first abnormal feature information and the second abnormal feature information, wherein the auxiliary diagnosis report includes the auxiliary diagnosis category information, the sample analysis image by locating and marking the position of the first abnormal feature information, and the activation map highlighting the diagnosis basis of the first abnormal feature information obtained based on the sample analysis image, so that the user can obtain the auxiliary diagnosis category information determined by comprehensive multi-aspect information through the auxiliary diagnosis report, and fully uses the computer intelligence to identify the sample analysis image to excavate more image information containing the biological sample feature in depth, thereby improving the accuracy and efficiency of the auxiliary diagnosis result; and the accuracy of the current auxiliary diagnosis type information can be verified quickly by a doctor through the activation graph and the sample analysis image of the positioning mark which are output in the auxiliary diagnosis report, so that whether the current auxiliary diagnosis type information is adopted is considered.
In some embodiments, the auxiliary diagnostic report further comprises:
a target reference sample map matched to the sample analysis image; the target reference sample image is a reference image with similarity meeting preset conditions with the sample analysis image in a sample analysis image library; the sample analysis image library contains sample analysis images of historical diagnosis cases confirmed by microscopic examination.
Wherein the auxiliary diagnostic report further comprises a target reference sample graph displayed in the image display area. The sample analysis image library is a pre-established image database. The historical diagnosis example refers to a diagnosis record for determining whether the biological sample is abnormal or not based on sample detection data, clinical information data and corresponding standard parameter tables of the biological sample of the object to be detected, and judging conclusion information of an unhealthy type to which the object to be detected belongs. For example, a biological sample of the user a is collected as a blood sample, and according to the whole blood detection performed by the user a at the time 1, the whole blood detection record a1 correspondingly includes blood cell analysis data output by the blood detector for the blood sample of the user a at the time 1, clinical information data corresponding to the blood sample detection performed by the user a at the time 1 in the inspection information system, and comprehensive judgment made by the inspection doctor by using the data, and after the whole blood detection record a1 is subjected to microscopic examination confirmation by the user a at the time 1, the whole blood detection record a1 can be used as a historical diagnosis example of the diagnosis example database. The method comprises the steps of establishing a sample analysis image library in advance by collecting sample analysis images contained in a history diagnosis example after microscopic examination confirmation, obtaining the sample analysis images of biological samples of objects to be detected in the process of performing auxiliary diagnosis by an auxiliary diagnosis information providing device, performing similarity matching based on the sample analysis images and reference images in the sample analysis image library, and determining the reference images with the similarity meeting preset conditions as target reference sample images.
The reference images with the similarity meeting the preset condition can be the reference images with the maximum similarity with the sample analysis image in all the reference images in the sample analysis image library; and the method can also refer to a reference image with the similarity value higher than a threshold value being reached first in the process of matching the sample analysis image with the sample analysis image in the sample analysis image library. Alternatively, the target reference sample map may be multiple, and determining the target reference sample map that matches the current sample analysis image refers to determining multiple reference images in the sample analysis image library that have relatively highest similarity to the sample analysis image.
Optionally, the target reference sample map is a reference image carrying positioning marks. The adding manner of the positioning mark in the target reference sample graph can comprise: firstly, a historical diagnosis example is used as sample data on which an auxiliary diagnosis information providing device is constructed, a sample analysis image contained in the historical diagnosis example is used as training data of a neural network model, and the sample analysis image is marked to carry positioning marks, namely, each reference image in a sample analysis image library carries positioning marks; firstly, a sample analysis image contained in a historical diagnosis example does not carry a positioning mark, and an auxiliary diagnosis information providing device adds the positioning mark at a corresponding position of a matched reference image according to the position of the positioning mark in the sample analysis image after searching the reference image with similarity meeting a preset condition in a sample analysis image library after obtaining the sample analysis image carrying the positioning mark in the process of executing auxiliary diagnosis; the other is to perform gradient back propagation analysis on the target reference sample graph based on the classification label in the first abnormal characteristic information by an activation graph forming module of the auxiliary diagnosis information providing device to obtain a thermodynamic diagram, and form a positioning mark on the target reference sample graph based on the thermodynamic diagram by a positioning mark module. Similarly, the positioning marks of the target state reference map may also take several forms.
In the above embodiment, the auxiliary diagnostic report further displays the target reference sample image, so that the target reference sample image is conveniently compared with the currently obtained sample analysis image carrying the positioning mark, and the target reference sample image is the sample analysis image contained in the history diagnostic case confirmed by microscopic examination and can be used as a reliable basis for judgment, thereby being more convenient for a doctor to refer to and judge the accuracy of the currently obtained first abnormal characteristic information.
In some embodiments, the output module 114a further comprises:
when the category of the first abnormal characteristic information is a first type, the auxiliary diagnosis report comprises at least two target reference sample graphs with similarity meeting preset conditions, and the abnormality degree grades of the at least two target reference sample graphs are the same;
and when the category of the first abnormal characteristic information is the second type, the auxiliary diagnosis comprises a target reference sample graph with highest similarity and at least one target state reference graph, and the target reference sample graph and the target state reference graph are different in abnormal degree level.
Different image sub-libraries can be divided into different categories of the first abnormal characteristic information in the sample analysis image library. The image sub-library of the first abnormality characteristic information of different categories may be set to a reference image containing a plurality of abnormality degree class labels, or to a reference image containing the same abnormality degree class label. And if the class of the first abnormal characteristic information is the first type and the image sub-library corresponding to the first type is the reference image containing the labels with the same abnormal degree level, searching a plurality of target reference sample graphs with the same abnormal degree level and the highest similarity from the sample analysis image library, and displaying the target reference sample graphs in the auxiliary diagnosis report. If the class of the first abnormal characteristic information is the second type, if the image sub-library corresponding to the second type is a reference image containing labels with different abnormal degree grades, searching a target reference sample image with relatively highest similarity from the sample analysis image library and displaying the target reference image with different abnormal degree grades in the auxiliary diagnosis report.
For example, the first type includes platelet aggregation, and when the first abnormal characteristic information corresponding to the sample analysis image is platelet aggregation, the auxiliary diagnostic information providing apparatus may search for a plurality of target reference sample patterns having the highest similarity with the sample analysis image from the sample analysis image library, and display the searched plurality of target reference sample patterns in the auxiliary diagnostic report. The second type is other abnormal characteristic information than the first type, optionally the second type includes other abnormal information than platelet aggregation, e.g., the second type may include the presence of reactive lymphocytes, primitive cells, immature granulocytes, etc.
In the above embodiment, the sample analysis image library is set to be compatible with the recognition results of the first abnormal feature information of different categories to match the corresponding reference images, and for some case types, there may be cases where the abnormality degree levels are not distinguished, or the history diagnosis cases acquired at present are insufficient to distinguish between the multiple abnormality degree levels, or the cases where the doctor does not need to refer to the multiple abnormality degree levels, etc., so that the image sub-library corresponding to the first abnormal feature information of some categories contains the reference images where the abnormality degree levels are not distinguished; meanwhile, for part of case types, the image sub-library of the first abnormal characteristic information of the corresponding type to be considered when the suspected case type is confirmed is set to contain reference images with different abnormal degree grades, so that the auxiliary diagnosis information providing device can be matched with a plurality of reference images with different abnormal degree grades in the sample analysis image library, the accuracy of an auxiliary diagnosis result is improved, and the reference value of an auxiliary diagnosis report to a doctor is effectively improved.
Optionally, the auxiliary diagnostic report further includes:
a target state reference map which is matched with the sample analysis image and has a degree of abnormality different from the target reference sample map;
the abnormality degree level of the target reference sample map is one of a severity, a moderate, and a mildness, and the abnormality degree level of the target state reference map includes the other two of the severity, the moderate, and the mildness.
According to the previous embodiment, the auxiliary diagnostic information providing apparatus may be configured to provide the auxiliary diagnostic report with reference images matching the sample analysis image as target reference sample images including only the level of non-discrimination between the degree of abnormality in practical use. In this embodiment, the reference images matched with the sample analysis image in the auxiliary diagnosis report are reference images including the degree of abnormality of the degree of severity, the degree of moderate, and the degree of mild. In a sample analysis image library pre-established based on sample analysis images included in the historical diagnosis examples, corresponding image sub-libraries are respectively established for different types of first abnormal characteristic information, and the corresponding image sub-libraries for the preset types of first abnormal characteristic information respectively include the sample analysis images with the degree of abnormality being severe, moderate and mild respectively as reference images. In the auxiliary diagnosis report, the auxiliary diagnosis information providing device further displays target state reference pictures with different abnormality degree grades in the image display area besides the target reference sample pictures so as to be used as more contrast angles of the sample analysis image with the positioning mark obtained at present, thereby facilitating a doctor to judge more reliably directly according to the reference images with different abnormality degree grades output by the auxiliary diagnosis report.
The target state reference diagram comprises a first target state reference diagram and a second target state reference diagram which correspond to the two abnormal degree grades respectively; if the abnormality degree grade of the target reference sample image is severe, the abnormality degree grades of the first target state reference image and the second target state reference image are moderate and mild respectively; if the abnormality degree grade of the target reference sample image is moderate, the abnormality degree grades of the first target state reference image and the second target state reference image are heavy and light respectively; the degree of abnormality of the target reference sample map is mild, and the degree of abnormality of the first target state reference map and the second target state reference map is severe and moderate, respectively.
It should be noted that the target state reference image may also be a reference image carrying a positioning mark. The adding mode of the positioning mark in the target state reference image can be the same as the adding mode of the positioning mark in the target reference sample image, namely, the sample analysis image contained in the historical diagnosis example according to which the sample analysis image library is built originally has the positioning mark; or, after the matching reference image is found in the sample analysis image library according to the sample analysis image carrying the positioning mark currently obtained, the positioning mark is correspondingly added in the matching reference image according to the position of the positioning mark in the sample analysis image.
In the above embodiment, the auxiliary diagnostic report further displays a target state reference image, where the target state reference image and the target reference sample image together form a reference image combination with a degree of abnormality of severe, moderate and mild, so that a doctor can directly perform more reliable judgment according to the reference images with different degrees of abnormality output by the auxiliary diagnostic report, and the recognition of the sample analysis image based on machine learning is completed to maximize the value in the process of obtaining the auxiliary diagnostic conclusion, while ensuring that a reliable reference is provided.
Optionally, the auxiliary diagnostic information providing apparatus further includes:
the image matching module is used for determining a matched image set in the sample analysis image library according to the category of the first abnormal characteristic information; determining a target reference sample graph with similarity meeting preset conditions according to the similarity between the sample analysis image and each reference image in the matched image set; and determining the target state reference diagram which is the same as the mode category and has different abnormality degree grades from the target reference sample diagram in the sample analysis image library according to the mode category to which the target reference sample diagram belongs.
For the first abnormal characteristic information of the same category, the sample analysis images with the same first abnormal characteristic information possibly contain the same biological characteristic information, but display differences, such as color depth display differences, exist due to the image differences output by different sample analyzers and/or the individual differences of objects to be detected, so that in order to eliminate the error influence of the display differences on the process of searching the target state reference image and the target reference sample image in the sample analysis image library, the sample analysis image library is set as an image set divided according to the category of the first abnormal characteristic information, the reference images are further distinguished according to the mode category under different image sets, and the reference images with different abnormal degree levels are contained under the same mode category.
The image set may be a reference image set formed according to different classification conditions, which may be different sample properties, sample features, etc. And analyzing the same reference image in the image library based on the classification condition 1 and the image set A, and simultaneously, based on the classification condition 2, the same reference image belongs to the image set B. The determining of the matching image set in the sample analysis image library according to the category of the first abnormal feature information may refer to the image set hit from the sample analysis image library with the category of the first abnormal feature information as a classification condition. The pattern category may be another dimension for classifying each reference image in the sample analysis image library, the pattern category may be classified according to feature similarity between different reference images in the image set, and the feature used for classification may be one or more, for example, may be classified according to attribute features (clinical information, microscopic information) of a historical diagnosis case from which the reference image is derived; the image feature may be divided according to the image feature, and the division result in the mode category may be determined by calculating the distance between the image features before each reference image, or the division may be performed by combining the attribute feature and the image feature distance.
In an optional specific example, the sample analysis image library includes image sub-libraries correspondingly built based on different types of first abnormal feature information, the image sub-libraries corresponding to the same type of first abnormal feature information are divided into a plurality of mode sub-libraries by feature similarity, and each mode sub-library includes reference images with different abnormal degree grades. And the image sub-libraries corresponding to the first abnormal characteristic information of the same category are further divided into a plurality of mode sub-libraries by analyzing the characteristic similarity of the reference images in the image sub-libraries to determine the mode category. In the sample analysis image library, the image sub-library can be used as a first-level catalog, the mode sub-library is used as a next-level catalog under the image sub-library, the auxiliary diagnosis information providing device determines a matched image sub-library through the first-level catalog according to the category of the first abnormal characteristic information before outputting the auxiliary diagnosis report, and a reference image with similarity meeting preset conditions is searched in the range of the matched image sub-library to be used as a target reference sample image; and then according to the pattern sub-library where the target reference sample image is located, if the abnormality degree grade of the target reference sample image is A1 (A1 is one of severe, moderate and mild), selecting the reference image with the abnormality degree grade of A2 and A3 (A2 and A3 are the other two of severe, moderate and mild) from the pattern sub-library where the target reference sample image is located as the target state reference image. In this embodiment, the image matching module may determine the target reference sample image according to the maximum value of the overall similarity between the sample analysis image obtained at present and the reference image in the matching image sub-library; and determining two other target state reference pictures with different abnormality degree grades from the target reference sample picture according to the maximum value of the image local similarity of the preset attention area between the sample analysis image obtained currently and the reference image in the matching mode sub-library in which the target reference sample picture is positioned. In an alternative embodiment, the predetermined region of interest may be a region in which the positioning mark is located in the sample analysis image. In another optional example, the image matching module determines a target reference sample image according to a maximum value of the overall similarity of the images between the sample analysis image obtained currently and the reference images in the matching image sub-library; and then, in a matching mode sub-library where the target reference sample diagram is located, randomly selecting two other target state reference diagrams with different abnormality degree grades from the target reference sample diagram respectively.
In the above embodiment, by setting the sample analysis image library to divide the image sets according to the categories of the first abnormal feature information and dividing the image sets in the form of the pattern categories, it is advantageous to promote the accuracy of the combination of the heavy, medium and light reference images (the combination of the target reference sample map and the target state reference map) provided in the auxiliary diagnostic report.
It should be noted that, in each embodiment for outputting the target reference sample map and the target state reference map in the auxiliary diagnostic report, at least one of the target reference sample map and the target state reference map carries a positioning mark. That is, the output display in the auxiliary diagnostic report with respect to the reference image matched with the sample analysis image includes the following cases: outputting one or more target reference sample graphs only, wherein the target reference sample graphs are provided with no positioning mark or positioning marks; outputting a target reference sample diagram and one or more target state reference diagrams, wherein the target reference sample diagram is provided with no positioning mark or positioning mark, and the target state reference diagram is provided with no positioning mark or positioning mark. In the embodiments with positioning marks in the target reference sample diagram and the target state reference diagram, the adding manner of the positioning marks is described in the foregoing embodiments, and is not described herein.
In some embodiments, the first anomaly identification module comprises: the abnormal feature classification module is used for determining classification labels of abnormal features in the sample analysis image through an image classification neural network model to obtain first abnormal feature information;
the auxiliary diagnostic information providing apparatus further includes:
the activation graph forming module is used for carrying out gradient back propagation analysis based on the classification labels in the first abnormal characteristic information to obtain the thermodynamic diagram, and the thermodynamic diagram is overlapped with the sample analysis image after being amplified to obtain the activation graph;
and the positioning mark module is used for forming a positioning mark on the sample analysis image based on the highlight area of the activation graph.
In an alternative example, the auxiliary diagnostic information providing apparatus obtains an activation map in an auxiliary diagnostic report and a sample analysis image carrying a positioning mark based on the sample analysis image, including: identifying a sample analysis image by adopting an image classification neural network model, and outputting a corresponding classification label based on the identified abnormal characteristics in the sample analysis image; the method comprises the steps that a Grad-CAM algorithm is adopted, the weight value of each channel of a feature map output to a classification output layer by utilizing a feature extraction network of an image classification neural network model is adopted, a machine vision visualization algorithm is adopted to carry out linear weighted summation on image features output by each channel based on the weight value, and a thermodynamic diagram is obtained according to the linear weighted summation result; performing image matching on the thermodynamic diagram and the sample analysis image, and then superposing to obtain an activation diagram; the highlight region in the thermodynamic diagram is identified, and a minimum bounding rectangle is constructed based on the outline of the highlight region to form a positioning mark. The classifying neural network model comprises a feature extraction layer and a classifying and predicting layer, a sample analysis image is input into the classifying neural network model, feature extraction is carried out on the sample analysis image through the feature extraction layer, the feature extraction layer can be provided with a plurality of layers, the last layer is connected with the classifying and predicting layer, the classifying and predicting layer carries out classifying and predicting according to feature vectors output by the feature extraction layer, and corresponding classifying labels are determined.
In some embodiments, the activation pattern formation module may also employ GAP, CAM, grad-CAM++ or other algorithms to perform gradient back-propagation analysis based on classification tags in the first anomaly characteristic information to obtain the thermodynamic diagram.
It should be noted that, different implementations may be used for the auxiliary diagnostic information providing apparatus to obtain the sample analysis image carrying the positioning mark. For example, in another alternative example, the auxiliary diagnostic information providing apparatus identifies a sample analysis image using a target detection neural network, outputs a corresponding classification tag based on the identified abnormal feature in the sample analysis image, and outputs a sample analysis image carrying a positioning mark. The target detection neural network model comprises a convolution layer and a RPN (regionproposalnetworks) network layer, the convolution layer performs feature extraction on an input image to obtain a feature map, the RPN (regionproposalnetworks) network layer outputs a rectangular candidate region set with an object socre by using a priori anchor, and an image region where a corresponding abnormal feature is located is selected based on the rectangular candidate region set. In still another alternative example, the auxiliary diagnostic information providing device detects whether an abnormal feature exists in the sample analysis image by using an image segmentation neural network, obtains a target detection result of a local image where the abnormal feature corresponds to, and determines the position of the positioning mark in the sample analysis image based on the target detection result of the local image. In yet another alternative example, the positioning mark may be formed based on a target detection algorithm, peak and valley seeking, etc. of the region of interest, in which example the activation map may be generated from a particle density in a third dimension within the region in which the positioning mark is located; the third dimension is another dimension different from the display plane of the activation map, for example, when the sample analysis image includes three dimensions of forward scattered light, side scattered light and side fluorescence, if the activation map displayed by the auxiliary diagnostic report is two dimensions of side scattered light and side fluorescence, the third dimension may be forward scattered light, and if the activation map is two dimensions of forward scattered light and side fluorescence, the third dimension may be side scattered light.
It should be noted that the positioning mark is a focus area for highlighting the first abnormal feature information obtained from the sample analysis image, and may be a positioning frame with various regular or irregular geometric shapes, or may be an image area marked by different colors. In an alternative specific example, the positioning mark refers to a rectangular positioning frame.
In the above embodiment, the neural network model is adopted for processing the sample analysis image, so that the advantage of the neural network model on image recognition is fully utilized, intelligent recognition of the brain of a professional inspection doctor on the sample analysis image is completed, and the image salient features in the output result are visualized.
In some embodiments, the sample analysis image comprises at least one of a blood cell histogram, a blood cell scatter plot, a pulse signal waveform plot, a pulse signal signature plot, a thromboelastography, a biochemical or immune response curve.
The auxiliary diagnostic information providing device may be communicatively connected to different types of sample analyzers to obtain different types of sample analysis images as inputs. The blood cell histogram may include histograms corresponding to different blood cells in blood, such as a platelet histogram, a red blood cell histogram, a white blood cell histogram, a peak height of a pulse signal, a front peak width, a rear peak width, a half peak width, and the like, and histograms formed by pulse characteristic values (such as RBC, PLT, and WBC histograms formed by peak heights of the pulse signal). The blood cell scatter plot may include different types of scatter plots obtained by detecting scattered light, converting an optical signal into an electrical pulse, such as a white blood cell DIFF scatter plot, a RET scatter plot, a scatter plot composed of two, three or even more dimensions of characteristic values of pulse signals of several dimensions (such as DIFF three-dimensional scatter plot data sets composed of peak heights of SFL, SSC and FSC three-way pulse signals), a two-dimensional scatter plot projection plot composed of three-dimensional and high-dimensional scatter plot data, and the like, in which light beams produce light scattering in different directions for each blood cell. The pulse signal waveform diagram may be as follows: the blood cell analyzer detects a waveform chart formed by the collected original pulse signals of the blood sample and a pulse signal waveform chart formed by the pulse signals screened by the pulse recognition algorithm; the pulse signal feature map may be as follows: and a vector characteristic diagram formed by pulse characteristic values such as peak height, front peak width, rear peak width, half peak width and the like of the pulse signals. The sample analyzer may also include a coagulation analyzer, an immunoassay analyzer, etc., and the sample analysis image may also include a thromboelastography, a biochemical or an immune response curve, respectively. The auxiliary diagnostic information providing device can take one or more sample analysis images output by the sample analyzer as input, identify the sample analysis images and output first abnormal characteristic information of abnormal characteristics respectively carried in the sample analysis images.
In the above embodiment, the auxiliary diagnosis information providing apparatus, by cooperating with the sample analyzer, can accurately determine whether there is an abnormality in the biological sample of the object to be detected by acquiring the sample detection data output from the sample analyzer for analysis, so as to provide the examining physician with auxiliary diagnosis.
Referring to fig. 5, another embodiment of the present application provides an auxiliary diagnostic information providing apparatus, including: an acquisition module 111, a first abnormality identification module 112, a second abnormality identification module 113, and an output module 115. The acquiring module 111 is configured to acquire sample detection data obtained by performing detection analysis on a biological sample of an object to be detected; the sample detection data comprises a sample analysis image and sample detection parameters; the first anomaly identification module 112 is configured to obtain first anomaly characteristic information that characterizes an anomaly characteristic in the sample analysis image according to the sample analysis image; the second abnormality identification module 113 is configured to obtain second abnormality characteristic information that characterizes abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter; the output module 114b is configured to output an auxiliary diagnostic report according to the sample analysis image, the first abnormal feature information, and the second abnormal feature information, where the auxiliary diagnostic report includes: auxiliary diagnostic category information; the sample analysis image carrying a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image; a target reference sample image matched with the sample analysis image, wherein the target reference sample image is a reference image with similarity meeting a preset condition with the sample analysis image in a sample analysis image library; the sample analysis image library comprises sample analysis images of historical diagnosis cases confirmed by microscopic examination, and the positioning marks in the target reference sample image are used for highlighting the positions of the diagnosis basis for obtaining the first abnormal characteristic information.
The main difference from the embodiment shown in fig. 1 is that, in the auxiliary diagnostic report output by the output module 114b, an activation map may be omitted, and a reference sample map of the target confirmed by microscopy, which matches the sample analysis image obtained currently, is output.
In the above embodiment, the auxiliary diagnosis information providing apparatus obtains first abnormal feature information characterizing abnormal features in the sample analysis image by analyzing and identifying the sample analysis image, and obtains second abnormal feature information characterizing abnormal parameter values in the biological sample determined based on the sample detection parameters, and outputs an auxiliary diagnosis report according to the sample analysis image, the first abnormal feature information and the second abnormal feature information, wherein the auxiliary diagnosis report includes auxiliary diagnosis category information, a sample analysis image showing the position of the first abnormal feature information through a positioning mark, and a target reference sample image obtained by a history diagnosis example confirmed by microscopic examination, so that a user can obtain auxiliary diagnosis category information determined by comprehensive multi-aspect information through the auxiliary diagnosis report, and accuracy and efficiency of an auxiliary diagnosis result are improved; moreover, the target reference sample graph which is output in the auxiliary diagnosis report and confirmed by microscopic examination carries a sample analysis image of a positioning mark, so that a doctor can conveniently and rapidly verify the accuracy of the current auxiliary diagnosis type information to judge the reliability of the current auxiliary diagnosis type information, and whether the current auxiliary diagnosis type information is adopted or not is considered.
In some embodiments, the auxiliary diagnostic report further comprises:
a target state reference map which is matched with the sample analysis image and has a degree of abnormality different from the target reference sample map; wherein the degree of abnormality classes include severe, moderate and mild;
the abnormality degree level of the target reference sample map is one of a severity, a moderate, and a mildness, and the abnormality degree level of the target state reference map includes the other two of the severity, the moderate, and the mildness.
In the above embodiment, the auxiliary diagnostic report further displays a target state reference image, where the target state reference image and the target reference sample image together form a reference image combination with a degree of abnormality of severe, moderate and mild, so that a doctor can directly perform more reliable judgment according to the reference images with different degrees of abnormality output by the auxiliary diagnostic report, and the recognition of the sample analysis image based on machine learning is completed to maximize the value in the process of obtaining the auxiliary diagnostic conclusion, while ensuring that a reliable reference is provided.
In some embodiments, the auxiliary diagnostic information providing apparatus further includes:
the reference image determining module is used for determining a matched image set in the sample analysis image library according to the category of the first abnormal characteristic information; determining a target reference sample graph with similarity meeting preset conditions according to the similarity between the sample analysis image and the reference image in the matching image set; or, the target reference sample graph with the similarity meeting the preset condition is determined according to the result of the two searches.
The image set may be an image set formed by classifying the reference images in the sample analysis image library according to different classification conditions, and the classification conditions may be different sample attributes, sample characteristics, and the like. For the same reference image in the sample analysis image library, the reference image can be respectively divided into different image sets based on different classifying conditions. The determining of the matched image set in the sample analysis image library according to the category of the first abnormal feature information may refer to determining the reference image with the largest similarity or determining the first several reference images with the largest similarity as the target reference sample images according to the similarity between the current sample analysis image and each reference image in the matched image set from the hit image set in the sample analysis image library by taking the category of the first abnormal feature information as a classifying condition.
Optionally, the auxiliary diagnostic information providing device may further determine that the target reference sample image is searched in the sample analysis image library according to the similarity of the current sample analysis image, obtain a first search result of the similarity between the sample analysis image and each reference image in real time, determine a matching image set according to the category of the first abnormal feature information, search the matching image set according to the similarity of the current sample analysis image, obtain a second search result of the similarity between the sample analysis image and each reference image in real time, and determine one or more reference images, of which the similarity first reaches a set threshold, as the target reference sample image according to the first search result and the second search result.
In the above embodiment, the sample analysis image library is configured to support different modes to find the target reference sample image, which is beneficial to supporting the requirements of more application scenes and improving the finding efficiency.
Referring to fig. 6, in another aspect of the embodiments of the present application, there is also provided a blood analysis system, including:
a sampling assembly 211 for collecting and dispensing a biological sample of an object to be detected, the biological sample being a blood sample;
a reaction component 212 for processing the biological sample to form a liquid to be tested;
a driving assembly 213 for driving a fluid path between the sampling assembly and the reaction assembly;
a detection component 214, configured to classify and count blood cells contained in the solution to be detected, so as to obtain sample detection data including sample detection parameters and a sample analysis image;
the auxiliary diagnostic information providing apparatus 11 according to any one of the embodiments of the present application is configured to output an auxiliary diagnostic report based on the sample detection data.
In this embodiment, the blood analysis system is formed as a medical auxiliary diagnosis device that integrates a sample detection image and a sample detection parameter obtained by performing detection analysis on a blood sample of a subject, and an auxiliary diagnosis report that identifies abnormal features in a biological sample and outputs a visual diagnosis basis according to the sample detection image and the sample detection parameter obtained by performing detection analysis on the blood sample. The blood analysis system can be obtained by upgrading a blood analyzer, and comprises a sampling component, a reaction component, a driving component and a detection component which are used for detecting and analyzing a blood sample to obtain sample detection data, the auxiliary diagnosis information providing device can be stored in a memory of the blood analysis system as a computer program product which takes a computer program flow as a basis to realize an auxiliary diagnosis function, and the auxiliary diagnosis function of the auxiliary diagnosis information providing device is implemented by a processor.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. An auxiliary diagnostic information providing apparatus, comprising:
the acquisition module is used for acquiring sample detection data obtained by detection analysis of a biological sample of an object to be detected; the sample detection data comprises a sample analysis image and sample detection parameters;
the first abnormal recognition module is used for obtaining first abnormal characteristic information representing abnormal characteristics in the sample analysis image according to the sample analysis image;
a second abnormality identification module for obtaining second abnormality characteristic information characterizing abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter;
the output module is used for outputting an auxiliary diagnosis report according to the sample analysis image, the first abnormal characteristic information and the second abnormal characteristic information, and the auxiliary diagnosis report comprises:
Auxiliary diagnostic category information;
an activation map for highlighting a diagnostic basis of the first abnormal feature information, the activation map being superimposed by a thermodynamic diagram obtained based on a feature map of the sample analysis image and the biological sample analysis image; wherein the thermodynamic diagram characterizes the degree of decision impact of each unit region of the sample analysis image on determining the first anomaly characteristic information;
the sample analysis image carries a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image.
2. The auxiliary diagnostic information providing apparatus according to claim 1, wherein the auxiliary diagnostic report further comprises:
a target reference sample map matched to the sample analysis image; the target reference sample image is a reference image with similarity meeting preset conditions with the sample analysis image in a sample analysis image library; the sample analysis image library contains sample analysis images of historical diagnosis cases confirmed by microscopic examination.
3. The auxiliary diagnostic information providing apparatus according to claim 2, wherein,
when the category of the first abnormal characteristic information is a first type, the auxiliary diagnosis report comprises at least two target reference sample graphs with similarity meeting preset conditions, and the abnormality degree grades of the at least two target reference sample graphs are the same;
And when the category of the first abnormal characteristic information is the second type, the auxiliary diagnosis comprises a target reference sample graph with highest similarity and at least one target state reference graph, and the target reference sample graph and the target state reference graph are different in abnormal degree level.
4. The auxiliary diagnostic information providing apparatus according to claim 2, wherein the auxiliary diagnostic report further comprises:
a target state reference map which is matched with the sample analysis image and has a degree of abnormality different from the target reference sample map;
the abnormality degree level of the target reference sample map is one of a severity, a moderate, and a mildness, and the abnormality degree level of the target state reference map includes the other two of the severity, the moderate, and the mildness.
5. The auxiliary diagnostic information providing apparatus as claimed in claim 4, wherein the auxiliary diagnostic information providing apparatus further comprises:
the image matching module is used for determining a matched image set in the sample analysis image library according to the category of the first abnormal characteristic information; determining a target reference sample graph with similarity meeting preset conditions according to the similarity between the sample analysis image and the reference image in the matched image set; and determining the target state reference diagram which is the same as the mode category and has different abnormality degree grades from the target reference sample diagram in the sample analysis image library according to the mode category to which the target reference sample diagram belongs.
6. The auxiliary diagnostic information providing apparatus according to any one of claims 3 to 5, wherein at least one of the target reference sample map and the target state reference map carries a positioning mark.
7. The auxiliary diagnostic information providing apparatus according to claim 1, wherein,
the first abnormality recognition module includes: the abnormal feature classification module is used for determining classification labels of abnormal features in the sample analysis image through an image classification neural network model to obtain first abnormal feature information;
the auxiliary diagnostic information providing apparatus further includes:
the activation graph forming module is used for carrying out gradient back propagation analysis based on the classification labels in the first abnormal characteristic information to obtain the thermodynamic diagram, and the thermodynamic diagram is overlapped with the sample analysis image after being amplified to obtain the activation graph;
and a positioning mark module for forming a positioning mark on the biological sample analysis image based on the highlight region of the activation map.
8. The auxiliary diagnostic information providing apparatus according to claim 1, wherein the sample analysis image includes at least one of a blood cell histogram, a blood cell scatter plot, a pulse signal waveform plot, a pulse signal feature plot, a thromboelastography, a biochemical or an immune response curve.
9. An auxiliary diagnostic information providing apparatus, comprising:
the acquisition module is used for acquiring sample detection data obtained by detection analysis of a biological sample of an object to be detected; the sample detection data comprises a sample analysis image and sample detection parameters;
the first abnormal recognition module is used for obtaining first abnormal characteristic information representing abnormal characteristics in the sample analysis image according to the sample analysis image;
a second abnormality identification module for obtaining second abnormality characteristic information characterizing abnormality of a parameter value in the biological sample, which is determined based on the sample detection parameter;
the output module is used for outputting an auxiliary diagnosis report according to the sample analysis image, the first abnormal characteristic information and the second abnormal characteristic information, and the auxiliary diagnosis report comprises:
auxiliary diagnostic category information;
the sample analysis image carrying a positioning mark, wherein the positioning mark is used for showing the position of the first abnormal characteristic information in the sample analysis image;
a target reference sample image matched with the sample analysis image, wherein the target reference sample image is a reference image with similarity meeting a preset condition with the sample analysis image in a sample analysis image library; the sample analysis image library comprises sample analysis images of historical diagnosis cases confirmed by microscopic examination, and the positioning marks in the target reference sample image are used for highlighting the positions of the diagnosis basis for obtaining the first abnormal characteristic information.
10. The auxiliary diagnostic information providing apparatus as claimed in claim 9, wherein the auxiliary diagnostic report further comprises:
a target state reference map which is matched with the sample analysis image and has a degree of abnormality different from the target reference sample map; wherein the degree of abnormality classes include severe, moderate and mild;
the abnormality degree level of the target reference sample map is one of a severity, a moderate, and a mildness, and the abnormality degree level of the target state reference map includes the other two of the severity, the moderate, and the mildness.
11. The auxiliary diagnostic information providing apparatus according to claim 9, wherein,
the auxiliary diagnostic information providing apparatus further includes: the reference image determining module is used for determining a matched image set in the sample analysis image library according to the category of the first abnormal characteristic information; determining a target reference sample graph with similarity meeting preset conditions according to the similarity between the sample analysis image and the reference image in the matching image set; or, the target reference sample graph with the similarity meeting the preset condition is determined according to the result of the two searches.
12. A blood analysis system, comprising:
the sampling assembly is used for collecting and distributing a biological sample of an object to be detected, wherein the biological sample is a blood sample;
the reaction component is used for processing the biological sample to form a liquid to be tested;
the driving assembly is used for driving a liquid path between the sampling assembly and the reaction assembly;
the detection component is used for classifying and counting blood cells contained in the liquid to be detected to obtain sample detection data containing sample detection parameters and sample analysis images;
the auxiliary diagnostic information providing apparatus according to any one of claims 1 to 11, configured to output an auxiliary diagnostic report based on the sample detection data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310323347.9A CN116046643B (en) | 2023-03-30 | 2023-03-30 | Auxiliary diagnostic information providing device and blood analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310323347.9A CN116046643B (en) | 2023-03-30 | 2023-03-30 | Auxiliary diagnostic information providing device and blood analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116046643A true CN116046643A (en) | 2023-05-02 |
| CN116046643B CN116046643B (en) | 2024-01-16 |
Family
ID=86129852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310323347.9A Active CN116046643B (en) | 2023-03-30 | 2023-03-30 | Auxiliary diagnostic information providing device and blood analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116046643B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522878A (en) * | 2024-01-08 | 2024-02-06 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Method and system for identifying image anomalies of primary kitchen range based on multi-source data detection |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101358983A (en) * | 2007-07-31 | 2009-02-04 | 希森美康株式会社 | Diagnosis support system and device for providing diagnosis support information |
| US20090323062A1 (en) * | 2008-06-30 | 2009-12-31 | Sysmex Corporation | Sample analyzer, particle distribution diagram displaying method and computer program product |
| CN103852404A (en) * | 2012-11-28 | 2014-06-11 | 株式会社堀场制作所 | Display device and display method for scattergram relating to blood cells, and blood analyzer |
| US20190236779A1 (en) * | 2016-11-01 | 2019-08-01 | Hitachi High-Technologies Corporation | Diagnostic imaging assistance apparatus and system, and diagnostic imaging assistance method |
| CN110755045A (en) * | 2019-10-30 | 2020-02-07 | 湖南财政经济学院 | Skin disease comprehensive data analysis and diagnosis auxiliary system and information processing method |
| CN111785363A (en) * | 2020-06-03 | 2020-10-16 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | AI-guidance-based chronic disease auxiliary diagnosis system |
| CN114018924A (en) * | 2021-11-23 | 2022-02-08 | 杭州智微信息科技有限公司 | Method for automatically detecting abnormal cells in urine exfoliative cells |
| CN115184244A (en) * | 2021-04-07 | 2022-10-14 | 深圳迈瑞生物医疗电子股份有限公司 | Blood analysis system |
-
2023
- 2023-03-30 CN CN202310323347.9A patent/CN116046643B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101358983A (en) * | 2007-07-31 | 2009-02-04 | 希森美康株式会社 | Diagnosis support system and device for providing diagnosis support information |
| US20090323062A1 (en) * | 2008-06-30 | 2009-12-31 | Sysmex Corporation | Sample analyzer, particle distribution diagram displaying method and computer program product |
| CN103852404A (en) * | 2012-11-28 | 2014-06-11 | 株式会社堀场制作所 | Display device and display method for scattergram relating to blood cells, and blood analyzer |
| US20190236779A1 (en) * | 2016-11-01 | 2019-08-01 | Hitachi High-Technologies Corporation | Diagnostic imaging assistance apparatus and system, and diagnostic imaging assistance method |
| CN110755045A (en) * | 2019-10-30 | 2020-02-07 | 湖南财政经济学院 | Skin disease comprehensive data analysis and diagnosis auxiliary system and information processing method |
| CN111785363A (en) * | 2020-06-03 | 2020-10-16 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | AI-guidance-based chronic disease auxiliary diagnosis system |
| CN115184244A (en) * | 2021-04-07 | 2022-10-14 | 深圳迈瑞生物医疗电子股份有限公司 | Blood analysis system |
| CN114018924A (en) * | 2021-11-23 | 2022-02-08 | 杭州智微信息科技有限公司 | Method for automatically detecting abnormal cells in urine exfoliative cells |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522878A (en) * | 2024-01-08 | 2024-02-06 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Method and system for identifying image anomalies of primary kitchen range based on multi-source data detection |
| CN117522878B (en) * | 2024-01-08 | 2024-03-22 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Method and system for identifying image anomalies of primary kitchen range based on multi-source data detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116046643B (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5425814B2 (en) | Method and system for analyzing flow cytometry data using a support vector machine | |
| US20160169786A1 (en) | Automated flow cytometry analysis method and system | |
| US20200158734A1 (en) | System, method, and article for detecting abnormal cells using multi-dimensional analysis | |
| Hortinela et al. | Identification of abnormal red blood cells and diagnosing specific types of anemia using image processing and support vector machine | |
| US20100279341A1 (en) | Methods and system for analyzing cells | |
| CN116046643B (en) | Auxiliary diagnostic information providing device and blood analysis system | |
| CN111652095A (en) | CTC image identification method and system based on artificial intelligence | |
| JP2022039780A (en) | Measurement method, measurement device, and measurement program | |
| WO2023186051A1 (en) | Auxiliary diagnosis method and apparatus, and construction apparatus, analysis apparatus and related product | |
| KR20010017092A (en) | Method for counting and analyzing morphology of blood cell automatically | |
| EP3611695A1 (en) | Generating annotation data of tissue images | |
| Priyankara et al. | An extensible computer vision application for blood cell recognition and analysis | |
| Hortinela IV et al. | Development of abnormal red blood cells classifier using image processing techniques with support vector machine | |
| US10235495B2 (en) | Method for analysis and interpretation of flow cytometry data | |
| US8512977B2 (en) | Analyzing reticulocytes | |
| CN116030957A (en) | Knowledge graph construction method, knowledge graph construction device, auxiliary diagnosis equipment and storage medium | |
| US20110167029A1 (en) | Method and device for classifying, displaying and exploring biological data | |
| EP3230887A1 (en) | Automated flow cytometry analysis method and system | |
| EP3244191A1 (en) | Method and system for characterizing particles using a flow cytometer | |
| Lina et al. | Focused color intersection for leukocyte detection and recognition system | |
| Gil et al. | Automatic analysis system for abnormal red blood cells in peripheral blood smears | |
| AU2020207365A1 (en) | Optimized sorting gates | |
| CN116936113A (en) | Auxiliary diagnosis method, device, equipment, server, product, system and medium | |
| CN116029960A (en) | Auxiliary diagnosis method, image processing model and storage medium | |
| CN116030958A (en) | Auxiliary diagnosis method, device, equipment and system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |