CN113902687A

CN113902687A - Methods, devices and media for determining the positivity and positivity of antibodies

Info

Publication number: CN113902687A
Application number: CN202111110439.6A
Authority: CN
Inventors: 王晶; 房柯池
Original assignee: Institute of Psychology of CAS
Current assignee: Institute of Psychology of CAS
Priority date: 2021-09-18
Filing date: 2021-09-18
Publication date: 2022-01-07

Abstract

Embodiments of the present disclosure relate to a method, computing device, and medium for determining the positivity and titer of antibodies. The method comprises the following steps: applying the indirect immunofluorescence image of the cell-based antibody to a negative-positive interpretation model to determine whether the antibody is positive; if the antibody is determined to be positive, determining a nuclear karyotype mask for the cell and a cytoplasmic karyotype mask for the cell based on the indirect immunofluorescence image; determining a class of the indirect immunofluorescence image based on the nuclear and cytoplasmic karyotype masks; and determining the titer based on the class and a gray value of a partial image of the indirect immunofluorescence image corresponding to the nuclear karyotype mask or the cytoplasmic karyotype mask. By the method, the positive and negative of the antibody and the titer of the antibody can be determined quickly and accurately, the accuracy of titer judgment is improved, and the efficiency is improved.

Description

Methods, devices and media for determining the positivity and positivity of antibodies

Technical Field

The present disclosure relates generally to bioinformation processing, and in particular, to methods, devices, and storage media for predicting titers of antibodies.

Background

Cell-based antibodies recognize various nuclear components and are present in many autoimmune diseases. In these autoimmune diseases, antinuclear antibodies will all be positive to varying degrees. Therefore, the degree of positivity of antinuclear antibodies can be used as a basis for diagnosis of many diseases. Such as rheumatoid lupus erythematosus SLE.

Common methods for detecting antinuclear antibodies include indirect immunofluorescence, ELISA, radioimmunoassay, and the like. Among them, indirect immunofluorescence is currently the most commonly used method for detection. The method mainly determines the positive and negative through the artificial fluorescence observation under a microscope. However, such manual interpretation process has many subjective factors and takes time. Therefore, with the development of computer technology, many methods for processing indirect immunofluorescence images by using a computer have appeared. However, there are many problems to be solved in processing the indirect immunofluorescence image.

Disclosure of Invention

The present disclosure provides a method, computing device, and computer storage medium for determining the positivity and titer of antibodies.

According to a first aspect of the present disclosure, a method for determining the positivity and titer of an antibody is provided. The method comprises the following steps: applying the indirect immunofluorescence image of the cell-based antibody to a negative-positive interpretation model to determine whether the antibody is positive; if the antibody is determined to be positive, determining different karyotype masks corresponding to different cell nuclear karyotypes or cytoplasmic karyotypes based on the indirect immunofluorescence image; determining a class of the indirect immunofluorescence image based on the nuclear and cytoplasmic karyotype masks; and determining the titer based on the class and a gray value of a partial image of the indirect immunofluorescence image corresponding to the nuclear karyotype mask or the cytoplasmic karyotype mask.

According to a second aspect of the present invention, there is also provided a computing device comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit, cause the computing device to perform the method of the first aspect of the disclosure.

According to a third aspect of the present disclosure, there is also provided a computer-readable storage medium. The computer readable storage medium has stored thereon machine executable instructions which, when executed, cause a machine to perform the method of the first aspect of the disclosure.

In some embodiments, applying the indirect immunofluorescence image to a negative-positive interpretation model comprises: obtaining an indirect immunofluorescence image of the antibody with the cells as the matrix; adjusting pixel values of a target pixel using a set of pixel values of pixels surrounding the target pixel in the indirect immunofluorescence image to generate an adjusted indirect immunofluorescence image; and applying the adjusted indirect immunofluorescence image to a negative-positive interpretation model to determine whether the antibody is positive.

In some embodiments, applying the adjusted indirect immunofluorescence image to a negative-positive interpretation model comprises: the adjusted indirect immunofluorescence image is resized for application to a negative-positive interpretation model.

In some embodiments, determining the nuclear karyotype mask and the cytoplasmic karyotype mask includes: segmenting the indirect immunofluorescence image using a first gray value in a gray value range corresponding to the indirect immunofluorescence image to obtain a first mask, the first mask indicating pixels in the indirect immunofluorescence image having gray values greater than the first gray value; segmenting the indirect immunofluorescence image with a second gray value of all gray values to obtain a second mask, wherein the second mask indicates pixels of the indirect immunofluorescence image with gray values larger than the second gray value; a nuclear karyotype mask and a cytoplasmic karyotype mask are determined based on the first mask and the second mask.

In some embodiments, determining the nuclear karyotype mask and the cytoplasmic karyotype mask based on the first mask and the second mask includes: performing AND operation on the first mask and the second mask to obtain a nuclear karyotype mask; the first mask and the second mask are exclusive-ored to determine a cytoplasmic karyotype mask.

In some embodiments, determining the category comprises: and applying the nuclear and cytoplasmic nuclear type masks to a classification model to determine the class of the indirect immunofluorescence image, wherein the classification model is obtained by training through a residual error neural network.

In some embodiments, determining the titer comprises: determining a first gray value range of a plurality of pixels in the indirect immunofluorescence image corresponding to the nuclear karyotype, if the category is determined to be the nuclear type; determining a second gray scale value range for a plurality of pixels in the indirect immunofluorescence image corresponding to the cytoplasmic-nuclear mask if the classification is determined to be cytoplasmic; and acquiring a mapping relation between the gray value range and the titer, and determining the titer corresponding to the first gray value range or the second gray value range based on the mapping relation.

In some embodiments, the negative-positive interpretation model is trained using a residual neural network, and the training process utilizes a training dataset, a test dataset, and an evaluation dataset.

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the disclosure, nor is it intended to be used to limit the scope of the disclosure.

Drawings

Fig. 1 shows a schematic diagram of a system 100 for determining positivity and titer of antibodies according to an embodiment of the present disclosure.

Fig. 2 shows a flow diagram of a method 200 for determining positivity and titer of antibodies according to an embodiment of the disclosure.

Fig. 3 shows a schematic diagram of a negative-positive cell image according to an embodiment of the disclosure.

FIG. 4 shows a schematic diagram of a process 400 of training a positive-negative module, according to an embodiment of the present disclosure.

FIG. 5 shows a schematic diagram of extracting a nuclear karyotype mask and a cytoplasmic karyotype mask according to an embodiment of the disclosure.

Fig. 6 shows a schematic diagram for grayscale value according to an embodiment of the disclosure.

Fig. 7 shows a flow diagram of a method 700 for pre-processing image data according to an embodiment of the present disclosure.

FIG. 8 shows a flow diagram of a method 800 for determining a nuclear karyotype mask and a cytoplasmic karyotype mask according to an embodiment of the disclosure.

FIG. 9 schematically illustrates a block diagram of an electronic device 900 suitable for use in implementing embodiments of the present disclosure.

Like or corresponding reference characters designate like or corresponding parts throughout the several views.

Detailed Description

Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". Unless specifically stated otherwise, the term "or" means "and/or". The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same object.

As mentioned above, there are many subjective factors in the manual interpretation process, and the interpretation process is time-consuming. To solve these problems, some conventional solutions utilize a computer for automatic interpretation. In these protocols, various data processing models are set up to process the image data to identify the negative or positive and titer of cell-based antibodies. The traditional schemes improve the accuracy of the determination of the negative and positive titer to a certain extent, but have certain precision bottlenecks and defects. Besides the precision aspect, some existing systems have the problems of low interpretation efficiency and certain limitation on generalization.

The factors causing the accuracy bottleneck of the current related technology mainly include the following factors: insufficient data. The real data is often directly from clinical collection, and therefore the collection is difficult. The performance of the algorithm is bottleneck, and a single model is mostly adopted for prediction. Therefore, the performance is difficult to be improved to clinical requirements. For some cytoplasmic karyotypes, titer calculation for both cytoplasmic and nuclear karyotypes cannot be performed. Leading to inaccurate titer calculations.

To address, at least in part, one or more of the above issues and other potential issues, an example embodiment of the present disclosure proposes a scheme for determining the positivity and titer of antibodies. In this scenario, the computing device applies an indirect immunofluorescence image of the cell-based antibody to a negative-positive interpretation model to determine whether the antibody is positive. If the antibody is determined to be positive, the computing device determines a nuclear karyotype mask for the cell and a cytoplasmic karyotype mask for the cell based on the indirect immunofluorescence image. The computing device next determines a classification of the indirect immunofluorescence image based on the nuclear and cytoplasmic karyotype masks. Finally, the computing device determines the titer based on the category and the gray value of the nuclear or cytoplasmic karyotype mask. By the method, the positive and negative of the antibody and the titer of the antibody can be determined quickly and accurately, the accuracy of titer judgment is improved, and the efficiency is improved.

Fig. 1 shows a schematic diagram of a system 100 for determining positivity and titer of antibodies according to an embodiment of the present disclosure. As shown in fig. 1, system 100 includes, for example, a computing device 104.

The computing device 104 is configured to receive the indirect immunofluorescence image 102 and then process the indirect immunofluorescence image 102 to determine whether there is antibody positivity and to determine a titer 110 for the antibody if positive. Titer refers to the minimum concentration required to measure a particular epitope for recognition by an antibody, and in this disclosure is primarily an assessment of the actual titer of an antibody based on the fluorescence intensity of the picture.

Examples of computing device 104 include, but are not limited to, personal computers, server computers, hand-held or laptop devices, mobile devices (such as mobile phones, Personal Digital Assistants (PDAs), media players, and the like), multiprocessor systems, consumer electronics, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

Included in the computing device 104 is a negative-positive interpretation model 106 and a titer interpretation module 108. The negative-positive interpretation model 106 is used to determine whether the antibodies in the picture 102 are negative or positive. The negative-positive interpretation model 106 is a trained machine learning model. In some embodiments, the negative-positive interpretation model is trained on a residual neural network, such as Resnet 18. In some embodiments, the negative-positive interpretation model 106 is any suitable machine learning model that can classify images. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure.

If the antibody in the picture 102 is negative after the negative-positive interpretation model 106 is determined, the picture 102 does not need to be processed. If the antibody of panel 102 is positive, it needs to be further processed. At this point, the picture 102 is input to the titer interpretation module 108 to determine the titer corresponding to the positive antibody.

By the method, the positive and negative of the antibody and the titer of the antibody can be determined quickly and accurately, the accuracy of titer judgment is improved, and the efficiency is improved.

Fig. 1 above illustrates a schematic diagram of a system 100 in which various embodiments of the present disclosure can be implemented. A flow chart of a method 200 for determining positivity and titer of antibodies according to an embodiment of the present disclosure is described below in conjunction with fig. 2. The method 200 may be implemented by the computing device 104 of fig. 1 or any other suitable device.

At block 202, the computing device 104 applies the indirect immunofluorescence image of the cell-stromal antibody to a negative-positive interpretation model to determine whether the antibody is positive. The computing device 104 determines the positivity of the antibody using a trained negative-positive interpretation model. As shown in fig. 3, which shows images of negative and positive cells according to an embodiment of the present disclosure, the image antibody on the left side of fig. 3 is positive and the picture antibody on the right side is negative.

Furthermore, in some embodiments, pre-processing is required for the received indirect immunofluorescence image, a process of which will be described below in connection with fig. 7.

In some embodiments, the negative-positive interpretation model is trained using a residual neural network. In some embodiments, any suitable neural network or machine learning model may be employed for generation.

In some embodiments, during the training of the negative-positive interpretation model, the trained negative-positive interpretation model is determined by dividing the training sample pictures into a training data set, an evaluation data set, and a test data set. In some embodiments, the quantitative ratio between the training data set, the evaluation data set, and the test data set is 7:2: 1. In some embodiments, the quantitative ratio between the training data set, the evaluation data set, and the test data set may be any other suitable value. As shown in fig. 4, the training data set 402, the evaluation data set 406, and the testing data set 408 are used to train the negative-positive interpretation model 404, which is mainly to perform an evaluation through the evaluation data set 406 after training the negative-positive interpretation model 404 one or more times through the training data set 402, and determine whether training is needed again based on the evaluation result. If the evaluation results are not appropriate, training is performed again with the training data set 402. After the evaluation data set 406 is used to evaluate appropriateness, the test data set 408 is reused for testing. And finishing the training of the positive and negative model through the test. Otherwise, training is followed.

Returning to fig. 2, as described next, for three sets of data sets, predetermined processing may be performed to increase the amount of data or improve the detection effect. For the pre-processing of the training data, see the description of fig. 7 below.

In some embodiments, the images in the three sets of data sets are subjected to a predetermined process to increase the amount of data in the data sets, such as flipping left-to-right and flipping top-to-bottom. In some embodiments, the negative-positive interpretation model may be trained directly using the training sample pictures as a training data set.

In some embodiments, the images in the dataset are resized to accommodate the input of the negative-positive interpretation model. For example, the image data is downsampled or sampled in another suitable manner. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure.

In some embodiments, the computing device 104 needs to resize the adjusted indirect immunofluorescence image for application to the negative-positive interpretation model. If the size of the indirect immunofluorescence image is smaller than the data input by the negative-positive interpretation model at one time, no resizing is needed.

At block 204, the computing device 104 determines a nuclear karyotype mask for the cell and a cytoplasmic karyotype mask for the cell based on the indirect immunofluorescence image if the antibody is determined to be positive. As shown in fig. 5, in which a nucleus karyotype mask and a cytoplasmic karyotype mask extracted according to an embodiment of the present disclosure are shown, the upper two images in fig. 5 are a nucleus and a nucleus karyotype mask corresponding to the nucleus, and the lower two images in fig. 5 are a cytoplasm and a cytoplasmic karyotype mask corresponding to the cytoplasm. The process of obtaining the nuclear and cytoplasmic karyotype masks is described below in FIG. 8.

At block 206, the computing device 104 determines a category of the indirect immunofluorescence image based on the nuclear and cytoplasmic karyotype masks. The computing device determines a class of the image by inputting the mask data into a classification model.

In some embodiments, the computing device 104 applies the nuclear karyotype mask and the cytoplasmic karyotype mask to the classification model to determine the classification of the indirect immunofluorescence image. In one example, the classification model is trained on a residual neural network. In another example, the classification model is trained on other machine learning models.

At block 208, the computing device 104 determines a titer based on the class and a grayscale value of a portion of the image of the indirect immunofluorescence image corresponding to the nuclear or cytoplasmic karyotype mask.

In this process, a mapping of titer to gray value is needed. The mapping is determined based on statistical data of titers for which resistance is observed. Within its range of values, may be divided into a number of levels, each level having a corresponding range of grey values. The foregoing is by way of example only, and is not intended as a limitation upon the present disclosure. The person skilled in the art can set the corresponding relationship between the titer and the gray value according to the needs.

In some embodiments, if the category is determined to be a cell karyotype, the computing device 104 determines a first range of grayscale values for a plurality of pixels in the indirect immunofluorescence image corresponding to the cell nuclear karyotype marinade. If the category is determined to be cytoplasmic, the computing device 104 determines a second range of gray scale values for a plurality of pixels in the indirect immunofluorescence image corresponding to the cytoplasmic-karyotype mask. As shown in fig. 6, which shows a schematic diagram for grayscale value according to an embodiment of the present disclosure. For example, for a pixel in the mask, the pixel value of the pixel in the indirect immunofluorescence image corresponding thereto is determined. The computing device 104 also obtains a mapping of gray value ranges to titers. Then, based on the mapping, a titer corresponding to the first gray value range or the second gray value range is determined.

The process for determining positivity and titer is described above in connection with FIGS. 2-6. A flow chart of a method 700 for pre-processing image data is described below in conjunction with fig. 7.

At block 702, the computing device 104 acquires an indirect immunofluorescence image 102 of the cell-stromal antibody. Next, at block 704, the computing device 104 adjusts the pixel values of the target pixel using a set of pixel values of pixels surrounding the target pixel in the indirect immunofluorescence image to generate an adjusted indirect immunofluorescence image.

In some embodiments, for each pixel in the image, the size of the pixel values of the pixels surrounding the pixel is determined. For example, a sliding window of nine pixels is determined for each pixel, the window being three rows and three columns with the pixel in the center. The pixel values of the other surrounding eight pixels are then determined. The pixel values of the surrounding pixels are then sorted to determine a minimum pixel value and a maximum pixel value. If the center pixel value is less than the minimum pixel value, the center pixel value is determined to be the minimum pixel value. If the center pixel value is greater than the minimum value but less than the maximum value, the center pixel value is set to the maximum value. In some examples, a sliding window comprising other suitable numbers of pixels may be employed. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure.

At block 706, the computing device 104 applies the adjusted indirect immunofluorescence image to a negative-positive interpretation model to determine whether the antibody is positive. In this way, the brightness of pixels that appear positive can be significantly increased.

In some embodiments, the above-described preprocessing is performed on the images in the three datasets used to train the negative-positive interpretation model to improve the training dataset.

While fig. 7 above describes a flow diagram of a method 700 for pre-processing image data, a flow diagram of a method 800 for determining a nuclear and cytoplasmic karyotype mask according to an embodiment of the disclosure is described below in conjunction with fig. 8.

At block 802, the computing device 104 segments the indirect immunofluorescence image with a first grayscale value in a range of grayscale values corresponding to the indirect immunofluorescence image to obtain a first mask indicating pixels in the indirect immunofluorescence image having grayscale values greater than the first grayscale value. In one example, the first gray value may be an intermediate gray value between the maximum gray value and the minimum gray value in the indirect immunofluorescence image. In another example, the first gray value may be an optional one of a maximum gray value and a minimum gray value in the indirect immunofluorescence image. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure. In this way, the initial nuclear karyotype mask can be determined.

At block 804, the computing device 104 segments the indirect immunofluorescence image with a second gray value of the full gray values to obtain a second mask indicating pixels in the indirect immunofluorescence image having gray values greater than the second gray value. In one example, the second gray value is a middle gray value of all gray values. In another example, the second gray value is a suitable gray value selected from all gray values. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure. In the above manner, a mask including a nucleus and a cytoplasm that show a positive can be determined.

At block 806, the computing device 104 determines a nuclear karyotype mask and a cytoplasmic karyotype mask using the determined first mask and second mask. In some embodiments, the computing device 104 and the first mask and the second mask to determine the nuclear karyotype mask. Next, the computing device xors the first mask and the second mask to determine a cytoplasmic karyotype mask. In some embodiments, the computing device 104 ANDs the first mask and the second mask, and then negates to obtain the nuclear karyotype mask and the cytoplasmic karyotype mask. The above examples are intended to be illustrative of the present disclosure, and are not intended to be limiting of the present disclosure.

FIG. 9 schematically illustrates a block diagram of an electronic device 900 suitable for use in implementing embodiments of the present disclosure. The electronic device 900 may be used to implement the computing device 104 of claim 1. Device 900 may be a component for implementing the method 200 of fig. 2, the method 700 of fig. 7, and the method 800 of fig. 8. As shown in fig. 9, device 900 includes a Central Processing Unit (CPU)901 that can perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)902 or loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM903, various programs and data required for the operation of the device 900 can also be stored. The CPU 901, ROM 902, and RAM903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.

A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, a processing unit 901 performs the respective methods and processes described above, for example performing the

methods

200, 700 and 800. For example, in some embodiments,

methods

200, 700, and 800 may be implemented as a computer software program stored on a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When loaded into RAM903 and executed by CPU 901, may perform one or more of the operations of

methods

200, 700, and 800 described above. Alternatively, in other embodiments, CPU 901 may be configured in any other suitable manner (e.g., by way of firmware) to perform one or more acts of

methods

200, 700, and 800.

It should be further appreciated that the present disclosure may be embodied as methods, apparatus, systems, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for carrying out various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor in a voice interaction device, a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

The above are only alternative embodiments of the present disclosure and are not intended to limit the present disclosure, which may be modified and varied by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for determining the positivity or positivity and titer of an antibody comprising:

applying an indirect immunofluorescence image of a cell-based antibody to a negative-positive interpretation model to determine whether the antibody is positive;

determining a nuclear karyotype mask for the cell and a cytoplasmic karyotype mask for the cell based on the indirect immunofluorescence image if the antibody is determined to be positive;

determining a class of indirect immunofluorescence images based on the nuclear karyotype mask and the cytoplasmic karyotype mask; and

determining the titer based on the class and a gray value of a partial image of the indirect immunofluorescence image corresponding to the nuclear karyotype mask or the cytoplasmic karyotype mask.

2. The method of claim 1, wherein applying the indirect immunofluorescence image to a negative-positive interpretation model comprises:

obtaining an indirect immunofluorescence image of the antibody with the cells as the matrix;

adjusting pixel values of a target pixel in the indirect immunofluorescence image using a set of pixel values of pixels surrounding the target pixel to generate an adjusted indirect immunofluorescence image; and applying the adjusted indirect immunofluorescence image to the negative-positive interpretation model to determine whether the antibody is positive.

3. The method of claim 2, wherein applying the adjusted indirect immunofluorescence image to a negative-positive interpretation model comprises:

resizing the adjusted indirect immunofluorescence image for application to the negative-positive interpretation model.

4. The method of claim 1, wherein determining the nuclear karyotype mask and the cytoplasmic karyotype mask comprises:

segmenting the indirect immunofluorescence image using a first gray value in a range of gray values corresponding to the indirect immunofluorescence image to obtain a first mask indicating pixels in the indirect immunofluorescence image having gray values greater than the first gray value;

segmenting the indirect immunofluorescence image with a second gray value of all gray values to obtain a second mask, the second mask indicating pixels in the indirect immunofluorescence image having gray values greater than the second gray value; and

determining the nuclear karyotype mask and the cytoplasmic karyotype mask based on the first mask and the second mask.

5. The method of claim 4, wherein determining the nuclear karyotype mask and the cytoplasmic karyotype mask based on the first mask and the second mask comprises:

performing an AND operation on the first mask and the second mask to determine the nuclear karyotype mask; and

exclusive-OR' ing the first mask and the second mask to determine the cytoplasmic karyotype mask.

6. The method of claim 1, wherein determining the category comprises:

applying the nuclear karyotype mask and the cytoplasmic karyotype mask to a classification model to determine the class of the indirect immunofluorescence image, the classification model being trained on a residual neural network.

7. The method of claim 1, wherein determining the titer comprises:

determining a first gray value range for a plurality of pixels in the indirect immunofluorescence image corresponding to the nuclear karyotype, if the category is determined to be a cell karyotype;

determining a second gray value range for a plurality of pixels in the indirect immunofluorescence image corresponding to the cytoplasmic-karyotype mask if the class is determined to be cytoplasmic;

acquiring a mapping relation between a gray value range and titer; and

determining a titer corresponding to the first range of grayscale values or the second range of grayscale values based on the mapping.

8. The method of claim 1, wherein the negative-positive interpretation model is trained using a residual neural network, and the training process utilizes a training data set, a test data set, and an evaluation data set.

9. A computing device, comprising:

at least one processing unit;

at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit causing the computing device to perform the method of any of claims 1-8.

10. A computer readable storage medium having stored thereon machine executable instructions which, when executed, cause a machine to perform the method of any one of claims 1 to 8.