Artificial Intelligence-Based Protein Chip Detection and Analysis Method and System

Abstract

The present disclosure relates to a method and system for detecting and analyzing a protein chip based on artificial intelligence. The method includes: obtaining a scanned image scanned by a protein chip scanner for a target protein chip, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by processing a biological sample to be detected and labeling the protein with a fluorescent dye; inputting the scanned image into a pre-trained detection model to obtain protein biomarker detection data; where the detection model is obtained by training a machine learning model based on a plurality of sample scanned images, and the plurality of sample scanned images include scanned images of a plurality of historical protein chips obtained by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease; determining a lesion result based on the protein biomarker detection data.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of medical intelligent testing, and in particular, to a method and system for protein chip detection and analysis based on artificial intelligence. Background Art

[0002] Currently, as part of medical testing science, the protein chip detection method is a high-throughput detection means that can simultaneously analyze the interactions of multiple proteins on a protein chip. Therefore, using the protein chip technology, it is possible to detect the change results of the expression levels of at least one protein caused by a certain disease such as cancer, which helps to assist in diagnosing whether a patient has a certain disease such as cancer.

[0003] In the related art, when using the protein chip technology for detection, a scanning instrument is required to scan the protein chip loaded with the sample. The rays emitted by the scanning instrument react with the fluorescent agent in the protein sample to form a scanning image, and then the supporting analysis software is used to further analyze and process the scanning image to obtain corresponding multiple protein numerical data based on the analysis of the scanning image. Finally, based on the multiple protein numerical data, it is evaluated whether there is a disease such as cancer and the severity of the disease, etc. However, the inventor has found through research that both the scanning instrument and the supporting software are existing products purchased and their settings cannot be changed. The accuracy of the protein numerical data obtained by the software analysis method based on the scanning image is still not high, resulting in easy occurrence of disease detection errors and affecting the doctor's accurate judgment of the condition. Summary of the Invention

[0004] To solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide a method and system for protein chip detection and analysis based on artificial intelligence.

[0005] In a first aspect, embodiments of the present disclosure provide a method for protein chip detection and analysis based on artificial intelligence, including:

[0006] Obtaining a scanning image obtained by scanning a target protein chip with a protein chip scanner, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by treating a biological sample to be detected and labeling the protein with a fluorescent dye;

[0007] Inputting the scanning image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on multiple sample scanning images, and the multiple sample scanning images include the scanning images of multiple historical protein chips obtained by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease;

[0008] Determine the lesion result based on the protein biomarker detection data.

[0009] In one embodiment, the machine learning model at least includes a target convolutional neural network model, and the training process of the detection model includes:

[0010] Input the sample scan image and the corresponding label data into the target convolutional neural network model for iterative training until the loss value of the loss function is less than or equal to the preset threshold to end the training to obtain the detection model; wherein, the target convolutional neural network model includes a first network layer and a second network layer, the first network layer is used to extract the first feature information of the sample scan image, the second network layer is used to extract the second feature information of the sample scan image, and the second feature information is different from the first feature information; the loss function includes a first loss function and a second loss function, the first loss function characterizes the difference between the output data of the target convolutional neural network model and the label data, and the second loss function characterizes the difference between the output of the second network layer and the output of the first network layer.

[0011] In one embodiment, the loss value of the loss function is determined based on the first loss value of the first loss function and the second loss value of the second loss function; wherein, the second loss value is determined by the output of the second network layer and the output of the first network layer, and the influence weight of the output of the first network layer is greater than the influence weight of the output of the second network layer.

[0012] In one embodiment, the first feature information includes color features and texture features, and the second feature information includes shape features and spatial relationship features.

[0013] In one embodiment, the training process of the detection model further includes:

[0014] Preprocess the multiple sample scan images respectively, and the preprocessing at least includes image denoising and image background segmentation;

[0015] Iteratively train the target convolutional neural network model based on the preprocessed multiple sample scan images.

[0016] In one embodiment, the target protein chip includes a microplate protein chip or a microarray protein chip.

[0017] In one embodiment, the biological sample to be detected includes a blood sample, the target protein chip is used to detect tumors, and the protein biomarker detection data includes tumor-related protein biomarker detection data.

[0018] Second aspect, embodiments of the present disclosure provide an artificial intelligence-based protein chip detection and analysis system, including:

[0019] An acquisition module, configured to acquire a scanned image obtained by a protein chip scanner scanning a target protein chip, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by processing a biological sample to be detected and labeling the protein with a fluorescent dye;

[0020] A detection module, configured to input the scanned image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on a plurality of sample scanned images, and the plurality of sample scanned images include scanned images of a plurality of historical protein chips acquired by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease;

[0021] A determination module, configured to determine a lesion result based on the protein biomarker detection data.

[0022] Third aspect, embodiments of the present disclosure provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the artificial intelligence-based protein chip detection and analysis method described in any of the above embodiments is implemented.

[0023] Fourth aspect, embodiments of the present disclosure provide an electronic device, including:

[0024] A processor; and

[0025] A memory, configured to store a computer program;

[0026] wherein, the processor is configured to execute the artificial intelligence-based protein chip detection and analysis method described in any of the above embodiments by executing the computer program.

[0027] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art:

[0028] The protein chip detection and analysis method and system based on artificial intelligence provided by the embodiments of the present disclosure obtain a scanned image obtained by scanning a target protein chip with a protein chip scanner. The target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by treating a biological sample to be detected and labeling the protein with a fluorescent dye. The scanned image is input into a pre-trained detection model to obtain protein biomarker detection data. The detection model is obtained by training a machine learning model based on multiple sample scanned images. The multiple sample scanned images include the scanned images of multiple historical protein chips obtained by the protein chip scanner. The historical protein chips and the target protein chip are protein chips for detecting the same disease. The lesion result is determined based on the protein biomarker detection data. In this way, compared with software analysis of the scanned image, the solution of this embodiment can obtain more accurate protein biomarker detection data from the scanned image of the protein chip through a detection model pre-trained by artificial intelligence machine learning, that is, improve the accuracy of the analyzed protein biomarker detection data. Therefore, based on the protein biomarker detection data, the disease result can be accurately determined, avoiding disease detection errors, and further improving the doctor's accurate judgment of the condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a flowchart of the protein chip detection and analysis method based on artificial intelligence according to the embodiments of the present disclosure;

[0032] Figure 2 It is an image after gray-scale processing of the scanned image of the present disclosure;

[0033] Figure 3 It is a schematic diagram of the architecture of the target convolutional neural network model according to the embodiments of the present disclosure;

[0034] Figure 4 It is a schematic diagram of the protein chip detection and analysis system based on artificial intelligence according to the embodiments of the present disclosure;

[0035] Figure 5 It is a schematic diagram of the electronic device according to the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In order to more clearly understand the above-mentioned objects, features, and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0037] In the following description, many specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all of the embodiments.

[0038] It should be understood that, hereinafter, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may represent: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B may be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c may be single or multiple.

[0039] Figure 1 It is a flowchart of a protein chip detection and analysis method based on artificial intelligence according to an embodiment of the present disclosure. This method can be executed by a computing device such as a computer, and specifically may include the following steps:

[0040] Step S101: Obtain a scanned image obtained by scanning a target protein chip with a protein chip scanner. The target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by treating a biological sample to be detected and labeling the protein with a fluorescent dye.

[0041] Exemplarily, in one embodiment, the target protein chip may include, but is not limited to, a microplate protein chip or a microarray protein chip. In one embodiment, the biological sample to be detected may include, but is not limited to, a blood sample. The target protein chip can be used to detect tumors, but is not limited thereto, and it can vary according to different detected diseases such as tumors. For example, detection antibodies related to disease detection such as tumor detection can be preset inside the protein chip. Proteins such as proteins related to tumor detection can be extracted from the blood sample, and then the proteins are labeled to obtain a protein solution. When labeling, fluorescent dyes can be used to label the proteins. Since the proteins related to different disease detections are different, different fluorescent dyes can be used. These can be understood with reference to the prior art and will not be elaborated here. The protein solution is loaded and injected into several detection holes on the protein chip. After that, the labeled proteins will bind to the detection antibodies inside the protein chip. Finally, the protein chip can be placed in a protein chip scanner, and the scanning rays react with the fluorescent dyes in the protein solution to form a scanning image and can be stored. Among them, the protein chip scanner can use a relevant scanner of the PerkinElmer series. Here, parameters such as the scanning pixel size and scanning laser power of the scanner can also be set and then scanning can be started. In this embodiment, the scanning image corresponding to the target protein chip can be obtained from the protein chip scanner.

[0042] Step S102: Input the scanning image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on multiple sample scanning images; the multiple sample scanning images include the scanning images of multiple historical protein chips obtained by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease.

[0043] Exemplarily, the detection model can be pre-trained based on a machine learning model such as a convolutional neural network model. The training sample data can be the scanning images of multiple historical protein chips of the same disease such as tumors obtained by the protein chip scanner. Specifically, the scanning images and the corresponding label data in the training sample data can be input into the convolutional neural network model for iterative training until the loss value of the loss function of the convolutional neural network model meets the threshold condition and the training ends, and then the detection model can be obtained. The label data can be the protein biomarker detection data corresponding to the scanning images in the training sample data, such as tumor-related protein biomarker detection data.

[0044] After the training is completed, the scanned image obtained during actual application can be input into the trained detection model. The detection model outputs protein biomarker detection data. The larger the protein biomarker detection data, the higher the expression level of the corresponding protein in the biological sample to be detected, that is, the more abnormal it is, and vice versa. In healthy individuals, it is relatively stable. Therefore, based on this, it is possible to determine whether there is a disease and the degree of the disease.

[0045] Step S103: Determine the lesion result based on the protein biomarker detection data.

[0046] Exemplarily, if the protein biomarker detection data is different, the lesion result of the disease, such as the severity, is different. Based on the corresponding relationship between different severities of clinical diagnoses of, for example, tumors and the corresponding protein biomarker detection data set in advance, the lesion result, such as the current tumor severity, can be determined.

[0047] Compared with software for analyzing scanned images, the above solution of the embodiments of the present disclosure can obtain protein biomarker detection data more accurately from the scanned image of the protein chip through a detection model trained by artificial intelligence through pre-machine learning. That is, the accuracy of analyzing the protein biomarker detection data is improved. Therefore, based on the protein biomarker detection data, the disease result can be accurately determined, avoiding disease detection errors, and thus improving the doctor's accurate judgment of the condition.

[0048] To further improve the accuracy of the protein biomarker detection data analyzed based on the scanned image, in one embodiment, the machine learning model at least includes a target convolutional neural network model. The training process of the detection model may include: inputting the sample scanned image and the corresponding label data, such as the protein biomarker detection data corresponding to the sample scanned image, into the target convolutional neural network model for iterative training until the loss value of the loss function is less than or equal to a preset threshold to end the training to obtain the detection model; wherein, the target convolutional neural network model includes a first network layer and a second network layer. The first network layer is used to extract the first feature information of the sample scanned image, and the second network layer is used to extract the second feature information of the sample scanned image, and the second feature information is different from the first feature information; the loss function includes a first loss function and a second loss function. The first loss function represents the difference between the output data of the target convolutional neural network model and the label data, and the second loss function represents the difference between the output of the second network layer and the output of the first network layer.

[0049] Exemplarily, refer to Figure 2As shown in the figure, the target convolutional neural network model may include a first network layer, a second network layer, a pooling layer, and a fully connected layer FC. That is, two parallel network layers are set up to change the architecture of the traditional convolutional neural network model, such as adding a second network layer. Both the first network layer and the second network layer are convolutional layers and can include multiple convolutional kernels. During the model training process, the first network layer extracts the first feature information of the sample scanned image, and the second network layer extracts the second feature information of the sample scanned image, and the second feature information is different from the first feature information. At the same time, a second loss function is added, which characterizes the difference between the output of the second network layer and the output of the first network layer. The first loss function is a constraint on the overall model, and the second loss function is a constraint on the two network layers inside the model. Moreover, as a part of the loss function of the target convolutional neural network model, the second loss function will also affect the loss value of the loss function of the target convolutional neural network model. In this way, by extracting different features through the first network layer and the second network layer and jointly superimposing the constraints of the first loss function and the second loss function for training, more rich and detailed information in the image can be mined for constrained training. Furthermore, the detection model obtained at the end of the training can output more accurate protein biomarker detection data, so that the disease result can be determined more accurately, the disease detection error can be avoided, and further the doctor's accurate judgment of the condition can be improved.

[0050] Based on the above embodiments, in one embodiment, the first feature information may include color features and texture features, and the second feature information may include shape features and spatial relationship features. In the application scenario of this embodiment, referring to Figure 3 As shown in the figure, based on the characteristics of the scanned image of the protein chip, the protein site, that is, the circular area, is used as the detection area, which usually contains obvious color features and texture features, different from the features of the area outside the detection area, and is more conducive to distinguishing and identifying. Therefore, during model training, the first network layer extracts color features and texture features, while the second network layer extracts shape features and spatial relationship features. At the same time, based on the settings of the above first loss function and second loss function, the constraints are jointly superimposed for training, and the rich and detailed information related to the detection area in the image can be accurately mined for constrained training. Furthermore, the detection model obtained at the end of the training can output more accurate protein biomarker detection data, so that the disease result can be determined more accurately, the disease detection error can be avoided, and further the doctor's accurate judgment of the condition can be improved.

[0051] Based on the above embodiments, in one embodiment, the loss value of the loss function is determined based on the first loss value of the first loss function and the second loss value of the second loss function, for example, determined by their sum. Wherein, the second loss value is determined by the output of the second network layer and the output of the first network layer, for example, determined by weighted summation based on the outputs of the two network layers and their corresponding weights, and the influence weight of the output of the first network layer is greater than the influence weight of the output of the second network layer.

[0052] Exemplarily, as described above, the protein site, i.e., the circular region, is used as the detection region, which usually contains obvious color features and texture features, different from the features of the regions outside the detection region, and is more conducive to differentiation and recognition. During model training, the first network layer extracts color features and texture features, and the second network layer extracts shape features and spatial relationship features. The second loss value of the second loss function is determined by the output of the second network layer and the output of the first network layer, that is, it is related to the second network layer and the first network layer. Therefore, the influence weight of the output of the first network layer is set to be greater than the influence weight of the output of the second network layer, that is, the color features and texture features extracted by the first network layer have a greater influence weight on the second loss value than the features extracted by the second network layer. Thus, based on the above settings of the first loss function and the second loss function, they are jointly superimposed and constrained for training, which can more accurately mine rich and detailed information related to the detection region in the image for constrained training. Furthermore, the detection model obtained after the training is completed can output more accurate protein biomarker detection data, thereby more accurately determining the disease result, avoiding disease detection errors, and further improving the doctor's accurate judgment of the condition.

[0053] Based on any of the above embodiments, in one embodiment, the training process of the detection model may further include: preprocessing the multiple sample scanned images, and the preprocessing at least includes image denoising and image background segmentation; iteratively training the target convolutional neural network model based on the preprocessed multiple sample scanned images.

[0054] That is to say, before training the target convolutional neural network model, the training data, that is, the multiple sample scanned images, are first preprocessed, such as image denoising and image background segmentation. Image denoising can be performed based on filtering methods such as mean filtering or median filtering, etc., and image background segmentation can be achieved based on RGB values or grayscale values, etc., to remove the background region in the image. In this way, the influence of the background and noise in the preprocessed sample scanned images is reduced, highlighting the features of the detection target. Based on this, the target convolutional neural network model is iteratively trained. Thus, the detection model obtained by training can output more accurate protein biomarker detection data, thereby more accurately determining the disease result, avoiding disease detection errors, and further improving the doctor's accurate judgment of the condition.

[0055] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. Additionally, it is also easy to understand that these steps may be executed synchronously or asynchronously, for example, in multiple modules / processes / threads.

[0056] As Figure 4 shown, an embodiment of the present disclosure shows a protein chip detection and analysis system based on artificial intelligence, including:

[0057] An acquisition module 401, configured to acquire a scanned image obtained by a protein chip scanner scanning a target protein chip, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by processing a biological sample to be detected and labeling the protein with a fluorescent dye;

[0058] A detection module 402, configured to input the scanned image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on multiple sample scanned images, and the multiple sample scanned images include scanned images of multiple historical protein chips obtained by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease;

[0059] A determination module 403, configured to determine a lesion result based on the protein biomarker detection data.

[0060] In one embodiment, the machine learning model at least includes a target convolutional neural network model, and the training process of the detection model includes: inputting the sample scanned image and the corresponding label data into the target convolutional neural network model for iterative training until the loss value of the loss function is less than or equal to a preset threshold to end the training to obtain the detection model; wherein, the target convolutional neural network model includes a first network layer and a second network layer, the first network layer is used to extract first feature information of the sample scanned image, the second network layer is used to extract second feature information of the sample scanned image, and the second feature information is different from the first feature information; the loss function includes a first loss function and a second loss function, the first loss function represents the difference between the output data of the target convolutional neural network model and the label data, and the second loss function represents the difference between the output of the second network layer and the output of the first network layer.

[0061] In one embodiment, the loss value of the loss function is determined based on the first loss value of the first loss function and the second loss value of the second loss function; wherein, the second loss value is determined by the output of the second network layer and the output of the first network layer, and the influence weight of the output of the first network layer is greater than the influence weight of the output of the second network layer.

[0062] In one embodiment, the first feature information includes color features and texture features, and the second feature information includes shape features and spatial relationship features.

[0063] In one embodiment, the training process of the detection model further includes: preprocessing the multiple sample scanned images, and the preprocessing at least includes image denoising and image background segmentation; iteratively training the target convolutional neural network model based on the preprocessed multiple sample scanned images.

[0064] In one embodiment, the target protein chip includes a microplate protein chip or a microarray protein chip.

[0065] In one embodiment, the biological sample to be detected includes a blood sample, the target protein chip is used to detect tumors, and the protein biomarker detection data includes tumor-related protein biomarker detection data.

[0066] Regarding the system in the above embodiments, the specific manners in which each module performs operations and the corresponding technical effects have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0067] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units. The components shown as modules or units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present disclosure. Those of ordinary skill in the art can understand and implement it without creative effort.

[0068] The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for protein chip detection and analysis based on artificial intelligence described in any one of the above embodiments.

[0069] Exemplarily, the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0070] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0071] Embodiments of the present disclosure further provide an electronic device, including a processor and a memory, where the memory is used to store a computer program. Among them, the processor is configured to execute the protein chip detection and analysis method based on artificial intelligence in any one of the above embodiments by executing the computer program.

[0072] Next, refer to Figure 5 to describe the electronic device 600 according to this embodiment of the present invention. Figure 5 The shown electronic device 600 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0073] As Figure 5 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0074] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the method embodiment part of this specification. For example, the processing unit 610 may execute the steps of the method as Figure 1 shown.

[0075] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0076] The storage unit 620 may also include a program / utilities 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0077] The bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0078] The electronic device 600 may also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or may communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface 650. Moreover, the electronic device 600 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0079] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the steps of the above-described embodiments of the artificial intelligence-based protein chip detection and analysis method according to the embodiments of the present disclosure.

[0080] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0081] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. An artificial intelligence-based protein chip detection and analysis method, characterized in that, Including: Obtain a scanned image obtained by a protein chip scanner scanning a target protein chip, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by treating a biological sample to be detected and labeling the protein with a fluorescent dye; Input the scanned image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on multiple sample scanned images, and the multiple sample scanned images include scanned images of multiple historical protein chips obtained by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease; Determine a lesion result based on the protein biomarker detection data; Wherein, the machine learning model at least includes a target convolutional neural network model, and the training process of the detection model includes: Input the sample scanned image and the corresponding label data into the target convolutional neural network model for iterative training until the loss value of the loss function is less than or equal to a preset threshold to end the training to obtain a detection model; wherein, the target convolutional neural network model includes a first network layer and a second network layer, the first network layer is used to extract the first feature information of the sample scanned image, the second network layer is used to extract the second feature information of the sample scanned image, and the second feature information is different from the first feature information; the loss function includes a first loss function and a second loss function, the first loss function characterizes the difference between the output data of the target convolutional neural network model and the label data, and the second loss function characterizes the difference between the output of the second network layer and the output of the first network layer.

2. The method according to claim 1, wherein The loss value of the loss function is determined based on the first loss value of the first loss function and the second loss value of the second loss function; wherein, the second loss value is determined by the output of the second network layer and the output of the first network layer, and the influence weight of the output of the first network layer is greater than the influence weight of the output of the second network layer.

3. The method according to claim 2, wherein The first feature information includes color features and texture features, and the second feature information includes shape features and spatial relationship features.

4. The method according to any one of claims 1 to 3, characterized in that, The training process of the detection model further includes: Perform preprocessing on the multiple sample scanned images respectively, and the preprocessing at least includes image denoising and image background segmentation; Perform iterative training on the target convolutional neural network model based on the preprocessed multiple sample scanned images.

5. The method according to claim 4, wherein The target protein chip includes a microplate protein chip or a microarray protein chip.

6. The method according to claim 4, wherein The biological sample to be detected includes a blood sample, the target protein chip is used to detect tumors, and the protein biomarker detection data includes tumor-related protein biomarker detection data.

7. An artificial intelligence-based protein chip detection and analysis system, characterized in that, Including: An acquisition module, configured to obtain a scanned image obtained by a protein chip scanner scanning a target protein chip, where the target protein chip is a protein chip loaded with a protein solution, and the protein solution is obtained by treating a biological sample to be detected and labeling the protein with a fluorescent dye; A detection module, configured to input the scanned image into a pre-trained detection model to obtain protein biomarker detection data; wherein, the detection model is obtained by training a machine learning model based on a plurality of sample scanned images, and the plurality of sample scanned images include scanned images of a plurality of historical protein chips acquired by the protein chip scanner, and the historical protein chips and the target protein chip are protein chips for detecting the same disease; A determination module, configured to determine a lesion result based on the protein biomarker detection data; Wherein, the machine learning model at least includes a target convolutional neural network model, and the training process of the detection model includes: Inputting the sample scanned image and the corresponding label data into the target convolutional neural network model for iterative training until the loss value of the loss function is less than or equal to a preset threshold to end the training to obtain the detection model; wherein, the target convolutional neural network model includes a first network layer and a second network layer, the first network layer is configured to extract first feature information of the sample scanned image, the second network layer is configured to extract second feature information of the sample scanned image, and the second feature information is different from the first feature information; the loss function includes a first loss function and a second loss function, the first loss function represents the difference between the output data of the target convolutional neural network model and the label data, and the second loss function represents the difference between the output of the second network layer and the output of the first network layer.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the artificial intelligence-based protein chip detection and analysis method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, Comprising: A processor; And A memory, configured to store a computer program; Wherein, the processor is configured to execute the artificial intelligence-based protein chip detection and analysis method according to any one of claims 1 to 6 by executing the computer program.

Images