Embryo development prediction method and device

Abstract

The invention belongs to the field of computers, and particularly relates to an embryonic development prediction method and device.The method comprises the steps that preprocessing units are arranged in at least one assisted reproduction center, and each preprocessing unit receives data from different data sources of the corresponding assisted reproduction center, the data comprises an embryo image, embryo fertilization time, placement time and basic information of a patient; the preprocessing unit performs multi-data fusion on data of different data sources to obtain fusion feature information; the preprocessing unit sends the fusion feature information to an analysis system; and the analysis system analyzes the fusion feature information through an analysis model to obtain a prediction result. According to the method, multi-source data fusion can be achieved, and data safety is achieved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for predicting embryo development. Background Art

[0002] At present, assisted reproductive (IVF) technology is developing towards integration and intelligence. In the process of assisted reproductive treatment, mature artificial intelligence software has become a key link. The architecture design of artificial intelligence software ignores the problem of how to process and integrate different data sources, and the processing of data security and privacy data desensitization are not enough, which needs to be further strengthened to ensure the security of patient information. Summary of the invention

[0003] The embodiments of the present application provide a method and device for predicting embryo development, which are capable of multi-data fusion and data security.

[0004] In a first aspect, the present application provides an embryonic development prediction method, comprising:

[0005] A pre-processing unit is set in at least one assisted reproductive center, each of which receives data from different data sources in the assisted reproductive center, the data including embryo images, embryo fertilization time, embryo placement time and basic information of the patient;

[0006] The preprocessing unit performs multi-data fusion on data from different data sources to obtain fusion feature information;

[0007] The preprocessing unit sends the fused feature information to the analysis system;

[0008] The analysis system analyzes the fused feature information through an analysis model to obtain a prediction result.

[0009] In an optional embodiment, receiving data from different data sources includes:

[0010] Generate new data based on new data sources or existing data sources, and receive data from different data sources.

[0011] In an alternative embodiment, data is received from various data sources via standardized interfaces and protocols.

[0012] In an optional embodiment, multiple data fusion is performed on data from different data sources to obtain fusion feature information, including:

[0013] Analyze the data format of each data source separately, and convert the data received from different data sources into a unified format;

[0014] The data from various data sources converted into a unified format are spliced ​​together to obtain the fused feature information.

[0015] In an optional embodiment, the analysis system analyzes the fused feature information through an analysis model to obtain a prediction result, including:

[0016] Analyze the fused feature information and input it into the multimodal AI analysis module, analyze the fused feature information through the multimodal AI analysis module, and generate an analysis report;

[0017] The analysis report is displayed through a WEB interface so that experts can review and edit the analysis report online, and the result information is transmitted back to the analysis system in real time.

[0018] In an optional embodiment, it also includes:

[0019] The analysis model is trained based on the result information, and the trained model is used as the current analysis model to analyze the feature information.

[0020] In an optional embodiment, training the analysis model based on the result information includes:

[0021] The obtained fusion feature information is used as input data, and the result information is used as output data to form a training data set;

[0022] The analysis model is trained using the training data set.

[0023] In a second aspect, an embodiment of the present application provides an embryo development prediction device, comprising:

[0024] A preprocessing unit is provided in at least one assisted reproductive center, each of which is used to receive data from different data sources in the assisted reproductive center, the data including embryo images, embryo fertilization time, placement time and basic information of the patient; perform multi-data fusion on the data from different data sources to obtain fusion feature information and send the fusion feature information;

[0025] An analysis system receives the fused feature information and analyzes the fused feature information through an analysis model to obtain a prediction result.

[0026] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements any of the methods described above when the program is executed by a processor.

[0027] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the computer program.

[0028] The embryo development prediction method of the embodiment of the present application can receive data from different data sources; and obtain fusion feature information by fusing multiple data on the data; send the fusion feature information to the analysis system; the analysis system analyzes the fusion feature information through the analysis model to obtain the prediction result. By uniformly analyzing the data from multiple data sources, the prediction effect can be improved. In addition, the analysis system can analyze the data of multiple assisted reproductive centers, realize sharing among multiple assisted reproductive centers, and serve more patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A schematic diagram showing a flow chart of a method for predicting embryonic development according to an embodiment of the present application;

[0031] Figure 2 A schematic diagram showing the structure of an embryo development analysis device according to an embodiment of the present application;

[0032] Figure 3 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0034] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] See also Figure 1 The present application embodiment provides a method for predicting embryo development, comprising:

[0037] A pre-processing unit is arranged in at least one assisted reproductive center, each pre-processing unit receiving data from different data sources of the assisted reproductive center;

[0038] The preprocessing unit performs multi-data fusion on data from different data sources to obtain fusion feature information;

[0039] The preprocessing unit sends the fused feature information to the analysis system;

[0040] The analysis system analyzes the fused feature information through the analysis model to obtain the prediction result.

[0041] The embryo development prediction method of the embodiment of the present application can receive data from different data sources; and obtain fusion feature information by fusing multiple data from different data sources; send the fusion feature information to the analysis system; the analysis system analyzes the fusion feature information through the analysis model to obtain the prediction result. By uniformly analyzing the data from multiple data sources, the prediction effect can be improved. In addition, the analysis system can analyze the data from multiple assisted reproductive centers, realize sharing among multiple assisted reproductive centers, and serve more patients.

[0042] In the embodiments of the present application, the data source includes different devices and platforms. In an exemplary embodiment, the data source includes a timelapse incubator, an ICSI (intracytoplasmic sperm injection) system, an inverted microscope data, etc. Medical data can be obtained through a timelapse incubator, an ICSI system, an inverted microscope data, etc.

[0043] In the embodiment of the present application, the data received from different data sources include embryo images, embryo fertilization time, placement time, basic information of the patient, etc. The basic information of the patient may include one or more of the patient's PID (primary immunodeficiency?), age, BMI (body mass index), gender, etc. The basic information of the patient received may be desensitized information to avoid leakage of patient privacy.

[0044] In some embodiments, the preprocessing unit performs multi-data fusion on data from different data sources, including extracting features from the data to obtain feature information. For example, feature extraction is performed on embryo images to obtain feature data. The preprocessing unit only uploads feature information to the analysis system, excluding privacy information, to improve data security, avoid leakage of sensitive information during remote data transmission, and thus protect patient privacy.

[0045] In some embodiments, receiving data from different data sources includes: generating new data based on a newly added data source or an existing data source, and receiving data from different data sources. In the embodiment of the present application, data collection and data integration may be automatically triggered when a new data source is added or new data is generated. For example, data collection is triggered when a new embryo image is generated.

[0046] In the embodiments of the present application, data from different data sources are integrated to provide richer information for embryo evaluation, thereby making the model more generalizable.

[0047] In some embodiments, data is received from various data sources through standardized interfaces and protocols. In embodiments of the present application, data can be collected from different data sources through standardized interfaces and protocols.

[0048] In some embodiments, data from different data sources are fused to obtain fused feature information, including: format parsing the data from each data source, converting the data received from different data sources into a unified format; splicing the data from each data source converted into a unified format together to obtain fused feature information. Through format parsing, heterogeneous data is converted into a unified format for easy analysis. Through data conversion, data integration is completed to form a unified data format, so that an integrated data set containing multiple data sources can be formed, realizing the effective integration of different data sources. It can be input into the analysis system as a whole for analysis.

[0049] In the embodiment of the present application, a deep learning model is used to extract features from data, and format parsing and splicing can be performed. In a specific implementation, the data converted into a unified format can be combined in a certain order.

[0050] In the embodiment of the present application, the data such as embryo images, time information and patient information received from different data sources are subjected to multi-data fusion to obtain fusion feature information. In the specific implementation, the data fields of each data source are analyzed and processed, and the data structures of different data sources are converted into a unified format by internal code logic for data storage and use. For example, the data of each data source can be subjected to feature extraction respectively to extract feature data of the same format, for example, the feature data extracted respectively are one-dimensional vectors. The features extracted from the data of different data sources are then spliced ​​together to obtain fusion feature information, which can be input into a prediction model for learning. Thus multimodal fusion is achieved.

[0051] In the embodiment of the present application, taking embryo pictures as an example, feature extraction of embryo pictures can be realized through AI models. In the specific implementation, the deep learning model is used to extract features of embryo pictures, and the extracted feature information does not contain sensitive information, protects privacy, and improves data transmission security, so that it can be transmitted to the outside for further analysis and prediction. For example, the feature information can be transmitted to an external server for analysis and prediction. An analysis model is running on the server. The external server can be a cloud server.

[0052] The fused feature information transmitted in this application can ensure that key patient data is desensitized and data privacy is guaranteed in multi-laboratory or multi-center deployment scenarios.

[0053] By performing feature extraction on the data, we can obtain a floating-point matrix and corresponding label values, and extract the specified interpretable feature areas and parameters.

[0054] In some embodiments, the analysis system analyzes the fusion feature information through the analysis model to obtain a prediction result, including: analyzing the fusion feature information and inputting it into the multimodal AI analysis module, analyzing the fusion feature information through the multimodal AI analysis module to generate an analysis report; displaying the analysis report through the WEB interface so that experts can review and edit the analysis report online, and transmit the result information back to the analysis system in real time. By generating an analysis report through the multimodal AI analysis module, auxiliary diagnosis and suggestions can be provided. When experts need to conduct remote or local consultations or provide professional opinions, the analysis report generated by AI can be displayed to embryologists through the consultation terminal. Experts can review the analysis report through the WEB interface.

[0055] Embryology experts can review and edit the analysis report through the online review interface of the WEB, and can send the results back to the system in real time. Realize real-time interaction among multiple centers and laboratories. Cross geographical restrictions, provide high-quality expert resources, combine expert experience and AI analysis, and improve the accuracy of diagnosis.

[0056] After the expert completes the consultation and provides diagnostic opinions or treatment suggestions, a consultation report containing the expert's opinions can be generated as result information and transmitted back to the system.

[0057] In some embodiments, the embryonic development prediction method of the embodiment of the present application also includes: training the analysis model based on the result information, and using the trained model as the current analysis model to analyze the feature information. When there is new data source data, the method of the embodiment of the present application can realize the labeling, training and deployment process of the automatic triggering model. It can also be the labeling, training and deployment process of the model manually triggered by the user.

[0058] In some embodiments, the analysis model is trained based on the result information, including: using the obtained fusion feature information as input data and the result information as output data to form a training data set; and using the training data set to train the analysis model. After the collected data is uniformly parsed and processed, a training data set is formed based on the obtained result information or the new annotation information of the expert, and the trained model is integrated into the existing analysis system. Ensure that the system always uses the latest model for data analysis and prediction to adapt to the ever-changing data and improve the analysis efficiency and accuracy. Solve the problem of difficult model deployment, long iteration cycle, and inapplicability to application scenarios with rapid data growth and changes.

[0059] The method of the embodiment of the present application can unify the management and automatically collect embryo data from different data sources. All patient information is read and stored on the local device to ensure the physical isolation and privacy security of the data. The local deep learning network is deployed to extract embryo image features, and the extracted features are then sent to the analysis model for further prediction. Remote processing and analysis of data can be achieved without uploading sensitive information to the outside.

[0060] The method of the embodiment of the present application can support remote and local consultation functions, resolve geographical restrictions, and allow embryology expert resources to collaborate remotely across geographical restrictions.

[0061] In the method of the embodiment of the present application, the analysis model can be continuously trained and improved based on new data to adapt to the ever-changing data and improve the analysis efficiency and accuracy.

[0062] In the embodiment of the present application, the expert can review and edit the analysis report through the online review interface through the user interface of the local consultation terminal and the remote consultation terminal, and can transmit the results back to the system in real time.

[0063] An embodiment of the present application provides an embryonic development prediction device. The device of the embodiment of the present application can implement the method of the above-mentioned embodiment. The above-mentioned method embodiment can be used to understand the device of the embodiment of the present application, and the description part of the embodiment of the following device can also be used to understand the method of the above-mentioned embodiment.

[0064] The embryo development prediction device of the embodiment of the present application includes a preprocessing unit and an analysis system. The preprocessing unit is arranged in at least one assisted reproductive center. Each preprocessing unit is used to receive data from different data sources of the assisted reproductive center, and the data includes embryo images, embryo fertilization time, placement time and basic information of the patient; multi-data fusion is performed on the data from different data sources to obtain fused feature information and send the fused feature information; the analysis system receives the fused feature information, and analyzes the fused feature information through an analysis model to obtain a prediction result.

[0065] The embryonic development prediction device of the embodiment of the present application also includes a display terminal, which is used to display the analysis report through a WEB interface, so that experts can review and edit the analysis report online, and transmit the result information back to the analysis system in real time. The analysis report can provide auxiliary diagnosis and suggestions. When the expert needs to conduct a remote or local consultation or provide professional advice, the analysis report generated by AI can be displayed to the embryology expert through the display terminal. The expert can review the analysis report through the WEB interface of the display terminal.

[0066] Embryology experts can review and edit the analysis report through the online review interface of the WEB, and can send the results back to the system in real time. Realize real-time interaction among multiple centers and laboratories. Cross geographical restrictions, provide high-quality expert resources, combine expert experience and AI analysis, and improve the accuracy of diagnosis.

[0067] After the expert completes the consultation and provides diagnostic opinions or treatment suggestions, a consultation report containing the expert's opinions can be generated as result information and transmitted back to the system.

[0068] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above methods when executing the computer program.

[0069] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the terminal 600 may include: at least one processor 601 , at least one network interface 604 , a user interface 603 , a memory 605 , and at least one communication bus 602 .

[0070] The communication bus 602 is used to realize the connection and communication between these components.

[0071] The user interface 603 may include a display screen (Display) and a camera (Camera), and the optional user interface 603 may also include a standard wired interface and a wireless interface.

[0072] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0073] Among them, the processor 601 may include one or more processing cores. The processor 601 uses various interfaces and lines to connect various parts in the entire terminal 600, and executes various functions and processes data of the terminal 600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 605, and calling data stored in the memory 605. Optionally, the processor 601 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 601 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 601, and it can be implemented separately through a chip.

[0074] Among them, the memory 605 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 605 includes a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 605 may optionally be at least one storage device located away from the aforementioned processor 601. As Figure 3 As shown, the memory 605 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program.

[0075] exist Figure 3 In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 601 can be used to call the application stored in the memory 605 and specifically perform the operations of any of the above method embodiments.

[0076] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0077] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods recorded in the above method embodiments.

[0078] Those skilled in the art can clearly understand that the technical solution of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0080] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., and other media that can store program codes.

[0085] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0086] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for predicting embryo development, characterized in that: include: A pre-processing unit is set in at least one assisted reproductive center, each of which receives data from different data sources in the assisted reproductive center, the data including embryo images, embryo fertilization time, embryo placement time and basic information of the patient; The preprocessing unit performs multi-data fusion on data from different data sources to obtain fusion feature information; The preprocessing unit sends the fused feature information to the analysis system; The analysis system analyzes the fused feature information through an analysis model to obtain a prediction result.

2. The method according to claim 1, characterized in that Receive data from various data sources, including: Generate new data based on new data sources or existing data sources, and receive data from various data sources.

3. The method according to claim 1 or 2, characterized in that: Receive data from various data sources through standardized interfaces and protocols.

4. The method according to claim 1, characterized in that: Perform multi-data fusion on data from different data sources to obtain fusion feature information, including: Analyze the data format of each data source separately, and convert the data received from different data sources into a unified format; The data from various data sources converted into a unified format are spliced ​​together to obtain the fused feature information.

5. The method according to claim 1, characterized in that The analysis system analyzes the fused feature information through an analysis model to obtain a prediction result, including: Analyze the fused feature information and input it into the multimodal AI analysis module, analyze the fused feature information through the multimodal AI analysis module, and generate an analysis report; The analysis report is displayed through a WEB interface so that experts can review and edit the analysis report online, and the result information is transmitted back to the analysis system in real time.

6. The method according to claim 5, characterized in that Also includes: The analysis model is trained based on the result information, and the trained model is used as the current analysis model to analyze the feature information.

7. The method according to claim 6, characterized in that Training the analysis model based on the result information includes: The obtained fusion feature information is used as input data, and the result information is used as output data to form a training data set; The analysis model is trained using the training data set.

8. An embryo development prediction device, characterized in that: include: A preprocessing unit is provided in at least one assisted reproductive center, each of which is used to receive data from different data sources in the assisted reproductive center, the data including embryo images, embryo fertilization time, placement time and basic information of the patient; perform multi-data fusion on the data from different data sources to obtain fusion feature information and send the fusion feature information; An analysis system receives the fused feature information and analyzes the fused feature information through an analysis model to obtain a prediction result.

9. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

Images