WO2021146941A1 - Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur - Google Patents

Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur Download PDF

Info

Publication number
WO2021146941A1
WO2021146941A1 PCT/CN2020/073580 CN2020073580W WO2021146941A1 WO 2021146941 A1 WO2021146941 A1 WO 2021146941A1 CN 2020073580 W CN2020073580 W CN 2020073580W WO 2021146941 A1 WO2021146941 A1 WO 2021146941A1
Authority
WO
WIPO (PCT)
Prior art keywords
disease
data
location
dimensional
classification information
Prior art date
Application number
PCT/CN2020/073580
Other languages
English (en)
Chinese (zh)
Inventor
白桦
颜永阳
王雨楠
杨立民
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to CN202080000061.1A priority Critical patent/CN113728398A/zh
Priority to PCT/CN2020/073580 priority patent/WO2021146941A1/fr
Publication of WO2021146941A1 publication Critical patent/WO2021146941A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • This application relates to the field of computer human-computer interaction technology. Specifically, this application relates to a method, device, equipment, computer-readable storage medium, and electronic equipment for obtaining the location of human diseases.
  • the present disclosure is made in view of the above-mentioned problems.
  • the present disclosure provides a method, device, equipment, computer-readable storage medium, and electronic equipment for acquiring the location of human diseases.
  • a method for acquiring a disease location including: acquiring element characteristics of the disease data through disease data; and acquiring the disease using multiple disease location models based on the element characteristics of the disease data The three-dimensional position of the disease, wherein the multiple disease position models respectively correspond to different three-dimensional positions of the body.
  • the multiple disease location models correspond to multiple human organs, and each model includes at least one tag corresponding to it, and the multiple disease location models are used based on the element characteristics of the disease data.
  • Obtaining the three-dimensional location of the disease includes: corresponding element features of the disease data to at least one label in the multiple disease location models to obtain the three-dimensional location of the disease.
  • the method further includes: obtaining a corrected three-dimensional position of the disease through a first neural network based on the disease data, wherein the first neural network is obtained through training data training,
  • the training data includes feature data and identification tags, the feature data includes multiple disease information, the identification tags include three-dimensional positions corresponding to the multiple disease information, and the multiple disease information includes multiple disease information.
  • Disease data includes: obtaining a corrected three-dimensional position of the disease through a first neural network based on the disease data, wherein the first neural network is obtained through training data training,
  • the training data includes feature data and identification tags, the feature data includes multiple disease information, the identification tags include three-dimensional positions corresponding to the multiple disease information, and the multiple disease information includes multiple disease information.
  • the method further includes: when the element feature of the disease data cannot correspond to at least one of the multiple disease location models, obtaining the disease through a second neural network based on the disease data
  • the second neural network is obtained by training with training data
  • the training data includes feature data and identification tags
  • the feature data includes disease classification information that is different from the disease classification information
  • the identification label includes the three-dimensional position corresponding to the disease classification information included in the feature data.
  • the multiple disease location models are obtained by dividing the disease classification information based on different three-dimensional locations of the body.
  • the disease classification information corresponds to different disease names, and each disease classification information contains at least one name tag corresponding to the disease classification information.
  • the method further includes: matching element characteristics of the disease data to At least one name tag of the disease classification information to obtain the disease name corresponding to the disease data.
  • the disease data is obtained from one or more of health assessment, physical examination report, health data, and peripheral input.
  • the three-dimensional position is highlighted on the three-dimensional human body structure.
  • a device for acquiring a disease location including: an element feature acquiring unit for acquiring element features of the disease data through disease data; and a three-dimensional location acquiring unit for acquiring disease data based on the disease data. Using multiple disease location models to obtain the three-dimensional location of the disease, wherein the multiple disease location models respectively correspond to different three-dimensional locations of the body.
  • the multiple disease location models correspond to multiple human organs, and each model contains at least one tag corresponding to it, and the three-dimensional location acquisition unit corresponds to the element characteristics of the disease data to all the human organs. At least one label in the multiple disease location models to obtain the three-dimensional location of the disease.
  • the device further includes: a three-dimensional position obtaining unit obtains the corrected three-dimensional position of the disease through a first neural network based on the disease data, wherein the first neural network is trained through training data Obtained, the training data includes feature data and identification tags, the feature data includes multiple disease information, the identification tags include three-dimensional positions corresponding to the multiple disease information, and the multiple disease information includes multiple Disease data for different diseases.
  • the device further includes: when the element feature of the disease data cannot correspond to at least one of the multiple disease position models, the three-dimensional position acquisition unit is based on the disease data through the second nerve
  • the network obtains the three-dimensional position of the disease, wherein the second neural network is obtained by training with training data, the training data includes feature data and identification tags, and the feature data includes diseases that are different from the disease classification information Classification information, and the identification label includes a three-dimensional position corresponding to the disease classification information included in the characteristic data.
  • the multiple disease location models are obtained by dividing the disease classification information based on different three-dimensional locations of the body.
  • the disease classification information corresponds to different disease names, and each disease classification information contains at least one name tag corresponding to it, and the three-dimensional position acquisition unit matches the element characteristics of the disease data to At least one name tag of the disease classification information to obtain the disease name corresponding to the disease data.
  • the three-dimensional position obtaining unit after obtaining the three-dimensional position of the disease, the three-dimensional position obtaining unit highlights the three-dimensional position on the three-dimensional human body structure.
  • a disease location acquisition device including: a processor; and a memory, in which computer-readable instructions are stored, wherein the disease location is executed when the computer-readable instructions are executed by the processor
  • An acquiring method comprising: acquiring element characteristics of the disease data through disease data; and acquiring the three-dimensional position of the disease using multiple disease location models based on the element characteristics of the disease data, wherein the multiple diseases The position models respectively correspond to different three-dimensional positions of the body.
  • a computer-readable storage medium for storing a computer-readable program, which causes a computer to execute the disease location acquisition method as described above.
  • an electronic device including the above-mentioned disease location acquisition device and a display interface; wherein the display interface is configured to display a three-dimensional human body model, and the three-dimensional human body model uses the above-mentioned disease location acquisition method.
  • the disease classification information is displayed at the obtained three-dimensional position, and the organ corresponding to the obtained three-dimensional position is highlighted.
  • a method for acquiring disease location is proposed. Specifically, the present disclosure creates a disease location model based on different three-dimensional locations, and then maps the acquired disease data to the disease location model to obtain the disease location model. Three-dimensional position, so as to realize the 3D display of the disease on the 3D model, to more accurately show the disease information to the user, improve the interactive display effect of the disease and abnormal indicators, and improve the efficiency and user experience.
  • Fig. 1 shows a flowchart of a method for acquiring a disease location according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram outlining an application scenario of a training method of a neural network model according to an embodiment of the present disclosure
  • Fig. 3 shows a flowchart of a method for acquiring a disease location according to another embodiment of the present disclosure
  • FIG. 4 shows a schematic diagram of an example of acquiring a disease location according to an embodiment of the present disclosure
  • Fig. 5 shows a schematic diagram of a display interface for displaying human body information according to an embodiment of the present disclosure
  • Fig. 6 shows a schematic diagram of a display interface for disease display according to an embodiment of the present disclosure
  • FIG. 7 shows a block diagram of a device for acquiring a disease location according to an embodiment of the present disclosure
  • Fig. 8 shows a block diagram of a disease location acquiring device according to an embodiment of the present disclosure
  • FIG. 9 shows a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 10 shows a schematic diagram of a storage medium according to an embodiment of the present disclosure.
  • first”, “second” and similar words used in the present disclosure do not indicate any order, quantity, or importance, but are only used to distinguish different components.
  • “including” or “including” and other similar words mean that the element or item appearing before the word covers the element or item listed after the word and their equivalents, but does not exclude other elements or items.
  • Similar words such as “connected” or “connected” are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up”, “Down”, “Left”, “Right”, etc. are only used to indicate the relative position relationship. When the absolute position of the described object changes, the relative position relationship may also change accordingly.
  • the International Classification of Diseases is a unified international classification for various diseases in order to analyze the differences in the health status of the populations of the world and the cause of death. It is very important for clinical application and management to assign the correct ICD10 code to each patient according to the diagnosis (that is, to add the ICD10 code to the patient's medical record). However, assigning the correct ICD10 code to the patient when visiting a doctor only finds the 2D position of the corresponding disease or disease for the visiting patient, but cannot accurately locate the 3D position of the disease, and cannot show the user accurate medical icons. Cause user misunderstanding.
  • ICD10 codes are organized in a hierarchical structure, where the upper code represents a wide range of disease categories, and the lower code represents more specific diseases. Therefore, when the coder matches the diagnosis description to an overly broad code instead of a more specific code, a wrong code will also occur, which makes it more difficult to locate the disease location.
  • the present disclosure provides a disease location acquisition method, which creates a disease location model based on different three-dimensional locations, and then obtains the three-dimensional location of the disease by mapping the acquired disease data to the disease location model, thereby realizing the disease on the 3D model 3D display to more accurately display disease information to users and improve user experience.
  • At least one embodiment of the present disclosure provides a method for acquiring a disease location, a device for acquiring a disease location, a device for acquiring a disease location, and a computer-readable storage medium.
  • the following is a non-limiting description of the disease location acquisition provided according to at least one embodiment of the present disclosure through several examples and embodiments. As described below, these specific examples and embodiments are different if they do not conflict with each other. The features can be combined with each other to obtain new examples and embodiments, and these new examples and embodiments also fall within the protection scope of the present disclosure.
  • FIGS. 1-4 a method for acquiring a disease location according to an embodiment of the present disclosure will be described with reference to FIGS. 1-4.
  • This method can be automatically completed by a computer or the like.
  • the method can be applied to display the three-dimensional position of human diseases and so on.
  • the method for acquiring the disease location can be implemented in software, hardware, firmware or any combination thereof, loaded and executed by a processor in a device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a network server.
  • the method for obtaining the location of the disease is applicable to a computing device that includes any electronic device with computing functions, such as a mobile phone, a laptop, a tablet, a desktop computer, a web server, etc., which can load and execute the disease
  • the location acquisition method is not limited in the embodiment of the present disclosure.
  • the computing device may include a central processing unit (CPU) or a graphics processing unit (Graphics Processing Unit, GPU) and other forms of processing units, storage units, etc.
  • CPU central processing unit
  • GPU Graphics Processing Unit
  • the computing device is also installed with an operating system, an application programming interface (for example, OpenGL (Open Graphics Library), Metal, etc.), etc., and the method for acquiring the disease location provided in the embodiments of the present disclosure is implemented by running code or instructions.
  • the computing device may also include a display component, such as a liquid crystal display (LCD), an organic light emitting diode (OLED) display, and a quantum dot light emitting diode (Quantum Dot Light Emitting).
  • Diode, QLED display screens, projection components, VR head-mounted display devices (for example, VR helmets, VR glasses), etc., which are not limited in the embodiments of the present disclosure.
  • the display part can display the object to be displayed.
  • the method for acquiring the location of the disease includes the following steps S101 to S102.
  • step S101 the element characteristics of the disease data are acquired through the disease data.
  • step S102 based on the element characteristics of the disease data, multiple disease location models are used to obtain the three-dimensional location of the disease, wherein the multiple disease location models respectively correspond to different three-dimensional locations of the body.
  • the disease data may be data related to the user's current disease, which contains a language description of the disease, which can be obtained from the user's personal health information.
  • the user's disease data can be obtained from analyzing one or more of health assessment, physical examination report, health data, and peripheral input.
  • the disease data may be data related to the current disease in the main complaint of a given medical record (or health data), current medical history, past history, and diagnosis results given by a doctor.
  • the disease data can be handwritten data, and the data required in the disease data can be obtained through OCR or manual reading; it can also be electronic disease data, which can be exported through the electronic disease data management platform data.
  • multiple disease location models are obtained by dividing disease classification information based on different three-dimensional locations of the body.
  • the disease classification information can be ICD10 or other suitable disease classification databases, which is not limited here.
  • the disease classification information may correspond to different disease names, and each disease classification information contains at least one name tag corresponding to it.
  • the element characteristics of the disease data may be matched to at least one of the disease classification information.
  • the name tag obtains the disease name corresponding to the disease data.
  • diabetes in the disease classification information corresponds to label 1
  • the disease data is matched to label 1 in the disease classification information, so that the disease name corresponding to the disease data is diabetes.
  • the element characteristics of the disease data can be represented by a vector representation or a word vector of each element of the disease data.
  • a neural network can be used to obtain the probability of matching each disease in the disease classification information to the disease data. If the probability is greater than a predetermined threshold, the disease in the disease classification information corresponding to the probability is matched to the disease data. To get the name of the disease.
  • a disease location model can be obtained based on ICD10.
  • 13904 diseases in the ICD10 can be integrated and analyzed, and the ICD10 can be divided into multiple disease location models based on different human organs or tissues, so as to map the diseases to the 3D model.
  • the ICD 10 can be divided into multiple disease location models through a classifier (such as clustering, support vector machine (SVM), K-nearest neighbor algorithm) or neural network, where different disease location models correspond to different human organs or tissues.
  • SVM support vector machine
  • K-nearest neighbor algorithm K-nearest neighbor algorithm
  • multiple disease location models correspond to multiple human organs, and each model includes at least one label corresponding to it.
  • the disease classification information can be divided into multiple disease location models according to organs such as heart, liver, spleen, lung, and kidney, and each disease location model corresponds to labels such as heart, liver, spleen, lung, and kidney.
  • the label of each disease location model may also include sub-labels.
  • the "heart” tag may contain subtags "left atrium”, “left ventricle”, “right atrium”, “right ventricle” and so on.
  • step S102 based on the element features of the disease data, using multiple disease location models to obtain the three-dimensional location of the disease may include: corresponding the element features of the disease data to those in the multiple disease location models. At least one tag to obtain the three-dimensional location of the disease.
  • each tag can correspond to a code
  • each subtag can also correspond to a code.
  • the code for labeling myasthenia gravis is G80.001
  • the code for labeling the esophagus is I95
  • the code for esophageal varices is I95.5.
  • the disease data is "the test tube cavity is not significantly narrowed, the gastroscope can pass, and the lower esophageal varices can be seen"
  • the disease data is matched to the disease location model according to the element feature "lower esophageal vein” in the disease data The code of I95.5, so that the three-dimensional position of the disease can be obtained as "esophagus, esophageal vein”.
  • the above process of matching disease data to the encoding of the disease location model can be automatically completed by a computer.
  • the technical effect of matching the disease data to the encoding of the disease location model can also be achieved through a neural network or other methods, which will not be repeated here.
  • the disease After obtaining the three-dimensional position of the disease, the disease can be displayed on the organ position corresponding to the three-dimensional human body model in the display interface of the electronic device to realize human-computer interaction.
  • the three-dimensional position of the disease can be highlighted on the three-dimensional human body structure, or the three-dimensional position of the disease can be displayed on the display interface of the mobile device through the engine.
  • a method for acquiring disease location is proposed. Specifically, the present disclosure creates a disease location model based on different three-dimensional locations, and then maps the acquired disease data to the disease location model to obtain the disease location model. Three-dimensional position, so as to realize the 3D display of the disease on the 3D model, to more accurately show the disease information to the user, improve the interactive display effect of the disease and abnormal indicators, and improve the efficiency and user experience.
  • the neural network model can be used to analyze the disease data to obtain the corrected three-dimensional position of the disease.
  • a neural network can be directly used to obtain the three-dimensional location of the disease.
  • Neural network is a large-scale, multi-parameter optimization tool. Relying on a large amount of training data, deep neural networks can learn hidden features that are difficult to summarize in the data, thereby completing a number of complex tasks, such as face detection, image semantic segmentation, text summary extraction, object detection, motion tracking, natural language translation Wait.
  • Obtaining the vector representation of the text through the word vector refers to expressing each word in the text as a single vector, and generating a vector representation of the text through a high degree of summary and abstraction.
  • Techniques based on neural network models can be used in, for example, medical disease location processing, so as to automatically process disease data.
  • FIG. 2 An application scenario of a training method of a neural network model according to an embodiment of the present disclosure is schematically described with reference to FIG. 2.
  • a neural network model 20 is used to receive an input 10, and the input 10 performs feature extraction processing, and based on the extracted features, an output 30 is generated.
  • the input 10 may be, for example, an image, video, or natural language text waiting to be processed.
  • the neural network model 20 performs image semantic segmentation, object detection, motion tracking, natural language translation and other processing on the input 10 to generate the output 30.
  • the neural network model 20 can be embedded in a terminal device or a server to process input.
  • the neural network model 20 may be trained according to the training method shown in FIG. 3.
  • Fig. 3 is a flowchart of a method for acquiring a disease location according to another embodiment of the present disclosure. As shown in FIG. 3, the method for acquiring the location of the disease includes the following steps S201 to S203.
  • step S201 the element characteristics of the disease data are acquired through the disease data.
  • step S202 based on the element characteristics of the disease data, multiple disease location models are used to obtain the three-dimensional location of the disease, wherein the multiple disease location models respectively correspond to different three-dimensional locations of the body.
  • step S203 based on the disease data, the corrected three-dimensional position of the disease is obtained through the first neural network.
  • step S203 the corrected three-dimensional position of the disease may be obtained through the first neural network based on the disease data.
  • the first neural network is obtained by training with training data
  • the training data includes feature data and identification tags
  • the feature data includes multiple disease information
  • the identification tags include three-dimensional positions corresponding to the multiple disease information
  • the plurality of disease information includes disease data of a plurality of different diseases.
  • the first neural network may be Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Back Propagation (BP), Linear Neural Network, etc. Do restrictions.
  • CNN Convolutional Neural Networks
  • RNN Recurrent Neural Network
  • BP Back Propagation
  • Linear Neural Network etc. Do restrictions.
  • multiple disease information may be obtained from analyzing one or more of health assessment, physical examination report, health data, and peripheral input, and the three-dimensional location corresponding to the multiple disease information may be more detailed location information manually labeled.
  • the three-dimensional position corresponding to the disease data can be corrected, so that the obtained three-dimensional position is more accurate.
  • the training data may include feature data and an identification label, the feature data including a plurality of disease information and disease classification information, and the identification label includes a three-dimensional position corresponding to the plurality of disease information and corresponding to the disease classification information.
  • the three-dimensional location information It should be realized that in addition to the disease classification information and its corresponding three-dimensional position in the training data, multiple disease information and their corresponding three-dimensional positions are newly added, thereby increasing the types and scope of disease positions. Therefore, when the disease location model corresponding to the disease data is inaccurate, the first neural network trained with more training data can be used to correct the three-dimensional location of the disease data.
  • the first neural network can be directly used to obtain the three-dimensional location of the disease based on the disease data. Since the trained neural network has a predictive function, when the disease data cannot correspond to at least one of the disease location models, the three-dimensional position of the disease can be obtained through the neural network with the predictive function.
  • the three-dimensional position of the disease after obtaining the three-dimensional position of the disease, it can be displayed on the corresponding organ model to achieve human-computer interaction.
  • the three-dimensional position of the disease can be highlighted on the three-dimensional human body structure, or the three-dimensional position of the disease can be displayed on the display interface of the mobile device through the engine.
  • a method for acquiring disease location is proposed. Specifically, the present disclosure creates a disease location model based on different three-dimensional locations, and then maps the acquired disease data to the disease location model to obtain the disease location model. 3D position, and then use neural network to analyze the disease data to obtain the corrected 3D position of the disease, so as to realize the 3D display of the disease on the 3D model, to more accurately show the disease information to the user, and to improve the interaction between the disease and abnormal indicators Display effect, improve efficiency and user experience.
  • the three-dimensional location of the disease can be directly obtained by a second neural network trained using training data different from the disease classification information.
  • the element characteristics of some disease data may not correspond to the existing disease location model.
  • the second neural network can be trained through training data composed of other disease classification information or disease location models, and the second neural network can be used. The network obtains the three-dimensional position of the disease.
  • the second neural network is obtained by training with training data
  • the training data includes feature data and identification tags
  • the feature data includes disease classification information different from the disease classification information
  • the identification tags include the same as the feature data.
  • the second neural network may also be Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Back Propagation (BP), Linear Neural Network, etc., here No restrictions.
  • CNN Convolutional Neural Networks
  • RNN Recurrent Neural Network
  • BP Back Propagation
  • Linear Neural Network etc., here No restrictions.
  • the training data uses disease classification information different from the disease classification information, thereby increasing the type and range of disease locations. Therefore, when the disease data cannot correspond to at least one of the multiple disease location models, the three-dimensional location of the disease can be directly obtained through the second neural network.
  • the three-dimensional position of the disease after obtaining the three-dimensional position of the disease, it can be displayed on the corresponding organ model to achieve human-computer interaction.
  • the three-dimensional position of the disease can be highlighted on the three-dimensional human body structure, or the three-dimensional position of the disease can be displayed on the display interface of the mobile device through the engine.
  • a method for acquiring disease location is proposed. Specifically, the present disclosure creates a disease location model based on different three-dimensional locations, and then maps the acquired disease data to the disease location model to obtain the disease location model.
  • the three-dimensional position when the disease data cannot correspond to at least one of the multiple disease position models, based on the disease data, the three-dimensional position of the disease is directly obtained through the second neural network to obtain the three-dimensional position of the disease, thereby Realize the 3D display of the disease on the 3D model to more accurately show the disease information to the user, improve the interactive display effect of the disease and abnormal indicators, and improve the efficiency and user experience.
  • FIGS. 1-3 After the disease location acquisition method according to the embodiment of the present disclosure is described above through FIGS. 1-3, the following describes an example of the disease location acquisition according to the embodiment of the present disclosure based on FIG. 4.
  • Fig. 4 shows a schematic diagram of an example of acquiring the location of a disease according to an embodiment of the present disclosure.
  • the disease data may be obtained from one or more of the health assessment 51, the physical examination report 52, the health data 53, and the peripheral input 54.
  • the element characteristics of the disease data are obtained from the disease data, and then the element characteristics of the disease data are mapped to the disease classification information 55 to obtain the disease name corresponding to the disease data.
  • the multiple disease location models 56 are obtained through the disease classification information 55, the element characteristics of the disease data can be mapped to the multiple disease location models 56 to obtain the three-dimensional location of the disease, thereby achieving 3D display.
  • the disease classification information contains various descriptions of the disease, based on the element characteristics of the disease data, the disease location acquisition method can also be used to obtain the disease or problem corresponding to the disease data.
  • the disease information display method provided in this application generally runs through electronic equipment to realize information interaction with the user. After turning on the electronic equipment to enter the display interface of disease information display (for example, the digital human body APP), the initial display on the display interface is usually A complete three-dimensional human body model is generally presented as a three-dimensional human body image that is upright and in a natural stretched state. In addition, highlight the diseased organ in the place where the disease is detected so that the patient can understand it.
  • disease information display for example, the digital human body APP
  • FIG. 5 is a schematic diagram of a display interface for displaying human body information according to an embodiment of the disclosure.
  • FIG. 6 is a schematic diagram of a display interface for displaying diseases according to an embodiment of the disclosure.
  • the curve includes at least one of the following: elliptical arc and spiral; the elliptical arc surrounds the position of the chest cavity of the three-dimensional human model; the spiral extends from the foot of the three-dimensional human model to the head of the three-dimensional human model; curve and display
  • the interface is relatively static.
  • the curve can also be another form of geometric curve that can surround the three-dimensional human body model. It can be one or two parallel displayed at a certain interval, or when the curve is a spiral line, it can appear as a double helix structure. Of course, the quantity It can even be 3, 4, etc., which can be set according to actual needs.
  • the human body information tags correspond to different parts of the three-dimensional human body model. Different parts of the three-dimensional human body model can be determined according to multiple classifications.
  • the human body information label includes at least one of the following: human organ category information, Human body system category information or human body parameter information; the distance between adjacent human body information labels on the curve is equal.
  • human organ category information is classified according to organs, including heart, liver, spleen, lung, kidney, etc., and according to human system categories, including circulatory system, digestive system, respiratory system, reproductive system, immune system, etc., or according to Partial classification, including head, chest, upper and lower limbs, etc. It even includes other human body parameter information related to human health, such as health history data, trauma data, etc.
  • human body information labels are set along the curve.
  • the human body information labels on the curve are of different sizes, but the distance between adjacent human body information labels on the curve is equal. As it gets farther and farther from the middle position, the human body information label gradually becomes smaller.
  • the human body information labels can also be set to different states.
  • the curve includes a preset prominent area and a preset non-highlighted area.
  • On the display interface displaying the three-dimensional human body model at least one curve surrounding the human body model is displayed, and a number of human body information labels are set on the curve, specifically including: if the human body information label moves to the preset highlight area, the human body information label is enlarged and displayed, and Set the human body information label to the activated state; if the human body information label moves to the preset non-protruding area, the human body information label is reduced to be displayed, and the human body information label is set to the inactive state.
  • the human body information label can move on the curve, and at a specific position of the curve, for example, on the curve segment close to the central axis of the three-dimensional human body model, the human body information label moves to this preset highlight area, then the human body information label is activated , The appearance is shown in an enlarged state, can be selected, and the next operation is performed accordingly, the other areas are the preset non-protruding areas, and the human body information tags in the preset non-protruding areas are in the inactive state, so compare them accordingly. Small size display.
  • the process of zooming in and out is also displayed on the display interface, which can form a vivid three-dimensional dynamic process and improve the user's immersion in human-computer interaction.
  • the characteristics of changing the brightness and color of the human body information label can also be added.
  • the corresponding position of the three-dimensional human body model is highlighted, so as to realize the 3D display of the disease on the 3D model, so as to show the user more accurately Disease information to enhance user experience.
  • FIG. 7 is a functional block diagram illustrating a disease location acquiring device according to an embodiment of the present disclosure.
  • a disease location acquiring device 1000 according to an embodiment of the present disclosure includes an element feature acquiring unit 1001 and a three-dimensional location acquiring unit 1002.
  • the above-mentioned modules can respectively execute the steps of the method for acquiring the location of the disease according to the embodiment of the present disclosure as described above with reference to FIGS. 1 to 3.
  • these unit modules can be implemented in various ways by hardware alone, software alone, or a combination thereof, and the present disclosure is not limited to any one of them.
  • CPU central processing unit
  • GPU image processor
  • TPU tensor processor
  • FPGA field programmable logic gate array
  • Processing units and corresponding computer instructions implement these units.
  • the element feature acquiring unit 1001 is configured to acquire the element feature of the disease data through the disease data.
  • the disease data may be data related to the user's current disease, which may be obtained from the user's personal health information.
  • the user's disease data can be obtained from analyzing one or more of health assessment, physical examination report, health data, and peripheral input.
  • the three-dimensional position acquiring unit 1002 is configured to acquire the three-dimensional position of the disease using multiple disease location models based on the element characteristics of the disease data, wherein the multiple disease location models respectively correspond to different three-dimensional positions of the body.
  • multiple disease location models are obtained by dividing disease classification information based on different three-dimensional locations of the body.
  • the disease classification information can be ICD10 or other suitable disease classification databases, which is not limited here.
  • the disease classification information may correspond to different disease names, and each disease classification information contains at least one name tag corresponding to it.
  • the element characteristics of the disease data may be matched to at least one of the disease classification information.
  • the name tag obtains the disease name corresponding to the disease data.
  • a disease location model can be obtained based on ICD10.
  • the diseases in the ICD10 can be integrated and analyzed, and the ICD10 can be divided into multiple disease location models based on different human organs or tissues, so as to map the diseases to the 3D model.
  • the three-dimensional position obtaining unit 1002 may correspond the element feature of the disease data to at least one label in the multiple disease position models to obtain the three-dimensional position of the disease.
  • the above process of matching disease data to the encoding of the disease location model can be automatically completed by a computer.
  • the technical effect of matching the disease data to the encoding of the disease location model can also be achieved through a neural network or other methods, which will not be repeated here.
  • the three-dimensional position of the disease After obtaining the three-dimensional position of the disease, it can be displayed on the corresponding organ model to realize human-computer interaction. For example, the three-dimensional position of the disease can be highlighted on the three-dimensional human body structure, or the three-dimensional position of the disease can be displayed on the display interface of the mobile device through the engine.
  • the three-dimensional position acquiring unit 1002 can use the neural network to analyze the disease data to obtain the corrected three-dimensional position of the disease.
  • the three-dimensional position obtaining unit 1002 may obtain the corrected three-dimensional position of the disease through the first neural network based on the disease data.
  • the first neural network is obtained by training with training data
  • the training data includes feature data and identification tags
  • the feature data includes multiple disease information
  • the identification tags include three-dimensional positions corresponding to the multiple disease information
  • the plurality of disease information includes disease data of a plurality of different diseases.
  • the three-dimensional position obtaining unit 1002 may directly obtain the three-dimensional position of the disease through the first neural network.
  • the three-dimensional position obtaining unit 1002 may obtain the three-dimensional position of the disease through a second neural network based on the disease data.
  • the second neural network is obtained by training with training data.
  • the training data includes feature data and identification labels
  • the feature data includes disease classification information that is different from the disease classification information
  • the identification labels include diseases that are different from those included in the feature data.
  • the three-dimensional position corresponding to the classification information, and the plurality of disease information includes disease data of a plurality of different diseases.
  • a method for acquiring disease location is proposed. Specifically, the present disclosure creates a disease location model based on different three-dimensional locations, and then maps the acquired disease data to the disease location model to obtain the disease location model. Three-dimensional position.
  • the three-dimensional position acquiring unit 1002 can then use the neural network to analyze the disease data to obtain the corrected three-dimensional position of the disease.
  • the three-dimensional location obtaining unit 1002 may also directly obtain the three-dimensional location of the disease through the first neural network or the second neural network based on the disease data. , So as to realize the 3D display of the disease on the 3D model, to more accurately display the disease information to the user, improve the interactive display effect of the disease and abnormal indicators, and improve the efficiency and user experience.
  • FIG. 8 is a schematic diagram of a disease location acquiring device 2000 according to an embodiment of the present disclosure. Since the disease location acquisition device of this embodiment has the same details as the method described above with reference to FIG. 1, for the sake of simplicity, detailed description of the same content is omitted here.
  • the disease location acquisition device 2000 includes a processor 210, a memory 220, and one or more computer program modules 221.
  • the processor 210 and the memory 220 are connected through a bus system 230.
  • one or more computer program modules 221 are stored in the memory 220.
  • one or more computer program modules 221 include instructions for executing the disease location acquisition method provided by any embodiment of the present disclosure.
  • instructions in one or more computer program modules 221 may be executed by the processor 210.
  • the bus system 230 may be a commonly used serial or parallel communication bus, etc., which is not limited in the embodiments of the present disclosure.
  • the processor 210 may be a central processing unit (CPU), a digital signal processor (DSP), an image processor (GPU), or other forms of processing units with data processing capabilities and/or instruction execution capabilities, and may be general-purpose processing units.
  • CPU central processing unit
  • DSP digital signal processor
  • GPU image processor
  • the memory 220 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include random access memory (RAM) and/or cache memory (cache), for example.
  • the non-volatile memory may include read-only memory (ROM), hard disk, flash memory, etc., for example.
  • One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 210 may run the program instructions to implement the functions (implemented by the processor 210) and/or other desired functions in the embodiments of the present disclosure, For example, how to obtain the location of the disease.
  • the computer-readable storage medium can also store various application programs and various data, such as element characteristics of disease data, disease location models, and various data used and/or generated by the application programs.
  • the embodiment of the present disclosure does not provide all the components of the disease location acquisition device 2000.
  • those skilled in the art can provide and set other unshown component units according to specific needs, which are not limited in the embodiments of the present disclosure.
  • the disease location acquiring device 1000 and the disease location acquiring device 2000 can be used in various appropriate electronic devices.
  • FIG. 9 is a schematic structural diagram of an electronic device provided by at least one embodiment of the present disclosure.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 9 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device includes the disease location acquiring device 1000 provided by any embodiment of the present disclosure and a display interface (for example, the output device 307 shown in FIG. 9); wherein the display interface is configured to display a three-dimensional human body model,
  • the three-dimensional human body model displays disease classification information at the three-dimensional position obtained by the above-mentioned disease position acquisition method, and highlights the organ corresponding to the obtained three-dimensional position.
  • the electronic device 300 includes a processing device (such as a central processing unit, a graphics processor, etc.) 301, which can be based on a program stored in a read-only memory (ROM) 302 or from a storage device.
  • the device 308 loads a program in a random access memory (RAM) 303 to perform various appropriate actions and processing.
  • RAM random access memory
  • various programs and data required for the operation of the computer system are also stored.
  • the processing device 301, the ROM 302, and the RAM 303 are connected by the bus 304 here.
  • An input/output (I/O) interface 305 is also connected to the bus 304.
  • the following components can be connected to the I/O interface 305: including input devices 306 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including input devices such as liquid crystal displays (LCD), speakers, vibration
  • the output device 307 of the device, etc. includes a storage device 308 such as a magnetic tape, a hard disk, etc.; and a communication device 309 including a network interface card such as a LAN card, a modem, and the like.
  • the communication device 309 may allow the electronic device 300 to perform wireless or wired communication with other devices to exchange data, and perform communication processing via a network such as the Internet.
  • the driver 310 is also connected to the I/O interface 305 as needed.
  • FIG. 9 shows the electronic device 300 including various devices, it should be understood that it is not required to implement or include all of the illustrated devices. More or fewer devices may be implemented alternatively or included.
  • the electronic device 300 may further include a peripheral interface (not shown in the figure) and the like.
  • the peripheral interface can be various types of interfaces, such as a USB interface, a lightning interface, and the like.
  • the communication device 309 can communicate with a network and other devices through wireless communication, such as the Internet, an intranet, and/or a wireless network such as a cellular telephone network, a wireless local area network (LAN), and/or a metropolitan area network (MAN).
  • wireless communication such as the Internet, an intranet, and/or a wireless network such as a cellular telephone network, a wireless local area network (LAN), and/or a metropolitan area network (MAN).
  • LAN wireless local area network
  • MAN metropolitan area network
  • Wireless communication can use any of a variety of communication standards, protocols and technologies, including but not limited to Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (W-CDMA) , Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Wi-Fi (e.g. based on IEEE 802.11a, IEEE 802.11b, IEEE 802.11g and/or IEEE 802.11n standards), voice transmission based on Internet protocol (VoIP), Wi-MAX, protocols used for e-mail, instant messaging and/or short message service (SMS), or any other suitable communication protocol.
  • GSM Global System for Mobile Communications
  • EDGE Enhanced Data GSM Environment
  • W-CDMA Wideband Code Division Multiple Access
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • Wi-Fi e.g. based on IEEE 802.11a, IEEE 802.11b, IEEE 802.11g and/or IEEE 802.11n standards
  • VoIP Internet protocol
  • Wi-MAX
  • the electronic device can be any device such as a mobile phone, a tablet computer, a notebook computer, an e-book, a game console, a television, a digital photo frame, a navigator, etc., or can be any combination of electronic devices and hardware. This is not limited.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302.
  • the processing device 301 the above-mentioned disease location acquisition function defined in the method of the embodiment of the present disclosure is executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the 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 a combination of any of the above.
  • Computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein.
  • This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication e.g., communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device obtains at least two Internet protocol addresses; A node evaluation request for an Internet Protocol address, the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; the obtained Internet Protocol address Indicates the edge node in the content distribution network.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; Among at least two Internet Protocol addresses, an Internet Protocol address is selected; the selected Internet Protocol address is returned; the received Internet Protocol address indicates an edge node in the content distribution network.
  • the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include but are not limited to object-oriented programming languages such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • FIG. 10 is a schematic diagram of a storage medium provided by at least one embodiment of the present disclosure.
  • the storage medium 400 non-transitory stores computer-readable instructions 401, and when the non-transitory computer-readable instructions are executed by a computer (including a processor), any one of the embodiments of the present disclosure can be executed. How to get the location of the disease.
  • the storage medium may be any combination of one or more computer-readable storage media.
  • one computer-readable storage medium contains computer-readable program code for determining the number of display faces of the sub-model, and another computer-readable storage medium
  • the medium contains computer-readable program code that determines the location of the disease.
  • the computer can execute the program code stored in the computer storage medium, and execute, for example, the disease location acquisition method provided in any embodiment of the present disclosure.
  • the storage medium may include a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), Portable compact disk read-only memory (CD-ROM), flash memory, or any combination of the foregoing storage media may also be other suitable storage media.
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • CD-ROM Portable compact disk read-only memory
  • flash memory or any combination of the foregoing storage media may also be other suitable storage media.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

La présente invention concerne un procédé d'acquisition d'emplacement d'une maladie humaine, un appareil, un dispositif et un support de stockage lisible par ordinateur. Ledit procédé comprend les étapes consistant : à acquérir des caractéristiques d'élément de données d'une maladie au moyen des données de la maladie (S101) ; à acquérir, sur la base des caractéristiques d'élément des données de la maladie, un emplacement tridimensionnel de la maladie à l'aide d'une pluralité de modèles d'emplacement de la maladie, la pluralité de modèles d'emplacement de la maladie correspondant respectivement à différents emplacements tridimensionnels d'un corps (S102). À l'aide dudit procédé, l'affichage d'une maladie sur un modèle 3D peut être mis en œuvre, de telle sorte que des informations de la maladie puissent être affichées à un utilisateur de manière plus précise, ce qui permet d'améliorer l'affichage interactif d'une maladie et d'un indicateur anormal, et d'améliorer également l'efficacité et l'expérience utilisateur.
PCT/CN2020/073580 2020-01-21 2020-01-21 Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur WO2021146941A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080000061.1A CN113728398A (zh) 2020-01-21 2020-01-21 疾病位置获取方法、装置、设备以及计算机可读存储介质
PCT/CN2020/073580 WO2021146941A1 (fr) 2020-01-21 2020-01-21 Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/073580 WO2021146941A1 (fr) 2020-01-21 2020-01-21 Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur

Publications (1)

Publication Number Publication Date
WO2021146941A1 true WO2021146941A1 (fr) 2021-07-29

Family

ID=76991759

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/073580 WO2021146941A1 (fr) 2020-01-21 2020-01-21 Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur

Country Status (2)

Country Link
CN (1) CN113728398A (fr)
WO (1) WO2021146941A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114388085A (zh) * 2021-11-23 2022-04-22 皖南医学院第一附属医院（皖南医学院弋矶山医院） 一种基于病案的实时智能辅助icd编码方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106021920A (zh) * 2016-05-17 2016-10-12 华南师范大学 基于神经网络面向自动诊断的医疗数据处理系统和装置
CN106909778A (zh) * 2017-02-09 2017-06-30 北京市计算中心 一种基于深度学习的多模态医学影像识别方法及装置
CN109447183A (zh) * 2018-11-27 2019-03-08 东软集团股份有限公司 模型训练方法、装置、设备以及介质
CN109741806A (zh) * 2019-01-07 2019-05-10 北京推想科技有限公司 一种医学影像诊断报告辅助生成方法及其装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106021920A (zh) * 2016-05-17 2016-10-12 华南师范大学 基于神经网络面向自动诊断的医疗数据处理系统和装置
CN106909778A (zh) * 2017-02-09 2017-06-30 北京市计算中心 一种基于深度学习的多模态医学影像识别方法及装置
CN109447183A (zh) * 2018-11-27 2019-03-08 东软集团股份有限公司 模型训练方法、装置、设备以及介质
CN109741806A (zh) * 2019-01-07 2019-05-10 北京推想科技有限公司 一种医学影像诊断报告辅助生成方法及其装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114388085A (zh) * 2021-11-23 2022-04-22 皖南医学院第一附属医院（皖南医学院弋矶山医院） 一种基于病案的实时智能辅助icd编码方法及系统

Also Published As

Publication number Publication date
CN113728398A (zh) 2021-11-30

Similar Documents

Publication Publication Date Title
US11657044B2 (en) Semantic parsing engine
CN110738263B (zh) 一种图像识别模型训练的方法、图像识别的方法及装置
CN111863170A (zh) 一种电子病历信息的生成方法、装置及系统
CN109074165A (zh) 基于用户的大脑活动和凝视修改用户界面
US20200151186A1 (en) Cognitive Computer Assisted Attribute Acquisition Through Iterative Disclosure
CN110472251A (zh) 翻译模型训练的方法、语句翻译的方法、设备及存储介质
US11900594B2 (en) Methods and systems for displaying a region of interest of a medical image
TW202040587A (zh) 圖像分割方法及裝置、電子設備和儲存媒體
WO2020242622A1 (fr) Validation à distance de modèles d'apprentissage automatique pour un déséquilibre de données
CN108369585B (zh) 用于提供翻译服务的方法及其电子装置
WO2020242641A1 (fr) Procédé et système de détection de déséquilibre de données dans un ensemble de données utilisé dans l'apprentissage automatique
US10311613B2 (en) Electronic device for processing image and method for controlling thereof
US20210240931A1 (en) Visual question answering using on-image annotations
US20160253318A1 (en) Apparatus and method for processing text
WO2021195670A1 (fr) Mappage d'emplacement pour réalité augmentée à grande échelle
CN114765075A (zh) 药品推荐方法、装置及系统、电子设备及存储介质
CN112970013A (zh) 电子装置及其控制方法
CN108536725A (zh) 电子设备及其提供信息的方法
WO2021146941A1 (fr) Procédé d'acquisition d'emplacement de maladie, appareil, dispositif et support de stockage lisible par ordinateur
US20230162844A1 (en) Patient provider matching system
US10409623B2 (en) Graphical user interface for localizing a computer program using context data captured from the computer program
CN107402659A (zh) 电子设备及接收其用户输入的方法
CN110489563B (zh) 图结构的表示方法、装置、设备及计算机可读存储介质
US20230125321A1 (en) User-guided structured document modeling
CN113657325A (zh) 用于确定标注样式信息的方法、装置、介质及程序产品

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20915424

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20915424

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27.03.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20915424

Country of ref document: EP

Kind code of ref document: A1