A scoliosis identification system and method based on active millimeter-wave imaging technology.

Abstract

The present invention relates to scoliosis identification, and more specifically to a scoliosis identification system and method based on active millimeter-wave imaging technology. The active millimeter-wave scanning assembly emits millimeter-wave signals of a specific frequency band onto the back of the human body, receives the reflected signals from the back of the human body, and transmits the received reflected signals to a terminal control device, thereby realizing a non-invasive scan of the back of the human body. The active millimeter-wave tablet device drives the active millimeter-wave scanning assembly under the control of the terminal control device to scan from top to bottom and acquire three-dimensional morphological data of the back of the human body. The pressure sensing device measures pressure profile data of the human body while standing and transmits the collected pressure profile data to the terminal control device. The technical solution provided by the present invention can effectively overcome the drawbacks of the prior art, such as low accuracy and efficiency in scoliosis identification when faced with high-throughput and high-speed periodic screening.

Description

[Technical Field]

[0001] This invention relates to scoliosis identification, and more specifically to a scoliosis identification system and method based on active millimeter-wave imaging technology. [Background technology]

[0002] In the field of medicine, idiopathic scoliosis is a common condition in adolescents, and its severity cannot be ignored. A prominent characteristic of this condition is the abnormal curvature of the spine when viewed from the front. This not only detracts from the aesthetic appearance of the patient but can also cause back pain, difficulty breathing, and other serious complications. Therefore, timely detection and treatment of scoliosis are crucial for ensuring the patient's health and improving their quality of life.

[0003] While the diagnosis and treatment of scoliosis have advanced considerably, in clinical practice, mild to moderate scoliosis symptoms are often overlooked by patients and their guardians because they are not noticeable. Furthermore, insufficient awareness of the condition among schools and medical staff can lead to missed diagnoses, increasing the risk of disease progression.

[0004] Currently, medical imaging tests such as X-rays and CT scans play a crucial role in the definitive diagnosis of scoliosis. However, these imaging methods inevitably cause some degree of ionizing radiation damage to patients, especially growing children and adolescents. Furthermore, medical imaging technologies are not suitable as routine monitoring tools due to their high cost and operational complexity.

[0005] While B-mode ultrasound has some practical value in the examination of scoliosis, it is rarely used in actual routine monitoring. This is mainly due to a lack of physicians with the expertise to perform the procedure and interpret the results, which limits the application of B-mode ultrasound technology in large-scale screening and routine monitoring.

[0006] The leveling method is a widely recommended and preferred screening method due to its ease of use. However, this method has low accuracy, is susceptible to body sway and other factors, and can lead to errors in the test results. Furthermore, it relies on human operation and is time-consuming.

[0007] While binocular vision function testing, a non-invasive examination method, can reduce reliance on human intervention to some extent, it has limitations in that it is susceptible to external factors such as changes in ambient light and differences in examination angles. Furthermore, like the reflex level measurement method, binocular vision function testing is also susceptible to body sway and external disturbances, limiting its application in daily monitoring.

[0008] As described above, currently used methods for examining spinal curvature have certain limitations, and these shortcomings become particularly apparent when faced with the demands for high-throughput and rapid periodic screening. Therefore, developing new spinal curvature examination techniques to improve the accuracy and efficiency of scoliosis identification is now an urgent task. [Overview of the project] [Problems that the invention aims to solve]

[0009] The present invention provides a scoliosis identification system and method based on active millimeter-wave imaging technology that can effectively overcome the drawbacks of the prior art, namely the low accuracy and efficiency of scoliosis identification when faced with high-throughput and high-speed periodic screening. [Means for solving the problem]

[0010] To achieve the above objective, the present invention is realized by the following technical solutions.

[0011] The scoliosis identification system based on active millimeter-wave imaging technology includes an active millimeter-wave scanning assembly, an active millimeter-wave tablet device, a pressure sensing device, a plantar indication module, a terminal display device, and a terminal control device. An active millimeter-wave scanning assembly emits millimeter-wave signals of a specific frequency band onto the back of the human body, receives the reflected signals from the back, and transmits the received reflected signals to a terminal control device, thereby achieving a non-invasive scan of the back of the human body. The active millimeter-wave tablet device drives the active millimeter-wave scanning assembly under the control of the terminal control device to scan from top to bottom, acquiring 3D morphological data of the human back. The pressure sensing device measures pressure profile data of a standing human body and transmits the collected pressure profile data to a terminal control device. The terminal control device evaluates whether the human body's posture and position are standard based on pressure profile data, generates corresponding feedback information if the posture and position are not standard, and guides the user to adjust their posture and position using a foot sole instruction module. It also examines whether the human body's spine is curved based on the echo signal, generates a corresponding diagnostic report according to the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device. The terminal display device shows the scan progress, device status, scoliosis identification results, and diagnostic report in real time.

[0012] Preferably, the terminal control device includes a pressure profile data preprocessing module, a pressure profile data analysis module, a critical position inspection module, and a standing posture and position evaluation module. The pressure profile data preprocessing module digitizes the received pressure profile data, removes noise, and converts it into a data format suitable for algorithmic analysis through normalization. The pressure profile data analysis module performs bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. The critical position inspection module inspects the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performs position identification and position comparison analysis of the foot shape in the pressure sensing device. The standing posture and stance evaluation module combines the symmetry of the pressure profile and the result of the stance comparison analysis to evaluate whether the standing posture and stance of the human body are standard, generates corresponding feedback information when the standing posture and stance are not standard, and transmits the feedback information to the sole instruction module, so as to guide the user by the sole instruction module to adjust the standing posture and stance. Here, the sole instruction module guides the user to adjust the standing posture and stance by voice or visual cues.

[0013] Preferably, the pressure profile data analysis module performs bilateral foot pressure profile analysis based on the preprocessed pressure profile data, and the steps of determining the center of gravity weight of the human body and the symmetry of the pressure profile include the following: Calculate the bilateral foot pressure profiles with the following formula: JPEG2026521285000002.jpg2240JPEG2026521285000003.jpg2950 Here, C L (t) is the left foot pressure value profile at time t, P i (t) is the pressure value detected by the i-th pressure sensor under the left foot at time t, x i is the coordinate on the plane of the i-th pressure sensor under the left foot, m is the number of pressure sensors under the left foot, C R (t) is the right foot pressure value profile at time t, P j (t) is the pressure value detected by the j-th pressure sensor under the right foot at time t, y j is the coordinate on the plane of the j-th pressure sensor under the right foot, n is the number of pressure sensors under the right foot, Calculate the center of gravity weight of the human body based on the bilateral foot pressure profiles with the following formula: JPEG2026521285000004.jpg2750Here, W L (t), W R (t) are the left foot center of gravity weight and the right foot center of gravity weight at time t respectively, S L, S R are the left foot contact area and the right foot contact area respectively, Based on the center of gravity weight of the human body, calculate the symmetry score of the pressure profile by the following formula: JPEG2026521285000005.jpg1444 Here, S(t) is the symmetry score of the pressure profile at time t. When the symmetry score of the pressure profile is higher than 0.85, it indicates that the standing posture of the human body is symmetrical, meeting the requirement of posture symmetry. Otherwise, the standing posture of the human body is not symmetrical and does not meet the requirement of posture symmetry.

[0014] Preferably, the terminal control device includes a response signal preprocessing module, a back key point identification module, a spinal column fitting analysis module, and a diagnosis report generation module. The response signal preprocessing module performs filtering and noise removal processing on the received response signal and converts it into 3D form data of the human back. The back key point identification module uses the deep learning algorithm BlazePose to identify the back key points from the 3D form data of the human back, and then divides the 3D data of the human back. The spinal column fitting analysis module identifies the preliminary curve of the spinal column contour using an improved active contour algorithm based on the 3D data of the human back, and then performs cubic B-spline curve smoothing to obtain the fitted curve of the spinal column contour. The diagnosis report generation module checks whether the human spinal column is scoliosis based on the calculated Cobb angle of the spinal column, and generates a corresponding diagnosis report based on the identification result of spinal scoliosis. It transmits both the identification result of spinal scoliosis and the diagnosis report to the terminal display device. Here, the back key points include bilateral acromions, scapulas, lumbar dimples, and iliac crests. The diagnosis report includes the Cobb angle of the spinal column, the spinal scoliosis severity interval, and corresponding medical suggestions.

[0015] The spinal scoliosis identification method based on the active millimeter wave imaging technology is Step S1 involves starting up the active millimeter-wave tablet device and the active millimeter-wave scan assembly, allowing the system to enter a scan waiting state, and automatically executing inspection and spatial calibration procedures to ensure scan accuracy. Step S2: The user stands in a designated position based on the foot position identifier in the pressure sensing device. Step S3 involves a pressure sensing device measuring pressure profile data of a standing human body and transmitting the collected pressure profile data to a terminal control device. Step S4 involves a terminal control device evaluating whether the human body's standing posture and position are standard based on pressure profile data, generating corresponding feedback information if the standing posture and position are not standard, and guiding the user to adjust their standing posture and position using a foot sole instruction module. Step S5 involves repeating steps S3-S4 until the posture and position meet standard requirements, Step S6 involves an active millimeter-wave tablet device and an active millimeter-wave scanning assembly beginning to perform a non-invasive scan of the back of a person, the active millimeter-wave scanning assembly emitting a millimeter-wave signal of a specific frequency band onto the back of the person, and transmitting the received echo signals from the back of the person to a terminal control device. Step S7 involves a terminal control device inspecting whether the human spine is curved based on the echo signal, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to a terminal display device. Step S8 includes a terminal display device that displays the scoliosis identification results and diagnostic report in real time, and which can be electronically transmitted or printed by a terminal control device, and which is used by medical staff for further analysis and to formulate a treatment plan.

[0016] Preferably, in S4, the terminal control device evaluates whether the human body's standing posture and position are standard based on pressure profile data, generates corresponding feedback information if the standing posture and position are not standard, and instructs the user to adjust their standing posture and position using the sole instruction module. Step S41 involves digitizing the received pressure profile data, removing noise, and converting it into a data format suitable for algorithmic analysis through normalization. Step S42 involves performing a bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. Step S43 involves examining the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performing a position comparison analysis with the foot shape identifier in a pressure sensing device. Step S44 includes: evaluating whether the human body's standing posture and position are standard by combining the results of pressure profile symmetry and position comparison analysis, generating corresponding feedback information if the standing posture and position are not standard, and transmitting the feedback information to the foot sole instruction module, thereby guiding the user to adjust their standing posture and position via the foot sole instruction module; Here, the foot support module guides the user through voice or visual cues to adjust their posture and position.

[0017] Preferably, in S7, the terminal control device checks whether the human spine is curved based on the echo signal, generates a corresponding diagnostic report based on the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device. Step S71 involves filtering and noise reduction processing the received echo signal and converting it into 3D morphological data of the human back. Step S72 involves using the deep learning algorithm BlazePose to identify important points on the back from 3D morphological data of the human back, and then dividing the 3D data of the human back into segments. Step S73 involves identifying preliminary curves of the spinal contour using an improved active contour algorithm based on 3D data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour. Step S74 includes examining whether the human spine is scoliotic based on the calculated Cobb angle of the spine, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to a terminal display device. Here, key points of the back include both acromions, scapulae, lumbar dimples, and iliac crests, and the diagnostic report includes the Cobb angle of the spine, the degree of scoliosis, and corresponding medical recommendations.

[0018] Preferably, in S73, the steps of identifying a preliminary curve of the spinal contour using an improved active contour algorithm based on three-dimensional data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour are as follows: Step S731 initializes the curve at the central axis position of the 3D data of the human back as an initial curve that approximates the true contour of the spine, The active contour algorithm constructs an energy function that includes internal energy terms and external energy terms, where internal energy maintains the degree of curve smoothing and structure, and external energy, based on image gradient information, pulls the initial curve closer to the edge of the spine according to the magnitude of the gradient in step S732. Step S733 involves updating the initial curve position based on the decreasing direction of the gradient of the energy function, minimizing the energy function through iterations, and gradually approximating the initial curve to the true contour of the spine. Step S734 involves setting a stopping condition such that the decrease in the energy function falls below a threshold or the number of iterations reaches the upper limit, and after the iterations are completed, removing outliers to obtain a preliminary curve of the spinal contour. The process includes step S735, which involves obtaining a fitted curve for the contour of the spine using cubic B-spline curve smoothing. [Effects of the Invention]

[0019] Compared to conventional technologies, the scoliosis identification system and method based on active millimeter-wave imaging technology provided by the present invention offers a radiation-free, high-precision, high-throughput, high-speed, periodic, and user-friendly scoliosis identification system and method by introducing active millimeter-wave imaging technology. Based on the principle of millimeter-wave radar, it acquires 3D morphological data of the human back by transmitting and receiving millimeter-wave signals, and then applies deep learning algorithms and surface fitting algorithms to perform spinal key point identification and 3D spinal morphological analysis, respectively. Finally, it calculates the Cobb angle of the spine and generates a corresponding diagnostic report. Such a method not only improves the accuracy and efficiency of scoliosis identification but also helps reduce the risk of oversight and misdiagnosis, protects user privacy, and provides a solid foundation for early treatment and improved quality of life for scoliosis patients. The present invention specifically includes the following beneficial effects: 1) Protection of user privacy: By performing scoliosis examination using active millimeter-wave imaging technology without requiring the user to undress or assume a specific posture, user privacy is protected. 2) No direct contact required: Millimeter-wave imaging technology enables non-invasive scanning within a certain distance without requiring medical staff to have direct physical contact with the user, respecting user privacy and reducing the workload of medical staff. 3) Convenient inspection process: The entire scanning process is fast and automated, requiring users to simply stand on the scanning platform as instructed, without needing to perform any other complex tasks, thus making the inspection process more convenient. 4) Reducing human error: By adopting an automated scanning and analysis flow, reliance on operators is reduced, thereby avoiding situations where inaccurate scoliosis identification occurs due to human factors. 5) Immediate result feedback: The system can provide immediate scoliosis identification results and diagnostic reports, eliminating the need for long waits and meeting the demands for high-throughput and rapid periodic screening. [Brief explanation of the drawing]

[0020] To more clearly illustrate embodiments of the present invention or technical solutions in the prior art, the following briefly introduces the drawings necessary for describing the embodiments or prior art. Clearly, the drawings in the following description are merely some embodiments of the present invention, and those skilled in the art can obtain further drawings based on these without any creative effort. [Figure 1] This is a schematic diagram of the system of the present invention. [Figure 2] Figure 1 is a schematic plan view of the pressure sensing device of the present invention. [Figure 3] This is a schematic diagram of the results of identifying important points on the back in the present invention. [Figure 4] This is a schematic flowchart of the present invention. [Modes for carrying out the invention]

[0021] To further clarify the objectives, technical solutions, and advantages of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the drawings of the embodiments. Clearly, the embodiments described are some, but not all, embodiments of the present invention. All other embodiments obtained based on the embodiments of the present invention without the creative effort of those skilled in the art are all within the scope of protection of the present invention.

[0022] As shown in Figure 1, the scoliosis identification system based on active millimeter-wave imaging technology includes an active millimeter-wave scanning assembly 1, an active millimeter-wave tablet device 2, a pressure sensing device 3, a sole-positioning module 4, a terminal display device 5, and a terminal control device 6. The active millimeter-wave scanning assembly 1 emits a millimeter-wave signal of a specific frequency band (Ka-band) onto the back of the human body, receives the reflected signal from the back of the human body, and transmits the received reflected signal to the terminal control device 6, thereby achieving a non-invasive scan of the back of the human body. The active millimeter-wave tablet device 2, under the control of the terminal control device 6, drives the active millimeter-wave scan assembly 1 to scan from top to bottom, acquiring 3D morphological data of the human back. The pressure sensing device 3 measures pressure profile data of the human body while it is standing (collecting pressure profile data from each of the two feet using two sets of pressure sensor arrays, as shown in Figure 2), and transmits the collected pressure profile data to the terminal control device 6. The terminal control device 6 evaluates whether the human body's standing posture and position are standard based on pressure profile data, generates corresponding feedback information if the standing posture and position are not standard, and guides the user to adjust their standing posture and position using the sole instruction module 4. It also checks whether the human body's spine is curved based on the echo signal, generates a corresponding diagnostic report according to the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device 5. Terminal display device 5 displays the scan progress, device status, scoliosis identification results, and diagnostic report in real time.

[0023] 1. The terminal control device 6 includes a pressure profile data preprocessing module, a pressure profile data analysis module, a critical position inspection module, and a standing posture and position evaluation module. The pressure profile data preprocessing module digitizes the received pressure profile data, removes noise, and normalizes it (to remove the influence of different user weights) to convert it into a data format suitable for algorithmic analysis. The pressure profile data analysis module performs bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. The critical position inspection module inspects the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performs a position comparison analysis with the foot shape position identifier (shown in Figure 2) in the pressure sensing device 3. The posture and position evaluation module combines the results of pressure profile symmetry and position comparison analysis to evaluate whether the human body's posture and position are standard, generates corresponding feedback information if the posture or position is not standard, and transmits this feedback information to the foot sole instruction module 4, which then guides the user to adjust their posture and position. Here, the foot support module 4 guides the user to adjust their posture and position using voice or visual cues (for example, "move your left foot slightly forward" or "straighten your hips").

[0024] Specifically, the pressure profile data analysis module performs a bilateral pressure profile analysis based on pre-processed pressure profile data, and the steps to determine the center of gravity weight and pressure profile symmetry of the human body include the following: The bilateral pressure profile is calculated using the following formula: JPEG2026521285000006.jpg2243JPEG2026521285000007.jpg2748 Here, C L (t) is the left foot pressure profile at time t, P i (t) is the pressure value measured by the i-th pressure sensor located below the left foot at time t, and x i is the coordinate on the plane of the i-th pressure sensor below the left foot, and m is the number of pressure sensors below the left foot. C R (t) is the right foot pressure profile at time t, P j (t) is the pressure value measured by the j-th pressure sensor located below the right foot at time t, and y j is the coordinate on the plane of the j-th pressure sensor below the right foot, and n is the number of pressure sensors below the right foot. Based on the bilateral pressure profile, the weight of the human body's center of gravity is calculated using the following formula: JPEG2026521285000008.jpg2751 Here, W L (t), W R(t) represents the weight distribution of the left foot and the right foot at time t, respectively, and S L S R These represent the contact area of ​​the left foot and the contact area of ​​the right foot, respectively. The symmetry score of the pressure profile is calculated using the following formula based on the weight of the human body's center of gravity: JPEG2026521285000009.jpg1448 Here, S(t) is the symmetry score of the pressure profile at time t. A symmetry score of the pressure profile greater than 0.85 indicates that the standing posture of the human body is symmetrical and satisfies the requirement of symmetry. Otherwise, the standing posture of the human body is not symmetrical and does not satisfy the requirement of symmetry.

[0025] 2. The terminal control device 6 includes a reverberation signal preprocessing module, a back key point identification module, a spinal column alignment analysis module, and a diagnostic report generation module. The echo signal preprocessing module performs filtering and noise reduction on the received echo signal and converts it into 3D morphological data of the human back. The back importance point identification module uses the deep learning algorithm BlazePose to identify important points on the back (shown in Figure 3) from 3D morphological data of the human back, and then divides the 3D data of the human back. The spinal alignment analysis module uses an improved active contour algorithm to identify preliminary curves of the spinal contour based on 3D data of the human back, and then performs cubic B-spline curve smoothing to obtain a fitted curve for the spinal contour. The diagnostic report generation module examines whether the human spine is curvature based on the calculated Cobb angle of the spine (an important parameter for measuring the degree of spinal curvature), generates a corresponding diagnostic report based on the spinal curvature identification result, and transmits both the spinal curvature identification result and the diagnostic report to the terminal display device 5. Here, key points of the back include both acromions, scapulae, lumbar dimples, and iliac crests, and the diagnostic report includes the Cobb angle of the spine, the degree of scoliosis, and corresponding medical recommendations.

[0026] In the technical solution of this application, as shown in Figure 4, a method for identifying scoliosis based on active millimeter-wave imaging technology is further provided. Step S1 involves starting the active millimeter-wave tablet device 2 and the active millimeter-wave scan assembly 1, allowing the system to enter a scan waiting state, and automatically executing inspection and spatial calibration procedures to ensure scan accuracy. Step S2 involves the user standing in a designated position based on the foot position identifier in the pressure sensing device 3, Step S3 involves the pressure sensing device 3 measuring pressure profile data of a standing human body and transmitting the collected pressure profile data to the terminal control device 6. Step S4 involves the terminal control device 6 evaluating whether the human body's standing posture and position are standard based on pressure profile data, generating corresponding feedback information if the standing posture and position are not standard, and instructing the user to adjust their standing posture and position using the sole instruction module 4. Step S5 involves repeating steps S3-S4 until the posture and position meet standard requirements, Step S6 involves the active millimeter-wave tablet device 2 and the active millimeter-wave scan assembly 1 beginning to perform a non-invasive scan of the back of a person, the active millimeter-wave scan assembly 1 emitting a millimeter-wave signal of a specific frequency band onto the back of the person, and transmitting the received echo signal from the back of the person to the terminal control device 6. Step S7 involves the terminal control device 6 inspecting whether the human spine is curved based on the echo signal, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to the terminal display device 5. Step S8 includes a terminal display device 5 that displays the scoliosis identification results and diagnostic report in real time, and which can be electronically transmitted or printed by a terminal control device 6, and which is used by medical staff for further analysis and to formulate a treatment plan.

[0027] 1. In S4, the terminal control device 6 evaluates whether the human body's standing posture and position are standard based on pressure profile data, generates corresponding feedback information if the standing posture and position are not standard, and instructs the user to adjust their standing posture and position using the sole instruction module 4. Step S41 involves digitizing the received pressure profile data, removing noise, and converting it into a data format suitable for algorithmic analysis through normalization. Step S42 involves performing a bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. Step S43 involves inspecting the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performing a position comparison analysis with the foot shape identifier (shown in Figure 2) in the pressure sensing device 3. Step S44 includes: evaluating whether the human body's standing posture and position are standard by combining the results of the symmetry of the pressure profile and the position comparison analysis; generating corresponding feedback information if the standing posture and position are not standard; and transmitting the feedback information to the sole instruction module 4, thereby guiding the user to adjust their standing posture and position via the sole instruction module 4. Here, the foot support module 4 guides the user through voice or visual signals to adjust their posture and position.

[0028] 2, In S7, the terminal control device 6 checks whether the human spine is curved based on the echo signal, generates a corresponding diagnostic report based on the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device 5. Step S71 involves filtering and noise reduction processing the received echo signal and converting it into 3D morphological data of the human back. Step S72 involves using the deep learning algorithm BlazePose to identify important points on the back from 3D morphological data of the human back, and then dividing the 3D data of the human back into segments. Step S73 involves identifying preliminary curves of the spinal contour using an improved active contour algorithm based on 3D data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour. Step S74 includes examining whether the human spine is scoliotic based on the calculated Cobb angle of the spine, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to the terminal display device 5. Here, key points of the back include both acromions, scapulae, lumbar dimples, and iliac crests, and the diagnostic report includes the Cobb angle of the spine, the degree of scoliosis, and corresponding medical recommendations.

[0029] Specifically, in S73, the steps of identifying a preliminary curve of the spinal contour using an improved active contour algorithm based on 3D data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour are as follows: Step S731 initializes the curve at the central axis position of the 3D data of the human back as an initial curve that approximates the true contour of the spine, The active contour algorithm constructs an energy function that includes internal energy terms and external energy terms, where internal energy maintains the degree of curve smoothing and structure, and external energy, based on image gradient information, pulls the initial curve closer to the edge of the spine according to the magnitude of the gradient in step S732. Step S733 involves updating the initial curve position based on the decreasing direction of the gradient of the energy function, minimizing the energy function through iterations, and gradually approximating the initial curve to the true contour of the spine. Step S734 involves setting a stopping condition such that the decrease in the energy function falls below a threshold or the number of iterations reaches the upper limit, and after the iterations are completed, removing outliers to obtain a preliminary curve of the spinal contour. The process includes step S735, which involves obtaining a fitted curve for the contour of the spine using cubic B-spline curve smoothing.

[0030] The present invention provides a radiation-free, high-precision, high-throughput, high-speed, periodic, and user-friendly scoliosis identification system and method by introducing active millimeter-wave imaging technology. Based on the principle of millimeter-wave radar, it acquires 3D morphological data of the human back by transmitting and receiving millimeter-wave signals. Subsequently, it applies deep learning algorithms and surface fitting algorithms to perform spinal keypoint identification and 3D spinal morphological analysis, respectively. Finally, it calculates the Cobb angle of the spine and generates a corresponding diagnostic report. This method not only improves the accuracy and efficiency of scoliosis identification but also helps reduce the risk of oversight and misdiagnosis, protects user privacy, and provides a solid foundation for early treatment and improved quality of life for scoliosis patients.

[0031] The above embodiments are merely for illustrating the technical solutions of the present invention and do not limit the present invention. Although the present invention has been described in detail with reference to the above embodiments, as will be understood by those skilled in the art, it is still possible to modify the technical solutions described in the above embodiments or to substitute some of their technical features equally, and such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. The system includes an active millimeter-wave scanning assembly (1), an active millimeter-wave tablet device (2), a pressure sensing device (3), a sole-mounted indicator module (4), a terminal display device (5), and a terminal control device (6), The active millimeter-wave scanning assembly (1) emits a millimeter-wave signal of a specific frequency band onto the back of the human body, receives the reflected signal from the back of the human body, and transmits the received reflected signal to a terminal control device (6), thereby realizing a non-invasive scan of the back of the human body. The active millimeter-wave tablet device (2) drives the active millimeter-wave scan assembly (1) under the control of the terminal control device (6) to scan from top to bottom and acquire three-dimensional morphological data of the human back. The pressure sensing device (3) measures the pressure profile data of a standing human body and transmits the collected pressure profile data to the terminal control device (6). The terminal control device (6) evaluates whether the human body's standing posture and position are standard based on pressure profile data, generates corresponding feedback information if the standing posture and position are not standard, and guides the user to adjust their standing posture and position using the sole instruction module (4), and also checks whether the human body's spine is curved based on the echo signal, generates a corresponding diagnostic report according to the spinal scoliosis identification result, and transmits both the spinal scoliosis identification result and the diagnostic report to the terminal display device (5). The terminal display device (5) is a scoliosis identification system based on active millimeter-wave imaging technology, characterized by displaying scan progress, device status, scoliosis identification results, and diagnostic reports in real time.

2. The terminal control device (6) includes a pressure profile data preprocessing module, a pressure profile data analysis module, a critical position inspection module, and a standing posture and position evaluation module. The pressure profile data preprocessing module digitizes the received pressure profile data, removes noise, and converts it into a data format suitable for algorithmic analysis through normalization. The pressure profile data analysis module performs bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. The critical position inspection module inspects the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performs positional identification and positional comparison analysis of the foot shape in the pressure sensing device (3). The posture and position evaluation module combines the results of pressure profile symmetry and position comparison analysis to evaluate whether the human body's posture and position are standard, generates corresponding feedback information if the posture or position is not standard, and transmits this feedback information to the sole instruction module (4), thereby guiding the user to adjust their posture and position via the sole instruction module (4). Herein, the foot support module (4) guides the user to adjust their standing posture and position using voice or visual cues, characterized in that it is a scoliosis identification system based on active millimeter-wave imaging technology as described in claim 1.

3. The pressure profile data analysis module performs a bilateral pressure profile analysis based on pre-processed pressure profile data and determines the center of gravity weight and pressure profile symmetry of the human body, and the steps include the following: The bilateral pressure profile is calculated using the following formula: Here, C Ｌ (t) is the left foot pressure profile at time t, P ｉ (t) is the pressure value measured by the i-th pressure sensor located below the left foot at time t, and x ｉ is the coordinate on the plane of the i-th pressure sensor below the left foot, and m is the number of pressure sensors below the left foot. C Ｒ (t) is the right foot pressure profile at time t, P ｊ (t) is the pressure value measured by the j-th pressure sensor located below the right foot at time t, and y ｊ n is the coordinate on the plane of the j-th pressure sensor below the right foot, and n is the number of pressure sensors below the right foot. Based on the bilateral pressure profile, the weight of the human body's center of gravity is calculated using the following formula: Here, W Ｌ (t), W Ｒ (t) are the left-foot center-of-gravity weights and right-foot center-of-gravity weights at time t, respectively, and S Ｌ , S Ｒ are the left-foot contact area and right-foot contact area, respectively, The symmetry score of the pressure profile is calculated using the following formula based on the weight of the human body's center of gravity: Here, S(t) is the symmetry score of the pressure profile at time t, and if the symmetry score of the pressure profile is higher than 0.85, it indicates that the standing posture of the human body is symmetrical and satisfies the requirement of symmetry of posture, and if it is not higher, the standing posture of the human body is not symmetrical and does not satisfy the requirement of symmetry of posture, characterized in that the scoliosis identification system based on active millimeter-wave imaging technology according to claim 2.

4. The terminal control device (6) includes a reverberation signal preprocessing module, a back key point identification module, a spinal column alignment analysis module, and a diagnostic report generation module. The echo signal preprocessing module performs filtering and noise reduction processing on the received echo signal, and converts it into 3D morphological data of the human back. The back importance point identification module uses the deep learning algorithm BlazePose to identify important points on the back from 3D morphological data of the human back, and then divides the 3D data of the human back. The spinal alignment analysis module uses an improved active contour algorithm to identify preliminary curves of the spinal contour based on 3D data of the human back, and then performs cubic B-spline curve smoothing to obtain a fitted curve for the spinal contour. The diagnostic report generation module examines whether the human spine is scoliotic based on the calculated Cobb angle of the spine, generates a corresponding diagnostic report based on the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device (5). Herein, the key points of the back include both acromions, scapulae, lumbar dimples, and iliac crests, and the diagnostic report includes the Cobb angle of the spine, the degree of scoliosis, and the corresponding medical recommendations, characterized in that the scoliosis identification system based on active millimeter-wave imaging technology according to claim 1.

5. A method for identifying scoliosis based on active millimeter-wave imaging technology, which is applied to the scoliosis identification system based on active millimeter-wave imaging technology described in claim 1, Step S1 involves starting the active millimeter-wave tablet device (2) and the active millimeter-wave scan assembly (1), allowing the system to enter a scan waiting state, and automatically executing inspection and spatial calibration procedures to ensure scan accuracy. Step S2 involves the user standing in a designated position based on the foot position identifier in the pressure sensing device (3), Step S3 involves the pressure sensing device (3) measuring pressure profile data of a standing human body and transmitting the collected pressure profile data to the terminal control device (6), Step S4 involves the terminal control device (6) evaluating whether the human body's standing posture and position are standard based on pressure profile data, generating corresponding feedback information if the standing posture and position are not standard, and instructing the user to adjust their standing posture and position using the sole instruction module (4), Step S5 involves repeating steps S3 and S4 until the posture and position meet standard requirements, Step S6 involves the active millimeter-wave tablet device (2) and the active millimeter-wave scan assembly (1) beginning to perform a non-invasive scan of the back of a person, the active millimeter-wave scan assembly (1) emitting a millimeter-wave signal of a specific frequency band onto the back of the person, and transmitting the received echo signal from the back of the person to the terminal control device (6), Step S7 involves the terminal control device (6) inspecting whether the human spine is curved based on the echo signal, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to the terminal display device (5). A method for identifying spinal scoliosis based on active millimeter-wave imaging technology, characterized by including step S8, in which a terminal display device (5) displays the spinal scoliosis identification results and diagnostic report in real time, and a terminal control device (6) can electronically transmit or print them, which are used by medical staff for further analysis and to formulate a treatment plan.

6. In S4, the terminal control device (6) evaluates whether the human body's standing posture and position are standard based on pressure profile data, generates corresponding feedback information if the standing posture and position are not standard, and instructs the user to adjust their standing posture and position using the sole instruction module (4). Step S41 involves digitizing the received pressure profile data, removing noise, and converting it into a data format suitable for algorithmic analysis through normalization. Step S42 involves performing a bilateral pressure profile analysis based on pre-processed pressure profile data to determine the center of gravity weight and pressure profile symmetry of the human body. Step S43 involves inspecting the positions of the heel, arch, and sole of the forefoot of the human body based on pre-processed pressure profile data, and performing a position comparison analysis with the foot shape identifier in the pressure sensing device (3). Step S44 includes combining the results of pressure profile symmetry and position comparison analysis to evaluate whether the human body's standing posture and position are standard, generating corresponding feedback information if the standing posture and position are not standard, and transmitting the feedback information to the sole-foot instruction module (4), thereby guiding the user to adjust their standing posture and position via the sole-foot instruction module (4). Herein, the foot support module (4) guides the user to adjust their standing posture and position using voice or visual cues, characterized in that the scoliosis identification method based on active millimeter-wave imaging technology according to claim 5.

7. In S7, the terminal control device (6) checks whether the human spine is curved based on the echo signal, generates a corresponding diagnostic report based on the scoliosis identification result, and transmits both the scoliosis identification result and the diagnostic report to the terminal display device (5). Step S71 involves filtering and noise reduction processing the received echo signal and converting it into three-dimensional morphological data of the human back. Step S72 involves using the deep learning algorithm BlazePose to identify important points on the back from 3D morphological data of the human back, and then dividing the 3D data of the human back into sections. Step S73 involves identifying preliminary curves of the spinal contour using an improved active contour algorithm based on 3D data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour. Step S74 includes examining whether the human spine is scoliotic based on the calculated Cobb angle of the spine, generating a corresponding diagnostic report based on the scoliosis identification result, and transmitting both the scoliosis identification result and the diagnostic report to a terminal display device (5). Herein, the important points on the back include both acromions, scapulae, lumbar dimples, and iliac crests, and the diagnostic report includes the Cobb angle of the spine, the degree of scoliosis, and the corresponding medical recommendations, characterized in that the method for identifying scoliosis based on active millimeter-wave imaging technology according to claim 6.

8. In S73, the steps of identifying a preliminary curve of the spinal contour using an improved active contour algorithm based on three-dimensional data of the human back, and then performing cubic B-spline curve smoothing to obtain a fitted curve of the spinal contour are as follows: Step S731 initializes the curve at the central axis position of the 3D data of the human back as an initial curve that approximates the true contour of the spine, The active contour algorithm constructs an energy function that includes internal energy terms and external energy terms, where the internal energy maintains the degree of curve smoothing and structure, and the external energy, based on image gradient information, pulls the initial curve closer to the edge of the spine according to the magnitude of the gradient in step S732. Step S733 involves updating the initial curve position based on the decreasing direction of the gradient of the energy function, minimizing the energy function through iteration, and gradually approximating the initial curve to the true contour of the spine. Step S734 involves setting a stopping condition such that the decrease in the energy function falls below a threshold or the number of iterations reaches the upper limit, and after the iterations are completed, removing outliers to obtain a preliminary curve of the spinal contour. A method for identifying scoliosis based on active millimeter-wave imaging technology according to claim 7, comprising step S735 of obtaining a fit curve of the spinal contour using cubic B-spline curve smoothing.

Images