Tic disorder detection method and device

Abstract

The present application discloses a tic disorder detection method and device, wherein the method comprises: obtaining the time sequence information of the patient's tic disorder; extracting at least one three-dimensional human body deformation feature of the time sequence information; and inputting at least one three-dimensional human body deformation feature into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluating the patient's actual condition based on at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the patient's three-dimensional reconstruction result. Thus, the problem that the tic disorder degree assessment result of the related art is greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting subsequent treatment, is solved.

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a tic disorder detection method and device. Background Art

[0002] Tic disorder is a complex, chronic neuropsychiatric disorder that begins in childhood and adolescence and is characterized by rapid, involuntary, sudden, repetitive, non-rhythmic, stereotyped, single or multiple muscle movements and / or vocal tics.

[0003] The diagnosis and treatment of tic disorders are inseparable from various assessments of the severity of the tic disorder, including doctor observations and oral statements from family members.

[0004] However, the motor tics manifested by tic disorder are involuntary, sudden, rapid, repetitive, and non-rhythmic. They can be controlled by the will and not occur temporarily for a short period of time, or they may occur more frequently under psychological stimulation, emotional tension or other stressful situations. Therefore, during the doctor's diagnosis and daily communication with family members, there may be special circumstances such as symptom reduction, aggravation or disappearance, which is not conducive to the assessment of the disease. The accuracy and reliability of tic disorder detection are low and cannot meet the detection needs. Summary of the invention

[0005] The present application provides a tic disorder detection method and device to solve the problem that the tic disorder degree assessment results of the related art are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting subsequent treatment.

[0006] The first aspect of the present application provides a tic disorder detection method, comprising the following steps: obtaining timing information of a patient's tic disorder; extracting at least one three-dimensional human body deformation feature of the timing information; and inputting the at least one three-dimensional human body deformation feature into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluating the patient's actual condition based on the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the three-dimensional reconstruction result of the patient.

[0007] Optionally, in one embodiment of the present application, before inputting the at least one tic disorder feature into the pre-constructed tic disorder detection model, it also includes: acquiring video data of a preset duration of the patient; based on the video data, reconstructing a three-dimensional model of the human body using a preset three-dimensional reconstruction strategy; extracting at least one required feature vector through the three-dimensional model to generate a tic disorder data set; training the tic disorder detection model using the three-dimensional deformation features of the human body in the tic disorder data set to obtain the pre-constructed tic disorder detection model.

[0008] Optionally, in one embodiment of the present application, the at least one required feature vector includes at least one of a facial expression deformation vector, an eye rotation vector, a head rotation vector, and a limb rotation vector.

[0009] Optionally, in one embodiment of the present application, the tic disorder detection model is trained using the three-dimensional deformation features of the human body of the tic disorder data set to obtain the pre-constructed tic disorder detection model, including: determining the corresponding neural network according to the task objectives of each preset feature evaluation task, and using the three-dimensional deformation features of the human body as input to train the tic disorder detection model to obtain the pre-constructed tic disorder detection model.

[0010] Optionally, in one embodiment of the present application, after obtaining the pre-built tic disorder detection model, it also includes: setting a corresponding model terminal branch for each preset feature evaluation task of a plurality of preset feature evaluation tasks.

[0011] The second aspect of the present application provides a tic disorder detection device, including: a first acquisition module, used to obtain the timing information of the patient's tic disorder; an extraction module, used to extract at least one three-dimensional human body deformation feature of the timing information; and a detection module, used to input the at least one three-dimensional human body deformation feature into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluate the patient's actual condition based on the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the three-dimensional reconstruction result of the patient.

[0012] Optionally, in one embodiment of the present application, it also includes: a second acquisition module, used to acquire video data of a preset length of time of the patient; a reconstruction module, used to reconstruct a three-dimensional model of the human body based on the video data using a preset three-dimensional reconstruction strategy; a generation module, used to extract at least one required feature vector through the three-dimensional model to generate a tic disorder data set; a training module, used to train a tic disorder detection model using the three-dimensional deformation features of the human body in the tic disorder data set to obtain the pre-constructed tic disorder detection model.

[0013] Optionally, in one embodiment of the present application, the at least one required feature vector includes at least one of a facial expression deformation vector, an eye rotation vector, a head rotation vector, and a limb rotation vector.

[0014] Optionally, in one embodiment of the present application, the training module includes: a training unit, used to determine the corresponding neural network according to the task objectives of each preset feature evaluation task, and use the three-dimensional deformation features of the human body as input to train the tic disorder detection model to obtain the pre-constructed tic disorder detection model.

[0015] Optionally, in one embodiment of the present application, the training module is further used to set a corresponding model terminal branch for each preset feature evaluation task of a plurality of preset feature evaluation tasks.

[0016] A third aspect 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 executes the program to implement the tic disorder detection method as described in the above embodiment.

[0017] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the tic disorder detection method as described in the above embodiment.

[0018] The embodiment of the present application can use the time series information of the patient's tic disorder to extract the three-dimensional deformation characteristics of the human body and input them into the tic disorder detection model to obtain the tic disorder manifestation characteristics, and then evaluate the patient's actual condition. It can eliminate interference factors and generate data by itself, which can greatly expand the scale of training data and improve the robustness of the model. It is widely used, and different characteristic indicators can assist in the multi-faceted evaluation of the condition, which is convenient for the subsequent implementation of more targeted treatment plans for patients. Therefore, it solves the problem that the tic disorder degree assessment results of the related technology are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting subsequent treatment.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A flowchart of a tic disorder detection method provided according to an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the principle of constructing a tic disorder detection model according to an embodiment of the present application;

[0023] Figure 3 A flowchart of a method for constructing a tic disorder detection model according to an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of a tic disorder detection device provided according to an embodiment of the present application;

[0025] Figure 5 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] The following describes the tic disorder detection method and device of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the tic disorder degree assessment results of the related technology mentioned in the background technology center are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting the subsequent treatment, the present application provides a tic disorder detection method, in which the patient's tic disorder time series information can be used to extract the three-dimensional deformation characteristics of the human body, and input into the tic disorder detection model to obtain the tic disorder performance characteristics, and then the patient's actual condition is evaluated, interference factors can be eliminated, data can be generated by itself, the scale of training data can be greatly expanded, the model robustness can be improved, and it is widely used. Different feature indicators can assist in the multi-faceted assessment of the condition, which is convenient for the subsequent implementation of more targeted treatment plans for patients. Thus, the problem that the tic disorder degree assessment results of the related technology are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting the subsequent treatment, is solved.

[0028] Specifically, Figure 1 A flowchart of a tic disorder detection method provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the tic disorder detection method includes the following steps:

[0030] In step S101, the timing information of the patient's tic disorder is obtained.

[0031] During the actual implementation process, the embodiment of the present application can obtain the timing information of the patient in a tic disorder state, which is convenient for the subsequent extraction of the patient's body deformation characteristics through the timing information, thereby confirming the patient's tic disorder manifestations. The different characteristics manifested under the timing information of tic disorder have general guiding significance for tic disorder detection.

[0032] Therefore, the embodiments of the present application can evaluate the condition over a long time series by acquiring the time series information of the patient's tic disorder, and can provide strong assistance for the modern tic disorder diagnosis and treatment process, which is conducive to avoiding communication errors caused by oral description of the disease characteristics, thereby resulting in the problem that the evaluation results cannot fit the patient's symptoms.

[0033] In step S102, at least one three-dimensional deformation feature of the human body is extracted from the time series information.

[0034] As a possible implementation method, the embodiment of the present application can extract at least one three-dimensional deformation feature of the human body from the time series information. Through the three-dimensional deformation feature of the human body, interference factors can be eliminated, and the patient's tic disorder manifestations can be further judged, which is convenient for evaluating the patient's tic disorder manifestations, which is beneficial to improving the accuracy of the evaluation results, and then facilitating the formulation of more targeted treatment plans.

[0035] In step S103, at least one three-dimensional deformation feature of the human body is input into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and the patient's actual condition is evaluated based on the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the patient's three-dimensional reconstruction results.

[0036] Specifically, the embodiment of the present application can input at least one three-dimensional deformation feature of the human body into a tic disorder detection model constructed based on the patient's three-dimensional reconstruction results, and then obtain at least one corresponding tic disorder manifestation feature to evaluate the patient's actual condition. The embodiment of the present application can eliminate interference factors and generate data by itself, which can greatly expand the scale of training data and improve the robustness of the model. It is also widely used. Different feature indicators can assist in the multi-faceted assessment of the condition, making it easier to implement more targeted treatment plans for patients in the future.

[0037] Optionally, in one embodiment of the present application, before inputting at least one tic disorder feature into a pre-constructed tic disorder detection model, it also includes: acquiring video data of a preset duration of the patient; reconstructing a three-dimensional model of the human body based on the video data using a preset three-dimensional reconstruction strategy; extracting at least one required feature vector through the three-dimensional model to generate a tic disorder data set; training the tic disorder detection model using the three-dimensional deformation features of the human body in the tic disorder data set to obtain a pre-constructed tic disorder detection model.

[0038] It can be understood that three-dimensional reconstruction can reconstruct the human body structure in three-dimensional space, allowing all patients to reconstruct the same set of human body templates under different recording environments, which is conducive to eliminating interference such as clothing, hair and background, and unifying the input standards of tics. In addition, the large amount of data required for tic disorder assessment can also be conveniently constructed on the three-dimensional model. Therefore, the embodiment of the present application can use the three-dimensional reconstruction method to reconstruct a real-time, high-precision three-dimensional human body model from the patient's long-term video data, which is conducive to the evaluation of the patient's actual condition, can eliminate interference factors, generate data by itself, can greatly expand the scale of training data, and improve the robustness of the model.

[0039] Specifically, the embodiments of the present application can reconstruct a three-dimensional model of the human body through the patient's long-term video data, and can use image processing methods to process the input long-term patient video frame by frame to ensure that the input video image can meet the requirements of three-dimensional reconstruction.

[0040] Furthermore, after the video processing is completed, the embodiment of the present application can use a high-precision three-dimensional reconstruction method to reconstruct a three-dimensional model of the human body, and abstract the required feature vectors through the deformation parameters of the three-dimensional model, and then map the tic disorder manifestation characteristics in the original video to the deformation characteristics of the three-dimensional model.

[0041] Among them, the embodiment of the present application can independently construct a tic disorder data set by controlling and changing the deformation characteristics of the three-dimensional model, thereby solving the problem of insufficient data.

[0042] Furthermore, the embodiment of the present application can train a tic disorder detection model based on the three-dimensional reconstruction results by utilizing the three-dimensional deformation features of the human body in the tic disorder data set to obtain a pre-constructed tic disorder detection model.

[0043] It should be noted that the preset duration can be set by technicians in this field according to the actual situation of the patient, and no specific limitation is made here.

[0044] Optionally, in one embodiment of the present application, at least one required feature vector includes at least one of a facial expression deformation vector, an eye rotation vector, a head rotation vector, and a limb rotation vector.

[0045] Those skilled in the art will appreciate that tic disorder is a complex, chronic neuropsychiatric disorder that begins in childhood and adolescence and is characterized by rapid, involuntary, sudden, repetitive, non-rhythmic, stereotyped, single or multiple muscle movement tics and / or vocal tics. Tic disorder is mainly manifested as repeated irregular eyebrow squeezing, eye contact, pouting, shaking head, shrugging shoulders, and making some strange noises in the throat. Therefore, the required feature vectors in the embodiments of the present application may include facial expression deformation vectors, eye movement vectors, head rotation vectors, and limb rotation vectors, so as to achieve comprehensive coverage of the characteristics of tic disorder and facilitate feature extraction, thereby obtaining the patient's actual condition.

[0046] Optionally, in one embodiment of the present application, a tic disorder detection model is trained using the three-dimensional deformation features of the human body in a tic disorder data set to obtain a pre-constructed tic disorder detection model, including: determining the corresponding neural network according to the task objectives of each preset feature evaluation task, and using the three-dimensional deformation features of the human body as input to train the tic disorder detection model to obtain a pre-constructed tic disorder detection model.

[0047] During the actual implementation process, the embodiment of the present application can determine the corresponding neural network according to the task objectives of each preset feature evaluation task, and use the three-dimensional deformation features of the human body in the tic disorder data set as input, use a large amount of data to train the tic disorder detection model, and obtain a pre-constructed tic disorder detection model.

[0048] The preset feature evaluation tasks can be set accordingly by those skilled in the art according to actual evaluation requirements. For example, Figure 2 As shown, the evaluation tasks can be tic frequency, complexity, tic intensity, etc., and the corresponding neural networks can be RepNet, LSTM and ResNet.

[0049] Optionally, in one embodiment of the present application, after obtaining the pre-built tic disorder detection model, it also includes: setting a corresponding model terminal branch for each preset feature evaluation task of a plurality of preset feature evaluation tasks.

[0050] For example, Figure 2 As shown, the embodiment of the present application can set different model terminal branches for different feature evaluation tasks, and input the same three-dimensional deformation feature of the human body into each branch, and use a large amount of data to realize the training of the tic disorder detection model. It can eliminate interference factors and generate data by itself, which can greatly expand the scale of training data and improve the robustness of the model. It is widely used, and different feature indicators can assist in the multi-faceted evaluation of the disease, making it easier to implement more targeted treatment plans for patients in the future.

[0051] Below through Figure 2 and Figure 3 As shown, the construction principle of the tic disorder model of the embodiment of the present application is described in detail with a specific embodiment.

[0052] in, Figure 2 Schematic diagram of the principles for building a tic disorder detection model using tic frequency, complexity, and tic intensity as examples.

[0053] like Figure 3 As shown, the embodiment of the present application includes the following steps:

[0054] Step S301: Video data processing. The embodiment of the present application can process the input video frame by frame by using an image processing method, thereby ensuring that the input video image meets the three-dimensional reconstruction requirements.

[0055] Step S302: Reconstructing a 3D model of a human body. In the embodiment of the present application, after the video data processing is completed, a high-precision 3D reconstruction method can be used to reconstruct a 3D model of a human body.

[0056] Step S303: Obtain the deformation characteristics of the three-dimensional model. Further, after the three-dimensional model processing is completed, the embodiment of the present application can abstract the required feature vector through the deformation parameters of the three-dimensional model, and map the tic disorder performance characteristics in the original video to the deformation characteristics of the three-dimensional model. Among them, the required feature vector may include facial expression deformation vectors, eyeball rotation vectors, head rotation vectors, and limb rotation vectors.

[0057] Step S304: constructing a tic disorder data set. The embodiment of the present application can construct a tic disorder data set by itself by controlling and changing the deformation characteristics of the three-dimensional model, thereby solving the problem of insufficient data.

[0058] Step S305: training a tic disorder detection model. For different feature evaluation tasks, such as Figure 2 As shown, in the embodiments of the present application, different model terminal branches can be set, such as tic frequency, complexity and tic intensity, all of which use the three-dimensional deformation features of the human body obtained in the above steps as input, and different task objectives are evaluated using neural networks with different functions, such as RepNet, LSTM and ResNet, and a large amount of data is used to train the model to obtain the final tic disorder detection model.

[0059] During the actual implementation process, the embodiment of the present application can extract the three-dimensional deformation characteristics of the human body through the timing information of the patient's tic disorder, and input the three-dimensional deformation characteristics of the human body into the constructed and trained tic disorder detection model, thereby obtaining the tic disorder manifestation characteristics to evaluate the tic disorder of the patient's actual condition.

[0060] According to the tic disorder detection method proposed in the embodiment of the present application, the time series information of the patient's tic disorder can be used to extract the three-dimensional deformation characteristics of the human body and input them into the tic disorder detection model to obtain the tic disorder manifestation characteristics, and then evaluate the patient's actual condition. Interference factors can be eliminated and data can be generated by itself. The scale of training data can be greatly expanded, the robustness of the model can be improved, and it is widely used. Different characteristic indicators can assist in the multi-faceted evaluation of the condition, which is convenient for the subsequent implementation of more targeted treatment plans for patients. Thus, the problem that the tic disorder degree assessment results of the related technology are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting subsequent treatment, is solved.

[0061] Next, the tic disorder detection device proposed in accordance with the embodiment of the present application will be described with reference to the accompanying drawings.

[0062] Figure 4 It is a block diagram of a tic disorder detection device according to an embodiment of the present application.

[0063] like Figure 4As shown, the tic disorder detection device 10 includes: a first acquisition module 100, an extraction module 200 and a detection module 300.

[0064] Specifically, the first acquisition module 100 is used to acquire the timing information of the patient's tic disorder.

[0065] The extraction module 200 is used to extract at least one three-dimensional deformation feature of the human body from the time series information.

[0066] The detection module 300 is used to input at least one three-dimensional deformation feature of the human body into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluate the patient's actual condition based on the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the patient's three-dimensional reconstruction results.

[0067] Optionally, in one embodiment of the present application, the tic disorder detection device 10 further includes: a second acquisition module, a reconstruction module, a generation module and a training module.

[0068] The second acquisition module is used to acquire video data of a preset duration of the patient.

[0069] The reconstruction module is used to reconstruct a three-dimensional model of the human body based on the video data using a preset three-dimensional reconstruction strategy.

[0070] A generation module is used to extract at least one required feature vector through a three-dimensional model to generate a tic disorder data set.

[0071] The training module is used to train the tic disorder detection model using the three-dimensional deformation features of the human body in the tic disorder data set to obtain a pre-built tic disorder detection model.

[0072] Optionally, in one embodiment of the present application, at least one required feature vector includes at least one of a facial expression deformation vector, an eye rotation vector, a head rotation vector, and a limb rotation vector.

[0073] Optionally, in one embodiment of the present application, the training module includes: a training unit.

[0074] Among them, the training unit is used to determine the corresponding neural network according to the task objectives of each preset feature evaluation task, and use the three-dimensional deformation features of the human body as input to train the tic disorder detection model to obtain a pre-constructed tic disorder detection model.

[0075] Optionally, in one embodiment of the present application, the training module is further used to set a corresponding model terminal branch for each preset feature evaluation task of a plurality of preset feature evaluation tasks.

[0076] It should be noted that the aforementioned explanation of the embodiment of the tic disorder detection method is also applicable to the tic disorder detection device of this embodiment, and will not be repeated here.

[0077] According to the tic disorder detection device proposed in the embodiment of the present application, the time series information of the patient's tic disorder can be used to extract the three-dimensional deformation characteristics of the human body and input them into the tic disorder detection model to obtain the tic disorder manifestation characteristics, and then evaluate the patient's actual condition. It can eliminate interference factors and generate data by itself, which can greatly expand the scale of training data and improve the robustness of the model. It is widely used, and different characteristic indicators can assist in the multi-faceted evaluation of the condition, which is convenient for the subsequent implementation of more targeted treatment plans for patients. In this way, the problem that the tic disorder degree assessment results of the related technology are greatly affected by the patient's will, emotions and other states, and cannot reflect the patient's true state, thereby affecting subsequent treatment, is solved.

[0078] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0079] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0080] When the processor 502 executes the program, the tic disorder detection method provided in the above embodiment is implemented.

[0081] Furthermore, the electronic device further comprises:

[0082] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0083] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0084] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0085] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0086] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0087] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0088] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above tic disorder detection method is implemented.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0090] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0091] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0093] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0094] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0095] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0096] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting tic disorder, characterized in that: The following steps are involved: Obtaining temporal information about the patient's tic disorder; Extracting at least one three-dimensional deformation feature of a human body from the time series information; as well as Inputting the at least one three-dimensional deformation feature of the human body into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluating the actual condition of the patient according to the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the three-dimensional reconstruction result of the patient; Before inputting the at least one human body three-dimensional deformation feature into the pre-built tic disorder detection model, the method further includes: Acquire video data of a preset duration of the patient; Based on the video data, reconstructing a three-dimensional model of the human body using a preset three-dimensional reconstruction strategy; Extracting at least one required feature vector through the three-dimensional model to generate a tic disorder data set; Using the three-dimensional deformation features of the human body in the tic disorder data set to train a tic disorder detection model to obtain the pre-constructed tic disorder detection model; The at least one required feature vector includes at least one of a facial expression deformation vector, an eyeball rotation vector, a head rotation vector, and a limb rotation vector; The method of training a tic disorder detection model using the three-dimensional human body deformation features of the tic disorder data set to obtain the pre-constructed tic disorder detection model further includes: For each of the plurality of preset feature evaluation tasks, setting a corresponding model terminal branch; After obtaining the pre-built tic disorder detection model, the method includes: Determine a corresponding neural network according to the task objectives of each preset feature evaluation task, and use the three-dimensional deformation features of the human body as input to train the tic disorder detection model to obtain the pre-constructed tic disorder detection model; The evaluation tasks include tic frequency, complexity and tic intensity, and the neural networks corresponding to the evaluation tasks are RepNet, LSTM and ResNe.

2. A tic disorder detection device, characterized in that: include: A first acquisition module is used to acquire the time sequence information of the patient's tic disorder; An extraction module, used to extract at least one three-dimensional deformation feature of a human body from the time series information; as well as A detection module, used to input the at least one three-dimensional deformation feature of the human body into a pre-constructed tic disorder detection model to obtain at least one tic disorder manifestation feature, and evaluate the actual condition of the patient according to the at least one tic disorder manifestation feature, wherein the tic disorder detection model is constructed based on the three-dimensional reconstruction result of the patient; Also includes: A second acquisition module is used to acquire video data of the patient for a preset time period; A reconstruction module, used to reconstruct a three-dimensional model of a human body based on the video data using a preset three-dimensional reconstruction strategy; A generating module, used for extracting at least one required feature vector through the three-dimensional model to generate a tic disorder data set; A training module, used to train a tic disorder detection model using the three-dimensional deformation features of the human body in the tic disorder data set to obtain the pre-constructed tic disorder detection model; The at least one required feature vector includes at least one of a facial expression deformation vector, an eyeball rotation vector, a head rotation vector, and a limb rotation vector; The training module is also used to set a corresponding model terminal branch for each preset feature evaluation task of the plurality of preset feature evaluation tasks; The training module includes: A training unit, configured to determine a corresponding neural network according to the task objective of each preset feature evaluation task, and to train the tic disorder detection model using the three-dimensional deformation feature of the human body as input to obtain the pre-constructed tic disorder detection model; The evaluation tasks include tic frequency, complexity and tic intensity, and the neural networks corresponding to the evaluation tasks are RepNet, LSTM and ResNe.

3. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the tic disorder detection method as claimed in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the tic disorder detection method as claimed in claim 1.

Images