Multimodal brain cognitive function detection device
By using a multimodal brain cognitive function detection device, multidimensional data is collected and image, temperature and sound information are comprehensively processed, which solves the problems of inaccurate diagnosis, time-consuming and costly in the existing technology, and realizes high accuracy, repeatability, non-contact and low cost detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- ACADEMY OF MILITARY MEDICAL SCIENCES
- Filing Date
- 2025-04-15
- Publication Date
- 2026-07-07
AI Technical Summary
Existing methods for detecting brain cognitive function suffer from problems such as inaccurate diagnosis, time-consuming and costly. In particular, scale tests are not repeatable, serum tests are highly invasive, medical imaging tests are time-consuming and the diagnosis is inaccurate due to single-modality images, and EEG signals are easily interfered with.
A multimodal brain cognitive function detection device is used to collect multidimensional data through image, temperature and voice acquisition modules, including image information of the face, top of the head and hands, facial and tongue temperature information and voice information. The data from these modalities are combined and processed to improve diagnostic accuracy.
It achieves highly accurate, repeatable, non-contact, and low-cost brain cognitive function testing, improving the accuracy and efficiency of diagnosis.
Smart Images

Figure CN224461683U_ABST
Abstract
Description
Technical Field
[0001] This utility model belongs to the field of medical device technology, specifically relating to a multimodal brain cognitive function detection device. Background Technology
[0002] Currently, cognitive function testing typically employs scales, serum testing, medical imaging, and electroencephalography (EEG). However, some scales cannot be repeated; serum testing is invasive; medical imaging is time-consuming and expensive, and mostly based on single-modality images, leading to inaccurate cognitive function diagnoses; EEG signals can be interfered with by various factors, including power line noise, muscle activity, eye movements, and cardiac activity, all of which can affect signal quality and interpretation, resulting in inaccurate cognitive function diagnoses. Utility Model Content
[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, one objective of the present invention is to provide a multimodal brain cognitive function detection device that has high accuracy in diagnosing brain cognitive function, features repeatable and non-contact measurement, and is convenient, efficient, and low-cost.
[0004] The multimodal brain cognitive function detection device according to an embodiment of the present invention includes:
[0005] support;
[0006] A chin support, which is mounted on the bracket and is used to support a person's chin;
[0007] An image acquisition module, mounted on a support, is used to acquire image information of a person's face, top of head, and hands.
[0008] A temperature acquisition module, which is mounted on a bracket, is used to collect temperature information of a person's face and tongue;
[0009] A voice acquisition module, which is mounted on a bracket, is used to acquire human voice information;
[0010] The computer is connected to the image acquisition module, the temperature acquisition module, and the voice acquisition module, and is used to process the image information, the temperature information, and the voice information.
[0011] The diagnostic information acquisition process of the multimodal brain cognitive function detection device of this utility model is as follows: first, static image information is acquired, and then audio and video image information is acquired. The acquisition of static image information includes three stages: the first stage acquires frontal face image, left side image, right side image and top of head image; the second stage acquires frontal tongue image and back of tongue image; the third stage acquires frontal hand image and back of hand image.
[0012] The multimodal brain cognitive function detection device according to this utility model acquires image information of a person's face, top of head, and hands through an image acquisition module, temperature information of a person's face and tongue through a temperature acquisition module, and sound information through a voice acquisition module. The acquisition time is short, and the acquired data has multiple dimensions. By comprehensively processing data of different levels and types from different modalities, such as image, temperature, and sound information, the accuracy of diagnosis can be improved. Furthermore, the multimodal brain cognitive function detection device of this utility model features repeatable and non-contact measurement, making measurement convenient, efficient, and low-cost.
[0013] In some embodiments, the image acquisition module includes a face camera, a top camera, a left camera, a right camera, and a depth camera; the face camera is used to acquire frontal image information of a face; the top camera is used to acquire image information of the top of a person's head and hand; the left camera is used to acquire image information of the left side of a face; the right camera is used to acquire image information of the right side of a face; and the depth camera is used to acquire frontal image information of a face, image information of a tongue, and scene information.
[0014] In some embodiments, the temperature acquisition module is an infrared temperature camera.
[0015] In some embodiments, the voice acquisition module is a microphone for acquiring sound.
[0016] In some embodiments, the bracket includes a flat plate, a left side bracket, a right side bracket, and a rear side bracket;
[0017] The chin rest is disposed on the front of the flat plate, and the microphone is disposed on the flat plate and located adjacent to the rear of the chin rest;
[0018] The computer's display screen is located on the back of the tablet.
[0019] The left bracket is located on the left side of the tablet, and the left camera is mounted on the left bracket; the right bracket is located on the right side of the tablet, and the right camera is mounted on the right bracket.
[0020] The rear bracket is located behind the display screen, and the face camera, the top camera, the depth camera, and the infrared temperature camera are mounted on the rear bracket.
[0021] In some embodiments, the rear support includes a rear vertical frame and a rear cantilever; the lower end of the rear vertical frame is fixed to the tablet, and the face camera, the depth camera, and the infrared temperature camera are mounted adjacent to each other on the rear vertical frame and are higher than the display screen; the rear cantilever extends back and forth above the tablet, the rear end of the rear cantilever is fixed to the upper end of the rear vertical frame, and the top camera is mounted on the rear cantilever.
[0022] In some embodiments, the position of the top camera on the rear cantilever is adjustable.
[0023] In some embodiments, the chin rest is height-adjustable.
[0024] In some embodiments, a control button is also included for controlling the raising and lowering of the chin rest.
[0025] In some embodiments, the chin rest is provided with a color card.
[0026] Additional aspects and advantages of this invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0027] The above and / or additional aspects and advantages of this utility model will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:
[0028] Figure 1 This is a three-dimensional schematic diagram of the multimodal brain cognitive function detection device according to an embodiment of the present invention;
[0029] Figure 2 This is a front view of the multimodal brain cognitive function detection device according to an embodiment of the present invention.
[0030] Figure label:
[0031] Multimodal brain cognitive function testing device 1000; support 1; tablet 101; rear support 102; rear vertical frame 1021; rear cantilever 1022; mounting hole 10221; left support 103; right support 104; chin rest 2; image acquisition module 3; face camera 301; top camera 302; left camera 303; right camera 304; depth camera 305; temperature acquisition module 4; voice acquisition module 5; computer 6; control buttons 7. Detailed Implementation
[0032] The embodiments of this utility model are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this utility model, and should not be construed as limiting this utility model.
[0033] The following is combined Figures 1 to 2 This invention describes a multimodal brain cognitive function detection device 1000 according to an embodiment of the present invention.
[0034] like Figure 1 and Figure 2 As shown, the multimodal brain cognitive function detection device 1000 according to an embodiment of the present invention includes a support 1, a chin rest 2, an image acquisition module 3, a temperature acquisition module 4, a voice acquisition module 5, and a computer 6.
[0035] Among them, bracket 1 is used to install chin support 2, image acquisition module 3, temperature acquisition module 4, voice acquisition module 5 and computer 6, mainly serving as installation support.
[0036] The chin support 2 is mounted on the bracket 1 to support the person's chin and position the person's head, facilitating multimodal brain cognitive function testing.
[0037] Image acquisition module 3 is mounted on bracket 1 and is used to acquire images of a person's face, including the front, left and right sides of the face, the top of the head, and the hands. These images include static images and video information. Since neurological diseases may manifest abnormalities in the appearance of the face, the top of the head, and the hands, using the acquired image information as diagnostic information for cognitive function can help improve the accuracy of cognitive function diagnosis.
[0038] Temperature acquisition module 4 is mounted on bracket 1 and is used to collect temperature information of a person's face and tongue. Since diseases of the brain nervous system may cause abnormalities in the temperature of a person's face and tongue, using the collected temperature information as diagnostic information for brain cognitive function is beneficial to improving the accuracy of brain cognitive function diagnosis.
[0039] The voice acquisition module 5 is mounted on the support 1 and is used to collect human voice information. Since neurological diseases may cause abnormalities in a person's voice, using the collected voice information as diagnostic information for brain cognitive function is beneficial to improving the accuracy of brain cognitive function diagnosis.
[0040] Computer 6 is optional and can be connected to image acquisition module 3, temperature acquisition module 4 and voice acquisition module 5 via data cable. It can store the acquired image information, temperature information and sound information into the database and export them for subsequent deep learning model training. Computer 6 is used to process image information, temperature information and sound information. By comprehensively processing data of different modalities, including different levels and types of data such as image information, temperature information and sound information, the accuracy of diagnosis can be improved.
[0041] The diagnostic information acquisition process of the multimodal brain cognitive function detection device 1000 of this utility model embodiment is as follows: first, static image information is acquired, and then audio and video image information is acquired; wherein, the acquisition of static image information includes three stages: the first stage acquires the frontal image, left side image, right side image and top of the head image of the face; the second stage acquires the frontal image and back image of the tongue; the third stage acquires the frontal image and back image of the hand.
[0042] The multimodal brain cognitive function detection device 1000 according to an embodiment of this utility model acquires image information of a person's face, top of head, and hands through an image acquisition module 3, temperature information of a person's face and tongue through a temperature acquisition module 4, and sound information through a voice acquisition module 5. The acquisition time is short, and the acquired data has multiple dimensions. By comprehensively processing data of different modalities, including image information, temperature information, and sound information, containing different levels and types of data, the accuracy of diagnosis can be improved. Furthermore, the multimodal brain cognitive function detection device 1000 of this utility model features repeatable measurement and non-contact measurement, making measurement convenient, efficient, and low-cost.
[0043] In some embodiments, the image acquisition module 3 includes a face camera 301, a top camera 302, a left camera 303, a right camera 304, and a depth camera 305; the face camera 301 is used to acquire frontal image information of a face; the top camera 302 is used to acquire image information of the top of a person's head and hand; the left camera 303 is used to acquire image information of the left side of a face; the right camera 304 is used to acquire image information of the right side of a face; and the depth camera 305 is used to acquire frontal image information of a face, image information of a tongue, and capture scene information. Understandably, by setting up a face camera 301, a top camera 302, a left camera 303, a right camera 304, and a depth camera 305, when a person's lower jaw is supported on the jaw rest 2, the face camera 301 can easily capture a frontal image of the face, the top camera 302 can easily capture a top-of-the-head image, the left camera 303 can easily capture a left-side image of the face, the right camera 304 can easily capture a right-side image, and the depth camera 305 can easily capture a frontal image of the face and an image of the tongue. This allows the acquisition of multimodal information and the capture of depth information of the scene, i.e., the distance information of each pixel. This enables the depth camera to create 3D models or augmented reality effects.
[0044] In some embodiments, the temperature acquisition module 4 is an infrared temperature camera, which can acquire the temperature of a person's face and tongue. It should be noted that the images captured by the depth camera 305 and the infrared temperature camera are combined with the images captured by the face camera 301 to form a frontal 3D image and a temperature distribution image, which can be used for basic diagnosis.
[0045] In some embodiments, the voice acquisition module 5 is a microphone for acquiring sound. The sound acquisition microphone extracts and processes the voice of the person using high-definition recording.
[0046] In some embodiments, the support 1 includes a tablet 101, a left support 103, a right support 104, and a rear support 102. A chin rest 2 is positioned on the front of the tablet 101, and a microphone is positioned on the tablet 101 and adjacent to the rear of the chin rest 2. This allows the person's jaw to rest on the chin rest 2, enabling them to speak or make sounds close to the microphone, facilitating the microphone's acquisition of vocal information. The computer 6's display screen is positioned on the rear of the tablet 101 for easy viewing by the person being tested or the doctor, facilitating brain cognitive function testing. The left support 103 is located on the left side of the tablet 101, and a left camera 303 is mounted on the left support 103, allowing the left camera 303 to easily capture images of the left side of the face. The right support 104 is located on the right side of the tablet 101, and a right camera 304 is mounted on the right support 104, allowing the left camera 303 to easily capture images of the left side of the face. The rear bracket 102 is located behind the display screen. The face camera 301, top camera 302, depth camera 305 and infrared temperature camera are mounted on the rear bracket 102. This allows the face camera 301 to easily capture frontal images of the face, the depth camera 305 to easily capture frontal image information of the face and tongue, as well as capture scene information, the infrared temperature camera to easily collect the temperature of the face and tongue, and the top camera 302 to easily capture images of the top of the head and hands. The top of the head image is captured first, followed by the hand image. When capturing the hand image, the hand needs to be placed flat on the tablet 101.
[0047] In some embodiments, the rear support 102 includes a rear vertical frame 1021 and a rear cantilever 1022. The lower end of the rear vertical frame 1021 is fixed to the tablet 101. The face camera 301, depth camera 305, and infrared temperature camera are mounted adjacent to each other on the rear vertical frame 1021 and are higher than the display screen. The rear cantilever 1022 extends back and forth above the tablet 101, and the rear end of the rear cantilever 1022 is fixed to the upper end of the rear vertical frame 1021. The top camera 302 is mounted on the rear cantilever 1022. In this way, the face camera 301, depth camera 305, infrared temperature camera, and top camera 302 can conveniently capture their respective desired images.
[0048] In some embodiments, the position of the top camera 302 on the rear cantilever 1022 is adjustable, which makes it convenient for the top camera 302 to take pictures of the top of the head and the hands separately. For example, when it is necessary to take pictures of the top of the head, the position of the top camera 302 is moved directly above the chin rest 2. When it is necessary to take pictures of the hands, the top camera 302 is moved back to a suitable position so that when the hands are placed on the tablet 101, the top camera 302 is just directly above the hands.
[0049] Preferably, the rear cantilever 1022 has a plurality of mounting holes 10221 evenly distributed along the front-rear direction. The top camera 302 is fixed to the rear cantilever 10222 by a fastener engaging with one of the mounting holes 10221. When the top camera 302 needs to be adjusted, the fastener is loosened, the top camera is moved to another suitable mounting hole 10221, and then the fastener engages with that mounting hole 10221 to fix the top camera 302 to the rear cantilever 10222, thus conveniently realizing the front-rear position adjustment of the top camera 302.
[0050] In some embodiments, the chin support 2 can be height-adjusted to accommodate the lower jaw of people of different heights.
[0051] In some embodiments, a control button 7 is also included, which is used to control the raising and lowering of the chin support 2. Thus, when the height of the chin support 2 needs to be adjusted, only the control button 7 needs to be operated.
[0052] In some embodiments, the chin support 2 is provided with a color card, which is used for color normalization.
[0053] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0054] Although embodiments of the present invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the claims and their equivalents.
Claims
1. A multimodal brain cognitive function detection device, characterized in that, include: support; A chin support, which is mounted on the bracket and is used to support a person's chin; An image acquisition module, mounted on a support, is used to acquire image information of a person's face, top of head, and hands. A temperature acquisition module, which is mounted on a bracket, is used to collect temperature information of a person's face and tongue; A voice acquisition module, which is mounted on a bracket, is used to acquire human voice information; The computer is connected to the image acquisition module, the temperature acquisition module, and the voice acquisition module, and is used to process the image information, the temperature information, and the voice information.
2. The multimodal brain cognitive function detection device according to claim 1, characterized in that, The image acquisition module includes a face camera, a top camera, a left camera, a right camera, and a depth camera; the face camera is used to acquire frontal facial image information; the top camera is used to acquire image information of the top of the head and hand; the left camera is used to acquire left-side facial image information; the right camera is used to acquire right-side facial image information; and the depth camera is used to acquire frontal facial image information, tongue image information, and capture scene information.
3. The multimodal brain cognitive function detection device according to claim 2, characterized in that, The temperature acquisition module is an infrared temperature camera.
4. The multimodal brain cognitive function detection device according to claim 3, characterized in that, The voice acquisition module is a microphone for acquiring sound.
5. The multimodal brain cognitive function detection device according to claim 4, characterized in that, The bracket includes a flat plate, a left side bracket, a right side bracket, and a rear side bracket; The chin rest is disposed on the front of the flat plate, and the microphone is disposed on the flat plate and located adjacent to the rear of the chin rest; The computer's display screen is located on the back of the tablet. The left bracket is located on the left side of the tablet, and the left camera is mounted on the left bracket; the right bracket is located on the right side of the tablet, and the right camera is mounted on the right bracket. The rear bracket is located behind the display screen, and the face camera, the top camera, the depth camera, and the infrared temperature camera are mounted on the rear bracket.
6. The multimodal brain cognitive function detection device according to claim 5, characterized in that, The rear support includes a rear vertical frame and a rear cantilever; the lower end of the rear vertical frame is fixed to the tablet, and the face camera, the depth camera, and the infrared temperature camera are mounted on the rear vertical frame adjacent to each other and higher than the display screen; the rear cantilever extends back and forth above the tablet, and the rear end of the rear cantilever is fixed to the upper end of the rear vertical frame, and the top camera is mounted on the rear cantilever.
7. The multimodal brain cognitive function detection device according to claim 6, characterized in that, The position of the top camera on the rear cantilever is adjustable.
8. The multimodal brain cognitive function detection device according to any one of claims 1-7, characterized in that, The chin rest is height-adjustable.
9. The multimodal brain cognitive function detection device according to claim 8, characterized in that, It also includes a control button for controlling the raising and lowering of the chin rest.
10. The multimodal brain cognitive function detection device according to any one of claims 1-7, characterized in that, The chin rest is equipped with a color card.