A method and system for assisting body position guidance

Abstract

This invention relates to the field of body positioning guidance technology and discloses an auxiliary body positioning guidance method, including the following steps: S1: Installing cameras, multiple cameras are installed around the detector of the X-ray examination equipment to ensure coverage of the subject's whole-body posture capture range; S2: Image capture, after the subject enters the examination area, the cameras capture their whole-body image in real time; This invention also proposes an auxiliary body positioning guidance system, including a system module assembly, which includes an information acquisition module, an algorithm module, a posture assessment module, and a voice interaction module. This invention establishes a standardized body positioning assessment system through AI algorithms, completely avoiding positioning deviations caused by differences in human experience, ensuring that the examination image parameters of different technicians and at different times remain consistent, and allowing for accurate comparison of lesion changes during clinical diagnosis, significantly reducing the risk of missed diagnosis and misdiagnosis caused by non-standard body positioning.

Description

Technical Field

[0001] This invention relates to the field of body positioning guidance technology, specifically to an auxiliary body positioning guidance method and system. Background Technology

[0002] Chest X-ray is a medical imaging examination method commonly used to observe and diagnose chest diseases and abnormalities. It uses the transmissive properties of X-rays to image the internal structures and tissues of the human body, and these images are used to detect and identify diseases.

[0003] In chest X-ray (DR) examinations, the correctness of the patient's positioning directly determines the image quality and the accuracy of clinical diagnosis. Incorrect positioning and improper attention to detail can easily lead to missed or misdiagnosed cases. In DR imaging teaching practice, it has been found that medical imaging technology interns commonly exhibit problems such as non-standard positioning, failure to remove foreign objects from the examination site, improper left and right markings, and unclear centerline positioning, directly affecting diagnostic results. Traditional positioning guidance methods heavily rely on the operator's experience, and individual differences in operation lead to insufficient consistency in positioning, becoming a core bottleneck restricting the standardization of examination quality.

[0004] The accuracy of patient positioning relies heavily on the operator's solid understanding of human anatomy. Normal human anatomy is the foundation of practical medical imaging techniques. A weak foundation in this knowledge can easily lead to deviations in crucial aspects such as patient positioning and centerline localization, further highlighting the limitations of traditional manual guidance methods. Existing positioning guidance methods, which depend on manual experience and basic theoretical knowledge, struggle to achieve precise and standardized control, failing to meet the stringent clinical demands for examination quality. Summary of the Invention

[0005] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides an auxiliary positioning guidance method and system that integrates depth vision recognition, posture estimation algorithms, and a voice interaction module. By assessing the examinee's position in real time and providing intelligent feedback, it breaks through the limitations of traditional methods, achieves standardized guidance for chest X-ray examination positioning, and thus improves examination quality and diagnostic efficiency.

[0006] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: A method for assisted positioning includes the following steps: S1: Install cameras. Mount multiple cameras around the detector of the X-ray examination equipment to ensure full-body posture capture of the subject; S2: Image capture. After the examinee enters the examination area, the camera captures a full-body image in real time and extracts key skeletal points of the human body through the algorithm module to generate a human skeleton model. S3: Posture Assessment. The posture assessment model pre-sets standard postural parameters for chest X-ray examination. It compares the coordinates of key points detected in real time with the standard parameters and calculates the postural deviation value. The postural deviation value is the difference between the coordinates of key points in the examinee's real-time posture and the standard postural parameters, including angular deviation and positional offset. S4: Feedback Adjustment: If the body position deviation exceeds the preset threshold, the voice interaction module will automatically play an adjustment prompt; if the deviation is within the threshold, the voice prompt will say "Body position is qualified, prepare for X-ray", and a ready signal for X-ray will be sent to the X-ray inspection equipment to trigger the inspection process.

[0007] Furthermore, in step S1, a voice player is installed simultaneously with the camera for voice broadcasting, and the camera is a high-definition camera.

[0008] Based on the foregoing, the algorithm module in S2 is the MediaPipe algorithm.

[0009] As a further aspect of the present invention, the posture evaluation model in S3 is obtained by AI simulation of a human skeleton model.

[0010] Furthermore, the pose evaluation model in S3 includes a DeepPose network, a BRNN network, and an output layer. The DeepPose network extracts static frame features from the preprocessed image, the BRNN network extracts dynamic frame features from the preprocessed image, and the output layer uses the static and dynamic frame features to obtain the coordinate prediction values ​​of multiple skeleton key points in the preprocessed image.

[0011] This invention also proposes an assisted posture guidance system, comprising a system module assembly. The system module assembly includes an information acquisition module, an algorithm module, a posture assessment module, and a voice interaction module. The information acquisition module includes multiple cameras to collect information, and is connected to the algorithm module, which uses the MediaPipe algorithm. The algorithm module is connected to a control module, which is connected to the posture assessment module and the voice interaction module. The posture assessment module evaluates whether the subject's posture exceeds a threshold. If it does, the control module controls the voice interaction module to perform voice communication adjustments, including a feedback module and an adjustment module.

[0012] Furthermore, the system module assembly includes a feedback module, which is connected to the posture evaluation module, the voice interaction module, and the control module.

[0013] (III) Beneficial Effects Compared with the prior art, the present invention provides an assisted posture guidance method and system, which has the following beneficial effects: 1. This invention improves image consistency and diagnostic accuracy: By establishing a standardized body positioning assessment system through AI algorithms, it completely avoids positioning deviations caused by differences in human experience, ensuring consistent image parameters across different technicians and at different times. This allows for precise comparison of lesion changes during clinical diagnosis, significantly reducing the risk of missed or misdiagnosed cases due to improper positioning. 2. This invention reduces reliance on technicians and optimizes manpower allocation: Technicians are no longer required to provide one-on-one guidance to patients throughout the entire examination process, significantly reducing the examination time for each patient and greatly improving efficiency; novice technicians can operate proficiently after simple training, significantly lowering the professional training threshold and labor costs, and effectively alleviating the shortage of medical human resources. 3. This invention is adaptable to multiple scenarios and lowers the application threshold: It can be directly integrated into existing X-ray examination equipment and self-service physical examination terminals without large-scale hardware modifications, significantly reducing the equipment upgrade and maintenance costs for medical institutions. It adapts to the actual application needs of medical scenarios at all levels, and can address the pain points of insufficient technician resources and uneven professional levels in primary medical institutions and community physical examination centers. Through intelligent and standardized guidance, it can achieve high-quality examinations, narrow the gap in image quality between primary and higher-level hospitals, directly improve the service capacity of primary medical institutions, and help promote the downward flow and balanced development of medical resources. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the process structure of an assisted body positioning guidance method in this invention.

[0015] Figure 2 This is a schematic diagram of the system framework of an auxiliary body positioning guidance system in this invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1

[0017] Reference Figure 1-2 An assisted posture guidance method includes the following steps: S1: Install cameras. Multiple cameras are mounted around the detector of the X-ray examination equipment to ensure full-body posture capture of the subject. A voice player is also installed in S1 to provide voice announcements. The cameras in S1 are high-definition cameras. S2: Image capture. After the subject enters the examination area, the camera captures the full-body image in real time and extracts key skeletal points of the human body through the algorithm module to generate a human skeleton model. The algorithm module in S2 is the MediaPipe algorithm. S3: Posture assessment. The posture assessment model presets standard postural parameters for chest X-ray examination (e.g., in the anterior view, the acromion line is parallel to the horizontal edge of the detector, the body midline coincides with the vertical line of the detector, and in the lateral view, the scapula is in contact with the detector). The coordinates of key points detected in real time are compared with the standard parameters to calculate the postural deviation value. In S3, the postural deviation value is the difference between the coordinates of key points in the examinee's real-time postural position and the standard postural parameters, including angular deviation (e.g., the tilt angle of the acromion line) and positional offset (e.g., the distance between the body midline and the detector midline). S4: Feedback Adjustment: If the body position deviation exceeds the preset threshold (e.g., angle deviation > 5°, position offset > 3cm), the voice interaction module will automatically play adjustment prompts (e.g., "Please move 2 cm to the left" or "Please spread your shoulders back and keep them horizontal"); if the deviation is within the threshold, the voice prompt will say "Body position is qualified, prepare for X-ray", and a ready signal for X-ray examination will be sent to the X-ray examination equipment to trigger the examination process.

[0018] An assisted posture guidance system includes a system module assembly. The system module assembly includes an information acquisition module, an algorithm module, a posture assessment module, and a voice interaction module. The information acquisition module includes multiple cameras to acquire information. The information acquisition module is connected to the algorithm module, which uses the MediaPipe algorithm. The algorithm module is connected to a control module, which is connected to the posture assessment module and the voice interaction module. The posture assessment module assesses whether the posture of the person being tested exceeds a threshold. If it does, the control module controls the voice interaction module to make adjustments via voice communication. Example 2

[0019] Reference Figure 1-2 An assisted posture guidance method includes the following steps: S1: Install cameras. Multiple cameras are mounted around the detector of the X-ray examination equipment to ensure full-body posture capture of the subject. A voice player is also installed in S1 to provide voice announcements. The cameras in S1 are high-definition cameras. S2: Image capture. After the subject enters the examination area, the camera captures the full-body image in real time and extracts key skeletal points of the human body through the algorithm module to generate a human skeleton model. The algorithm module in S2 is the MediaPipe algorithm. S3: Posture Assessment. The posture assessment model pre-sets standard posture parameters for chest X-ray examination (e.g., in the anterior view, the acromion line is parallel to the horizontal edge of the detector, and the body midline coincides with the vertical line of the detector; in the lateral view, the scapula is in contact with the detector). It compares the coordinates of key points detected in real-time with the standard parameters to calculate the posture deviation value. In S3, the posture deviation value is the difference between the coordinates of key points in the examinee's real-time posture and the standard posture parameters, including angular deviation (e.g., the tilt angle of the acromion line) and positional offset (e.g., the distance between the body midline and the detector midline). The posture assessment model in S3 is obtained through AI simulation of a human skeleton model. The posture assessment model in S3 includes a DeepPose network, a BRNN network, and an output layer. The DeepPose network extracts static frame features from the preprocessed image, the BRNN network extracts dynamic frame features from the preprocessed image, and the output layer uses the static and dynamic frame features to obtain the predicted coordinate values ​​of multiple skeletal key points in the preprocessed image. S4: Feedback Adjustment: If the body position deviation exceeds the preset threshold (e.g., angle deviation > 5°, position offset > 3cm), the voice interaction module will automatically play adjustment prompts (e.g., "Please move 2 cm to the left" or "Please spread your shoulders back and keep them horizontal"); if the deviation is within the threshold, the voice prompt will say "Body position is qualified, prepare for X-ray", and a ready signal for X-ray examination will be sent to the X-ray examination equipment to trigger the examination process.

[0020] An assisted posture guidance system includes a system module assembly. The system module assembly includes an information acquisition module, an algorithm module, a posture assessment module, and a voice interaction module. The information acquisition module includes multiple cameras to acquire information. The information acquisition module is connected to the algorithm module, which uses the MediaPipe algorithm. The algorithm module is connected to a control module, which is connected to the posture assessment module and the voice interaction module. The posture assessment module assesses whether the posture of the person being tested exceeds a threshold. If it does, the control module controls the voice interaction module to make adjustments via voice communication.

[0021] In the description herein, it should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0022] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for assisting in postural guidance, characterized in that, Includes the following steps: S1: Install cameras. Mount multiple cameras around the detector of the X-ray examination equipment to ensure full-body posture capture of the subject; S2: Image capture. After the examinee enters the examination area, the camera captures a full-body image in real time and extracts key skeletal points of the human body through the algorithm module to generate a human skeleton model. S3: Posture Assessment. The posture assessment model pre-sets standard postural parameters for chest X-ray examination. It compares the coordinates of key points detected in real time with the standard parameters and calculates the postural deviation value. The postural deviation value is the difference between the coordinates of key points in the examinee's real-time posture and the standard postural parameters, including angular deviation and positional offset. S4: Feedback Adjustment: If the body position deviation exceeds the preset threshold, the voice interaction module will automatically play an adjustment prompt; if the deviation is within the threshold, the voice prompt will say "Body position is qualified, prepare for X-ray", and a ready signal for X-ray will be sent to the X-ray inspection equipment to trigger the inspection process.

2. The assisted positioning guidance method according to claim 1, characterized in that, In step S1, a voice player is installed at the same time as the camera to provide voice broadcasts, and the camera is a high-definition camera.

3. The assisted positioning guidance method according to claim 1, characterized in that, The algorithm module in S2 is the MediaPipe algorithm.

4. The assisted positioning guidance method according to claim 1, characterized in that, The posture evaluation model in S3 is obtained by AI simulation of the human skeleton model.

5. The assisted positioning guidance method according to claim 1, characterized in that, The pose evaluation model in S3 includes a DeepPose network, a BRNN network, and an output layer. The DeepPose network extracts static frame features from the preprocessed image, the BRNN network extracts dynamic frame features from the preprocessed image, and the output layer uses the static and dynamic frame features to obtain the coordinate prediction values ​​of multiple skeleton key points in the preprocessed image.

6. An assisted posture guidance system, characterized in that, The system includes a system module assembly, which comprises an information acquisition module, an algorithm module, a posture assessment module, and a voice interaction module. The information acquisition module includes multiple cameras to collect information and is connected to the algorithm module, which uses the MediaPipe algorithm. The algorithm module is connected to a control module, which is connected to the posture assessment module and the voice interaction module. The posture assessment module evaluates whether the subject's posture exceeds a threshold. If it does, the control module controls the voice interaction module to make adjustments via voice communication, including a feedback module and an adjustment module.

7. The assisted positioning guidance system according to claim 6, characterized in that, The system module assembly includes a feedback module, which is connected to the posture evaluation module, the voice interaction module, and the control module.

Images