Biological band image analysis method and related products

Abstract

The present disclosure provides a biological band image analysis method and related products, wherein the biological band image is input into a biological band image analysis model, and band position information is output, wherein the band position information includes the position information of the biological band and the position information of the marker band; based on the position information of the marker band and its corresponding molecular weight, the molecular weight corresponding to the position information of the biological band is calculated. In this way, by adopting a biological band image analysis model constructed by a deep learning framework, automatic learning and accurate recognition of features in the biological band image are achieved, thereby significantly improving the accuracy and automation of the analysis. Compared with traditional methods, the present disclosure can effectively deal with the interference caused by complex background and noise, and no manual intervention is required during the entire analysis process, which significantly enhances the convenience of operation and ensures the consistency of results.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of image analysis, and in particular to a biological band image analysis method, device, electronic device, storage medium, and computer program product. Background Art

[0002] The current work of biological band image analysis mainly relies on traditional image processing techniques, including edge detection, threshold segmentation, and region recognition. Although these technologies perform well in some application scenarios, they are often difficult to achieve accurate analysis when faced with complex or low-contrast biological band images, and are easily affected by noise and background interference. In addition, these methods usually require manual setting of relevant parameters, which to some extent affects the repeatability and automation level of the analysis results. Summary of the invention

[0003] The embodiments of the present disclosure provide a biological band image analysis method, device, electronic device and storage medium.

[0004] In a first aspect, an embodiment of the present disclosure provides a biological band image analysis method, the method comprising:

[0005] Inputting the biological strip image into the biological strip image analysis model, and outputting strip position information, wherein the strip position information includes the position information of the biological strip and the position information of the marker strip;

[0006] The molecular weight corresponding to the position information of the biological band is calculated based on the position information of the marker band and its corresponding molecular weight.

[0007] In some optional implementations, the above-mentioned location information includes starting point location information and end point location information.

[0008] In some optional embodiments, the above-mentioned calculating the molecular weight corresponding to the position information of the above-mentioned biological band according to the position information of the above-mentioned marker band and the molecular weight corresponding thereto comprises:

[0009] According to the position information of the above marker bands and their corresponding molecular weights, the following band molecular weight calculation equation is fitted:

[0010] L = f(P);

[0011] Among them, L is the molecular weight corresponding to the position information of the biological band, f is the fitting function, and P is the position information of the biological band;

[0012] Substitute the position information of the biological band into the molecular weight calculation equation of the band to obtain the molecular weight corresponding to the position information of the biological band.

[0013] In some optional embodiments, the above-mentioned biological band image analysis model is trained by the following model training operations:

[0014] Obtaining a set of training biological strip images with strip end positions marked;

[0015] Input each training biological strip image into the initial Mask R-CNN model in turn, and output the strip end position identified by the model;

[0016] Calculate the loss function value between the marked strip end position and the strip end position identified by the model;

[0017] Based on the above loss function value, the above initial Mask R-CNN model is iteratively optimized and trained to finally obtain a trained biological strip image analysis model.

[0018] In some optional implementations, the above method further includes:

[0019] Obtaining expected PCR product information, wherein the expected PCR product information includes theoretical molecular weights of multiple bands;

[0020] According to the position information of each biological band output by the biological band image analysis model, the position information of each biological band is matched with the bands in the expected PCR product information one by one;

[0021] In response to the molecular weight corresponding to the position information of any biological band being the same as the theoretical molecular weight of the corresponding band in the expected PCR product information, the PCR verification result of the molecular weight corresponding to the position information of the biological band is recorded as correct;

[0022] In response to the molecular weight corresponding to the position information of any biological band being different from the theoretical molecular weight of the corresponding band in the above-mentioned expected PCR product information, the PCR verification result of the molecular weight corresponding to the position information of the biological band is recorded as incorrect.

[0023] In some optional implementations, the above method further includes:

[0024] Based on the molecular weight corresponding to the position information of the biological bands and the PCR verification results, a biological band image analysis report is generated.

[0025] In a second aspect, an embodiment of the present disclosure provides a biological band image analysis device, the device comprising:

[0026] A model recognition module, used for inputting the biological strip image into the biological strip image analysis model, and outputting strip position information, wherein the strip position information includes the position information of the biological strip and the position information of the marker strip;

[0027] The molecular weight calculation module is used to calculate the molecular weight corresponding to the position information of the biological band according to the position information of the marker band and its corresponding molecular weight.

[0028] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0029] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by one or more processors, implements the method described in any implementation manner in the first aspect.

[0030] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0031] In order to accurately and efficiently analyze biological band images, the embodiments of the present disclosure provide a biological band image analysis method, device, electronic device, storage medium and computer program product, which first input the biological band image into a biological band image analysis model, output band position information, and the above-mentioned band position information includes the position information of the biological band and the position information of the marker band; then calculate the molecular weight corresponding to the position information of the above-mentioned biological band based on the position information of the above-mentioned marker band and its corresponding molecular weight.

[0032] In this way, by adopting the biological strip image analysis model constructed by the deep learning framework, the automatic learning and accurate recognition of the features in the biological strip image are realized, thereby significantly improving the accuracy and automation of the analysis. Compared with the traditional method, the present disclosure can effectively deal with the interference caused by complex background and noise, and no manual intervention is required during the entire analysis process, which significantly enhances the convenience of operation and ensures the consistency of results. In addition, the present disclosure also has the ability to flexibly adjust the processing strategy according to the biological strip image, further enhancing the flexibility and accuracy of the analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects and advantages of the present disclosure will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating specific embodiments and are not to be considered as limiting the present disclosure. In the drawings:

[0034] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0035] Figure 2 is a flow chart of an embodiment of a biological band image analysis method according to the present disclosure;

[0036] Figure 3 is a flow chart of an embodiment of a model training operation training according to the present disclosure;

[0037] Figure 4 is a schematic structural diagram of an embodiment of a biological strip image analysis device according to the present disclosure;

[0038] Figure 5 It is a structural diagram of a computer system of an electronic device suitable for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the biological strip image analysis method, apparatus, electronic device, and storage medium of the present disclosure may be applied.

[0042] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0043] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as image processing applications, voice recognition applications, short video social applications, audio and video conferencing applications, video live broadcast applications, document editing applications, input method applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0044] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the terminal devices listed above. It can be implemented as multiple software or software modules (for example, to provide image processing services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0045] In some cases, the biological strip image analysis method provided by the present disclosure may be executed by the terminal devices 101, 102, 103, and accordingly, the biological strip image analysis apparatus may be disposed in the terminal devices 101, 102, 103. In this case, the system architecture 100 may not include the server 105.

[0046] In some cases, the biological band image analysis method provided by the present disclosure can be jointly performed by the terminal devices 101, 102, 103 and the server 105. For example, the step of "calculating the molecular weight corresponding to the position information of the above-mentioned biological band according to the position information of the above-mentioned marker band and its corresponding molecular weight" can be performed by the terminal devices 101, 102, 103, and the steps of "inputting the biological band image into the biological band image analysis model and outputting the band position information" can be performed by the server 105. The present disclosure does not limit this. Accordingly, the biological band image analysis device can also be respectively set in the terminal devices 101, 102, 103 and the server 105.

[0047] In some cases, the biological strip image analysis method provided by the present disclosure may be executed by the server 105 , and accordingly, the biological strip image analysis device may also be disposed in the server 105 . In this case, the system architecture 100 may not include the terminal devices 101 , 102 , and 103 .

[0048] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0049] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0050] Continue to refer Figure 2 , which shows a process 200 of an embodiment of a biological band image analysis method according to the present disclosure, the biological band image analysis method comprises the following steps:

[0051] Step 201: Input the biological strip image into the biological strip image analysis model, and output the strip position information.

[0052] Biological band images usually come from gel electrophoresis (such as polyacrylamide gel electrophoresis, PAGE) or similar separation techniques, which are used to separate proteins, nucleic acids or other biological macromolecules. First, load the biological sample (such as protein, nucleic acid sequence, etc.) and marker (maker) to be analyzed in a suitable gel; then, set the appropriate voltage and time for electrophoresis, the biological sample and marker will move, and the corresponding biological bands and marker bands will be generated; after the electrophoresis is completed, take a picture of the entire gel to obtain the biological band image.

[0053] The marker band in the biological band image contains molecules of known size. By comparing the migration distance with the biological sample, the molecular size of the biological sample can be estimated. The marker can help observe the migration of the sample during electrophoresis, such as whether it is uniform, whether there is tailing, etc. The number of biological samples and markers is not limited here, and it is preferred to load multiple markers to improve accuracy.

[0054] The biological strip image analysis model is a deep learning model, such as the Mask R-CNN (Mask Region-based Convolutional Neural Network) model used for object detection and instance segmentation in the field of computer vision. The deep learning model can learn the features of an image from a large amount of image data and perform tasks such as image classification and recognition. In the biological strip image analysis model, the convolutional neural network can extract and classify the input strip image, thereby achieving quantitative analysis and qualitative recognition of biological samples.

[0055] Specifically, the biological stripe image analysis model uses a convolutional neural network to preprocess the input stripe image, including operations such as image scaling and denoising, to improve the quality and stability of the image. Then, the model will extract features from the image, and use structures such as convolutional layers and pooling layers to abstract and encode the image layer by layer, thereby obtaining a more representative feature vector. Based on feature extraction, the biological stripe image analysis model can also use structures such as fully connected layers to classify and identify feature vectors. In addition, the biological stripe image analysis model can also be combined with other deep learning techniques, such as transfer learning and generative adversarial networks, to further improve the performance and accuracy of the model.

[0056] Finally, the biological strip image analysis model will output strip position information based on the input biological strip image. The strip position information here includes the position information of the biological strip and the position information of the marker strip. Each position information includes the starting position information and the end position information, wherein the starting position information can be known and set when the biological sample and the marker are loaded into the gel.

[0057] As a possible implementation, the above biological band image analysis model is implemented as follows: Figure 3 The model training operation 300 of steps 301 to 304 shown is trained:

[0058] Step 301: Input the biological strip image into the biological strip image analysis model, and output the strip position information.

[0059] The training biological band image set includes a series of biological band images (such as protein electrophoresis images, DNA gel electrophoresis images, etc.), and each image is marked with the end position of the band. In order to ensure the accuracy of the annotation, we may need to use professional image processing software or tools to carefully enlarge, adjust and align the image so that the end position of the band can be accurately marked.

[0060] Step 302, input each training biological strip image into the initial Mask R-CNN model in turn, and output the strip end position identified by the model.

[0061] Mask R-CNN is a deep learning model that combines the functions of object detection and semantic segmentation. It can accurately identify the target area in the image and give the precise boundaries of each area. In this step, we will use the powerful capabilities of the Mask R-CNN model to identify the end position of the strip for each training image.

[0062] Step 303, calculating the loss function value between the marked strip end position and the strip end position identified by the model.

[0063] After the model identifies the end position of each training biological stripe image, it is necessary to calculate the loss function value between the labeled end position of the stripe and the end position of the stripe identified by the model. The loss function value is an indicator that measures the gap between the model prediction result and the actual annotation, which can help us understand the performance of the model in its current state.

[0064] Step 304: Based on the loss function value, the initial Mask R-CNN model is iteratively optimized and trained to finally obtain a trained biological band image analysis model.

[0065] Based on the loss function value calculated above, the initial Mask R-CNN model is iteratively optimized and trained. This process usually involves using an optimization algorithm (such as the gradient descent algorithm) to gradually adjust the model's parameters to minimize the loss function value and improve the model's performance.

[0066] During the training process, multiple iterations may be required. Each iteration uses the current model to predict the training image and calculate the loss function value, and then adjusts the model parameters based on the loss function value. As the iterations proceed, the performance of the model usually gradually improves, and the accuracy of identifying the end position of the strip will continue to improve.

[0067] Finally, when the performance of the model on the training data reaches the preset standard, the model can be considered to have been trained and a trained biological band image analysis model has been obtained.

[0068] In summary, by using deep learning models, automatic learning and accurate recognition of features in biological strip images can be achieved. After model training, the system can accurately identify strips of different shapes and sizes, thereby significantly improving the accuracy and automation of the analysis. Compared with traditional methods, the present invention has shown significant advantages in dealing with complex backgrounds and noise interference, and does not require manual intervention, greatly enhancing the convenience of operation and the consistency of results. In addition, the present invention also has the ability to flexibly adjust the processing strategy according to the characteristics of the biological strip image, thereby further improving the adaptability and accuracy of the analysis.

[0069] Step 202: Calculate the molecular weight corresponding to the position information of the biological band according to the position information of the marker band and its corresponding molecular weight.

[0070] During electrophoresis, molecules in biological samples migrate in an electric field according to their size, charge, shape and other characteristics, forming specific bands on a gel or other supporting medium. These bands represent the distribution of different molecules in the sample.

[0071] In order to accurately measure the size of these molecules, markers are usually used as references. Markers are substances with known molecular sizes that are electrophoresed together with biological samples. Since the molecular weight of the marker is known, the molecular weight range of the biological sample molecules can be determined based on the position information of its band on the electrophoresis gel. In other words, by comparing the migration distance of the biological sample band and the marker band on the electrophoresis gel, the molecular weight of the sample molecule is estimated based on the known molecular weight information.

[0072] Specifically, step 202 may include the following steps 2021 and 2022:

[0073] Step 2021, according to the position information of the marker band and its corresponding molecular weight, the following band molecular weight calculation equation is fitted:

[0074] L = f(P);

[0075] Among them, L is the molecular weight corresponding to the position information of the biological band, f is the fitting function, and P is the position information of the biological band.

[0076] In the process of fitting, the appropriate function form can be selected according to the characteristics of the experimental data and the physical properties of the molecular weight. For example, in some cases, the molecular weight may show a linear relationship with the change of the band position; in other cases, it may be a quadratic, cubic or other complex relationship. Therefore, it is necessary to find the fitting function that can most accurately describe this relationship by trying different function forms according to the actual situation of the experimental data.

[0077] Step 2022: Substitute the position information of the biological band into the molecular weight calculation equation of the band to obtain the molecular weight corresponding to the position information of the biological band.

[0078] Once a suitable fitting function is obtained, the biological band position information P can be substituted into the equation to calculate the corresponding molecular weight L. In this way, not only can the molecular weight corresponding to each biological band be obtained, but the relationship and rules between these molecular weights can also be further analyzed. For example, by comparing the molecular weight differences between different bands, their possible roles in biological processes can be inferred; based on the distribution of molecular weights, the accuracy and reliability of the experiment can be evaluated.

[0079] In general, by fitting the band molecular weight calculation equation and substituting the position information of the biological band, the molecular weight of the biological band can be accurately calculated. This method is not only scientific and practical, but also provides important data support for subsequent biological research and applications.

[0080] As a possible implementation, the above method further includes:

[0081] Step 203, obtaining expected PCR product information.

[0082] Polymerase Chain Reaction (PCR) is a molecular biology technique that rapidly replicates specific DNA sequences in vitro. The expected PCR product information can include the theoretical molecular weights of multiple bands, such as a 96-well PCR plate and information on the expected PCR product length. The expected PCR product information is used to indicate the theoretical molecular weight corresponding to the bands identified by the model under theoretical conditions, and can be further used to verify the accuracy of the biological band image analysis model.

[0083] Step 204, according to the position information of each biological band output by the biological band image analysis model, match it with the bands in the expected PCR product information one by one.

[0084] The bands of the expected PCR product information correspond one to one with the bands of the biological band image. According to the position information of each biological band output by the biological band image analysis model, it can be matched one by one with the bands in the expected PCR product information.

[0085] Step 205 , in response to the molecular weight corresponding to the position information of any biological band being the same as the theoretical molecular weight of the corresponding band in the expected PCR product information, the PCR verification result of the molecular weight corresponding to the position information of the biological band is recorded as correct.

[0086] Step 206: In response to the molecular weight corresponding to the position information of any biological band being different from the theoretical molecular weight of the corresponding band in the expected PCR product information, the PCR verification result of the molecular weight corresponding to the position information of the biological band is recorded as incorrect.

[0087] Step 207, generating a biological band image analysis report based on the molecular weight corresponding to the position information of the biological band and the PCR verification result.

[0088] The biological band image analysis report records in detail the molecular weight, location information, verification results and other information of each biological band. Through this report, researchers can clearly understand the characteristics and distribution of PCR products, providing strong support for subsequent scientific research work.

[0089] The biological band image analysis method provided by the above-mentioned embodiment of the present disclosure realizes automatic learning and accurate recognition of features in biological band images by adopting a biological band image analysis model constructed by a deep learning framework, thereby significantly improving the accuracy and automation of the analysis. Compared with traditional methods, the present disclosure can effectively deal with the interference caused by complex background and noise, and no manual intervention is required during the entire analysis process, which significantly enhances the convenience of operation and ensures the consistency of results. In addition, the present disclosure also has the ability to flexibly adjust the processing strategy according to the biological band image, further enhancing the flexibility and accuracy of the analysis.

[0090] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a biological band image analysis device, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0091] like Figure 4 As shown, the biological band image analysis device 400 of this embodiment includes: a model recognition module 401 and a molecular weight calculation module 402, which is used to calculate the molecular weight corresponding to the position information of the biological band according to the position information of the marker band and its corresponding molecular weight.

[0092] The model recognition module 401 is used to input the biological strip image into the biological strip image analysis model and output strip position information, wherein the strip position information includes the biological strip position information and the marker strip position information;

[0093] The molecular weight calculation module 402 is used to calculate the molecular weight corresponding to the position information of the biological band according to the position information of the marker band and its corresponding molecular weight.

[0094] In this embodiment, the specific processing of the biological strip image analysis device 400 and the technical effects thereof can be referred to in Figure 2 The relevant descriptions of step 201 and step 202 in the corresponding embodiment are not repeated here.

[0095] In some optional implementations, the above-mentioned location information includes starting point location information and end point location information.

[0096] In some optional embodiments, the molecular weight calculation module 402 includes:

[0097] The equation fitting unit 4021 is used to fit the following band molecular weight calculation equation according to the position information of the marker band and its corresponding molecular weight:

[0098] L = f(P);

[0099] Among them, L is the molecular weight corresponding to the position information of the biological band, f is the fitting function, and P is the position information of the biological band;

[0100] The substitution unit 4022 is used to substitute the position information of the biological band into the molecular weight calculation equation of the band to obtain the molecular weight corresponding to the position information of the biological band.

[0101] In some optional embodiments, the above biological band image analysis model is trained by the following model training operations:

[0102] Obtaining a set of training biological strip images with strip end positions marked;

[0103] Input each training biological strip image into the initial Mask R-CNN model in turn, and output the strip end position identified by the model;

[0104] Calculate the loss function value between the marked strip end position and the strip end position identified by the model;

[0105] Based on the above loss function value, the above initial Mask R-CNN model is iteratively optimized and trained to finally obtain a trained biological strip image analysis model.

[0106] In some optional implementations, the apparatus 400 further includes:

[0107] PCR acquisition module 403, used to obtain expected PCR product information, the expected PCR product information includes theoretical molecular weights of multiple bands;

[0108] A matching module 404 is used to match each biological band with the bands in the expected PCR product information one by one according to the position information of each biological band output by the biological band image analysis model;

[0109] A verification correctness module 405 is used for recording the PCR verification result of the molecular weight corresponding to the position information of any biological band as correct in response to the molecular weight corresponding to the position information of the biological band being the same as the theoretical molecular weight of the corresponding band in the above-mentioned expected PCR product information;

[0110] The incorrect verification module 406 is used to record the PCR verification result of the molecular weight corresponding to the position information of any biological band as incorrect in response to the molecular weight corresponding to the position information of the biological band being different from the theoretical molecular weight of the corresponding band in the above-mentioned expected PCR product information.

[0111] In some optional implementations, the apparatus 400 further includes:

[0112] The report module 407 is used to generate a biological band image analysis report based on the molecular weight corresponding to the position information of the biological band and its PCR verification result.

[0113] It should be noted that the implementation details and technical effects of each module and unit in the device provided by the embodiments of the present disclosure can be referred to the description of other embodiments in the present disclosure, and will not be repeated here.

[0114] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 suitable for implementing the electronic device of the present disclosure. Figure 5 The computer system 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0115] like Figure 5 As shown, the computer system 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. Various programs and data required for the operation of the computer system 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0116] Typically, the following devices may be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the computer system 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The computer system 500 of an electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0117] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0118] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may 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 computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0119] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0120] The computer readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device implements the following Figure 2The illustrated embodiment and its alternative implementations illustrate a method for analyzing biological band images.

[0121] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving 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 may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0122] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0123] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit or module does not limit the unit itself in some cases. For example, the model recognition module may also be described as "inputting each training biological strip image into the initial Mask R-CNN model in turn, and outputting the strip end position recognized by the model".

[0124] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A biological band image analysis method, characterized in that: include: Inputting the biological strip image into the biological strip image analysis model, and outputting strip position information, wherein the strip position information includes the position information of the biological strip and the position information of the marker strip, and the biological strip image analysis model is a trained Mask R-CNN model; According to the position information of the marker band and its corresponding molecular weight, a band molecular weight calculation equation is fitted; Substitute the position information of the biological band into the band molecular weight calculation equation to obtain the molecular weight corresponding to the position information of the biological band.

2. The method according to claim 1, characterized in that The location information includes starting point location information and end point location information.

3. The method according to claim 1, characterized in that The biological band image analysis model is trained by the following model training operations: Obtaining a set of training biological strip images with strip end positions marked; Input each training biological strip image into the initial Mask R-CNN model in turn, and output the strip end position identified by the model; Calculate the loss function value between the marked strip end position and the strip end position identified by the model; Based on the loss function value, the initial Mask R-CNN model is iteratively optimized and trained to finally obtain a trained biological strip image analysis model.

4. The method according to claim 1, characterized in that The method further comprises: Acquiring expected PCR product information, wherein the expected PCR product information includes theoretical molecular weights of multiple bands; According to the position information of each biological band output by the biological band image analysis model, matching it with the bands in the expected PCR product information one by one; In response to the molecular weight corresponding to the position information of any biological band being the same as the theoretical molecular weight of the corresponding band in the expected PCR product information, recording the PCR verification result of the molecular weight corresponding to the position information of the biological band as correct; In response to the molecular weight corresponding to the position information of any biological band being different from the theoretical molecular weight of the corresponding band in the expected PCR product information, the PCR verification result of the molecular weight corresponding to the position information of the biological band is recorded as incorrect.

5. The method according to claim 4, characterized in that The method further comprises: A biological band image analysis report is generated based on the molecular weight corresponding to the position information of the biological band and the PCR verification result thereof.

6. A biological band image analysis device, characterized in that: include: A model recognition module, used for inputting a biological strip image into a biological strip image analysis model, and outputting strip position information, wherein the strip position information includes the position information of the biological strip and the position information of the marker strip, and the biological strip image analysis model is a trained Mask R-CNN model; An equation fitting unit, used for fitting a band molecular weight calculation equation according to the position information of the marker band and its corresponding molecular weight; The substitution unit is used to substitute the position information of the biological band into the band molecular weight calculation equation to obtain the molecular weight corresponding to the position information of the biological band.

7. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by one or more processors, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The method comprises a computer program / instruction, which implements the method according to any one of claims 1 to 5 when executed by a processor.

Images