WO2024001723A1 - 控制设备、医疗系统及计算机可读存储介质 - Google Patents

控制设备、医疗系统及计算机可读存储介质 Download PDF

Info

Publication number
WO2024001723A1
WO2024001723A1 PCT/CN2023/099381 CN2023099381W WO2024001723A1 WO 2024001723 A1 WO2024001723 A1 WO 2024001723A1 CN 2023099381 W CN2023099381 W CN 2023099381W WO 2024001723 A1 WO2024001723 A1 WO 2024001723A1
Authority
WO
WIPO (PCT)
Prior art keywords
specified
designated
control device
action
diagnosis result
Prior art date
Application number
PCT/CN2023/099381
Other languages
English (en)
French (fr)
Inventor
刘鑫蕊
周国新
Original Assignee
苏州景昱医疗器械有限公司
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 苏州景昱医疗器械有限公司 filed Critical 苏州景昱医疗器械有限公司
Publication of WO2024001723A1 publication Critical patent/WO2024001723A1/zh

Links

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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • 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 technical fields of implantable devices, remote program control, Internet of Things, deep learning and Parkinson's diagnosis, such as control equipment, medical systems and computer-readable storage media.
  • Implantable devices refer to implantable devices that are fully or partially inserted into the human body or cavity (mouth) through surgery, or are used to replace the human epithelial surface or ocular surface, and remain in the human body for more than 30 days (inclusive) after the surgical procedure is completed, or Medical devices that are absorbed by the human body.
  • Implantable medical systems including programmable equipment and implantable devices can provide patients with precision treatment with controllable parameters, and are welcomed by many consumers in the market.
  • Patent CN113362946A discloses a video processing device, electronic equipment and computer-readable storage media.
  • the video processing device is applied to electronic equipment.
  • the electronic equipment interacts with data respectively with a display screen, a camera and a doctor's equipment.
  • the electronic equipment Used to perform data processing on videos of patients with Parkinson's disease; the device includes: a prompt display module, used to use the display screen to display prompt information of at least one designated action; a video collection module, used to use the The camera collects video of the patient; an action prediction module is used to input the patient's video into a Parkinson's detection model, predict the patient's action information and send it to the doctor's equipment, where the action information at least includes: A specified amplitude and/or frequency of action; an information acquisition module for acquiring the patient's disease information; a suggested strategy module for acquiring the patient's recommended program control strategy based on the patient's disease information and action information and sent to the physician device.
  • This device helps doctors quantitatively understand the patient's local posture and performance during exercise, but this method only detects the patient's local movements.
  • the performance Because the patient's attention is focused on the specified action, the performance The status that comes out may not be the real status, and this partial detection result cannot reflect the patient's true condition.
  • the purpose of this application is to provide a control device, a medical system and a computer-readable storage medium that can reflect the patient's true state through intermediate diagnosis results and accurately reflect the patient's performance of the specified action.
  • this application provides a control device, the control device is configured to:
  • the process of obtaining the intermediate diagnosis results corresponding to the specified action includes:
  • One or more part images of non-specified parts are intercepted from each frame of the image to be processed.
  • the non-specified parts are parts other than the specified part.
  • the display content of the image to be processed includes at least one designated part and At least one non-designated site;
  • an intermediate diagnosis result corresponding to the designated action is obtained.
  • control device is further configured to obtain the site diagnosis results of each of the non-specified sites in the following manner:
  • the multi-frame part images of each of the non-specified parts are respectively input into the corresponding part diagnosis model to obtain the part diagnosis result of each of the non-specified parts.
  • control device is further configured to obtain all data in the following manner:
  • the intermediate diagnosis results corresponding to the specified actions are as follows:
  • an intermediate diagnosis result corresponding to the designated action is obtained, wherein the first weight is greater than the site diagnosis result and the second weight.
  • the second weight, or the first weight is equal to the second weight, or the first weight is smaller than the second weight.
  • control device is further configured to obtain the site diagnosis result of the designated site in the following manner:
  • the multi-frame part images of the designated part are input into the corresponding part diagnosis model to obtain the part diagnosis result of the designated part.
  • control device is further configured to:
  • the display device is used to display the rehabilitation training video corresponding to the designated part.
  • control device performs data interaction with the stimulator implanted in the patient's body, and the control device is further configured to:
  • the stimulator is controlled to release corresponding electrical stimulation energy.
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following manner:
  • the reference configuration information corresponding to the stimulator is obtained.
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following manner:
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following manner:
  • the training process of the reference configuration model includes:
  • the first training set including a plurality of first training data, each of the first training data including a Parkinson's diagnosis result of a sample object and annotation data of the reference configuration information of the sample object;
  • control device is further configured to obtain the designated part corresponding to the designated action in the following manner:
  • the designated part corresponding to the designated action is obtained.
  • this application provides a medical system, which includes a camera and any one of the above control devices, and the control device performs data interaction with the camera;
  • the camera is used to collect video data of each specified action performed by the patient.
  • the present application provides a computer-readable storage medium that stores a computer program.
  • the computer program When the computer program is executed by a processor, it implements the functions of any of the above control devices.
  • the intermediate diagnostic results corresponding to each designated action When assessing the severity of a patient's Parkinson's disease, reference is made to the intermediate diagnostic results corresponding to each designated action. That is to say, the whole-body video of the patient performing different designated actions can be obtained separately, and combined with the corresponding results of the different designated actions.
  • the intermediate diagnosis results comprehensively evaluate the severity of the patient's Parkinson's disease. Compared with the diagnosis results that are limited to a certain specified action, the Parkinson's diagnosis results of this application can more accurately reflect the patient's condition.
  • Figure 1 is a structural block diagram of a medical device provided by an embodiment of the present application.
  • Figure 2 is a schematic flow chart of a control method provided by this application.
  • Figure 3 is a schematic flowchart of obtaining intermediate diagnosis results provided by this application.
  • Figure 4 is a schematic flowchart of another method of obtaining intermediate diagnosis results provided by an embodiment of the present application.
  • FIG. 5 is a structural block diagram of a control device provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a program product for a control method provided by an embodiment of the present application.
  • At least one means one or more, and “plurality” means two or more.
  • “And/or” describes the association of associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the related objects are in an “or” relationship.
  • “At least one of the following” or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items).
  • At least one of a, b or c can mean: a, b, c, a and b, a and c, b and c, a and b and c, where a, b and c can It can be single or multiple. It is worth noting that "at least one item (item)” can also be interpreted as “one item (item) or multiple items (item)”.
  • Parkinson’s disease is a common degenerative disease of the nervous system. It is more common in the elderly. The average age of onset is about 60 years old. Parkinson’s disease is less common in young people under the age of 40. The prevalence of PD in people over 65 years old in my country is approximately 1.7%. Most patients with Parkinson's disease have sporadic cases, and less than 10% of patients have a family history. The most important pathological change of Parkinson's disease is the degeneration and death of dopamine (DA) neurons in the substantia nigra of the midbrain, which leads to a significant reduction in DA content in the striatum and causes the disease. The exact cause of this pathological change is still unclear. Genetic factors, environmental factors, age, oxidative stress, etc. may all be involved in the degeneration and death process of dopaminergic neurons in PD.
  • DA dopamine
  • Parkinson's disease mainly relies on medical history, clinical symptoms and signs. According to the characteristics of insidious onset and gradual progression, unilateral involvement progresses to the contralateral side, manifesting as resting tremor and slow movement. Clinical diagnosis can be made by excluding atypical Parkinson's disease-like symptoms. Effective treatment with levodopa preparations further supports the diagnosis. Routine blood and cerebrospinal fluid examinations were mostly normal. Head CT and MRI also showed no characteristic changes. Olfactory examination can often reveal that patients with PD have hyposmia. Functional PET imaging of dopa uptake using 18F-dopa as a tracer can show reduced dopamine transmitter synthesis.
  • Dopamine transporter (DAT) functional imaging using 125I- ⁇ -CIT and 99mTc-TRODAT-1 as tracers can show a decrease in the number of DAT, which can be shown to be reduced in the early or even subclinical stages of the disease, which can support diagnosis.
  • this inspection is relatively expensive and has not yet been performed routinely.
  • An implantable neurostimulation system (a type of neurostimulation system) mainly includes a stimulator implanted in the body (i.e., an implantable neurostimulator, a type of neurostimulator) and a programmable device installed outside the patient's body.
  • Existing neuromodulation technology mainly implants electrodes into specific structures (i.e. target points) in the body through stereotaxic surgery, and the stimulator implanted in the patient's body sends electrical pulses to the target point through the electrodes to regulate the corresponding neural structures and networks. electrical activity and its functions, thereby improving symptoms and relieving pain.
  • the stimulator can be an implantable nerve electrical stimulation device, an implantable cardiac electrical stimulation system (also known as a pacemaker), an implantable drug delivery system (IDDS for short) and a lead switch. any of the connecting devices.
  • Implantable neuroelectric stimulation devices include, for example, Deep Brain Stimulation (DBS), Cortical Nerve Stimulation (CNS), and Spinal Cord Stimulation. , referred to as SCS), implantable sacral nerve electrical stimulation System (Sacral Nerve Stimulation, referred to as SNS), implantable vagus nerve stimulation system (Vagus Nerve Stimulation, referred to as VNS), etc.
  • the stimulator can include IPG, extension wires and electrode wires.
  • the IPG implantable pulse generator
  • the IPG is placed in the patient's body and relies on sealed batteries and circuits to provide controllable electrical stimulation energy to the tissues in the body through the implanted Extension wires and electrode leads provide one or two channels of controllable specific electrical stimulation energy to specific areas of tissue in the body.
  • the extension lead is used in conjunction with the IPG as a transmission medium for electrical stimulation signals to transmit the electrical stimulation signals generated by the IPG to the electrode leads.
  • the electrode leads transmit the electrical stimulation signals generated by the IPG through multiple electrode contacts to release electrical stimulation energy to specific areas of the body tissue; the implantable medical device has one or more electrode leads on one or both sides, so A plurality of electrode contacts are provided on the electrode lead, and the electrode contacts may be uniformly or non-uniformly arranged in the circumferential direction of the electrode lead. As an example, the electrode contacts are arranged in an array of 4 rows and 3 columns (12 electrode contacts in total) in the circumferential direction of the electrode wire.
  • the electrode contacts may include stimulation electrode contacts and/or collection electrode contacts.
  • the electrode contacts may be in the shape of, for example, a sheet, a ring, a dot, or the like.
  • the stimulated internal tissue may be the patient's brain tissue, and the stimulated site may be a specific part of the brain tissue.
  • the stimulated parts are generally different, the number of stimulation contacts used (single source or multiple sources), one or more channels (single channel or multi-channel) specific electrical stimulation signals
  • the application and stimulation parameter data are also different. This application does not limit the applicable disease types, which can be the disease types applicable to deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation.
  • DBS deep brain stimulation
  • SCS spinal cord stimulation
  • pelvic stimulation gastric stimulation
  • peripheral nerve stimulation and functional electrical stimulation.
  • DBS diseases that DBS can be used to treat or manage
  • diseases include, but are not limited to: spastic diseases (eg, epilepsy), pain, migraine, mental illness (eg, major depressive disorder (MDD)), bipolar disorder, anxiety disorder, Post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental status disorders, mobility disorders (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease Alzheimer's disease, substance addiction, autism, or other neurological or psychiatric diseases and impairments.
  • spastic diseases eg, epilepsy
  • pain migraine
  • mental illness eg, major depressive disorder (MDD)
  • bipolar disorder e.g., anxiety disorder, Post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD)
  • OCD obsessive-compulsive disorder
  • behavioral disorders e.g., essential tremor or Parkinson'
  • the program-controlled device when the program-controlled device and the stimulator establish a program-controlled connection, can be used to adjust the stimulation parameters of the stimulator's electrical stimulation signal, and the stimulator can also be used to sense the bioelectrical activity in the deep brain of the patient, and the sensed The bioelectric activity continues to adjust the stimulation parameters of the electrical stimulation signal of the stimulator.
  • the stimulation parameters of the electrical stimulation signal may include frequency (for example, the electrical stimulation pulse signal within 1 s per unit time). number, unit is Hz), pulse width (duration of each pulse, unit is ⁇ s), amplitude (generally expressed in voltage, that is, the intensity of each pulse, unit is V), timing (for example, it can be continuous or trigger), stimulation mode (including one or more of current mode, voltage mode, timing stimulation mode and cyclic stimulation mode), physician control upper and lower limits (doctor-adjustable range) and patient control upper and lower limits (patient one or more of the ranges that can be adjusted independently). any one or more of them.
  • various stimulation parameters of the stimulator can be adjusted in current mode or voltage mode.
  • the programmable device can be a doctor programmer (that is, a programmer used by doctors) or a patient programmer (that is, a programmer used by patients).
  • the doctor's program controller can be, for example, a tablet computer, a laptop computer, a desktop computer, a mobile phone and other intelligent terminal devices equipped with program control software.
  • the patient program controller can be, for example, a tablet computer, a notebook computer, a desktop computer, a mobile phone and other intelligent terminal devices equipped with program control software.
  • the patient program controller can also be other electronic devices with program control functions (such as chargers, data sets with program control functions). collection equipment).
  • This application does not limit the data interaction between the doctor's programmer and the stimulator.
  • the doctor's programmer can interact with the stimulator through the server and the patient's programmer.
  • the doctor's programmer can interact with the stimulator through the patient's programmer, and the doctor's programmer can also directly interact with the stimulator.
  • the patient programmer can also interact directly with the stimulator.
  • the patient programmer may include a host (in communication with the server) and a slave (in communication with the stimulator), the host and slave being communicatively connected.
  • the doctor program controller can interact with the server through 3G/4G/5G network/wired network/wireless network
  • the server can interact with the host through 3G/4G/5G network/wired network/wireless network
  • the host can interact with the host through Bluetooth.
  • Protocol/WIFI protocol/USB protocol for data interaction with the handset.
  • the handset can interact with the stimulator through the 401MHz-406MHz working frequency band/2.4GHz-2.48GHz working frequency band.
  • the doctor programmable controller can interact with the stimulator through the 401MHz-406MHz working frequency band/2.4
  • the GHz-2.48GHz working frequency band directly interacts with the stimulator.
  • the patient programmer can directly interact with the stimulator through the 401MHz-406MHz operating frequency band/2.4GHz-2.48GHz operating frequency band.
  • Figure 1 shows a structural block diagram of a medical system provided by this application.
  • the medical system 100 includes:
  • Camera 101 is used to collect video data of each designated action performed by the patient
  • Control device 102 the control device performs data interaction with the camera 101, and the control device
  • the device 102 is configured to implement the steps of the control method.
  • the camera 101 in this application is, for example, an optical camera and/or an infrared camera.
  • the medical system 100 may further include a stimulator 103 implanted in the patient's body, where the stimulator 103 is used to release electrical stimulation energy to the patient's body tissue.
  • the control device 102 may be a program-controlled device, and the program-controlled device may include, for example, one or more of a tablet computer, a laptop computer, a desktop computer, a mobile phone, and a smart wearable device.
  • Figure 2 is a schematic flow chart of a control method provided by this application
  • Figure 3 is a schematic flow chart of obtaining intermediate diagnosis results provided by this application.
  • control methods include:
  • Step S101 Obtain video data of each designated action performed by the patient, where the video data includes multiple frames of images to be processed;
  • Step S102 Based on the video data of each designated action, obtain the intermediate diagnosis results corresponding to each designated action;
  • Step S103 Obtain the Parkinson's diagnosis result of the patient based on the intermediate diagnosis result corresponding to each designated action, and the Parkinson's diagnosis result is used to indicate the severity of Parkinson's disease;
  • the process of obtaining the intermediate diagnosis results corresponding to the specified action includes:
  • Step S201 Obtain the designated part corresponding to the designated action
  • Step S202 Obtain one or more part images of non-specified parts from each frame of the image to be processed.
  • the non-specified parts are parts other than the specified part.
  • the display content of the image to be processed includes at least one Designated parts and at least one non-designated part;
  • Step S203 Based on the multi-frame part images of each of the non-specified parts, obtain the location diagnosis result of each of the non-specified parts;
  • Step S204 Based on the site diagnosis result of each non-specified site, obtain the intermediate diagnosis result corresponding to the designated action.
  • the process of obtaining the patient's Parkinson's diagnosis result is: (video data of each specified action performed by the patient) ⁇ intermediate diagnosis result (corresponding to non-specified actions) ⁇ patient's Parkinson's diagnosis result;
  • the process of obtaining the intermediate diagnosis results of the specified action is: determining the specified Part ⁇ intercept part images of non-specified parts ⁇ obtain the part diagnosis results of each non-specified part ⁇ obtain the intermediate diagnosis results of the corresponding specified actions.
  • the part diagnosis result can indicate that the part is in a normal state or an abnormal state, and can also use scores or grades to indicate the part in a more refined manner.
  • the degree of normality (for example, a higher score or level indicates a more normal part, while a lower score or level indicates an abnormal part), combined with the location diagnosis results of each non-specified part, the intermediate diagnosis result corresponding to the corresponding specified action is obtained.
  • the intermediate diagnosis result can indicate the performance of the specified action.
  • the patient's Parkinson's diagnosis result can be obtained.
  • the Parkinson's diagnosis result can indicate the severity of the patient's Parkinson's disease. .
  • this application refers to the site diagnosis results of each non-specified site instead of the site diagnosis results of the designated site. This is because this application takes into account the patient's When doing a certain movement, such as pointing fingers, because all the attention is focused on pointing fingers, the control of fingers and wrists is quite different from the usual natural state. This application does the opposite. In practice, observe whether the patient's legs shake when pointing fingers, whether he can walk in a straight line, and other items that have nothing to do with the hands. In this way, the patient's true state can be better reflected, and the obtained intermediate diagnosis results can more accurately reflect the patient's condition. Action performance for the specified action.
  • the intermediate diagnostic results corresponding to each designated action When assessing the severity of a patient's Parkinson's disease, reference is made to the intermediate diagnostic results corresponding to each designated action. That is to say, the whole-body video of the patient performing different designated actions can be obtained separately, and combined with the corresponding results of the different designated actions.
  • the intermediate diagnosis results comprehensively evaluate the severity of the patient's Parkinson's disease. Compared with the diagnosis results that are limited to a certain specified action, the Parkinson's diagnosis results of this application can more accurately reflect the patient's condition.
  • the video data may be whole-body video data or partial video data of the patient, and accordingly, the image to be processed may be a whole-body image or partial image of the patient.
  • the display content of the image to be processed includes at least one designated part and at least one non-designated part.
  • Whole-body video data refers to video data that can capture the patient's entire body.
  • whole-body images refer to images in which the patient's entire body appears.
  • Partial video data refers to video data that can capture part of the patient's body.
  • partial images refer to images in which part of the patient's body appears.
  • the interactive device can be used to indicate prompt information, and the patient can perform corresponding designated actions under the prompts of the prompt information, and the camera can be used to collect video data of the patient making each designated action.
  • Interactive devices may include audio playback devices, video playback devices, display devices, etc.
  • prompt information may include one or more of video information, audio information, picture information, and text information. Specifically, it may be a " Please raise your right hand" audio message, or a video message of cartoon characters doing pointing movements.
  • the specified action may be a preset action or may be specified by a doctor.
  • monitoring equipment can be used for monitoring to obtain the patient's video data within a preset time period, and intercept the video data of each specified action made by the patient.
  • the default duration is, for example, 1 day, a week or a month.
  • the patient is not prescribed in advance to perform a specific action.
  • the behaviors performed by the patient are all daily behaviors, such as getting up from the bed, walking to the door, picking up a water cup to drink, sitting on a chair and playing with a mobile phone, etc. Behavior.
  • the specified action is walking in a straight line, you can focus on the video data of the patient walking.
  • step S201 may include:
  • the designated part corresponding to the designated action is obtained.
  • the correspondence between action types and parts can be established in advance.
  • the action type of a specified action corresponds to multiple specified parts (for example, the action type of pointing generally corresponds to the left hand and right hand)
  • multiple specified parts can be Specify parts for separate diagnosis. This can be done in batches.
  • image processing is performed on one of the designated parts to obtain the part diagnosis results.
  • the part diagnosis results of multiple designated parts are obtained respectively, further improving the The degree of intelligence improves the user experience.
  • This application does not limit the action type of the specified action.
  • it can be finger pointing, making a fist, raising a hand, raising the arm (making the arm perpendicular to the trunk), walking in a straight line, walking in a curve, etc.
  • the action type of pointing can include pointing fingers with the left hand and pointing with the right hand.
  • the action type of making a fist can include making a fist with the left hand and making a fist with the right hand.
  • the action type of raising a hand can include raising the left hand and raising the right hand.
  • the action type of raising the arm can include Including raising the left arm and raising the right arm.
  • Walking in a straight line can include walking in a straight line for 30 steps and walking in a straight line for 10 steps.
  • walking in a curve can include walking in a circle, walking in a semicircle, walking in an S-shape, etc.
  • the specified part corresponding to the specified action can be obtained based on the action type of the specified action and the first correspondence relationship.
  • the first correspondence relationship may be a correspondence relationship between action types and parts, and the first correspondence relationship may adopt a part mapping table.
  • the action type of pointing fingers can correspond to the two parts of the left hand and the right hand
  • the action type of making a fist can correspond to the two parts of the left hand and the right hand
  • the action type of raising the hand can correspond to the left arm and the right arm.
  • the action type of raising the arm can correspond to the left arm and the right arm.
  • the action type of walking in a straight line can correspond to the left leg and the right leg.
  • the action type of walking in a preset curve can correspond to the left leg. and two parts of the right leg.
  • the site diagnosis result can indicate whether the site is in a normal or abnormal state, and can also use scores or grades to more accurately indicate the degree of abnormality of the site (for example, a higher score or grade indicates a more abnormal site, and a lower score or grade means the site is more abnormal. Indicates that the part is normal).
  • the intermediate diagnosis results corresponding to the specified action can be used to indicate the performance of the specified action, for example: excellent performance, good performance, poor performance, extremely poor performance. Scores or grades can also be used to indicate the specified action in a more detailed manner. performance (for example, the higher the score or level, the worse the performance of the specified action).
  • the patient's Parkinson's disease diagnosis result can indicate the severity of the patient's Parkinson's disease. For example, it can indicate that the patient's Parkinson's disease is mild, moderate, or severe. Scores or grades can also be used to more accurately indicate the severity of the disease. degree (for example, higher scores and levels indicate a more severe condition, while lower scores and levels indicate a milder condition).
  • the part diagnosis result can be expressed by the part diagnosis score.
  • the higher the score the more abnormal the part is.
  • the intermediate diagnosis result corresponding to the specified action can be expressed by the intermediate diagnosis score.
  • the higher the score the more abnormal the performance of the specified action. Poor, the patient's Parkinson's diagnosis result can be expressed by the Parkinson's Diagnostic Score. The higher the score, the more serious the condition.
  • the part diagnostic score of the non-specified part can be used as the intermediate diagnostic score of the corresponding specified action
  • the intermediate diagnostic score of the corresponding designated action may be the average of the part diagnostic scores of these non-specified parts.
  • the intermediate diagnostic score of the specified action can be used as the patient's Parkinson's diagnosis score.
  • the patient's Parkinson's diagnostic score may be the average of the median diagnostic scores of the specified actions.
  • the designated actions include pointing fingers and walking in a straight line.
  • the designated parts are the left hand and right hand, and the non-designated parts include the left leg and right leg.
  • the whole-body video of the patient Xiao Li doing finger pointing and obtain the part images of the left leg and the right leg from the corresponding images to be processed.
  • the part diagnosis score of the left leg is 30, and for the right leg
  • the designated parts are the left leg and the right leg, and the non-designated parts include the left hand and the right hand.
  • step S103 may include:
  • the patient's Parkinson's diagnosis result is obtained.
  • the difficulty coefficient can be used to indicate the difficulty of completing the specified action.
  • the difficulty coefficient can be expressed as a number. The higher the value, the more difficult it is to complete the specified action.
  • the difficulty coefficient is, for example, 0.8, 1.1 or 1.5.
  • step S203 may include:
  • the multi-frame part images of each of the non-specified parts are respectively input into the corresponding part diagnosis model to obtain the part diagnosis result of each of the non-specified parts.
  • the parts corresponding to the part can be Related) multi-frame part images are input into the part diagnosis model corresponding to the part, and the part diagnosis model is used to (automatically) output the part diagnosis result of the part.
  • the diagnosis efficiency is high and the level of intelligence is high.
  • step S302 may include:
  • the multi-frame part images of the designated part are input into the corresponding part diagnosis model to obtain the part diagnosis result of the designated part.
  • multiple frames of part images corresponding to the part can be input into the part diagnosis model corresponding to the part, and the part diagnosis model can be used to (automatically) output the image of the part.
  • Part diagnosis model refers to a part diagnosis model corresponding to each part. For example, input multi-frame part images of the hand into the part diagnosis model corresponding to the hand, input multi-frame part images of the arm into the part diagnosis model corresponding to the arm, and input multi-frame part images of the leg into the part corresponding to the leg.
  • the diagnosis model inputs the multi-frame part images of the trunk into the corresponding part diagnosis model of the trunk.
  • This application does not limit the acquisition method of the part diagnosis model. In some possible ways, this application can train the part diagnosis model, and in other possible ways, this application can use a pre-trained part diagnosis model.
  • a corresponding part diagnosis model is set for each part.
  • a part diagnosis model corresponding to the hand also called a hand diagnosis model
  • a part diagnosis model also called a hand diagnosis model
  • a part diagnosis model also called a hand diagnosis model
  • a part diagnosis model corresponding to the arm is set for the arm.
  • an arm diagnostic model a part diagnostic model corresponding to the leg
  • a part diagnostic model corresponding to the trunk is set for the torso.
  • the part diagnosis model corresponding to each part can be trained using the following training process:
  • each training data in the second training set includes multi-frame part images of the part used for training and annotation data of part diagnosis results of the part corresponding to the training data;
  • the part diagnosis model can be trained by a large amount of training data, and can predict the part diagnosis results of each part based on different input data. It has a wide range of applications and a high level of intelligence.
  • this application can use the above training process to train and obtain a part diagnosis model. In other possible ways, this application can use a pre-trained part diagnosis model.
  • This application does not limit the method of obtaining annotated data.
  • manual annotation, automatic annotation, or semi-automatic annotation may be used.
  • This application does not limit the training process of the part diagnosis model.
  • the training method of the above-mentioned supervised learning may be used, or the training method of semi-supervised learning may be used, or the training method of unsupervised learning may be used.
  • This application does not limit the preset second training end condition, which may be, for example, that the number of training times reaches a preset number of times (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), Or it can be that all the training data in the second training set have completed one or more trainings, or it can be that the total loss value obtained in this training is not greater than the preset loss value.
  • Figure 4 is a schematic flowchart of another method of obtaining intermediate diagnosis results provided by an embodiment of the present application.
  • step S204 may include:
  • Step S301 Intercept the part image of the designated part from the image to be processed in each frame;
  • Step S302 Obtain the site diagnosis result of the designated site based on the multi-frame site images of the designated site;
  • Step S303 Obtain the intermediate diagnosis result corresponding to the designated action based on the site diagnosis result and the first weight of each non-specified site and the site diagnosis result and the second weight of the designated site, wherein the first The weight is greater than the second weight, or the first weight is equal to the second weight, or the first weight is less than the second weight.
  • the site diagnosis results of non-specified sites have a greater impact on the intermediate diagnosis results;
  • the weight given to the site diagnosis results of non-specified sites and the site diagnosis results of designated sites can be equal, and both have the same impact on the intermediate diagnosis results; on the other hand, the site diagnosis results of non-specified sites can be given a lower weight.
  • the first weight is given to the site diagnosis result of the specified site with a higher second weight, and the site diagnosis result of the designated site has a greater impact on the intermediate diagnosis result.
  • the first weight and the second weight can be expressed by numbers or percentages. The higher the value, the greater the weight.
  • the first weight is, for example, 70%
  • the second weight is, for example, 30%. .
  • the method may also include:
  • the display device is used to display the rehabilitation training video corresponding to the designated part.
  • the intermediate diagnosis result corresponding to the specified action indicates that the patient needs to perform rehabilitation training for the specified part, indicating that the patient's performance for the specified action is poor.
  • the display device can be used to display the rehabilitation training video corresponding to the specified part, which is useful for many patients. For example, after seeing a doctor in the hospital, you can only get a professional diagnosis report, but the patient does not know how to improve his condition through his own efforts and can only passively accept treatment.
  • This application displays the rehabilitation training video corresponding to the designated part through the display device. It helps to guide patients to carry out targeted training and improve the patient experience.
  • the intermediate diagnosis result corresponding to the specified action can be represented by an intermediate diagnosis score.
  • the intermediate diagnosis score corresponding to the specified action is not less than a preset score threshold, the specified The intermediate diagnosis result corresponding to the action indicates that the patient needs to perform rehabilitation training for the designated part.
  • the preset score threshold is, for example, 70, 75, or 80.
  • the method may also include:
  • the stimulator is controlled to release corresponding electrical stimulation energy.
  • data can be interacted with the patient's stimulator to realize program control functions.
  • the stimulator can be controlled to release the corresponding electrical stimulation energy.
  • reference configuration information is used to indicate stimulation parameters of the stimulator.
  • the stimulation parameters of the stimulator may include at least one of the following: frequency (for example, the number of electrical stimulation pulse signals per unit time 1 s, in Hz), pulse width (duration of each pulse, in ⁇ s), amplitude (Generally expressed in terms of voltage, that is, the intensity of each pulse, in V), stimulation mode (including one or more of current mode, voltage mode, timing stimulation mode and cyclic stimulation mode), upper and lower limits controlled by the doctor ( The range that the doctor can adjust) and the upper and lower limits of patient control (the range that the patient can adjust independently).
  • frequency for example, the number of electrical stimulation pulse signals per unit time 1 s, in Hz
  • pulse width duration of each pulse, in ⁇ s
  • amplitude Generally expressed in terms of voltage, that is, the intensity of each pulse, in V
  • stimulation mode including one or more of current mode, voltage mode, timing stimulation mode and cyclic stimulation mode
  • upper and lower limits controlled by the doctor The range that the doctor can adjust
  • the upper and lower limits of patient control the range that the patient can adjust
  • various stimulation parameters of the stimulator can be adjusted in current mode or voltage mode.
  • the stimulation parameter identification can be represented by at least one of Chinese characters, letters, numbers, symbols and special symbols. For example “A01”, “Amplitude” or "#01".
  • the configuration parameters of the stimulator include: the stimulation mode is voltage mode, the frequency is 130Hz, the pulse width is 60 ⁇ s, and the amplitude is 3V.
  • the process of obtaining the reference configuration information corresponding to the stimulator may include:
  • the reference configuration information corresponding to the stimulator is obtained.
  • the stimulation parameters of the stimulator can also include identification of stimulation contacts. That is to say, according to the intermediate diagnosis results corresponding to each specified action, the corresponding stimulation contacts can be selected to provide patients with accurate electrical stimulation. Stimulate.
  • the designated actions include pointing fingers and walking in a straight line, where the intermediate diagnosis result corresponding to the pointing action is "normal", and the intermediate diagnosis result corresponding to the straight walking action is "mild abnormal”.
  • the reference configuration of the stimulator The information is "stimulation contact a, voltage mode, frequency is 100Hz, pulse width is 50 ⁇ s and amplitude is 2V".
  • the process of obtaining the reference configuration information corresponding to the stimulator may include:
  • the patient's Parkinson's diagnosis results can reflect the severity of the patient's overall Parkinson's disease.
  • the patient can be provided with electrocardiograms suitable for different parts. Stimulate.
  • the process of obtaining the reference configuration information corresponding to the stimulator may further include:
  • the training process of the reference configuration model includes:
  • the first training set including a plurality of first training data, each of the first training data including a Parkinson's diagnosis result of a sample object and annotation data of the reference configuration information of the sample object;
  • the preset first deep learning model can be obtained.
  • the learning and tuning of the model establishes the functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can be as close as possible to the realistic correlation relationship, thus training
  • the obtained reference configuration model can obtain the reference configuration information corresponding to the stimulator based on the patient's Parkinson's diagnosis results, and the calculation results are highly accurate and reliable.
  • This application does not limit the method of obtaining the annotated data.
  • manual annotation, automatic annotation, or semi-automatic annotation may be used.
  • This application does not limit the training process of the reference configuration model.
  • it may adopt the above-mentioned supervised learning training method, or may adopt the semi-supervised learning training method, or may adopt the unsupervised learning training method.
  • This application does not limit the preset first training end condition, which may be, for example, that the number of training times reaches a preset number of times (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), Or it can be that all the training data in the first training set have completed one or more trainings, or it can be that the total loss value obtained in this training is not greater than the preset loss value.
  • the process of obtaining the reference configuration information corresponding to the stimulator may further include:
  • the second correspondence relationship may be a correspondence relationship between Parkinson's diagnosis results and reference configuration information, and the second correspondence relationship may adopt a reference configuration mapping table.
  • the corresponding reference configuration information is "the frequency is 200 Hz, the pulse width is 80 ⁇ s, and the amplitude is 4V”;
  • the corresponding reference configuration information is "frequency is 100Hz, pulse width is 50 ⁇ s, and amplitude is 2V".
  • This application also provides a control device, the specific manner of which is consistent with the possible ways and achieved technical effects described in the possible ways of the above method, and some of the contents will not be described again.
  • the control device is configured to:
  • the patient's Parkinson's diagnosis results are obtained.
  • the Parkinson's disease diagnosis result is used to indicate the severity of Parkinson's disease
  • the process of obtaining the intermediate diagnosis results corresponding to the specified action includes:
  • One or more part images of non-specified parts are intercepted from each frame of the image to be processed.
  • the non-specified parts are parts other than the specified part.
  • the display content of the image to be processed includes at least one designated part and At least one non-designated site;
  • an intermediate diagnosis result corresponding to the designated action is obtained.
  • control device is further configured to obtain the location diagnosis results of each of the non-specified parts in the following manner:
  • the multi-frame part images of each of the non-specified parts are respectively input into the corresponding part diagnosis model to obtain the part diagnosis result of each of the non-specified parts.
  • control device is further configured to obtain the intermediate diagnosis results corresponding to the specified action in the following ways:
  • an intermediate diagnosis result corresponding to the designated action is obtained, wherein the first weight is greater than the site diagnosis result and the second weight.
  • the second weight, or the first weight is equal to the second weight, or the first weight is smaller than the second weight.
  • control device is further configured to obtain the site diagnosis result of the specified site in the following manner:
  • the multi-frame part images of the designated part are input into the corresponding part diagnosis model to obtain the part diagnosis result of the designated part.
  • control device is also configured to:
  • the display device is used to display the rehabilitation training video corresponding to the designated part.
  • control device performs data interaction with the stimulator implanted in the patient's body, and the control device is further configured to:
  • the stimulator is controlled to release corresponding electrical stimulation energy.
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following ways:
  • the reference configuration information corresponding to the stimulator is obtained.
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following ways:
  • control device is further configured to obtain reference configuration information corresponding to the stimulator in the following ways:
  • the training process of the reference configuration model includes:
  • the first training set including a plurality of first training data, each of the first training data including a Parkinson's diagnosis result of a sample object and annotation data of the reference configuration information of the sample object;
  • control device is further configured to obtain Get the specified part corresponding to the specified action:
  • the designated part corresponding to the designated action is obtained.
  • FIG. 5 shows a structural block diagram of a control device 200 provided by this application.
  • the control device 200 may include, for example, at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.
  • Memory 210 may include readable media in the form of volatile memory, such as random access memory (RAM) 211 and/or cache memory 212, and may further include read only memory (ROM) 213.
  • RAM random access memory
  • ROM read only memory
  • the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 realizes the function of any of the above-mentioned control devices, and the specific manner is the same as the possible manner described in the possible manners of the above method. The technical effects achieved are the same, and some contents will not be repeated again.
  • Memory 210 may also include a utility 214 having at least one program module 215, such program modules 215 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some of these examples. This combination may include the implementation of a network environment.
  • the processor 220 can execute the above-mentioned computer program, and can execute the utility tool 214.
  • the processor 220 may use one or more application specific integrated circuits (ASIC, Application Specific Integrated Circuit), DSP, programmable logic device (PLD, Programmable Logic Device), complex programmable logic device (CPLD, Complex Programmable Logic Device), on-site Programmable gate array (FPGA, Field-Programmable Gate Array) or other electronic components.
  • ASIC Application Specific Integrated Circuit
  • DSP digital signal processor
  • PLD programmable logic device
  • CPLD Complex Programmable logic device
  • FPGA Field-Programmable Gate Array
  • Bus 230 may be a local bus representing one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or any bus structure using a variety of bus structures.
  • the control device 200 may also communicate with one or more external devices 240, such as a keyboard, a pointing device, a Bluetooth device, etc., and may also communicate with one or more devices capable of interacting with the control device 200, and/or with the control device 200.
  • 200 is any device capable of communicating with one or more other computing devices (eg, router, modem, etc.). This communication may occur through the input/output interface 250.
  • the control device 200 may also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 260.
  • Network adapter 260 may communicate with other modules of control device 200 via bus 230.
  • control device 200 may be used in conjunction with the control device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.
  • This application also provides a computer-readable storage medium that stores a computer program.
  • the computer program When the computer program is executed by a processor, it can realize the function of any of the above control devices or the steps of the above control method.
  • the specific methods are consistent with the possible methods and the technical effects achieved described in the possible methods of controlling the equipment above, and some of the contents will not be repeated.
  • Figure 6 shows a schematic structural diagram of a program product 300 for implementing a control method provided by this application.
  • the program product 300 may be in the form of a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer.
  • the program product 300 of the present invention is not limited thereto.
  • the readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device.
  • Program product 300 may take the form of any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, 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.
  • a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave carrying the readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a readable storage medium may also be any readable medium that can transmit, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code contained on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.
  • Program code for performing the operations of the present invention may be written in any combination of one or more programming languages.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.
  • the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (such as an Internet service provider) through the Internet. ).
  • LAN local area network
  • WAN wide area network
  • an external computing device such as an Internet service provider

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Psychiatry (AREA)
  • Computational Linguistics (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

本申请提供了一种控制设备、医疗系统及计算机可读存储介质，所述控制设备被配置成：获取患者做出每种指定动作的视频数据；基于每种所述指定动作的视频数据，获取每种所述指定动作对应的中间诊断结果；基于每种所述指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结果；其中，获取中间诊断结果的过程包括：获取所述指定动作对应的指定部位；从每帧所述待处理图像中截取得到一个或多个非指定部位的部位图像；基于每个所述非指定部位的多帧部位图像，获取每个所述非指定部位的部位诊断结果；基于每个所述非指定部位的部位诊断结果，获取所述指定动作对应的中间诊断结果。本申请的帕金森诊断结果可以准确反映患者的病情。

Description

控制设备、医疗系统及计算机可读存储介质
本申请要求于2022年7月1日提交的申请号为202210767505.5的中国专利的优先权，上述中国专利通过全文引用的形式并入。
技术领域
本申请涉及植入式器械、远程程控、物联网、深度学习和帕金森诊断的技术领域，例如涉及控制设备、医疗系统及计算机可读存储介质。
背景技术
随着科技发展和社会进步，患者渴望通过各种治疗手段来提高生命质量，其中植入式器械的应用前景非常广阔。植入式器械是指借助手术全部或者部分进入人体内或腔道(口)中，或者用于替代人体上皮表面或眼表面，并且在手术过程结束后留在人体内30日(含)以上或者被人体吸收的医疗器械。包含程控设备和植入式器械的植入式医疗系统，能够为患者提供参数可控的精细化治疗，在市场上受到众多消费者的欢迎。
专利CN113362946A公开了一种视频处理装置、电子设备及计算机可读存储介质，所述视频处理装置应用于电子设备，所述电子设备分别与显示屏、摄像头和医生设备进行数据交互，所述电子设备用于对患有帕金森病的患者的视频进行数据处理；所述装置包括：提示显示模块，用于利用所述显示屏显示至少一种指定动作的提示信息；视频采集模块，用于利用所述摄像头采集所述患者的视频；动作预测模块，用于将所述患者的视频输入帕金森检测模型，预测得到所述患者的动作信息并发送至所述医生设备，所述动作信息至少包括其中一种指定动作的幅度和/或频率；信息获取模块，用于获取所述患者的疾病信息；建议策略模块，用于基于所述患者的疾病信息和动作信息，获取所述患者的建议程控策略并发送至所述医生设备。该装置帮助医生定量地了解到患者在运动过程中的局部体态和运动表现情况，但是这种方式只检测患者的局部动作，当患者做出指定动作时，由于注意力集中在指定动作上，表现出来的状态可能不是真实状态，这种局部的检测结果不能反映患者的真实病情。
因此，亟需提供控制设备、医疗系统及计算机可读存储介质，解决相关技术存在的问题。
发明内容
本申请的目的在于提供控制设备、医疗系统及计算机可读存储介质，通过中间诊断结果反映出患者的真实状态，准确地反映患者针对该指定动作的动作表现情况。
本申请的目的采用以下技术方案实现：
第一方面，本申请提供了一种控制设备，所述控制设备被配置成：
获取患者做出每种指定动作的视频数据，所述视频数据包括多帧待处理图像；
基于每种所述指定动作的视频数据，获取每种所述指定动作对应的中间诊断结果；
基于每种所述指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结果，所述帕金森诊断结果用于指示帕金森病的严重程度；
其中，获取所述指定动作对应的中间诊断结果的过程包括：
针对每种所述指定动作的视频数据，执行以下处理：
获取所述指定动作对应的指定部位；
从每帧所述待处理图像中截取得到一个或多个非指定部位的部位图像，所述非指定部位是所述指定部位以外的部位，所述待处理图像的显示内容包括至少一个指定部位和至少一个非指定部位；
基于每个所述非指定部位的多帧部位图像，获取每个所述非指定部位的部位诊断结果；
基于每个所述非指定部位的部位诊断结果，获取所述指定动作对应的中间诊断结果。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取每个所述非指定部位的部位诊断结果：
将每个所述非指定部位的多帧部位图像分别输入对应的部位诊断模型，得到每个所述非指定部位的部位诊断结果。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所 述指定动作对应的中间诊断结果：
从每帧所述待处理图像中截取得到所述指定部位的部位图像；
基于所述指定部位的多帧部位图像，获取所述指定部位的部位诊断结果；
基于每个所述非指定部位的部位诊断结果和第一权重以及所述指定部位的部位诊断结果和第二权重，获取所述指定动作对应的中间诊断结果，其中，所述第一权重大于所述第二权重，或者，所述第一权重等于所述第二权重，或者，所述第一权重小于所述第二权重。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所述指定部位的部位诊断结果：
将所述指定部位的多帧部位图像输入对应的部位诊断模型，得到所述指定部位的部位诊断结果。
在一些可选的实施例中，所述控制设备还被配置成：
当所述指定动作对应的中间诊断结果指示所述患者需要进行针对所述指定部位的康复训练时，利用显示设备显示所述指定部位对应的康复训练视频。
在一些可选的实施例中，所述控制设备与植入于所述患者体内的刺激器进行数据交互，所述控制设备还被配置成：
获取所述刺激器对应的参考配置信息；
基于所述参考配置信息，控制所述刺激器释放对应的电刺激能量。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
基于每种所述指定动作对应的中间诊断结果，获取所述刺激器对应的参考配置信息。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
基于所述患者的帕金森诊断结果，获取所述刺激器对应的参考配置信息。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
将所述患者的帕金森诊断结果输入参考配置模型，得到所述刺激器对应的参考配置信息；
其中，所述参考配置模型的训练过程包括：
获取第一训练集，所述第一训练集包括多个第一训练数据，每个所述第一训练数据包括一个样本对象的帕金森诊断结果以及所述样本对象的参考配置信息的标注数据；
针对所述第一训练集中的每个第一训练数据，执行以下处理：
将所述第一训练数据中的样本对象的帕金森诊断结果输入预设的第一深度学习模型，得到所述样本对象的参考配置信息的预测数据；
基于所述样本对象的参考配置信息的预测数据和标注数据，对所述第一深度学习模型的模型参数进行更新；
检测是否满足预设的第一训练结束条件；如果是，则将训练出的第一深度学习模型作为所述参考配置模型；如果否，则利用下一个所述第一训练数据继续训练所述第一深度学习模型。
在一些可选的实施例中，所述控制设备被进一步配置成采用如下方式获取所述指定动作对应的指定部位：
获取所述指定动作的动作类型；
基于所述指定动作的动作类型，获取所述指定动作对应的指定部位。
第二方面，本申请提供了一种医疗系统，所述医疗系统包括摄像头和上述任一项控制设备，所述控制设备与所述摄像头进行数据交互；
所述摄像头用于采集患者做出每种指定动作的视频数据。
第三方面，本申请提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述任一项控制设备的功能。
采用本申请提供的控制设备、医疗系统及计算机可读存储介质，至少具有以下优点：
在获取指定动作对应的中间诊断结果时，参考的是每个非指定部位的部位诊断结果，而不是指定部位的部位诊断结果，这是因为，本申请考虑到患者在做某一种动作时，例如对指时，由于注意力全部放在对指这件事上，对手指和手腕的控制力与平时自然状态下是有较大差距的，本申请反其道而行之，观察患者在对指的时候腿抖不抖，能不能走直线等和手无关的项目，这样的话，更能反映出患 者的真实状态，得到的中间诊断结果能更准确地反映患者针对该指定动作的动作表现情况。
在评估患者的帕金森病的严重程度时，参考的是每种指定动作对应的中间诊断结果，也就是说，可以分别获取患者先后做不同的指定动作的全身视频，结合不同的指定动作对应的中间诊断结果，综合评估患者的帕金森病的严重程度，相比于局限于某一种指定动作得到的病情诊断结果，本申请的帕金森诊断结果更能准确反映患者的病情。
附图说明
下面结合附图和实施例对本申请进一步说明。
图1是本申请实施例提供的一种医疗设备的结构框图。
图2是本申请提供的一种控制方法的流程示意图。
图3是本申请提供的一种获取中间诊断结果的流程示意图。
图4是本申请实施例提供的另一种获取中间诊断结果的流程示意图。
图5是本申请实施例提供的一种控制设备的结构框图。
图6是本申请实施例提供的一种用于控制方法的程序产品的结构示意图。
具体实施方式
下面，结合附图以及具体实施方式，对本申请做进一步描述，需要说明的是，在不相冲突的前提下，以下描述的各实施例之间或各技术特征之间可以任意组合形成新的实施例。
在本申请中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b或c中的至少一项(个)，可以表示：a，b，c，a和b，a和c，b和c，a和b和c，其中a、b和c可以是单个，也可以是多个。值得注意的是，“至少一项(个)”还可以解释成“一项(个)或多项(个)”。
还需说明的是，本申请中，“示例性的”或者“例如”等词用于表示作例子、例 证或说明。本申请中被描述为“示例性的”或者“例如”的任何实施方式或设计方案不应被解释为比其他实施方式或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
下面，首先对本申请的应用领域进行简单说明。
帕金森病(Parkinson’s disease，PD)是一种常见的神经系统变性疾病，老年人多见，平均发病年龄为60岁左右，40岁以下起病的青年帕金森病较少见。我国65岁以上人群PD的患病率大约是1.7％。大部分帕金森病患者为散发病例，仅有不到10％的患者有家族史。帕金森病最主要的病理改变是中脑黑质多巴胺(dopamine,DA)能神经元的变性死亡，由此而引起纹状体DA含量显著性减少而致病。导致这一病理改变的确切病因仍不清楚，遗传因素、环境因素、年龄老化、氧化应激等均可能参与PD多巴胺能神经元的变性死亡过程。
帕金森病的诊断主要依靠病史、临床症状及体征。根据隐袭起病、逐渐进展的特点，单侧受累进而发展至对侧，表现为静止性震颤和行动迟缓，排除非典型帕金森病样症状即可作出临床诊断。对左旋多巴制剂治疗有效则更加支持诊断。常规血、脑脊液检查多无异常。头CT、MRI也无特征性改变。嗅觉检查多可发现PD患者存在嗅觉减退。以18F-多巴作为示踪剂行多巴摄取功能PET显像可显示多巴胺递质合成减少。以125I-β-CIT、99mTc-TRODAT-1作为示踪剂行多巴胺转运体(DAT)功能显像可显示DAT数量减少，在疾病早期甚至亚临床期即可显示降低，可支持诊断。但此项检查费用较贵，尚未常规开展。
植入式神经刺激系统(一种神经刺激系统)主要包括植入体内的刺激器(即植入式神经刺激器，一种神经刺激器)以及设置于患者体外的程控设备。现有的神经调控技术主要是通过立体定向手术在体内特定结构(即靶点)植入电极，并由植入患者体内的刺激器经电极向靶点发放电脉冲，调控相应神经结构和网络的电活动及其功能，从而改善症状、缓解病痛。其中，刺激器可以是植入式神经电刺激装置、植入式心脏电刺激系统(又称心脏起搏器)、植入式药物输注装置(Implantable Drug Delivery System，简称I DDS)和导线转接装置中的任意一种。植入式神经电刺激装置例如是脑深部电刺激系统(Deep Brain Stimulation，简称DBS)、植入式脑皮层刺激系统(Cortical Nerve Stimulation，简称CNS)、植入式脊髓电刺激系统(Spinal Cord Stimulation，简称SCS)、植入式骶神经电刺激 系统(Sacral Nerve Stimulation，简称SNS)、植入式迷走神经电刺激系统(Vagus Nerve Stimulation，简称VNS)等。
刺激器可以包括IPG、延伸导线和电极导线，IPG(implantable pulse generator，植入式脉冲发生器)设置于患者体内，依靠密封电池和电路向体内组织提供可控制的电刺激能量，通过植入的延伸导线和电极导线，为体内组织的特定区域提供一路或两路可控制的特定电刺激能量。延伸导线配合IPG使用，作为电刺激信号的传递媒体，将IPG产生的电刺激信号，传递给电极导线。电极导线将IPG产生的电刺激信号，通过多个电极触点，向体内组织的特定区域释放电刺激能量；所述植入式医疗设备具有单侧或双侧的一路或多路电极导线，所述电极导线上设置有多个电极触点，所述电极触点可以均匀排列或者非均匀排列在电极导线的周向上。作为一个示例，所述电极触点以4行3列的阵列(共计12个电极触点)排列在电极导线的周向上。电极触点可以包括刺激电极触点和/或采集电极触点。电极触点例如可以采用片状、环状、点状等形状。
在一些可能的方式中，受刺激的体内组织可以是患者的脑组织，受刺激的部位可以是脑组织的特定部位。当患者的疾病类型不同时，受刺激的部位一般来说是不同的，所使用的刺激触点(单源或多源)的数量、一路或多路(单通道或多通道)特定电刺激信号的运用以及刺激参数数据也是不同的。本申请对适用的疾病类型不做限定，其可以是脑深部刺激(DBS)、脊髓刺激(SCS)、骨盆刺激、胃刺激、外周神经刺激、功能性电刺激所适用的疾病类型。其中，DBS可以用于治疗或管理的疾病类型包括但不限于：痉挛疾病(例如，癫痫)、疼痛、偏头痛、精神疾病(例如，重度抑郁症(MDD))、躁郁症、焦虑症、创伤后压力心理障碍症、轻郁症、强迫症(OCD)、行为障碍、情绪障碍、记忆障碍、心理状态障碍、移动障碍(例如，特发性震颤或帕金森氏病)、亨廷顿病、阿尔茨海默症、药物成瘾症、自闭症或其他神经学或精神科疾病和损害。当DBS用于治疗药物成瘾症患者时，可以帮助吸毒人员戒毒，提升他们的幸福感和生命质量。
本申请中，程控设备和刺激器建立程控连接时，可以利用程控设备调整刺激器的电刺激信号的刺激参数，也可以通过刺激器感测患者脑深部的生物电活动，并可以通过所感测到的生物电活动来继续调节刺激器的电刺激信号的刺激参数。
电刺激信号的刺激参数可以包括频率(例如是单位时间1s内的电刺激脉冲信 号个数，单位为Hz)、脉宽(每个脉冲的持续时间，单位为μs)、幅值(一般用电压表述，即每个脉冲的强度，单位为V)、时序(例如可以是连续或者触发)、刺激模式(包括电流模式、电压模式、定时刺激模式和循环刺激模式中的一种或多种)、医生控制上限及下限(医生可调节的范围)和患者控制上限及下限(患者可自主调节的范围)中的一种或多种。中的任意一种或多种。在具体应用中，可以在电流模式或者电压模式下对刺激器的各刺激参数进行调节。
程控设备可以是医生程控器(即医生使用的程控器)或者患者程控器(即患者使用的程控器)。医生程控器例如可以是搭载有程控软件的平板电脑、笔记本电脑、台式计算机、手机等智能终端设备。患者程控器例如可以是搭载有程控软件的平板电脑、笔记本电脑、台式计算机、手机等智能终端设备，患者程控器还可以是其他具有程控功能的电子设备(例如是具有程控功能的充电器、数据采集设备)。
本申请对医生程控器和刺激器的数据交互不进行限制，当医生远程程控时，医生程控器可以通过服务器、患者程控器与刺激器进行数据交互。当医生线下和患者面对面进行程控时，医生程控器可以通过患者程控器与刺激器进行数据交互，医生程控器还可以直接与刺激器进行数据交互。患者程控器还可以直接与刺激器进行数据交互。
患者程控器可以包括(与服务器通信的)主机和(与刺激器通信的)子机，主机和子机可通信的连接。其中，医生程控器可以通过3G/4G/5G网络/有线网络/无线网络与服务器进行数据交互，服务器可以通过3G/4G/5G网络/有线网络/无线网络与主机进行数据交互，主机可以通过蓝牙协议/WIFI协议/USB协议与子机进行数据交互，子机可以通过401MHz-406MHz工作频段/2.4GHz-2.48GHz工作频段与刺激器进行数据交互，医生程控器可以通过401MHz-406MHz工作频段/2.4GHz-2.48GHz工作频段与刺激器直接进行数据交互。患者程控器可以通过401MHz-406MHz工作频段/2.4GHz-2.48GHz工作频段与刺激器直接进行数据交互。
参见图1，图1示出了本申请提供的一种医疗系统的结构框图。
所述医疗系统100包括：
摄像头101，用于采集患者做出每种指定动作的视频数据；
控制设备102，所述控制设备与所述摄像头101进行数据交互，所述控制设 备102被配置成实现控制方法的步骤。
本申请中的摄像头101例如是光学摄像头和/或红外摄像头。
在一些可选的实施方式中，所述医疗系统100还可以包括植入于患者体内的刺激器103，所述刺激器103用于向所述患者的体内组织释放电刺激能量。
所述控制设备102可以是程控设备，程控设备例如可以包括平板电脑、笔记本电脑、台式机、手机和智能穿戴设备中的一种或多种。
下文将先对控制方法进行说明。
参见图2和图3，图2是本申请提供的一种控制方法的流程示意图，图3是本申请提供的一种获取中间诊断结果的流程示意图。
所述控制方法包括：
步骤S101：获取患者做出每种指定动作的视频数据，所述视频数据包括多帧待处理图像；
步骤S102：基于每种所述指定动作的视频数据，获取每种所述指定动作对应的中间诊断结果；
步骤S103：基于每种所述指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结果，所述帕金森诊断结果用于指示帕金森病的严重程度；
其中，获取所述指定动作对应的中间诊断结果的过程包括：
针对每种所述指定动作的视频数据，执行以下处理：
步骤S201：获取所述指定动作对应的指定部位；
步骤S202：从每帧所述待处理图像中截取得到一个或多个非指定部位的部位图像，所述非指定部位是所述指定部位以外的部位，所述待处理图像的显示内容包括至少一个指定部位和至少一个非指定部位；
步骤S203：基于每个所述非指定部位的多帧部位图像，获取每个所述非指定部位的部位诊断结果；
步骤S204：基于每个所述非指定部位的部位诊断结果，获取所述指定动作对应的中间诊断结果。
由此，获取患者的帕金森诊断结果的过程为：(患者做出每种指定动作的)视频数据→(非指定动作对应的)中间诊断结果→患者的帕金森诊断结果；
具体而言，获取指定动作的中间诊断结果的过程为：根据指定动作确定指定 部位→截取非指定部位的部位图像→获取每个非指定部位的部位诊断结果→获取对应的指定动作的中间诊断结果。
首先获取患者做出每种指定动作的视频数据，针对每种指定动作的视频数据，确定指定动作对应的指定部位，从每帧待处理图像中截取得到一个或多个非指定部位对应的部位图像，再针对每个非指定部位的部位图像，得到该非指定部位的部位诊断结果，部位诊断结果例如可以指示部位处于正常状态或者异常状态，还可以采用分数或者等级来更精细化地指示该部位的正常程度(例如分数、等级越高表示部位越正常，而采用较低的分数、等级表示部位异常)，结合每个非指定部位的部位诊断结果，得到对应的指定动作对应的中间诊断结果，中间诊断结果例如可以指示该指定动作的动作表现情况，结合每种指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结果，帕金森诊断结果可以指示该患者的帕金森病的严重程度。
相比于相关技术，本申请在获取指定动作对应的中间诊断结果时，参考的是每个非指定部位的部位诊断结果，而不是指定部位的部位诊断结果，这是因为，本申请考虑到患者在做某一种动作时，例如对指时，由于注意力全部放在对指这件事上，对手指和手腕的控制力与平时自然状态下是有较大差距的，本申请反其道而行之，观察患者在对指的时候腿抖不抖，能不能走直线等和手无关的项目，这样的话，更能反映出患者的真实状态，得到的中间诊断结果能更准确地反映患者针对该指定动作的动作表现情况。
在评估患者的帕金森病的严重程度时，参考的是每种指定动作对应的中间诊断结果，也就是说，可以分别获取患者先后做不同的指定动作的全身视频，结合不同的指定动作对应的中间诊断结果，综合评估患者的帕金森病的严重程度，相比于局限于某一种指定动作得到的病情诊断结果，本申请的帕金森诊断结果更能准确反映患者的病情。
在一些可能的方式中，所述视频数据可以是所述患者的全身视频数据或者局部视频数据，相应地，所述待处理图像可以是所述患者的全身图像或者局部图像。待处理图像的显示内容包括至少一个指定部位和至少一个非指定部位。
全身视频数据是指能够拍摄到患者全身的视频数据，相应地，全身图像是指患者全身出镜的图像。
局部视频数据是指能够拍摄到患者部分身体的视频数据，相应地，局部图像是指患者部分身体出镜的图像。
在一些可能的方式中，可以利用交互设备指示提示信息，患者在提示信息的提示作用下做出对应的指定动作，利用摄像头采集得到患者做出每种指定动作的视频数据。
交互设备可以包括音频播放设备、视频播放设备、显示设备等，对应地，提示信息可以包括视频信息、音频信息、图片信息、文字信息中的一种或几种，具体而言，可以是一条“请举起右手”的音频信息，或者是卡通人物正在做对指动作的视频信息。
其中，指定动作可以是预先设置好的动作，也可以由医生进行指定。
在另一些可能的方式中，可以利用监控设备进行监控，以获取患者在预设时长内的视频数据，从中截取患者做出每种指定动作的视频数据。预设时长例如是1天、一个星期或者一个月。
这种方式下，并未提前规定患者去做某种指定动作，患者所做的行为都是日常行为，例如，从床上起身、走到门口、端起水杯喝水、坐在椅子上玩手机等行为。当指定动作为走直线时，可以重点关注患者走路的视频数据。
在一些可选的实施例中，步骤S201可以包括：
获取所述指定动作的动作类型；
基于所述指定动作的动作类型，获取所述指定动作对应的指定部位。
由此，可以预先建立动作类型和部位之间的对应关系，当一个指定动作的动作类型对应多个指定部位时(例如对指这个动作类型一般对应左手和右手两个部位)，可以对多个指定部位进行单独诊断，此时可以分次进行，每次对其中一个指定部位进行图像处理以得到部位诊断结果，由此通过多次诊断，分别得到多个指定部位的部位诊断结果，进一步提升了智能化程度，提高了用户的使用体验。
本申请对指定动作的动作类型不作限定，例如可以是对指、握拳、举手、抬臂(使手臂与躯干相垂直)、走直线、走曲线等动作类型。
对指这一动作类型可以包括左手对指、右手对指，握拳这一动作类型可以包括左手握拳、右手握拳，举手这一动作类型可以包括举左手、举右手，抬臂这一动作类型可以包括抬左臂、抬右臂，走直线可以包括走直线30步、走直线10步 等，走曲线可以包括走圆形、走半圆形、走S形等。
在一些可能的方式中，可以基于所述指定动作的动作类型和第一对应关系，获取所述指定动作对应的指定部位。
第一对应关系可以是动作类型与部位之间的对应关系，第一对应关系可以采用部位映射表。
由部位映射表可以得知，对指这一动作类型可以对应左手和右手两个部位，握拳这一动作类型可以对应左手和右手两个部位，举手这一动作类型可以对应左臂和右臂两个部位，抬臂这一动作类型可以对应左臂和右臂两个部位，走直线这一动作类型可以对应左腿和右腿两个部位，走预设曲线这一动作类型可以对应左腿和右腿两个部位。
部位诊断结果可以指示部位处于正常状态或者异常状态，还可以采用分数或者等级来更精细化地指示该部位的异常程度(例如分数、等级越高表示部位越异常，而采用较低的分数、等级表示部位正常)。
指定动作对应的中间诊断结果可以用于指示该指定动作的动作表现情况，例如是：表现优秀、表现良好、表现差、表现极差，还可以采用分数或者等级来更精细化地指示该指定动作的表现情况(例如分数、等级越高表示该指定动作的表现情况越差)。
患者的帕金森诊断结果可以指示该患者的帕金森病的严重程度，例如可以指示该患者的帕金森病为轻重、中度或者重度，还可以采用分数或者等级来更精细化地指示病情的严重程度(例如分数、等级越高表示病情越重，而采用较低的分数、等级表示病情较轻)。
在一些可能的方式中，部位诊断结果可以用部位诊断评分表示，分数越高表示部位越异常，指定动作对应的中间诊断结果可以用中间诊断评分表示，分数越高表示该指定动作的表现情况越差，患者的帕金森诊断结果可以用帕金森诊断评分表示，分数越高表示病情越严重。
当选取的非指定部位只有1个时，该非指定部位的部位诊断评分可以作为对应的指定动作的中间诊断评分；
当选取的非指定部位不止1个时，对应的指定动作的中间诊断评分可以是这几个非指定部位的部位诊断评分的平均数。
当指定动作只有一种时，指定动作的中间诊断评分可以作为患者的帕金森诊断评分。
当指定动作包括不止一种时，患者的帕金森诊断评分可以是这几种指定动作的中间诊断评分的平均数。
在一具体应用中，指定动作包括对指和走直线。
针对对指这种指定动作，指定部位为左手和右手，非指定部位包括左腿和右腿。
获取患者小李做对指的全身视频，从对应的待处理图像中截取得到左腿和右腿的部位图像，针对左腿的多帧部位图像，得到左腿的部位诊断评分30，针对右腿的多帧部位图像，得到右腿的部位诊断评分70，对指动作的中间诊断评分为(30+70)/2＝50。
针对走直线这种指定动作，指定部位为左腿和右腿，非指定部位包括左手和右手。
获取患者小李走直线的全身视频，从对应的待处理图像中截取得到左手和右手的部位图像，针对左手的多帧部位图像，得到左手的部位诊断评分40，针对右手的多帧部位图像，得到右手的部位诊断评分80，走直线动作的中间诊断评分为(40+80)/2＝60。
患者小李的帕金森诊断评分为(50+60)/2＝55。
在一些可能的方式中，所述步骤S103可以包括：
获取每种指定动作对应的难度系数；
基于每种所述指定动作对应的中间诊断结果和难度系数，获取所述患者的帕金森诊断结果。
本申请对难度系数不作限定，难度系数可以用于表示完成该指定动作的难易程度，难度系数可以用数字表示，数值越高，该指定动作越难完成。难度系数例如是0.8、1.1或者1.5。
在一些可选的实施例中，所述步骤S203可以包括：
将每个所述非指定部位的多帧部位图像分别输入对应的部位诊断模型，得到每个所述非指定部位的部位诊断结果。
由此，可以针对每个非指定部位，将该部位对应的(在时间顺序上具有先后 关系的)多帧部位图像输入该部位对应的部位诊断模型，利用部位诊断模型(自动化地)输出该部位的部位诊断结果，诊断效率较高，智能化水平较高。
在一些可选的实施例中，步骤S302可以包括：
将所述指定部位的多帧部位图像输入对应的部位诊断模型，得到所述指定部位的部位诊断结果。
由此，可以针对每个指定部位，将该部位对应的(在时间顺序上具有先后关系的)多帧部位图像输入该部位对应的部位诊断模型，利用部位诊断模型(自动化地)输出该部位的部位诊断结果，诊断效率较高，智能化水平较高。
本申请中，“将每个所述非指定部位的多帧部位图像分别输入对应的部位诊断模型”以及“将所述指定部位的多帧部位图像输入对应的部位诊断模型”中的“对应的部位诊断模型”是指与每个部位相对应的部位诊断模型。例如，将手部的多帧部位图像输入手部对应的部位诊断模型，将臂部的多帧部位图像输入臂部对应的部位诊断模型，将腿部的多帧部位图像输入腿部对应的部位诊断模型，将躯干部的多帧部位图像输入躯干部对应的部位诊断模型。
本申请对部位诊断模型的获取方式不作限定，在一些可能的方式中，本申请可以训练得到部位诊断模型，在另一些可能的方式中，本申请可以采用预先训练好的部位诊断模型。
本申请中，针对每个部位设置对应的部位诊断模型，例如，针对手部设置手部对应的部位诊断模型(又称手部诊断模型)，针对臂部设置臂部对应的部位诊断模型(又称臂部诊断模型)，针对腿部设置腿部对应的部位诊断模型(又称腿部诊断模型)，针对躯干部设置躯干部对应的部位诊断模型(又称躯干部诊断模型)。
在一些可能的方式中，每个部位对应的部位诊断模型可以采用如下训练过程训练得到：
获取第二训练集，所述第二训练集中的每个训练数据包括用于训练的所述部位的多帧部位图像以及所述训练数据对应的所述部位的部位诊断结果的标注数据；
针对所述第二训练集中的每个训练数据，执行以下处理：
将所述训练数据中的多帧部位图像输入预设的第二深度学习模型，得到所述 训练数据对应的所述部位的部位诊断结果的预测数据；
基于所述训练数据对应的所述部位的部位诊断结果的预测数据和标注数据，对所述第二深度学习模型的模型参数进行更新；
检测是否满足预设的第二训练结束条件；如果是，则将训练得到的第二深度学习模型作为所述部位诊断模型；如果否，则利用下一个所述训练数据继续训练所述第二深度学习模型。
部位诊断模型可以由大量的训练数据训练得到，能够针对不同的输入数据预测得到各部位的部位诊断结果，适用范围广，智能化水平高。
通过设计，建立适量的神经元计算节点和多层运算层次结构，选择合适的输入层和输出层，就可以得到预设的第二深度学习模型，通过该预设的第二深度学习模型的学习和调优，建立起从输入到输出的函数关系，虽然不能100％找到输入与输出的函数关系，但是可以尽可能地逼近现实的关联关系，由此训练得到的部位诊断模型，可以实现获取部位诊断结果的功能，且计算结果准确性高、可靠性高。
在一些可能的方式中，本申请可以采用上述训练过程训练得到部位诊断模型，在另一些可能的方式中，本申请可以采用预先训练好的部位诊断模型。
本申请对标注数据的获取方式不作限定，例如可以采用人工标注的方式，也可以采用自动标注或者半自动标注的方式。
本申请对部位诊断模型的训练过程不作限定，其例如可以采用上述监督学习的训练方式，或者可以采用半监督学习的训练方式，或者可以采用无监督学习的训练方式。
本申请对预设的第二训练结束条件不作限定，其例如可以是训练次数达到预设次数(预设次数例如是1次、3次、10次、100次、1000次、10000次等)，或者可以是第二训练集中的训练数据都完成一次或多次训练，或者可以是本次训练得到的总损失值不大于预设损失值。
参见图4，图4是本申请实施例提供的另一种获取中间诊断结果的流程示意图。
在一些可能的方式中，所述步骤S204可以包括：
步骤S301：从每帧所述待处理图像中截取得到所述指定部位的部位图像；
步骤S302：基于所述指定部位的多帧部位图像，获取所述指定部位的部位诊断结果；
步骤S303：基于每个所述非指定部位的部位诊断结果和第一权重以及所述指定部位的部位诊断结果和第二权重，获取所述指定动作对应的中间诊断结果，其中，所述第一权重大于所述第二权重，或者，所述第一权重等于所述第二权重，或者，所述第一权重小于所述第二权重。
由此，在获取指定动作对应的中间诊断结果时，从指定部位和非指定部位两方面进行评估，分别得到指定部位的部位诊断结果和非指定部位的部位诊断结果，通过综合考察非指定部位的部位诊断结果和指定部位的部位诊断结果，由此得到的指定动作对应的中间诊断结果更能全面地反映患者针对该指定动作的动作表现情况。一方面，给非指定部位的部位诊断结果赋予较高的第一权重，给指定部位的部位诊断结果赋予较低的第二权重，非指定部位的部位诊断结果对中间诊断结果的影响更大；一方面，给非指定部位的部位诊断结果和指定部位的部位诊断结果赋予的权重可以相等，二者对中间诊断结果的影响一样；另一方面，可以给非指定部位的部位诊断结果赋予较低的第一权重，给指定部位的部位诊断结果赋予较高的第二权重，指定部位的部位诊断结果对中间诊断结果的影响更大。
本申请对第一权重和第二权重不做限定，第一权重和第二权重可以用数字或百分数表示，数值越高权重越大，第一权重例如是70％，第二权重例如是30％。
在一些可能的方式中，所述方法还可以包括：
当所述指定动作对应的中间诊断结果指示所述患者需要进行针对所述指定部位的康复训练时，利用显示设备显示所述指定部位对应的康复训练视频。
由此，指定动作对应的中间诊断结果指示患者需要进行针对该指定部位的康复训练，表明患者针对指定动作的动作表现较差，可以利用显示设备显示指定部位对应的康复训练视频，对很多患者而言，在医院看病后只能得到一个专业的诊断报告，但是患者并不知道如何通过自身的努力去改善病情，只能被动地接受治疗，本申请通过显示设备显示指定部位对应的康复训练视频，有助于引导患者进行针对性的训练，患者体验佳。
在一些可能的方式中，所述指定动作对应的中间诊断结果可以用中间诊断评分表示，当所述指定动作对应的中间诊断评分不小于预设评分阈值时，所述指定 动作对应的中间诊断结果指示所述患者需要进行针对所述指定部位的康复训练。
本申请对预设评分阈值不做限定，预设评分阈值例如是70、75或者80。
在一些可能的方式中，所述方法还可以包括：
获取所述刺激器对应的参考配置信息；
基于所述参考配置信息，控制所述刺激器释放对应的电刺激能量。
由此，可以与患者的刺激器进行数据交互，实现程控功能，通过获取刺激器对应的参考配置信息，控制刺激器释放对应的电刺激能量。
在一些可能的方式中，参考配置信息用于指示所述刺激器的刺激参数。
刺激器的刺激参数可以包括以下至少一种：频率(例如是单位时间1s内的电刺激脉冲信号个数，单位为Hz)、脉宽(每个脉冲的持续时间，单位为μs)、幅值(一般用电压表述，即每个脉冲的强度，单位为V)、刺激模式(包括电流模式、电压模式、定时刺激模式和循环刺激模式中的一种或多种)、医生控制上限及下限(医生可调节的范围)和患者控制上限及下限(患者可自主调节的范围)。
在一具体应用中，可以在电流模式或者电压模式下对刺激器的各刺激参数进行调节。
其中，刺激参数标识可以使用中文、字母、数字、符号和特殊符号中的至少一种来表示。例如“A01”、“幅值”或者“#01”。
在一具体应用中，刺激器的配置参数包括：刺激模式为电压模式、频率为130Hz、脉宽为60μs和幅值为3V。
在一些可能的方式中，获取所述刺激器对应的参考配置信息的过程可以包括：
基于每种所述指定动作对应的中间诊断结果，获取所述刺激器对应的参考配置信息。
由此，通过每种指定动作对应的中间诊断结果，根据每种指定动作对应的中间诊断结果，可以得知患者哪种指定动作的动作表现较好，哪种指定动作的动作表现较差，从而反映出患者的哪些部位需要进行治疗，通过(可以反映具体部位情况的)中间诊断结果得到的参考配置信息，可以为患者提供精准的电刺激。
在一些可能的方式中，刺激器的刺激参数还可以包括刺激触点的标识，也就是说，根据每种指定动作对应的中间诊断结果，可以选择对应的刺激触点，为患者提供精准的电刺激。
在一具体应用中，指定动作包括对指和走直线，其中，对指动作对应的中间诊断结果为“正常”，走直线动作对应的中间诊断结果为“轻度异常”，刺激器的参考配置信息为“刺激触点a、电压模式、频率为100Hz、脉宽为50μs和幅值为2V”。
在一些可能的方式中，获取所述刺激器对应的参考配置信息的过程可以包括：
基于所述患者的帕金森诊断结果，获取所述刺激器对应的参考配置信息。
由此，患者的帕金森诊断结果可以反映患者整体的帕金森病的严重程度，通过(可以反映患者整体病情的)帕金森诊断结果得到的参考配置信息，可以为患者提供适用于不同部位的电刺激。
在一些可能的方式中，获取所述刺激器对应的参考配置信息的过程可以进一步包括：
将所述患者的帕金森诊断结果输入参考配置模型，得到所述刺激器对应的参考配置信息；
其中，所述参考配置模型的训练过程包括：
获取第一训练集，所述第一训练集包括多个第一训练数据，每个所述第一训练数据包括一个样本对象的帕金森诊断结果以及所述样本对象的参考配置信息的标注数据；
针对所述第一训练集中的每个第一训练数据，执行以下处理：
将所述第一训练数据中的样本对象的帕金森诊断结果输入预设的第一深度学习模型，得到所述样本对象的参考配置信息的预测数据；
基于所述样本对象的参考配置信息的预测数据和标注数据，对所述第一深度学习模型的模型参数进行更新；
检测是否满足预设的第一训练结束条件；如果是，则将训练出的第一深度学习模型作为所述参考配置模型；如果否，则利用下一个所述第一训练数据继续训练所述第一深度学习模型。
由此，通过设计，建立适量的神经元计算节点和多层运算层次结构，选择合适的输入层和输出层，就可以得到预设的第一深度学习模型，通过该预设的第一深度学习模型的学习和调优，建立起从输入到输出的函数关系，虽然不能100％找到输入与输出的函数关系，但是可以尽可能地逼近现实的关联关系，由此训练 得到的参考配置模型，可以基于患者的帕金森诊断结果获取刺激器对应的参考配置信息，且计算结果准确性高、可靠性高。
本申请对标注数据的获取方式不作限定，例如可以采用人工标注的方式，也可以采用自动标注或者半自动标注的方式。
本申请对参考配置模型的训练过程不作限定，其例如可以采用上述监督学习的训练方式，或者可以采用半监督学习的训练方式，或者可以采用无监督学习的训练方式。
本申请对预设的第一训练结束条件不作限定，其例如可以是训练次数达到预设次数(预设次数例如是1次、3次、10次、100次、1000次、10000次等)，或者可以是第一训练集中的训练数据都完成一次或多次训练，或者可以是本次训练得到的总损失值不大于预设损失值。
在另一些可能的方式中，获取所述刺激器对应的参考配置信息的过程可以进一步包括：
基于所述患者的帕金森诊断结果和第二对应关系，获取所述刺激器对应的参考配置信息。
其中，第二对应关系可以是帕金森诊断结果和参考配置信息的对应关系，第二对应关系可以采用参考配置映射表。
在一具体应用中，根据参考配置映射表，可以得知，当患者的帕金森诊断结果指示患者为重度帕金森时，对应的参考配置信息为“频率为200Hz、脉宽为80μs和幅值为4V”；
当患者的帕金森诊断结果指示患者为轻度帕金森时，对应的参考配置信息为“频率为100Hz、脉宽为50μs和幅值为2V”。
本申请还提供了一种控制设备，其具体方式与上述方法可能的方式中记载的可能的方式、所达到的技术效果一致，部分内容不再赘述。
所述控制设备被配置成：
获取患者做出每种指定动作的视频数据，所述视频数据包括多帧待处理图像；
基于每种所述指定动作的视频数据，获取每种所述指定动作对应的中间诊断结果；
基于每种所述指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结 果，所述帕金森诊断结果用于指示帕金森病的严重程度；
其中，获取所述指定动作对应的中间诊断结果的过程包括：
针对每种所述指定动作的视频数据，执行以下处理：
获取所述指定动作对应的指定部位；
从每帧所述待处理图像中截取得到一个或多个非指定部位的部位图像，所述非指定部位是所述指定部位以外的部位，所述待处理图像的显示内容包括至少一个指定部位和至少一个非指定部位；
基于每个所述非指定部位的多帧部位图像，获取每个所述非指定部位的部位诊断结果；
基于每个所述非指定部位的部位诊断结果，获取所述指定动作对应的中间诊断结果。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取每个所述非指定部位的部位诊断结果：
将每个所述非指定部位的多帧部位图像分别输入对应的部位诊断模型，得到每个所述非指定部位的部位诊断结果。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取所述指定动作对应的中间诊断结果：
从每帧所述待处理图像中截取得到所述指定部位的部位图像；
基于所述指定部位的多帧部位图像，获取所述指定部位的部位诊断结果；
基于每个所述非指定部位的部位诊断结果和第一权重以及所述指定部位的部位诊断结果和第二权重，获取所述指定动作对应的中间诊断结果，其中，所述第一权重大于所述第二权重，或者，所述第一权重等于所述第二权重，或者，所述第一权重小于所述第二权重。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取所述指定部位的部位诊断结果：
将所述指定部位的多帧部位图像输入对应的部位诊断模型，得到所述指定部位的部位诊断结果。
在一些可选的可能的方式中，所述控制设备还被配置成：
当所述指定动作对应的中间诊断结果指示所述患者需要进行针对所述指定 部位的康复训练时，利用显示设备显示所述指定部位对应的康复训练视频。
在一些可选的可能的方式中，所述控制设备与植入于所述患者体内的刺激器进行数据交互，所述控制设备还被配置成：
获取所述刺激器对应的参考配置信息；
基于所述参考配置信息，控制所述刺激器释放对应的电刺激能量。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
基于每种所述指定动作对应的中间诊断结果，获取所述刺激器对应的参考配置信息。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
基于所述患者的帕金森诊断结果，获取所述刺激器对应的参考配置信息。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
将所述患者的帕金森诊断结果输入参考配置模型，得到所述刺激器对应的参考配置信息；
其中，所述参考配置模型的训练过程包括：
获取第一训练集，所述第一训练集包括多个第一训练数据，每个所述第一训练数据包括一个样本对象的帕金森诊断结果以及所述样本对象的参考配置信息的标注数据；
针对所述第一训练集中的每个第一训练数据，执行以下处理：
将所述第一训练数据中的样本对象的帕金森诊断结果输入预设的第一深度学习模型，得到所述样本对象的参考配置信息的预测数据；
基于所述样本对象的参考配置信息的预测数据和标注数据，对所述第一深度学习模型的模型参数进行更新；
检测是否满足预设的第一训练结束条件；如果是，则将训练出的第一深度学习模型作为所述参考配置模型；如果否，则利用下一个所述第一训练数据继续训练所述第一深度学习模型。
在一些可选的可能的方式中，所述控制设备被进一步配置成采用如下方式获 取所述指定动作对应的指定部位：
获取所述指定动作的动作类型；
基于所述指定动作的动作类型，获取所述指定动作对应的指定部位。
参见图5，图5示出了本申请提供的一种控制设备200的结构框图。控制设备200例如可以包括至少一个存储器210、至少一个处理器220以及连接不同平台系统的总线230。
存储器210可以包括易失性存储器形式的可读介质，例如随机存取存储器(RAM)211和/或高速缓存存储器212，还可以进一步包括只读存储器(ROM)213。
其中，存储器210还存储有计算机程序，计算机程序可以被处理器220执行，使得处理器220实现上述任一项控制设备的功能，其具体方式与上述方法可能的方式中记载的可能的方式、所达到的技术效果一致，部分内容不再赘述。
存储器210还可以包括具有至少一个程序模块215的实用工具214，这样的程序模块215包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例的每一个或某种组合中可能包括网络环境的实现。
相应的，处理器220可以执行上述计算机程序，以及可以执行实用工具214。
处理器220可以采用一个或多个应用专用集成电路(ASIC，Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD，ProgrammableLogic Device)、复杂可编程逻辑器件(CPLD，Complex Programmable Logic Device)、现场可编程门阵列(FPGA，Field-Programmable Gate Array)或其他电子元件。
总线230可以为表示几类总线结构的一种或多种，包括存储器总线或者存储器控制器、外围总线、图形加速端口、处理器或者使用多种总线结构的任意总线结构的局域总线。
控制设备200也可以与一个或多个外部设备240例如键盘、指向设备、蓝牙设备等通信，还可与一个或者多个能够与该控制设备200交互的设备通信，和/或与使得该控制设备200能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等)通信。这种通信可以通过输入输出接口250进行。并且，控制设备200还可以通过网络适配器260与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。网络适配器260可以通过总线230与控制设备200的其它模块通信。应当明白，尽管图中未示出，可 以结合控制设备200使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储平台等。
本申请还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述任一项控制设备的功能或者实现上述控制方法的步骤，其具体方式与上述控制设备的可能的方式中记载的可能的方式、所达到的技术效果一致，部分内容不再赘述。
参见图6，图6示出了本申请提供的一种用于实现控制方法的程序产品300的结构示意图。程序产品300可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在终端设备，例如个人电脑上运行。然而，本发明的程序产品300不限于此，在本申请中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。程序产品300可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读存储介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读存储介质还可以是任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等，或者上述的任意合适的组合。可以以一种或多种程序设计语言的任意组合来编写用于执行本发明操作的程序代码。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情 形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WA N)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。

Claims (12)

  1. 一种控制设备，所述控制设备被配置成：
    获取患者做出每种指定动作的视频数据，所述视频数据包括多帧待处理图像；
    基于每种所述指定动作的视频数据，获取每种所述指定动作对应的中间诊断结果；
    基于每种所述指定动作对应的中间诊断结果，获取所述患者的帕金森诊断结果，所述帕金森诊断结果用于指示帕金森病的严重程度；
    其中，获取所述指定动作对应的中间诊断结果的过程包括：
    针对每种所述指定动作的视频数据，执行以下处理：
    获取所述指定动作对应的指定部位；
    从每帧所述待处理图像中截取得到一个或多个非指定部位的部位图像，所述非指定部位是所述指定部位以外的部位，所述待处理图像的显示内容包括至少一个指定部位和至少一个非指定部位；
    基于每个所述非指定部位的多帧部位图像，获取每个所述非指定部位的部位诊断结果；
    基于每个所述非指定部位的部位诊断结果，获取所述指定动作对应的中间诊断结果。
  2. 根据权利要求1所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取每个所述非指定部位的部位诊断结果：
    将每个所述非指定部位的多帧部位图像分别输入对应的部位诊断模型，得到每个所述非指定部位的部位诊断结果。
  3. 根据权利要求1所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述指定动作对应的中间诊断结果：
    从每帧所述待处理图像中截取得到所述指定部位的部位图像；
    基于所述指定部位的多帧部位图像，获取所述指定部位的部位诊断结果；
    基于每个所述非指定部位的部位诊断结果和第一权重以及所述指定部位的部位诊断结果和第二权重，获取所述指定动作对应的中间诊断结果。
  4. 根据权利要求3所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述指定部位的部位诊断结果：
    将所述指定部位的多帧部位图像输入对应的部位诊断模型，得到所述指定部位的部位诊断结果。
  5. 根据权利要求1所述的控制设备，其中，所述控制设备还被配置成：
    当所述指定动作对应的中间诊断结果指示所述患者需要进行针对所述指定部位的康复训练时，利用显示设备显示所述指定部位对应的康复训练视频。
  6. 根据权利要求1所述的控制设备，其中，所述控制设备与植入于所述患者体内的刺激器进行数据交互，所述控制设备还被配置成：
    获取所述刺激器对应的参考配置信息；
    基于所述参考配置信息，控制所述刺激器释放对应的电刺激能量。
  7. 根据权利要求6所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
    基于每种所述指定动作对应的中间诊断结果，获取所述刺激器对应的参考配置信息。
  8. 根据权利要求6所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
    基于所述患者的帕金森诊断结果，获取所述刺激器对应的参考配置信息。
  9. 根据权利要求8所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述刺激器对应的参考配置信息：
    将所述患者的帕金森诊断结果输入参考配置模型，得到所述刺激器对应的参考配置信息；
    其中，所述参考配置模型的训练过程包括：
    获取第一训练集，所述第一训练集包括多个第一训练数据，每个所述第一训练数据包括一个样本对象的帕金森诊断结果以及所述样本对象的参考配置信息的标注数据；
    针对所述第一训练集中的每个第一训练数据，执行以下处理：
    将所述第一训练数据中的样本对象的帕金森诊断结果输入预设的第一深度 学习模型，得到所述样本对象的参考配置信息的预测数据；
    基于所述样本对象的参考配置信息的预测数据和标注数据，对所述第一深度学习模型的模型参数进行更新；
    检测是否满足预设的第一训练结束条件；如果是，则将训练出的第一深度学习模型作为所述参考配置模型；如果否，则利用下一个所述第一训练数据继续训练所述第一深度学习模型。
  10. 根据权利要求1所述的控制设备，其中，所述控制设备被进一步配置成采用如下方式获取所述指定动作对应的指定部位：
    获取所述指定动作的动作类型；
    基于所述指定动作的动作类型，获取所述指定动作对应的指定部位。
  11. 一种医疗系统，所述医疗系统包括摄像头和权利要求1-10任一项所述的控制设备，所述控制设备与所述摄像头进行数据交互；
    所述摄像头用于采集患者做出每种指定动作的视频数据。
  12. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1-10任一项所述控制设备的功能。
PCT/CN2023/099381 2022-07-01 2023-06-09 控制设备、医疗系统及计算机可读存储介质 WO2024001723A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210767505.5A CN114842956B (zh) 2022-07-01 2022-07-01 控制设备、医疗系统及计算机可读存储介质
CN202210767505.5 2022-07-01

Publications (1)

Publication Number Publication Date
WO2024001723A1 true WO2024001723A1 (zh) 2024-01-04

Family

ID=82575047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/099381 WO2024001723A1 (zh) 2022-07-01 2023-06-09 控制设备、医疗系统及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114842956B (zh)
WO (1) WO2024001723A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117643456A (zh) * 2024-01-29 2024-03-05 北京航空航天大学 一种帕金森神经病变的辅助评估系统、方法和存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114842956B (zh) * 2022-07-01 2022-09-13 苏州景昱医疗器械有限公司 控制设备、医疗系统及计算机可读存储介质
CN115881295B (zh) * 2022-12-06 2024-01-23 首都医科大学附属北京天坛医院 帕金森症状信息检测方法、装置、设备和计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110151188A (zh) * 2019-04-27 2019-08-23 嘉善医之爱生物技术有限公司 帕金森诊断系统
CN111048205A (zh) * 2019-12-17 2020-04-21 创新工场(北京)企业管理股份有限公司 对帕金森病症状进行评估的方法与装置
CN113362946A (zh) * 2021-07-20 2021-09-07 景昱医疗器械(长沙)有限公司 视频处理装置、电子设备及计算机可读存储介质
RU2764568C1 (ru) * 2021-04-05 2022-01-18 Автономная некоммерческая образовательная организация высшего образования «Сколковский институт науки и технологий» Способ диагностики болезни паркинсона на основе анализа видеоданных с применением машинного обучения
CN114842956A (zh) * 2022-07-01 2022-08-02 苏州景昱医疗器械有限公司 控制设备、医疗系统及计算机可读存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111539377A (zh) * 2020-05-11 2020-08-14 浙江大学 基于视频的人体运动障碍检测方法、装置及设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110151188A (zh) * 2019-04-27 2019-08-23 嘉善医之爱生物技术有限公司 帕金森诊断系统
CN111048205A (zh) * 2019-12-17 2020-04-21 创新工场(北京)企业管理股份有限公司 对帕金森病症状进行评估的方法与装置
RU2764568C1 (ru) * 2021-04-05 2022-01-18 Автономная некоммерческая образовательная организация высшего образования «Сколковский институт науки и технологий» Способ диагностики болезни паркинсона на основе анализа видеоданных с применением машинного обучения
CN113362946A (zh) * 2021-07-20 2021-09-07 景昱医疗器械(长沙)有限公司 视频处理装置、电子设备及计算机可读存储介质
CN114842956A (zh) * 2022-07-01 2022-08-02 苏州景昱医疗器械有限公司 控制设备、医疗系统及计算机可读存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117643456A (zh) * 2024-01-29 2024-03-05 北京航空航天大学 一种帕金森神经病变的辅助评估系统、方法和存储介质
CN117643456B (zh) * 2024-01-29 2024-05-24 北京航空航天大学 一种帕金森神经病变的辅助评估系统、方法和存储介质

Also Published As

Publication number Publication date
CN114842956B (zh) 2022-09-13
CN114842956A (zh) 2022-08-02

Similar Documents

Publication Publication Date Title
WO2024001723A1 (zh) 控制设备、医疗系统及计算机可读存储介质
WO2024021960A1 (zh) 脉冲发生器、医疗系统及计算机可读存储介质
WO2023005353A1 (zh) 基于多模态数据的配置信息获取装置及相关设备
WO2024021959A1 (zh) 程控装置、医疗系统及计算机可读存储介质
WO2022262495A1 (zh) 家用医疗设备的控制方法及相关装置
CN113856040B (zh) 植入式神经刺激器和植入式神经刺激系统
WO2024067449A1 (zh) 参数调节装置及其方法、程控设备、医疗系统、存储介质
WO2024083193A1 (zh) 脉冲发生器、刺激器、医疗系统及计算机可读存储介质
WO2023185410A1 (zh) 刺激电极导线的成像识别方法及相关装置
CN113362946A (zh) 视频处理装置、电子设备及计算机可读存储介质
CN113244533A (zh) 参数调整方法、装置、电子设备及计算机可读存储介质
WO2024041496A1 (zh) 充电提醒装置、植入式神经刺激系统及存储介质
WO2024007823A1 (zh) 体外充电器、程控系统和计算机可读存储介质
CN115501481A (zh) 应急程控设备、医疗系统及计算机可读存储介质
WO2024027781A1 (zh) 自诊断设备、程控系统及计算机可读存储介质
WO2023000787A1 (zh) 视频处理方法、装置、电子设备及计算机可读存储介质
WO2023000788A1 (zh) 参数比对方法、装置、电子设备及计算机可读存储介质
WO2023024881A1 (zh) 慢性病患者视频追溯方法及相关装置
WO2023226636A1 (zh) 控制器、植入式神经刺激系统及计算机可读存储介质
WO2024001695A1 (zh) 数据采集方法、装置、系统及计算机可读存储介质
CN116936060A (zh) 医疗系统的故障检测方法及相关装置
CN116895065A (zh) 核团标注装置及方法、可穿戴的xr设备、相关装置
CN114817168A (zh) 数据存储方法、装置、系统及计算机可读存储介质
WO2022271706A1 (en) Cloud-based patient monitoring system
CN115019948B (zh) 控制设备、远程会诊系统和计算机可读存储介质

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: 23829907

Country of ref document: EP

Kind code of ref document: A1