CN116952807A

CN116952807A - Auxiliary diagnosis method and biological sample analysis method, device, equipment and medium thereof

Info

Publication number: CN116952807A
Application number: CN202210416283.2A
Authority: CN
Inventors: 詹念吉; 方建伟; 王玉亭; 霍子凌; 刘治志; 李国军
Original assignee: Shenzhen Dymind Biotechnology Co Ltd
Current assignee: Shenzhen Dymind Biotechnology Co Ltd
Priority date: 2022-04-20
Filing date: 2022-04-20
Publication date: 2023-10-27

Abstract

The application provides an auxiliary diagnosis method, a biological sample analysis method, a device, equipment and a medium thereof, wherein the sample analysis method obtains pulse data acquired by biological samples of objects to be detected in different detection channels, respectively quantizes pulse characteristics of a plurality of set types carried by the pulse data of the different detection channels to obtain corresponding first arrays, fuses the first arrays corresponding to the pulse characteristics of the set types to obtain second arrays, extracts the characteristics of the second arrays, and outputs identification results of target objects in the biological samples carried by the second arrays. The second group comprises a plurality of pulse characteristics of set types of pulse data of different detection channels, so that accuracy of obtaining the identification result based on the second group serving as input data of an identification model is high.

Description

Auxiliary diagnosis method and biological sample analysis method, device, equipment and medium thereof

Technical Field

The application relates to the technical field of medical equipment, in particular to an auxiliary diagnosis method and a biological sample analysis method, device, equipment and medium thereof.

Background

At present, the blood cell analysis equipment detects and analyzes blood cells by converting different biological characteristics of the blood cells into corresponding pulse signals through an internally arranged detection channel, and converting the corresponding pulse signals into image data for analysis, so that relevant characteristics of the blood cells are extracted from the image data, and identification of the blood cells is realized. Some information is lost in the process of converting the pulse signal into the corresponding image data, for example, after converting the pulse height of the pulse data into the image data, the image data may lose pulse characteristics such as the full peak width, half peak width, pulse area and the like of the pulse signal, and obviously, in the process of analyzing blood cells based on the image data, the lost pulse characteristics cannot contribute to analysis.

However, from a priori knowledge, the missing pulse characteristics are related to the classification of blood cells, and therefore, the accuracy of analyzing blood cells based on the image data converted from the pulse signals corresponding to the biological characteristics of blood cells is not high.

Disclosure of Invention

In order to solve the technical problems, the application provides an auxiliary diagnosis method with higher accuracy, and a biological sample analysis method, device, equipment and medium thereof.

A method of biological sample analysis, comprising:

acquiring pulse data acquired by biological samples of an object to be detected in different detection channels;

respectively quantifying pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each corresponding first array;

fusing the first arrays corresponding to the pulse characteristics of the set type to obtain a second array;

and extracting the characteristics of the second array, and outputting the identification result of the target object in the biological sample carried by the second array.

A method of aiding diagnosis, comprising:

acquiring a recognition result of a target object in a biological sample of an object to be detected, which is obtained by analyzing the biological sample by the biological sample analysis method;

acquiring clinical information of the object to be detected;

and determining an abnormal target object in the biological sample of the object to be detected based on the identification result and the clinical information, and outputting auxiliary diagnosis decision information corresponding to the abnormal target object.

A biological sample recognition device, comprising:

the acquisition module is used for acquiring pulse data acquired by biological samples of the object to be detected in different detection channels;

The quantization module is used for respectively quantizing pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each corresponding first array;

the fusion module is used for fusing the first array corresponding to the pulse characteristics of the set type to obtain a second array;

and the identification module is used for extracting the characteristics of the second array and outputting the identification result of the target object in the biological sample carried by the second array.

A biological sample analysis device comprising a processor and a memory, the memory having stored thereon a computer program executable by the processor, the computer program when executed by the processor effecting the biological sample analysis method.

A computer readable storage medium having stored thereon a computer program which when executed by a controller implements the biological sample analysis method.

An auxiliary diagnostic device comprising a processor and a memory, wherein a computer program executable by the processor is stored in the memory, which computer program, when executed by the processor, implements the auxiliary diagnostic method.

A computer readable storage medium having stored thereon a computer program which when executed by a controller implements the auxiliary diagnostic method.

From the above, in one aspect, the present application provides the sample analysis method, by acquiring pulse data acquired by a biological sample of an object to be detected in each different detection channel, quantifying pulse features of a plurality of set types carried by the pulse data of each different detection channel, obtaining each corresponding first array, fusing the first arrays corresponding to the pulse features of the set types, obtaining a second array, extracting features of the second array, and outputting a recognition result of a target object in the biological sample carried by the second array. The second group comprises a plurality of pulse characteristics of set types of pulse data of different detection channels, so that accuracy of obtaining the identification result based on the second group serving as input data of an identification model is high.

On the other hand, according to the auxiliary diagnosis method provided by the application, the abnormal target object in the biological sample of the object to be detected is determined according to the identification result obtained by the biological sample analysis method and the clinical information of the object to be detected, and the auxiliary diagnosis decision information corresponding to the abnormal target object is output, so that the abnormal target object contained in the biological sample can be used as the identification object, the abnormal target object of the biological sample is determined by combining the clinical information of the object to be detected, the auxiliary diagnosis decision information corresponding to the abnormal target object is output based on the abnormal target object, and an accurate auxiliary diagnosis decision can be obtained without depending on the personal experience level of a checking doctor, thereby improving the checking efficiency, ensuring more accurate detection result and more interpretability of the diagnosis decision.

Drawings

The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 is a flow chart of a method for analyzing a biological sample according to an embodiment of the application;

FIG. 2 is a flow chart of a biological sample analysis method according to a second embodiment of the present application;

FIG. 3 is a flow chart of a biological sample analysis method according to a third embodiment of the present application;

FIG. 4 is a flowchart of a biological sample analysis method according to a fourth embodiment of the present application;

FIG. 5 is a flow chart of a biological sample analysis method according to a fifth embodiment of the present application;

FIG. 6 is a flowchart of a biological sample analysis method according to a sixth embodiment of the present application;

FIG. 7 is a flow chart of a biological sample analysis method according to a seventh embodiment of the application;

FIG. 8 is a flow chart illustrating a method for analyzing a biological sample according to an eighth embodiment of the present application;

FIG. 9 is a flow chart of a biological sample analysis method according to a ninth embodiment of the application;

FIG. 10 is a flow chart of a biological sample analysis method according to a tenth embodiment of the present application;

FIG. 11 is a flow chart illustrating a method for analyzing a biological sample according to an eleventh embodiment of the application;

FIG. 12 is a schematic diagram of a second array configuration in a biological sample analysis method according to some embodiments of the present application;

FIG. 13 is a schematic diagram of a biological sample analyzer according to a first embodiment of the present application;

FIG. 14 is a schematic diagram of a biological sample analysis device according to a first embodiment of the present application;

fig. 15 is a flowchart of an auxiliary diagnostic method according to some embodiments of the present application.

Detailed Description

The technical scheme of the application is further elaborated below by referring to the drawings in the specification and the specific embodiments.

The present application will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to the expression "some embodiments" which describe a subset of all possible embodiments, it being noted 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, third" and the like are used merely to distinguish between similar objects and do not represent a specific ordering of the objects, it being understood that the "first, second, third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.

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 is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.

Referring to fig. 1, a biological sample analysis method according to a first embodiment of the present application is applicable to a biological sample analysis device, and the biological sample analysis method includes, but is not limited to, S02, S04, S06, and S08, and is specifically described as follows:

s02: pulse data acquired by biological samples of an object to be detected in different detection channels are acquired.

S02 may be implemented by the acquisition module 101 in the biological sample analysis apparatus shown in fig. 13, or by the memory 202 in the biological sample analysis device shown in fig. 14 storing the corresponding acquisition program, and then implemented by the processor 201 in the biological sample analysis device shown in fig. 14 when executing the acquisition program stored in the memory 202.

The object to be detected refers to the subject of the biological sample to be detected, taking the biological sample to be detected as a blood sample of a human body as an example, and the object to be detected generally refers to a patient providing the blood sample. The biological sample of the object to be detected can be a sample containing 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 and the like, and the biological cell type can be at least one of neutrophil granulocyte, lymphocyte, single sphere, eosinophil granulocyte and basophil granulocyte; 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 detection channel comprises a counting channel for counting cells in a biological sample based on a Coulter resistance impedance principle, a concentration measurement channel for measuring the concentration of each component in the biological sample based on a colorimetry principle, a classification and identification channel for identifying each component of the biological sample based on laser radiation and a nucleic acid fluorescence staining technology, and the like. The counting channel further comprises a white blood cell counting channel, a red blood cell counting channel, a platelet counting channel and the like, the concentration measuring channel for measuring the concentration of each component in the biological sample based on the colorimetric principle is used for measuring the concentration of the component such as hemoglobin, albumin, globulin and the like, and the classifying and identifying channel is mainly used for white blood cell classification, reticulocyte identification, nucleated red blood cell identification, basophil identification, low-value platelet identification, primitive cell identification and the like. The pulse data is an electric pulse signal obtained by converting the biological characteristics corresponding to the biological sample by detecting the biological characteristics of the biological sample through each detection channel. Taking the biological sample as blood for example, the biological characteristics of blood include blood cell size, cell content complexity, nucleic acid content, etc.

Specifically, in some embodiments, taking the biological sample as an example of a blood sample, each of the detection channels includes, but is not limited to, an SFL (lateral fluorescence) channel for determining DNA/RNA content, an FSC (forward scattered light) channel for determining cell volume, an SSC (lateral scattering) channel for determining cell complexity, a WBC channel for performing white blood cell count, an RBC channel for performing red blood cell count, and a PLT channel for performing platelet count, etc. Further, in some embodiments, each of the detection channels may be provided inside a biological sample analysis device as shown in fig. 14, that is, each of the pulse data is raw data collected by the biological sample analysis device. In other embodiments, each detection channel is disposed within a biological sample detection device in communication with the biological sample analysis device, and the biological sample analysis device performs a corresponding analysis based on each of the pulse data collected by the biological sample detection device. However, it should be noted that, although the description of the embodiments of the present application will describe the biological sample as an example of the blood sample, it should not be construed as limiting the scope of the present application.

S04: and respectively quantifying pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each corresponding first array.

S04 may be implemented by the quantization module 102 in the biological sample analysis device shown in fig. 13, or by the memory 202 in the biological sample analysis apparatus shown in fig. 14 storing a corresponding quantization program, and then implemented by the processor 201 in the biological sample analysis apparatus shown in fig. 14 when executing the quantization program stored in the memory 202.

The set type of pulse characteristics refers to pulse characteristics related to performing corresponding analysis tasks on the biological sample, namely, the set requirements of the quantization are set according to the corresponding analysis tasks, and the obtained pulse characteristic types of the first array are obtained. The plurality of set types of pulse characteristics include, but are not limited to, pulse height, full-peak pulse width, front half-peak pulse width, rear half-peak pulse width, pulse area, and the like. The quantization of the pulse characteristics of the plurality of setting types, respectively, is a process in which the values of the pulse characteristics of the respective corresponding types or the changes in the values obtained by processing the values are expressed in the form of digital values. Each first array in the first arrays corresponding to the pulse characteristics of different setting types comprises information of the pulse characteristics of the setting type corresponding to the first array in the pulse data of different detection channels.

S06: and fusing the first array corresponding to the pulse characteristics of the set type to obtain a second array.

S06 may be implemented by the fusion module 103 in the biological sample analysis apparatus shown in fig. 13, or by the memory 202 in the biological sample analysis device shown in fig. 14 storing the corresponding fusion program, and then implemented by the processor 201 in the biological sample analysis device shown in fig. 14 when executing the fusion program stored in the memory 202.

Fusing the first arrays corresponding to the pulse characteristics of the setting type means that the first arrays corresponding to the pulse characteristics of each setting type in the pulse characteristics of the plurality of setting types are overlapped in a specified dimension direction, and a second array containing pulse characteristic information of a plurality of different setting types is obtained.

S08: and extracting the characteristics of the second array, and outputting the identification result of the target object in the biological sample carried by the second array.

S08 may be implemented by the identification module 104 in the biological sample analysis apparatus shown in fig. 13, or by the memory 202 in the biological sample analysis device shown in fig. 14 storing the corresponding identification program, and then implemented by the processor 201 in the biological sample analysis device shown in fig. 14 when executing the identification program stored in the memory 202.

In some embodiments, feature extraction may be performed on the second array by using an AI identification model, and a result of identifying a target object in the biological sample carried by the second array is output. The AI recognition model is an artificial intelligence (Artificial Intelligence) model, and the second group is analyzed through a machine learning brain to extract the characteristics related to the target object in the second group, so as to output the recognition result of the target object. The target object refers to an object related to a current analysis task in the biological sample. Taking the biological sample as a blood sample as an example, if it is currently required to analyze whether Ig (immature granulocyte) in blood to be detected is abnormal, the target object is the content, volume and/or distribution of immature granulocyte, etc. In some embodiments, the target object may include, but is not limited to, the number of different types of cells such as white blood cells, red blood cells, platelets, etc., and also the content, distribution, etc. of the biological sample components such as hemoglobin, albumin, globulin, DNA/RNA, etc., depending on the current analysis task.

In the above embodiment, the sample analysis method obtains the first arrays corresponding to each set type of pulse characteristics carried by the pulse data of each different detection channel by obtaining the pulse data collected by the biological sample of the object to be detected in each different detection channel, quantifying the pulse characteristics of each set type of pulse data respectively, then fusing the first arrays corresponding to the set type of pulse characteristics to obtain the second arrays, extracting the characteristics of the second arrays, and outputting the identification result of the target object in the biological sample carried by the second arrays. The second group comprises a plurality of pulse characteristics of set types of pulse data of different detection channels, so that accuracy of obtaining the identification result based on the second group serving as input data of an identification model is high.

In other embodiments, the feature extraction may be performed on the second array by using a conventional algorithm model, and the recognition result of the target object in the biological sample carried by the second array may be output. Such as image morphology algorithms, image classification algorithms, clustering algorithms, or threshold segmentation algorithms.

Referring to fig. 2, a biological sample analysis method according to a second embodiment of the present application is different from the first embodiment in that in the second embodiment, S04: the step of respectively quantifying pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each corresponding first array includes: and respectively quantifying pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each two-dimensional first array corresponding to each detection channel, wherein the first dimension value of each two-dimensional first array in the first dimension direction is determined according to the value range of the pulse characteristics of the plurality of set types, and the second dimension value of each two-dimensional first array in the second dimension direction is determined according to the channel number of the detection channel.

Further, in the second embodiment, S06 includes fusing the first array corresponding to the first pulse feature and the first array corresponding to the second pulse feature to obtain a multi-feature fused second array, where the fusing includes: and superposing and fusing the first array corresponding to the first pulse feature and the two-dimensional first array corresponding to the second pulse feature in a third dimension direction to obtain a multi-feature fused three-dimensional second array, wherein a third dimension value of the three-dimensional second array in the third dimension direction is determined according to the feature numbers of the pulse features of the multiple set types.

Specifically, as shown in fig. 12, the structural schematic diagram of the second array is that the H two-dimensional first arrays P1 to PH corresponding to the pulse characteristics of the H setting types are overlapped and fused in the third dimension direction to obtain the three-dimensional second array. The first dimension values L corresponding to the two-dimensional first arrays P1 to PH in the first dimension direction are equal, and the second dimension values W corresponding to the two-dimensional first arrays P1 to PH in the second dimension direction are equal. In some embodiments, the first dimension value of each two-dimensional first array P1 to PH in the first dimension direction is determined according to the value range of the pulse characteristics of the H set types, as it may be set to the maximum value in the value range. The second dimension value of the first arrays P1 to PH of each two dimensions in the second dimension direction is equal to the total number W of channels of each detection channel C1 to CW. One row of the two-dimensional first array corresponding to the pulse characteristics of each setting type represents L quantized values, such as F1, F2 to FL, of the pulse characteristics of the corresponding setting type carried in the pulse data of the corresponding detection channel. The first dimension direction of the three-dimensional second array is the same as the first dimension direction of each two-dimensional first array and the corresponding dimension value, the second dimension direction of the three-dimensional second array is the same as the second dimension direction of each two-dimensional first array and the corresponding dimension value, the third dimension direction of the three-dimensional second array is perpendicular to the first dimension direction and the second dimension direction respectively, and the corresponding third dimension value is the number H of the pulses of a plurality of set types.

Referring to fig. 3, the biological sample analysis method provided in the third embodiment is different from the first embodiment in that in the third embodiment, S04: the step of quantifying pulse characteristics of different setting types carried by the pulse data of different detection channels according to a setting mode to obtain corresponding first arrays, including S041 and S042, is specifically described as follows:

s041: and counting the frequency of the first pulse characteristics of the set type carried by the pulse data of each detection channel, and obtaining a first array of set length values corresponding to the first pulse characteristics.

S042: and calculating the average value of the second pulse characteristic corresponding to each frequency position of the first pulse characteristic based on the first array corresponding to the first pulse characteristic and the second pulse characteristic of a set type, and determining the first array corresponding to the second pulse characteristic.

The frequency statistics means that the values of the first pulse characteristics are counted, the occurrence times of each value of the first pulse characteristics are counted, and the times corresponding to different values are arranged in sequence to form a first array corresponding to the first pulse characteristics. In order to facilitate training of the AI identification model, the dimension values of the respective first arrays constituting the second array in different dimension directions need to be set identically and fixedly. The first dimension direction of the first array corresponding to the first pulse characteristic is the length direction, and the first dimension value corresponding to the first pulse characteristic is the length value. The second dimension direction of the first array corresponding to the first pulse feature is a width direction, and the second dimension value corresponding to the first pulse feature is a width value, wherein the width value is equal to the channel number of different detection channels.

The second pulse characteristic of the set type may comprise a second pulse characteristic of one set type or may comprise a plurality of second pulse characteristics of different set types. Each frequency position of the first pulse feature refers to a position corresponding to each element in the first array corresponding to the first pulse feature, that is, a position where the same first pulse feature value is located. Calculating the average value of the second pulse characteristics corresponding to each frequency position of the first pulse characteristics refers to calculating the average value of the second pulse characteristics corresponding to the same first pulse characteristic value by taking the average value of the second pulse characteristics corresponding to each frequency position. For example, in some embodiments, the first pulse feature is a pulse height, the second pulse feature is a peak width (full or half peak width), and each element in the first array corresponding to the second pulse feature is a peak width average corresponding to a pulse of the same pulse height.

Referring to fig. 4, in a biological sample analysis method according to a fourth embodiment of the present application, S041: counting the frequency of a first pulse characteristic of a set type carried by the pulse data of each detection channel to obtain a first array of set length values corresponding to the first pulse characteristic, wherein the counting comprises the following steps: and counting the frequency of the pulse heights carried by the pulse data of each detection channel to obtain a first array corresponding to the pulse heights.

Further, S042: based on a first array corresponding to the first pulse feature and a second pulse feature of a set type, calculating a mean value of the second pulse feature corresponding to each frequency position of the first pulse feature, and determining the first array corresponding to the second pulse feature, wherein the method comprises the following steps: and calculating the average value of the full peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the full peak width of the pulse data, and determining the first array corresponding to the full peak width.

The second array obtained after the first array corresponding to the pulse height and the first array corresponding to the full peak width are fused contains the pulse height information and the corresponding pulse width information of a plurality of different detection channels, so that the second array is input into the AI identification model, more characteristics which are beneficial to analysis tasks can be extracted, and the analysis accuracy is improved.

Referring to fig. 5, in the fifth embodiment, the full-width is decomposed into a first half-width and a second half-width, that is, the second pulse characteristic includes the first half-width and the second half-width, which are different from the biological sample analysis method provided in the fourth embodiment. S042: based on a first array corresponding to the first pulse feature and a second pulse feature of a set type, calculating a mean value of the second pulse feature corresponding to each frequency position of the first pulse feature, and determining the first array corresponding to the second pulse feature, wherein the method comprises the following steps: the method comprises the steps of calculating an average value of the first half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the first half peak width of the pulse data, determining a first array corresponding to the first half peak width, and calculating an average value of the second half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the second half peak width of the pulse data, and determining a first array corresponding to the second half peak width.

Furthermore, in other embodiments according to the application, S042: based on the first array corresponding to the first pulse feature and the second pulse feature of the set type, calculating a mean value of the second pulse feature corresponding to each frequency position of the first pulse feature, and determining the first array corresponding to the second pulse feature, the method may further include: and calculating the average value of the pulse area corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the pulse area of the pulse data, and determining the first array corresponding to the pulse area.

The second array obtained in S06 not only includes pulse height information for analyzing and identifying the biological sample to have a major contribution, but also includes information such as full-width, half-width, or pulse area for analyzing and identifying the biological sample to have a certain contribution, which is beneficial to improving the accuracy of the identification result in S08.

Referring to fig. 6, in a sixth embodiment provided according to the present application, in S041: the method for analyzing biological samples further comprises the step S03 of counting the frequency of the first pulse characteristics of the set type carried by the pulse data of each detection channel and obtaining a first array of set length values corresponding to the first pulse characteristics: and setting a length value of the first array corresponding to the first pulse characteristic in the length dimension direction according to the height range of the pulse height.

Specifically, in some embodiments, the setting, according to the height range of the pulse height, a length value of the first array in a length dimension direction, where the length value corresponds to the first pulse feature, includes: and selecting the maximum value of the pulse height as the length value of the first array corresponding to the first pulse characteristic in the length dimension direction according to the height range of the pulse height.

For example, in some embodiments, the height range of the pulse height is [0,4096], where the highest value is 4096, 4069 may be set as the length value of the first array, and if the number of each detection channel is 6, each first array corresponding to the pulse characteristics of each different setting type is a two-dimensional array of 6×4096, that is, the number of rows of each first array is 6, and the number of columns of each first array is 4096. In the fourth example, if the number of pulse features of different setting types is 2, in S06, a three-dimensional array with a second array of 2×6×4096 is obtained, where the first dimension value is 4096, the second dimension value is 6, and the third dimension value is 2. In the fourth example, if the number of pulse features of different setting types is 3, in S06, a three-dimensional array with a second array of 3×6×4096 is obtained, where the first dimension value is 4096, the second dimension value is 6, and the third dimension value is 3.

Referring to fig. 7, in a biological sample analysis method according to a seventh embodiment of the present application, a blood sample is taken as an example, S02: the acquiring the pulse data acquired by biological samples of the object to be detected in different detection channels comprises the following steps: and acquiring cell pulse signals acquired by a plurality of detection channels of the biological sample cells of the object to be detected. Each cell pulse signal is an electric pulse signal converted from the biological characteristics of the corresponding cell.

Referring to fig. 8, in a biological sample analysis method according to an eighth embodiment of the present application, S02: the method for acquiring the cell pulse signals acquired by the plurality of detection channels of the biological sample cells of the object to be detected further comprises S021a and S022a, and is specifically described as follows:

s021a: device information file data of a biological sample analyzer is acquired.

S022a: and determining a plurality of target detection channels of the biological sample cells of the object to be detected according to the equipment information file data, and acquiring cell pulse signals acquired by the plurality of target detection channels.

The biological sample analyzer is an instrument for analyzing detection data corresponding to the biological sample and outputting a corresponding analysis result. The apparatus information file (INF, device INFormation File) data, by acquiring the data, can determine channel information related to the number and the like of each detection channel related to the current analysis task in the biological sample analyzer, thereby determining a plurality of target detection channels of biological sample cells of the object to be detected, and acquiring cell pulse signals acquired by each detection channel from each determined detection channel. The method comprises the steps of obtaining equipment information file data of a biological sample analyzer, wherein the step of obtaining the equipment information file data of the biological sample analyzer comprises the steps of receiving the equipment information file data and analyzing the equipment information file data so as to determine each target detection channel related to an analysis task according to the analyzed equipment information file data.

Referring to fig. 9, unlike the eighth embodiment, in the biological sample analysis method according to the ninth embodiment of the present application, S02: the method comprises the steps of acquiring pulse data acquired by biological samples of an object to be detected in different detection channels, and further comprises S021b and S022b, wherein the specific description is as follows:

s021b: acquiring sample detection data output by a biological sample analyzer; the biological sample analyzer is internally provided with a combination of two or more detection channels as follows: SFL channel, FSC channel, SSC channel, WBC channel, PLT channel, and RBC channel.

S022b: and acquiring pulse data acquired by biological samples of the object to be detected in an SFL channel, an FSC channel, an SSC channel, a WBC channel, a PLT channel and an RBC channel according to the sample detection data.

Referring to fig. 10, a biological sample analysis method according to a tenth embodiment of the present application includes:

S0421: and calculating the average value of the first half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the first half peak width of the pulse data, and determining the first array corresponding to the first half peak width.

S0422: and calculating the average value of the second half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the second half peak width of the pulse data, and determining the first array corresponding to the second half peak width.

S06: and fusing the first array corresponding to the first pulse characteristic and the first array corresponding to the second pulse characteristic to obtain a multi-characteristic fused second array.

S08: and extracting the characteristics of the second array through a convolutional neural network model, and outputting the identification result of the abnormal target object in the biological sample borne by the second array.

S09: and forming an alarm of the abnormal target object based on the identification result of the abnormal target object.

In the tenth embodiment, the AI identification model is a convolutional neural network model such as res net, VGG, etc., and in other embodiments, the AI identification model may also be another model formed by adopting a one-dimensional convolution manner.

Before the second number is input to the AI identification model, training of the AI identification model is required. Training the AI-recognition model includes obtaining sample data. The sample data comprises a second array carrying classification labels of target object characteristics, wherein the classification labels of the second array comprise positive sample labels of target object anomalies (such as IG, erythrocyte double peaks and the like) and negative sample labels of target object normal.

In some embodiments, taking the AI identification model as a target object (IG, naive granulocyte) alert model, each detection channel is exemplified by an SFL channel, an FSC channel, an SSC channel, a WBC channel, a PLT channel, and an RBC channel. The first pulse characteristic is pulse height, the second pulse characteristic is front half peak width and rear half peak width, and the second array is obtained as follows:

s11: and (3) preprocessing the data to obtain pulse data of each detection channel of the biological sample.

S12: the pulse heights of the 6 channels are obtained, and the statistics frequency is carried out on the pulse heights. Obtaining a first array of 6x4096 corresponding to the pulse height;

s13: and obtaining the front half peak width and the rear half peak width of the 6 channels, and obtaining the average value of the front half peak width and the rear half peak width according to the frequency position of the pulse height to obtain a 6x4096 first array corresponding to the front half peak width and the rear half peak width.

S14: the three first arrays are superimposed to obtain a second array in three dimensions (3 x6x 4096).

After sample data is obtained, the positive sample and the negative sample are mixed and divided into a training set, a verification set and a test set according to a preset proportion, for example, the mixed positive sample and negative sample are divided into the training set, the verification set and the test set according to a proportion of 8:1:1, and the AI recognition model is trained.

After the training of the AI recognition model is completed, the second group is input into a trained target object alarm model, the alarm whether the target object is abnormal is output, and if the output result is a classification result, the alarm model only outputs the alarm of 'target object' and 'target object has no abnormality'.

From the above, the sample analysis method provided by the application obtains pulse data acquired by biological samples of objects to be detected in different detection channels, quantifies pulse characteristics of a plurality of set types carried by the pulse data of the different detection channels respectively to obtain corresponding first arrays, fuses the first arrays corresponding to the pulse characteristics of the set types to obtain second arrays, extracts characteristics of the second arrays through an AI identification model, and outputs identification results of target objects in the biological samples carried by the second arrays. The second group comprises a plurality of pulse characteristics of set types of pulse data of different detection channels, so that the accuracy of obtaining the identification result based on the second group serving as input data of an AI identification model is high.

In addition, referring to fig. 11, in the biological sample analysis method provided in the eleventh embodiment, pulse data of the SFL channel, the FSC channel, the SSC channel, the WBC channel, the PLT channel, and the RBC channel are obtained as an example, so that the biological sample analysis method provided in the application is further clearly and in detail described. In an eleventh embodiment, the biological sample analysis method includes first acquiring INF (Device INFormation File ) data of a biological sample analysis instrument, then analyzing the INF data, then determining SFL channel, FSC channel, SSC channel, WBC channel, PLT channel and RBC channel according to the analyzed INF data, then acquiring SFL channel pulse, FSC channel pulse, SSC channel pulse, WBC channel pulse, PLT channel pulse and RBC channel pulse, then acquiring pulse height and peak width data of the pulse data, so as to obtain a multi-channel fusion pulse frequency matrix (second set) according to the pulse height and peak width data, finally extracting and identifying characteristics of the multi-channel fusion pulse frequency matrix through an AI identification model formed by a convolutional neural network, obtaining a corresponding identification result, and outputting a model alarm prediction of the AI identification model alarm prediction such as an IG alarm or a red cell bimodal alarm.

Referring to fig. 13, in some embodiments, the present application further provides a biological sample analysis device. The biological sample analysis device includes an acquisition module 101, a quantization module 102, a fusion module 103, and an identification module 104. The acquiring module 101 is configured to acquire pulse data acquired by biological samples of an object to be detected in different detection channels; the quantization module 102 is configured to quantize a plurality of pulse characteristics of a set type carried by the pulse data of each of the different detection channels, so as to obtain each corresponding first array; the fusion module 103 is configured to fuse the first array corresponding to the pulse feature of the set type to obtain a second array; the identification module 104 is configured to perform feature extraction on the second array through an AI identification model, and output an identification result of the target object in the biological sample carried by the second array.

Referring to fig. 14, in some embodiments, the present application further provides a biological sample analysis device, which includes a memory 202 and a processor 201. The processor 201, when executing the computer program instructions stored in the memory 202, performs the steps of the biological sample analysis method according to any of the embodiments of the present application.

Furthermore, the application provides a computer readable storage medium, wherein the computer readable storage medium stores computer program instructions; the computer program instructions, when executed by a processor, implement the steps of the biological sample analysis method according to any of the embodiments of the present application.

The processor may be a CPU (central processing unit ) or ASIC (application specific integrated circuit, application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the moving object detection apparatus may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.

The Memory may include a high-speed RAM (random access Memory ) and may further include an NVM (Non-Volatile Memory), such as at least one magnetic disk Memory.

In addition, please refer to fig. 15, which is a schematic flow chart of the auxiliary diagnosis method according to the present application, wherein the auxiliary diagnosis method according to the present application determines an abnormal target object in a biological sample based on a recognition result obtained by the biological sample analysis method according to the present application in combination with clinical information of the object to be detected, and outputs corresponding auxiliary diagnosis information.

Specifically, as shown in fig. 15, the auxiliary diagnosis method includes the following steps:

s22: obtaining a recognition result of a target object in a biological sample obtained by analyzing the biological sample of the object to be detected by using the biological sample analysis method provided in any embodiment of the present application.

The auxiliary diagnosis method is applied to the auxiliary diagnosis equipment provided by the application. The auxiliary diagnostic apparatus acquires the identification result from the biological sample analysis apparatus as described in fig. 14.

S24: and acquiring clinical information of the object to be detected.

The clinical information is stored primarily in a test information system (Laboratory Information System, LIS) from which the auxiliary diagnostic device obtains the clinical information. The clinical information comprises different ages, sexes, test sample types, past medical histories and the like of different objects to be detected. In an alternative specific example, the clinical information of the subject to be tested includes age, sex, test sample type, past medical history of the subject to be tested.

S26: and determining an abnormal target object in the biological sample of the object to be detected based on the identification result and the clinical information, and outputting auxiliary diagnosis decision information corresponding to the abnormal target object.

The abnormal target object in the biological sample refers to a measurement index which can be used for representing whether the object to be detected has a disease hidden trouble or not, and taking a blood sample as an example, the abnormal target object in the blood sample refers to a target object in a blood sample which can be used for measuring whether the object to be detected has a disease hidden trouble or not. The auxiliary diagnosis decision information corresponding to the abnormal target object refers to an auxiliary diagnosis conclusion which is determined based on the biological sample of the object to be detected and is formed by integrating the identification result of the target object in the biological sample and the clinical information of the object to be detected, and can comprise a basis description of the determined abnormal target object, wherein the basis description can be text or an image with labels, and the auxiliary diagnosis decision information can reflect the information on which the decision is made, so that the basis of the abnormal target object determined in the current detection result can be intuitively known, and the readability of the auxiliary diagnosis result is improved.

Further, in some embodiments, the auxiliary diagnostic apparatus may further acquire other analysis results in the biological sample analysis apparatus, such as report parameters obtained based on analysis of a biological sample, in addition to the identification result, and then determine an abnormal target object in the biological sample data in combination with the other analysis results, the identification result, and the clinical information, and output a corresponding auxiliary diagnostic report. The auxiliary diagnosis decision information obtained by the auxiliary diagnosis equipment is used for rapidly screening the evidence of the sample of the abnormal target object in the detection result corresponding to the biological sample, so that a checking doctor can conveniently and efficiently make a next diagnosis and treatment decision according to the auxiliary diagnosis decision information.

The analysis result obtained by the biological sample analysis device, that is, biological sample analysis data, is corresponding analysis data obtained by detecting various biological samples containing target objects (biological cell information or other biological information), wherein the target objects can be healthy features or unhealthy corresponding objects represented in different types of corresponding biological samples, such as abnormal cell types, cell numbers, cell sizes, cell composition ratios, cell contents, nucleic acid contents and the like in the biological samples. The target object refers to an object determined according to the detection requirements of different biological samples, for example, the biological sample analysis data is taken as the cell analysis data, the target object refers to one or a plurality of cells determined according to the detection requirements of different biological samples, for example, PLT histograms in the cell analysis data of blood samples, and the target cells refer to the quantity distribution characteristics of platelets with different sizes. The biological sample analysis data also comprises sample data of other biological information, and the target object refers to information representing characteristics of the corresponding biological information, such as information representing whether a CRP reaction curve output by the immune analyzer has abnormal peaks, whether an impedance detection channel of the blood cell analyzer has holes blocking, whether a DIFF detection channel of the blood cell analyzer detects immature granulocyte and the like.

According to the auxiliary diagnosis method provided by the application, the identification result of the target object is obtained based on the sample analysis method, the abnormal target object in the biological sample is determined by combining the clinical information of the object to be detected, the auxiliary diagnosis decision information corresponding to the abnormal object is output, whether the abnormal target object exists in the biological sample of the object to be detected or not can be more intuitively known by the auxiliary diagnosis decision information, and the accurate auxiliary diagnosis result can be obtained without depending on the personal experience level of a checking doctor under the condition that the abnormal target object exists is determined, so that on one hand, the checking efficiency can be improved, the detection result is more accurate, on the other hand, the diagnosis conclusion is more interpretable, the numerical type detection report in the biological sample analysis equipment and the checking information system is converted into the descriptive auxiliary diagnosis decision information, the auxiliary checking doctor reduces the workload of checking detection data, and meanwhile, the result in the auxiliary diagnosis report can be better matched with the classification policy.

In some embodiments, the determining the abnormal feature of the sample to be detected of the object to be detected, and outputting the auxiliary diagnostic decision information corresponding to the abnormal feature include one of the following:

Determining abnormal characteristics of a sample to be detected of the object to be detected, correcting a parameter alarm state formed based on the identification result of the target cell characteristics according to the abnormal characteristics, and outputting corrected auxiliary diagnosis decision information corresponding to the abnormal characteristics;

determining abnormal characteristics of a sample to be detected of the object to be detected, and outputting auxiliary diagnosis decision information containing failure cause analysis corresponding to the abnormal characteristics;

determining abnormal characteristics of a sample to be detected of the object to be detected, determining supporting evidence and/or diagnosis and treatment advice corresponding to the abnormal characteristics, and outputting an auxiliary diagnosis report containing the supporting evidence and/or diagnosis and treatment advice.

The biological sample analyzer performs detection analysis on the sample to be detected, outputs biological sample image data, parameter reports, alarm parameters and the like, for example, the cell analyzer performs detection analysis on the sample to be detected, and outputs detection analysis results of cell analysis data, blood parameter reports, alarm parameters and the like. The auxiliary diagnosis equipment can comprehensively take a detection analysis result output by the biological sample analyzer, clinical information of an object to be detected in the detection information system and the like as input for auxiliary diagnosis solution based on an auxiliary diagnosis knowledge graph, and simulate a detection doctor to make an auxiliary diagnosis decision based on detection result data and output key information based on which the auxiliary diagnosis decision is made, so that dependence on individual experience level of the detection doctor can be reduced, workload of the detection doctor is reduced, and the auxiliary diagnosis decision is more readable, accurate and efficient. An alternative scheme of the auxiliary diagnosis decision information is to correct a parameter alarm state formed based on the identification result of the target feature according to the abnormal feature, output corrected auxiliary diagnosis decision information corresponding to the abnormal feature, and highlight the basis for correcting the parameter alarm state from key information contained in the auxiliary diagnosis decision information and used for making the auxiliary diagnosis decision; in this way, auxiliary diagnostic decisions are made by integrating multiple data sources to avoid one-sidedness of a single data source. Another alternative scheme of the auxiliary diagnosis decision information is to include unqualified reason analysis corresponding to the abnormal characteristics, and unqualified specimen decision logic can be highlighted from key information included in the auxiliary diagnosis decision information and used for making an auxiliary diagnosis decision; in this way, it is possible to distinguish between failure causes such as abnormal samples (chylomicronemia, hemolysis, red blood cell cold coagulation, etc.), abnormal biological sample analyzers (hole blocking, unstable voltage, etc.). Yet another alternative of the auxiliary diagnostic decision information is to determine supporting evidence and/or diagnosis and treatment advice corresponding to the abnormal feature, output an auxiliary diagnostic report comprising the supporting evidence and/or diagnosis and treatment advice, and form an auxiliary diagnostic report according to the key information on which the auxiliary diagnostic decision is made.

In the above embodiment, the auxiliary diagnostic device cooperates with the biological sample analyzer and the inspection information system to synthesize biological sample analysis data, the identification result and the clinical information to make auxiliary diagnostic decisions, and forms auxiliary diagnostic decision information in different forms based on key information on which the auxiliary diagnostic decisions are made, so that the auxiliary diagnostic result is more readable, and the reliability of the quick judgment result is facilitated.

In some embodiments, the determining an abnormal target object of the biological sample of the object to be detected, outputting auxiliary diagnostic decision information corresponding to the abnormal target object, includes:

determining an abnormal target object of the biological sample of the object to be detected, determining diagnosis and treatment suggestions corresponding to the abnormal target object, and outputting an auxiliary diagnosis report containing the text description of the diagnosis and treatment suggestions; or alternatively, the first and second heat exchangers may be,

and determining an abnormal target object of the biological sample of the object to be detected, determining supporting evidence corresponding to the abnormal target object, and outputting an auxiliary diagnosis report comprising text description, image data carrying labels and numerical description of the supporting evidence.

Taking a blood sample of the object to be detected as an example, the abnormal target object of the biological sample may correspond to the diagnosis result of each historical diagnosis example in the diagnosis example database, for example, the number of platelets is small, the number of white blood cells is increased with immature granulocytes, and the like. The diagnosis and treatment advice for the small number of platelets may be advice for checking for autoantibodies, platelet-related immature granulocytes and the like for clear diagnosis, and the diagnosis and treatment advice for the increased number of leukocytes accompanied by immature granulocytes may be advice for performing, if necessary, a related examination such as a myelologic examination. The auxiliary diagnosis report provides the abnormal target object of the biological sample and the text description of the diagnosis and treatment advice corresponding to the abnormal target object, so that the auxiliary diagnosis result is more readable. The supporting evidence corresponding to the abnormal target object refers to a reason for determining the abnormal characteristic, for example, the supporting evidence for the small number of platelets can comprise comparison of a platelet count value with a corresponding reference value, and the supporting evidence for the increased number of white blood cells with immature granulocytes can comprise comparison of a white blood cell count value with a corresponding reference value, comparison of an immature granulocyte ratio with a corresponding reference value, comparison of a patient scatter diagram marked with an abnormal part with a reference scatter diagram confirmed by microscopic examination. The auxiliary diagnosis report provides the abnormal characteristics of the blood sample and the corresponding text description of the supporting evidence, the image data carrying the labels and the numerical description thereof, thereby facilitating the checking doctor to know the specific reasons of the abnormality in the current detection result efficiently and accurately, grasping the basis of the conclusion forming process in the auxiliary diagnosis report and facilitating the checking doctor to make decisions according to the basis.

In the above embodiment, the determination basis of the abnormal target object in the biological sample detection result of the object to be detected can be provided through the auxiliary diagnosis report, and the description of the auxiliary diagnosis and the conclusion formation can be described through the text description or the text and image combination description, and the explanation of the supporting evidence of the auxiliary diagnosis conclusion of the auxiliary diagnosis report can be further provided, so that the auxiliary diagnosis result with higher readability can be output.

In some embodiments, the determining the abnormal target object of the biological sample of the object to be detected, outputting the auxiliary diagnostic report including the corresponding description of the abnormal target object, includes:

acquiring a selection instruction of a simplified diagnosis report or a detailed diagnosis report;

outputting an auxiliary diagnosis report containing the text description of the reasons of the abnormal target object according to the selection instruction of the simplified diagnosis report, or outputting an auxiliary diagnosis report containing the text description of the supporting evidence, the image data carrying the labels and the numerical description according to the selection instruction of the detailed diagnosis report.

The auxiliary diagnostic device can provide a selection button of an auxiliary diagnostic report type through an application program interface, and a user can select the type for acquiring the auxiliary diagnostic report to be a simplified diagnostic report or a detailed diagnostic report by clicking the selection button. The auxiliary diagnosis equipment determines an abnormal target object of a blood sample of the object to be detected according to a selection instruction of a user for the type of the auxiliary diagnosis report, if the user selects and outputs the simplified diagnosis report, determines diagnosis and treatment suggestions corresponding to the abnormal target object, and outputs the auxiliary diagnosis report containing the text description of the diagnosis and treatment suggestions; if the user selects to output the detailed diagnosis report, determining an abnormal target object of the blood sample of the object to be detected, determining supporting evidence corresponding to the abnormal characteristic, and outputting an auxiliary diagnosis report containing text description, image data carrying labels and numerical description of the supporting evidence.

In the above embodiment, the user may autonomously select the type of the currently received auxiliary diagnostic report, obtain the simplified diagnostic report, quickly browse the current auxiliary diagnostic conclusion, and select to obtain the detailed diagnostic report for the specific basis of knowing the corresponding auxiliary diagnostic conclusion so as to meet the more sexual use demands.

In some embodiments, S26: determining an abnormal target object in the biological sample of the object to be detected based on the identification result and the clinical information, and outputting auxiliary diagnosis decision information corresponding to the abnormal target object, further comprising: and determining an abnormal target object in the biological sample of the object to be detected based on biological sample analysis data corresponding to the biological sample, the identification result and the clinical information, and outputting auxiliary diagnosis decision information corresponding to the abnormal target object. The specific steps of the scheme are as follows:

inputting an auxiliary diagnostic model based on the report parameters in the biological sample analysis data, the identification result, and the clinical information;

and the auxiliary diagnosis model determines the abnormal characteristic type of the sample of the object to be detected according to the report parameters, the identification result and the clinical information, and outputs an auxiliary diagnosis report corresponding to the abnormal characteristic type.

The sample to be detected uses a blood sample, blood report parameters in cell analysis data, the identification result and clinical information of an object to be detected are used as input of an auxiliary diagnosis model by establishing the auxiliary diagnosis model, characteristics are learned from a large amount of multi-mode data by using the auxiliary diagnosis model, the characteristics are similar to the brain of a professional examining doctor, a forgetting curve is avoided, and the output result can be optimized step by step along with the increase of the data. Alternatively, the auxiliary diagnosis model can be obtained after training by adopting a neural network model, and can also be completed by constructing an auxiliary diagnosis knowledge graph.

In some embodiments, the present application also provides an auxiliary diagnostic apparatus, including a processor and a memory, in which a computer program executable by the processor thereof is stored, which computer program, when executed by the processor thereof, implements the auxiliary diagnostic method.

In addition, the application also provides another computer readable storage medium, wherein the other computer readable storage medium stores computer program instructions, which when executed by a processor, implement the steps of the method for assisting diagnosis provided by any embodiment of the application.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within 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

1. A method of analyzing a biological sample, comprising:

2. The method of claim 1, wherein the extracting features of the second array, outputting the identification result of the target object in the biological sample carried by the second array, includes:

Extracting features of the second array through an AI identification model, and outputting identification results of target objects in the biological samples carried by the second array; or alternatively, the first and second heat exchangers may be,

and extracting the characteristics of the second array through a traditional algorithm model, and outputting the identification result of the target object in the biological sample carried by the second array.

3. The method according to claim 1, wherein the quantifying the pulse features of the plurality of set types carried by the pulse data of each of the different detection channels to obtain each corresponding first array includes:

respectively quantifying pulse characteristics of a plurality of set types carried by the pulse data of each different detection channel to obtain each two-dimensional first array corresponding to each detection channel, wherein a first dimension value of each two-dimensional first array in a first dimension direction is determined according to a value range of the pulse characteristics of the plurality of set types, and a second dimension value of each two-dimensional first array in a second dimension direction is determined according to the channel number of the detection channel;

the fusing the first array corresponding to the first pulse feature and the first array corresponding to the second pulse feature to obtain a multi-feature fused second array includes:

And superposing and fusing the first array corresponding to the first pulse feature and the two-dimensional first array corresponding to the second pulse feature in a third dimension direction to obtain a multi-feature fused three-dimensional second array, wherein a third dimension value of the three-dimensional second array in the third dimension direction is determined according to the feature numbers of the pulse features of the multiple set types.

4. The method according to claim 1, wherein the quantifying the pulse characteristics of each different setting type carried by the pulse data of each different detection channel according to the setting manner to obtain each corresponding first array includes:

counting the frequency of a first pulse characteristic of a set type carried by the pulse data of each detection channel to obtain a first array of set length values corresponding to the first pulse characteristic;

and calculating the average value of the second pulse characteristic corresponding to each frequency position of the first pulse characteristic based on the first array corresponding to the first pulse characteristic and the second pulse characteristic of a set type, and determining the first array corresponding to the second pulse characteristic.

5. The method of analyzing a biological sample according to claim 4, wherein the counting the frequency of the first pulse characteristics of the set type carried by the pulse data of each detection channel to obtain a first array corresponding to the first pulse characteristics includes:

And counting the frequency of the pulse heights carried by the pulse data of each detection channel to obtain a first array corresponding to the pulse heights.

6. The method according to claim 5, wherein the calculating the average value of the second pulse characteristic corresponding to each frequency location of the first pulse characteristic based on the first array corresponding to the first pulse characteristic and the second pulse characteristic of the set type, and determining the first array corresponding to the second pulse characteristic includes at least one of:

calculating the average value of the full peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the full peak width of the pulse data, and determining the first array corresponding to the full peak width;

calculating the average value of the first half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the first half peak width of the pulse data, and determining the first array corresponding to the first half peak width;

calculating the average value of the second half peak width corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the second half peak width of the pulse data, and determining a first array corresponding to the second half peak width;

And calculating the average value of the pulse area corresponding to each frequency position of the pulse height based on the first array corresponding to the pulse height of the pulse data and the pulse area of the pulse data, and determining the first array corresponding to the pulse area.

7. The method according to claim 5, wherein before counting the pulse heights carried by the pulse data of each detection channel to obtain the first array corresponding to the pulse heights, the method further comprises:

setting a length value of a first array corresponding to the first pulse characteristic in the length dimension direction according to the height range of the pulse height;

counting the pulse heights carried by the pulse data of each detection channel, and obtaining a first array corresponding to the pulse heights, wherein the first array comprises:

and counting the frequency of the pulse heights carried by the pulse data of each detection channel, and obtaining a first array corresponding to the pulse heights according to the frequency counting result and the length value.

8. The method according to claim 7, wherein the setting the length value of the first array in the length dimension direction corresponding to the first pulse feature according to the height range of the pulse height comprises:

And selecting the maximum value of the pulse height as the length value of the first array corresponding to the first pulse characteristic in the length dimension direction according to the height range of the pulse height.

9. The method according to claim 1, wherein the acquiring pulse data collected in each of the different detection channels for the biological sample of the object to be detected comprises:

and acquiring cell pulse signals acquired by a plurality of detection channels of the biological sample cells of the object to be detected.

10. The biological sample analysis method according to claim 9, wherein the acquiring of the cell pulse signals acquired by the plurality of detection channels of the biological sample cells of the object to be detected comprises:

acquiring equipment information file data of a biological sample analyzer;

and determining a plurality of target detection channels of the biological sample cells of the object to be detected according to the equipment information file data, and acquiring cell pulse signals acquired by the plurality of target detection channels.

11. The method according to claim 1, wherein the acquiring pulse data collected in each of the different detection channels for the biological sample of the object to be detected comprises:

Acquiring sample detection data output by a biological sample analyzer; the biological sample analyzer is internally provided with a combination of two or more detection channels as follows: SFL detection channel, FSC detection channel, SSC detection channel, WBC detection channel, PLT detection channel and RBC detection channel;

and acquiring pulse data acquired by biological samples of the object to be detected in an SFL channel, an FSC channel, an SSC channel, a WBC channel, a PLT channel and an RBC channel according to the sample detection data.

12. The method of claim 1, wherein the extracting the features of the second array, and outputting the identification result of the target object in the biological sample carried by the second array, includes:

and forming a target object based on the identification result of the target object.

13. The method according to claim 2, wherein the feature extraction is performed on the second array by using an AI identification model, and the outputting the identification result of the target object in the biological sample carried by the second array includes:

performing feature extraction on the second array through an AI recognition model constructed based on a one-dimensional convolution mode, and outputting a recognition result of a target object in the biological sample carried by the second array; or (b)

And extracting the characteristics of the second array through a convolutional neural network model, and outputting the identification result of the target object in the biological sample borne by the second array.

14. An auxiliary diagnostic method, comprising:

obtaining a recognition result of a target object in a biological sample obtained by analyzing the biological sample of an object to be detected using the biological sample analysis method according to any one of claims 1 to 13;

acquiring clinical information of the object to be detected;

15. A biological sample analysis device, comprising:

16. A biological sample analysis device comprising a processor and a memory, the memory having stored therein a computer program executable by the processor, the computer program when executed by the processor implementing the biological sample analysis method of any one of claims 1 to 13.

17. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a controller, implements the biological sample analysis method according to any one of claims 1 to 13.

18. An auxiliary diagnostic device comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, the computer program implementing the auxiliary diagnostic method of claim 14 when executed by the processor.

19. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which computer program, when executed by a controller, implements the auxiliary diagnostic method according to claim 14.