Scoliosis screening device and method

By using a millimeter-wave radar imaging device to scan the back of the human body, high-quality SAR images are generated, which solves the problems of low efficiency, large error and high cost of scoliosis detection in the prior art, and achieves convenience, safety and low Cost of scoliosis screening.

CN119014818APending Publication Date: 2024-11-26CHANGCHUN UNIV OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411121957.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

At this stage, there is a convenient, harmless and low-priced scoliosis detection method. The existing artificial methods are inefficient and have large errors. Image methods such as CT and X-ray are expensive and harmful to the human body, making them difficult to apply to large Scale of scoliosis screening phase.

Method used

The millimeter-wave radar imaging device is adopted, including a computer terminal, a motion control module, a data acquisition module and a power supply module. The back of the human body is scanned by a data acquisition module through a two-dimensional slide rail, and the signal processing unit and a data processing unit are used to perform signals. Preprocessing and imaging, an imaging algorithm based on amplitude factor compensation generates high-quality SAR images for judging scoliosis type.

Benefits of technology

It realizes automated detection, reducing errors, millimeter-wave radar is harmless to the human body and is inexpensive, suitable for large-scale scoliosis screening, ensuring the safety and privacy of the detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119014818A_ABST
    Figure CN119014818A_ABST
Patent Text Reader

Abstract

The invention discloses a device and a method for scoliosis screening, and belongs to the field of scoliosis detection. The device comprises a motion control module, a data acquisition module, a power supply module and a computer end, the detection method comprises the following steps: scanning the back of a subject by using a two-dimensional sliding rail carrying a millimeter wave radar to obtain echo information, pre-processing the obtained original echo data, and respectively carrying out two-dimensional space Fourier transform on the pre-processed original echo data and a reference function of an amplitude factor in horizontal and vertical directions to convert the pre-processed original echo data into a wavenumber domain; carrying out coherent superposition under multiple wave numbers by dividing the two images and adopting dimension reduction operation to obtain a wave number domain form of the focused image, and then carrying out two-dimensional inverse Fourier transform on the wave number domain form to obtain a scattering intensity distribution diagram of the back of the subject, namely, an SAR image of the back of the subject; and finally, inputting the SAR image of the back of the subject into the trained model, and outputting a scoliosis screening result. According to the method, high-precision imaging and intelligent classification technologies are integrated, higher-quality SAR images are obtained while the imaging efficiency is improved, non-contact, non-radiation and high-privacy scoliosis screening is achieved, errors existing in manual measurement are effectively reduced, and the method is used for risk assessment of early-stage scoliosis of teenagers.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of scoliosis detection, and in particular to a device and method for scoliosis screening. Background Art

[0002] Scoliosis patients suffer from physical retardation, deformed appearance, and cardiopulmonary dysfunction. In severe cases, their lives may be in danger. my country advocates "early detection and early treatment" and includes scoliosis screening in adolescent physical examinations.

[0003] At present, the main methods for scoliosis screening are manual method and image method. The manual method is inefficient, has large errors, and wastes doctor's manpower; image methods such as CT method and X-ray method may cause harm to the human body and are expensive, and are more suitable for the recovery examination stage after scoliosis is diagnosed; these two scoliosis detection methods cannot be effectively applied to the large-scale census stage. Therefore, at this stage, there is a lack of a convenient, harmless, low-cost scoliosis detection method suitable for the screening stage.

[0004] The detection method of using millimeter-wave radar to image the back of the human body and then judging scoliosis based on the imaging results can be used in the scoliosis screening stage. Compared with the manual method, millimeter-wave radar imaging detection has a higher degree of automation and a smaller error caused by subjective judgment; the radar does not touch the back of the subject and can penetrate clothing to image the back, which has better privacy; compared with the imaging method, millimeter waves are non-ionizing radiation, harmless to the human body, and cheaper. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] The present invention provides a scoliosis screening device and method to solve the problems of low efficiency, large error, waste of manpower in manual detection and high price of CT method and X-ray method.

[0007] (II) Technical solution

[0008] The present invention proposes a millimeter wave radar imaging device and method for scoliosis screening. The device mainly comprises: a computer terminal, a motion control module, a data acquisition module, and a power supply module.

[0009] The motion control module includes a two-dimensional slide rail, a slider, a motor, a driver, and a controller; the slider is installed on the two-dimensional slide rail, and the data acquisition module is installed on the slider, and the movement of the slider is controlled to control the movement of the data acquisition module; the controller is connected to the computer end, receives the control instructions sent by the computer end instruction control unit, and controls the start and stop and movement through the driver to complete the execution of the control instructions; the data acquisition module is composed of a transmitting unit, a receiving unit, a signal processing unit, and a data processing unit; the transmitting unit includes a transmitter and a transmitting antenna for transmitting millimeter wave signals; the receiving unit includes a receiver and a receiving antenna for receiving millimeter wave signals; the signal processing unit is used to process the echo signal, improve the signal-to-noise ratio of the target echo, suppress clutter and interference, and perform target detection; the data processing unit is used to provide high-speed data conversion, data reception and processing, and is responsible for capturing the echo data processed by the signal processing unit and transmitting it to the computer end;

[0010] The computer end includes a command control module, a data preprocessing module and an imaging module. The command control module is used to control the two-dimensional slide motion of the motion control module and the data acquisition of the data acquisition module; the data preprocessing module is used to preprocess the received human back echo data, and the preprocessing process includes: frequency removal, matched filtering and phase correction; the imaging module is used to image the data processed by the data preprocessing module using an imaging algorithm based on amplitude factor compensation.

[0011] The power module mainly provides power to hardware devices.

[0012] The computer end is connected with the motion control module and the data acquisition module respectively.

[0013] A method for scoliosis screening, using the above device, specifically comprises the following steps:

[0014] Step 1: Initialize the system and determine the system parameters and mechanical scanning parameters. Build the hardware acquisition scene according to the system structure diagram, determine the experimental parameters, and prepare for data acquisition;

[0015] Step 2: Use the two-dimensional slide rail equipped with a data acquisition module to perform a bow-shaped scan on the back of the human body, and obtain the echo data of the back of the human body according to the instructions sent by the computer. The echo data is transmitted to the computer-side data preprocessing module after passing through the signal processing unit and the data processing unit;

[0016] Step 3: pre-processing the scanned human back echo data by frequency removal, matched filtering, and phase correction;

[0017] Step 4: The pre-processed data is imaged using an imaging algorithm based on amplitude factor compensation, thereby improving the imaging efficiency and obtaining a higher quality SAR image, namely, a SAR image of the subject's back;

[0018] Step 5: Determine the type of scoliosis based on the SAR image of the back of the human body;

[0019] Furthermore, the system initialization and determination of system parameters and mechanical scanning parameters include the following steps:

[0020] Step 1.1: Before starting the scan, the entire system needs to be initialized, including starting the data acquisition module, checking the motion control system of the guide rail, and ensuring the correct communication between all components;

[0021] Step 1.2: Set system parameters; according to the experimental requirements, calculate the system parameters, such as operating frequency band, starting frequency, number of ADC sampling points, number of chirp signals, frame interval period, number of frames and sampling rate, etc.;

[0022] Step 1.3: Set the mechanical scanning path parameters; according to the size of the human back, the type of data to be acquired and the accuracy requirements, set the mechanical scanning path parameters; the mechanical scanning path parameters include the number of data acquisition points in the horizontal direction, the number of data acquisition points in the vertical direction, the distance between the target and the plane where the acquisition module is located, the horizontal sampling interval, and the vertical sampling interval;

[0023] Furthermore, a two-dimensional slide rail equipped with a data acquisition module is used to perform a bow-shaped scan on the back of a human body to obtain echo data of the back of the human body, including the following steps:

[0024] Step 2.1: The person to be tested stands in front of the two-dimensional array scanning device in single clothing, parallel to the moving plane of the two-dimensional array scanning device, with both hands hanging naturally and keeping still;

[0025] Step 2.2: The two-dimensional array scanning device is equipped with a data acquisition module and placed at the scanning starting point. According to the control instructions transmitted by the computer, a bow-shaped scan of the human back plane is performed from the starting point according to the planned mechanical array path. The transmitting unit of the data acquisition module transmits millimeter wave signals, and the receiving unit receives the echo data of the human back. The data acquisition module transmits the collected data back to the computer in real time.

[0026] Step 2.3: According to the control command sent by the computer, the two-dimensional slide rail of the motion control module moves to the specified position and stops moving. At the same time, the data acquisition module also stops working, and all echo data are transmitted to the computer.

[0027] Further, the human body back echo data obtained by scanning is preprocessed, including the following steps:

[0028] Step 3.1: De-frequency modulate the echo data from the back of the human body, restore the modulated signal reflected from the target to the original signal, and extract useful information such as distance and speed from the signal for subsequent signal processing; Step 3.2: Perform matched filtering on the de-frequency modulated data, and perform correlation matching between the back template and the de-frequency modulated echo data to achieve pulse compression and improve the distance resolution;

[0029] Step 3.3: Perform phase correction on the data after matched filtering; when the original echo signal is de-frequency modulated, a residual video phase term will be introduced. Therefore, it is necessary to perform RVP correction compensation on the echo signal to ensure that the signals are superimposed in phase and improve the imaging quality.

[0030] Furthermore, the preprocessed data is imaged using an imaging algorithm based on amplitude factor compensation to obtain a SAR image of the back of a human body, including the following steps:

[0031] Step 4.1: Introduce the amplitude factor reference function, and perform two-dimensional spatial Fourier transform on it and the preprocessed echo signal in the horizontal and vertical directions respectively, and convert it into the wave number domain;

[0032] Step 4.2: Perform a division operation on the echo signal in the wavenumber domain and the reference function of the amplitude factor, and use a dimensionality reduction operation to coherently superimpose at multiple wavenumbers to obtain the wavenumber domain form of the focused image;

[0033] Step 4.3: Perform a two-dimensional inverse Fourier transform to convert the wavenumber domain into the spatial domain to obtain the target scattering intensity distribution map, that is, the SAR imaging result map of the human back.

[0034] Further, judging the type of scoliosis according to the SAR image of the back of the human body includes the following steps:

[0035] Step 5.1: Acquire simulated SAR images of models with different degrees of scoliosis through millimeter-wave radar near-field imaging simulation and construct a data set;

[0036] Step 5.2: After matching the features of the simulated human back SAR image with the corresponding labels, the image is annotated and the corresponding label is assigned to each sample;

[0037] Step 5.3: Select a classification algorithm for model deployment and training;

[0038] Step 5.4: Input the millimeter-wave radar near-field human back image into the trained model, and output the scoliosis screening result, which is classified into: normal spine, scoliosis;

[0039] (III) Beneficial effects

[0040] Compared with the prior art, the present invention provides a scoliosis screening device and method, which has the following features:

[0041] Beneficial effects:

[0042] The present invention uses millimeter wave radar to image the back of the human body. Since millimeter wave radar can penetrate clothes, the subject does not need to take off clothes for scoliosis screening, which has good privacy.

[0043] The present invention uses millimeter wave radar to image the back of the human body. Since millimeter waves are harmless to the human body, the detection process has no risk of harming the health of the subject and has high safety.

[0044] The present invention uses millimeter wave radar to image the back of the human body. Since the imaging equipment is inexpensive and simple, each school, hospital, etc. can install the equipment to conduct large-scale and rapid scoliosis screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the structure of the scoliosis screening device of the present invention;

[0046] Figure 2 This is a schematic diagram of the back scanning trajectory of the present invention;

[0047] Figure 3 It is a system structure diagram of the present invention;

[0048] Figure 4 is a flow chart of the method of the present invention;

[0049] In the figure: 1. Computer end; 2. Motion control module; 3. Two-dimensional slide rail; 4. Data acquisition module; 5. Controller and drive; 6. Power module; DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example

[0052] like Figure 1 As shown, an embodiment of the present invention provides a device for scoliosis screening, including a motion control module, a data acquisition module, a computer terminal, and a power supply module.

[0053] In this embodiment, a scoliosis screening is performed on a teenager, whose basic information is as follows: male, 15 years old, height 163 cm, weight 65 kg.

[0054] Step 1: System initialization and determination of system parameters and mechanical scanning parameters. Before starting the scan, the entire system needs to be initialized, including starting the data acquisition module, checking the motion control system of the guide rail, and ensuring the correct communication between all components; selecting system parameters and setting the mechanical scanning path parameters according to the actual back size of the teenager;

[0055] Step 2: The teenager is asked to stand in front of the two-dimensional array scanning device in single clothes at the position to be tested, parallel to the moving plane of the two-dimensional array scanning device, with both hands hanging naturally and keeping still; the two-dimensional array scanning device is equipped with a data acquisition module and placed at the scanning starting point, and performs a bow-shaped scan of the human back plane from the starting point according to the planned mechanical array path according to the control instructions transmitted by the computer end, the transmitting unit of the data acquisition module transmits millimeter wave signals, the receiving unit receives the echo data of the human back, and the data acquisition module transmits the collected data back to the computer end in real time; according to the control instructions sent by the computer end, the two-dimensional slide rail of the motion control module stops moving after moving to the specified position, and the data acquisition module also stops working, and all echo data are transmitted to the computer end;

[0056] Using frequency modulated continuous wave as the transmission signal model, the radar echo data s(x, y, k) is the superposition of the round-trip phase of each scattering point on the measured target, that is:

[0057]

[0058] Expands to:

[0059]

[0060] Step 3: De-frequency modulate the echo data from the back of the human body, restore the modulated signal reflected from the target to the original signal, and extract useful information such as distance and speed from the signal for subsequent signal processing; perform matched filtering on the de-frequency modulated data, and perform correlation matching between the back template and the de-frequency modulated echo data to achieve pulse compression and improve the distance resolution; perform phase correction on the matched filtered data; When de-frequency modulating the original echo signal, a residual video phase term will be introduced, so it is necessary to perform RVP correction compensation on the echo signal to ensure that the signals are superimposed in phase and improve the imaging quality;

[0061] Step 4: Perform two-dimensional spatial Fourier transform on the preprocessed echo signal and the reference function considering the amplitude factor in the horizontal and vertical directions respectively, and convert them into the wavenumber domain; then divide the two and use dimensionality reduction operation to coherently superimpose them at multiple wavenumbers to obtain the wavenumber domain form of the focused image, and then perform a two-dimensional inverse Fourier transform to convert the wavenumber domain to the spatial domain to obtain the target scattering intensity distribution map, which is the SAR imaging result map of the teenager's back.

[0062] The echo signal s(x, y, k) and the reference function h(x, y, k) considering the amplitude factor are transformed into the wave number domain by performing two-dimensional spatial Fourier transform in the horizontal and vertical directions respectively; x , k y and k z are the three components in the wave number domain, and the two-dimensional Fourier transform of p(x′, y′) is P(k x , k y ), so the wavenumber domain form of the reconstructed image is

[0063]

[0064] The two-dimensional Fourier transform of s(x, y, k) is S(k x , k y , k). The echo signal in the wavenumber domain is divided by the reference function, and the dimension reduction operation is used to coherently superimpose at multiple wavenumbers to obtain the wavenumber domain form of the focused image, and the reconstructed target image is

[0065]

[0066] Step 5: Input the SAR image of the adolescent's back into the trained model, and output the scoliosis screening result, which is: the spine is normal;

[0067] The scoliosis screening result indicated that the adolescent did not have scoliosis.

[0068] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A device and method for scoliosis screening, the device comprising: a computer terminal (1), a motion control module (2), a data acquisition module (4), and a power supply module (6).

2. The device according to claim 1, characterized in that: The motion control module (2) comprises a two-dimensional slide rail (3), a slider, a motor, a driver, and a controller; the data acquisition module (4) comprises a transmitting unit, a receiving unit, a signal processing unit, and a data processing unit; and the computer end (1) comprises a command control module, a data preprocessing module, and an imaging module.

3. The device according to claim 1, further characterized in that: The power supply module (6) supplies power to the motion control module (2) and the data acquisition module (4); the data acquisition module (4) communicates bidirectionally with the computer end (1); and the command control module of the computer end (1) sends commands for controlling the motion of the two-dimensional slide rail in the motion control module (2) and commands for data acquisition in the data acquisition module (4).

4. The device according to claim 1, further characterized in that: The motion control module (2) receives control instructions sent by the controller, controls the operation of the motor through the driver to control the start and stop motion, and thus completes the execution of the control instructions; the data acquisition module (4) receives control instructions sent by the instruction module of the computer end (1).

5. The device according to claim 1, further characterized in that: The transmitting unit in the data acquisition module (4) comprises a transmitter and a transmitting antenna for transmitting millimeter wave signals; the receiving unit comprises a receiver and a receiving antenna for receiving millimeter wave signals; the signal processing unit is used to process the echo signal, improve the signal-to-noise ratio of the target echo, suppress clutter and interference, and perform target detection; the data processing unit is used to provide high-speed data conversion, data reception and processing, and is responsible for capturing the echo data processed by the signal processing unit and transmitting it to the computer end.

6. The device and method according to claim 1, further characterized in that: The command control module of the computer end (1) is used to control the two-dimensional slide rail movement of the motion control module (2) and the data collection of the data collection module (4); The data preprocessing module is used to preprocess the received human back echo data, and the preprocessing process includes: frequency removal, matched filtering and phase correction; the imaging module is used to image the data processed by the data preprocessing module using an imaging algorithm based on amplitude factor compensation.

7. The device and method according to claim 1, further characterized in that: A method for scoliosis screening, using the above device, specifically comprises the following steps: Step 1: System initialization and determination of system parameters and mechanical scanning parameters. Before starting the scan, initialize the entire system and select system parameters and mechanical scanning path parameters according to the experimental requirements, such as system operating frequency band, number of ADC sampling points, number of chirp signals, sampling rate, sampling interval, etc. Step 2: Use a two-dimensional slide rail equipped with a data acquisition module to mechanically scan the back of the human body, and obtain the echo data of the back of the human body according to the instructions sent by the computer. The echo data is transmitted to the computer data preprocessing module after passing through the signal processing unit and the data processing unit; Step 3: preprocessing the scanned human back echo data by frequency removal, matched filtering and phase correction; Step 4: The pre-processed data is imaged using an imaging algorithm based on amplitude factor compensation, thereby improving the imaging efficiency and obtaining a higher quality SAR image, namely, a SAR image of the subject's back; Step 5: Construct a human back SAR image dataset through near-field SAR imaging simulation. After annotation and labeling, use the classification algorithm to deploy and train the model. Input the imaging results based on the echo data obtained by radar scanning into the trained model and output the scoliosis type judgment result.