Portable muscle quality assessment system for screening of sarcopenia

Abstract

Disclosed is a portable muscle quality assessment system (100) for screening of sarcopenia, comprising: a memory (110), storing personal information data of a user; an ultrasonic sensing apparatus (130), measuring muscle parameters and transmitting ultrasonic sensing data to the memory (110); a force sensing apparatus (140), measuring muscle strength and transmitting force sensing data to the memory (110); a motion sensing apparatus (150), measuring a pace and / or a gait of the user during motion and transmitting motion sensing data to the memory (110); and a processor (120), generating, on the basis of the personal information data, the ultrasonic sensing data, the force sensing data, and the motion sensing data on the memory (110), an assessment report on whether the user suffers from sarcopenia and the severity thereof.

Description

Portable muscle mass assessment system for sarcopenia screening

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present disclosure claims priority to Chinese patent application number 202410269629X, filed on March 11, 2024, entitled “Portable Muscle Mass Assessment System for Sarcopenia Screening”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to a portable muscle mass assessment system for sarcopenia screening and methods of using the same. Background Art

[0004] [Corrected 25.03.2025 in accordance with Rule 26] Falls are the leading cause of trauma-related deaths in the elderly, most of which are followed by intracranial injuries (ICIs). The risk of falls in the elderly is associated with obvious factors such as visual impairment, degenerative joint disease, and the use of antiplatelet or anticoagulant medications. However, risk factors such as gait abnormalities and decreased muscle mass (also known as sarcopenia) are often overlooked when screening for fall risk in the elderly. Among older adults in Hong Kong, China, approximately 11.2% of men and 7.6% of women suffer from sarcopenia.

[0005] Sarcopenia refers to the degenerative loss of skeletal muscle mass, quality, and strength with age or inactivity. Sarcopenia is an aging or degenerative process with a loss of 0.5-1% per year after the age of 50. Figure 1 shows the statistics of muscle mass loss with age. Sarcopenia can progress faster due to pathological or behavioral factors such as malnutrition or lack of adequate muscle training. Sarcopenia is characterized by a loss of muscle mass and muscle strength, which is associated with decreased physical function in the elderly and an increased risk of falls and fractures. Studies have also shown that patients with sarcopenia have increased hospitalization rates and fall-related mortality rates.

[0006] The diagnostic criteria for sarcopenia have many elements. In addition to quantifying muscle mass, recent approaches to assessing sarcopenia have emphasized functional testing such as gait, gait speed, sit-to-stand time, and grip strength. Gait assessment can be performed using a human movement maturation system mounted on the floor of an indoor laboratory environment, force plates, or through observation by trained clinicians. The facility and labor costs of gait assessment make frequent assessments challenging and may result in delayed diagnosis of severe cases that require immediate medical attention.

[0007] According to the recommendations of the "Asian Working Group on Sarcopenia (AWGS): 2019 Consensus Update on the Diagnosis and Treatment of Sarcopenia" (hereinafter referred to as the AWGS Consensus), the diagnosis of sarcopenia includes case detection through calf circumference measurement, SARC-F (strength, walking assistance, sit-to-stand, stair climbing, and falls) questionnaire, and muscle strength, physical performance assessment, and skeletal muscle mass. The AWGS consensus introduces the detection and severity assessment criteria for sarcopenia and provides a reference for the determination of sarcopenia in Asians. Although the AWGS consensus provides clinical thresholds for the diagnosis of sarcopenia, it does not specify the measurement methods in clinical operations, such as the measurement location of muscles or body posture.

[0008] Current assessments of sarcopenia include the use of computed tomography (CT), magnetic resonance imaging (MRI), dual-energy X-ray absorptiometry (DXA), or bioimpedance analyzer (BIA) to quantify muscle mass. For example, CN115376681A provides an automatic screening method for sarcopenia based on artificial intelligence. The method establishes an online screening and diagnosis platform based on an artificial intelligence model. The input data of the artificial intelligence model is based on the patient's personal data and abdominal CT plain scan images. Although this method reduces manual intervention, the input data is still based on abdominal CT images. Such methods are expensive and have radiation risks and cannot be applied to home or community monitoring. In addition, the above-mentioned equipment is not suitable for testing individual muscles.

[0009] Ultrasound imaging (USI) can measure all muscles in different locations, including superficial and deep parameters, and measure area and thickness in different body postures. Ultrasound has the advantages of being non-invasive and low-cost, and can directly identify specific muscles at risk of sarcopenia by visualizing them directly.

[0010] WO2021048776A1 provides a method for assessing sarcopenia based on MRI, CT, or ultrasound imaging. However, this method focuses on a diagnostic method for assessing sarcopenia by measuring the area of ​​the pectoral muscle at the distal end, primarily due to the association between breast cancer and sarcopenia. Therefore, this method is not universally applicable for diagnosing sarcopenia and cannot cover the multiple indicators mentioned in the AWGS consensus.

[0011] KR102436035B1 provides a device for diagnosing skeletal muscle conditions from ultrasound images using a deep neural network (DNN). This method focuses on using a deep neural network to build an ultrasound image-based artificial intelligence model to diagnose sarcopenia. Similarly, this method does not consider the device's portability or include the multiple indicators mentioned in the AWGS consensus for a comprehensive analysis of sarcopenia. Furthermore, this method does not specify measurement location or body posture.

[0012] There is a need in the art for a portable assessment system that is low-cost, easy to operate, highly reliable, and convenient for repeated monitoring, which can enable the elderly or susceptible people to screen for sarcopenia at home or in the community. Summary of the Invention

[0013] The present disclosure provides a portable muscle mass assessment system for screening sarcopenia, the system comprising: a memory, which stores a user's personal information data; an ultrasonic sensing device, which measures muscle parameters and transmits the ultrasonic sensing data to the memory; a force sensing device, which measures muscle strength and transmits the force sensing data to the memory; a motion sensing device, which measures the user's pace and / or gait during exercise and transmits the motion sensing data to the memory; and a processor, which generates an assessment report on whether the user suffers from sarcopenia and the severity of the disease based on the personal information data, ultrasonic sensing data, force sensing data, and motion sensing data in the memory.

[0014] In some embodiments, the ultrasonic sensing device is a portable ultrasonic probe with a force detection function, and the portable ultrasonic probe includes a force sensor.

[0015] In some embodiments, the muscle parameter includes one or more of the following: muscle amount, muscle thickness, muscle area, muscle hardness, and / or muscle activity.

[0016] In some embodiments, the ultrasonic sensing device uses the U-Net algorithm to segment the ultrasonic image and automatically measures muscle parameters through deep learning PyTorch.

[0017] In some embodiments, the force sensing device is a grip force sensor that detects the user's arm muscle strength.

[0018] In some embodiments, the motion sensing device is a wearable inertial measurement unit (IMU) for detecting the user's walking speed and / or gait performance.

[0019] In some embodiments, one or more of the following devices can be integrated into one hardware device: a memory, a processor, an ultrasound sensor device, a force sensor device, and / or a motion sensor device.

[0020] In some embodiments, data is transmitted between the ultrasound sensor device, the force sensor device, the motion sensor device and the memory via wired or wireless means.

[0021] In some embodiments, the personal information data includes one or more of the following: name, gender, year of birth, height, weight, calf circumference, and / or a questionnaire based on strength, walking assistance, sit-to-stand, stair climbing, and falls SARC-F.

[0022] In some embodiments, the system further includes an input device, which inputs the user's personal information data into the system manually or imports it through a file.

[0023] In some embodiments, the system further includes an output device, and a user interface UI is displayed on the output device, and the UI displays one or more of the following: software and hardware installation instructions, login settings, error diagnosis, personal information data, settings and activation of each sensing device, ultrasonic sensing data and / or analysis, force sensing data and / or analysis, motion sensing data and / or analysis, and / or evaluation reports.

[0024] In some embodiments, the UI is a display interface of a personal computer, a display interface of a laptop computer, a display interface of a tablet application, a display interface of a mobile phone application, or a display interface of other portable devices.

[0025] In some embodiments, the assessment report is saved locally and / or uploaded to the network according to user settings.

[0026] The present disclosure also provides a method for using a portable muscle quality assessment system, the method comprising: a user logs into the system; the system determines whether the user is a new user, and if so, creates a user profile for the new user, otherwise the old user chooses whether to update the user profile; the user fills out a questionnaire; a connected ultrasonic sensor device is used to measure muscle parameters, and the ultrasonic sensor data is transmitted to the system; a connected force sensor device is used to measure muscle strength, and the force sensor data is transmitted to the system; a connected motion sensor device is used to measure the user's pace and / or gait during exercise, and the motion sensor data is transmitted to the system; and a comprehensive analysis is performed on personal information data, ultrasonic sensor data, force sensor data, and motion sensor data to generate an assessment report.

[0027] In some embodiments, the ultrasonic sensing device is a portable ultrasonic sensing device with a force detection function, and the portable ultrasonic sensing device includes a force sensor.

[0028] In some embodiments, the muscle parameter includes one or more of the following: muscle amount, muscle thickness, muscle area, muscle hardness, and / or muscle activity.

[0029] In some embodiments, the ultrasonic sensing device uses the U-Net algorithm to segment the ultrasonic image and automatically measures muscle parameters through the deep learning PyTorch framework.

[0030] In some embodiments, the user profile includes one or more of the following: name, gender, year of birth, height, weight, calf circumference, and the questionnaire is a questionnaire based on strength, walking assistance, standing up from a chair, climbing stairs, and falls SARC-F, wherein the user profile and the questionnaire constitute personal information data.

[0031] In some embodiments, the comprehensive analysis is based on a trained artificial intelligence model.

[0032] Other features and advantages will become apparent from the following detailed description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The foregoing and further features of the present disclosure will become apparent from the following description of preferred embodiments provided by way of example only and taken in conjunction with the accompanying drawings, in which:

[0034] Figure 1 shows the statistics of muscle mass loss with age;

[0035] Figure 2 shows a schematic diagram of the algorithm for diagnosing sarcopenia in the AWGS consensus;

[0036] FIG3 shows a schematic diagram of a portable muscle mass assessment system for sarcopenia screening according to an embodiment of the present disclosure;

[0037] FIG4A shows a schematic diagram of a portable B-type ultrasound probe according to an embodiment of the present disclosure;

[0038] FIG4B shows an exploded view of a portable B-type ultrasound probe with a force detection function according to an embodiment of the present disclosure;

[0039] FIG5 shows a schematic diagram of a wearable inertial measurement unit according to an embodiment of the present disclosure;

[0040] FIG6 shows a schematic diagram of a user profile of a user interface according to an embodiment of the present disclosure;

[0041] FIG7 shows a schematic diagram of a questionnaire survey of a user interface according to an embodiment of the present disclosure;

[0042] FIG8 is a schematic diagram showing muscle size of a user interface according to an embodiment of the present disclosure;

[0043] FIG9 is a schematic diagram showing muscle stiffness of a user interface according to an embodiment of the present disclosure;

[0044] FIG10 is a schematic diagram showing muscle activity of a user interface according to an embodiment of the present disclosure;

[0045] FIG11 is a schematic diagram showing grip force of a user interface according to an embodiment of the present disclosure;

[0046] FIG12 shows a schematic diagram of a user interface for standing up and walking according to an embodiment of the present disclosure;

[0047] 13 to 16 are schematic diagrams showing muscle mass assessment reports according to embodiments of the present disclosure;

[0048] FIG17 shows a method flow chart corresponding to the use of the system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] As used herein, the singular expressions "a", "an" and "the" also include the plural, unless the context clearly dictates otherwise. Terms such as "coupled", "fixed", "connected to", and the like refer to direct coupling, fixing or connection as well as indirect coupling, fixing, or connection through one or more intermediate components or features, unless the context clearly dictates otherwise. The terms "comprises", "includes", "consists of", "has" or any other variations thereof herein are intended to cover non-exclusive inclusion. For example, a process, method, article or apparatus that includes a set of features is not necessarily limited to those features, but may include features that are not explicitly listed or other features inherent to such process, method, article or apparatus. In addition, unless expressly stated to the contrary, "or" is inclusive and not exclusive. For example, any of the following satisfies condition A or B: A is true (or exists) and B is false (or does not exist), A is false (or does not exist) and B is true (or exists), and both A and B are true (or exist).

[0050] Terms indicating approximation, such as "about," "approximately," "approximately," or "substantially," include values ​​within 10% greater or less than the stated value. When used in the context of an angle or direction, these terms include values ​​within 10 degrees greater or less than the stated angle or direction. For example, "approximately perpendicular" includes directions within 10 degrees of perpendicular in any direction (e.g., clockwise or counterclockwise).

[0051] It should be understood that, if any prior art publication is cited herein, such reference does not constitute an admission that the publication forms part of the common general knowledge in the art in any country.

[0052] Figure 2 shows a schematic diagram of the algorithm for diagnosing sarcopenia in the AWGS consensus. The inventors established a sarcopenia assessment system based on the AWGS consensus. The system integrates multiple information sources, including: personal information data (including personal files and standard clinical questionnaires), body measurements (such as calf circumference), muscle strength tests (such as hand grip tests), walking speed, and / or changes in the thickness and / or area of ​​leg muscles during specific postures or movements to assess muscle loss. The system can also measure other muscle mass parameters, such as hardness and activity. The sarcopenia assessment of this system combines physical assessment, functional assessment and biophysical assessment, wherein the biophysical assessment includes exercise capacity, muscle strength, muscle size (thickness or area), hardness and activity. The inventors designed a portable system kit (including hardware and software and corresponding interfaces) based on ultrasound imaging and artificial intelligence analysis, so that the elderly or people susceptible to sarcopenia can obtain a comprehensive assessment of whether they have sarcopenia and the severity at home or in the community (such as nursing homes or community medical service stations).

[0053] 3 shows a schematic diagram of a portable muscle mass assessment system 100 for sarcopenia screening according to an embodiment of the present disclosure. The system 100 includes a memory 110 , a processor 120 , an ultrasound sensor 130 , a force sensor 140 , and a motion sensor 150 .

[0054] The memory 110 and the processor 120 can be mounted on portable devices such as personal computers, laptops, tablet computers, mobile phones, and MCU-based dedicated devices to facilitate testing for the elderly at home or in the community. The memory 110 and the processor 120 can also be deployed on a cloud server, and users can access the memory 110 and the processor 120 through a terminal. Preferably, the system 100 has an input device (such as a keyboard, a mouse, a touch screen, etc.) and an output device (such as a display, a tablet or a mobile phone display, etc.). The input device, the output device, and each sensor device can interface with the portable device. The interface can include one or more of the following wired connections: IEEE 1394, Universal Serial Bus (USB), Thunderbolt, Lightning, Mini Display, Digital Video Interface (DVI), High-Definition Multimedia Interface (HDMI), coaxial cable, Video Graphics Array (VGA), or PS / 2 interface. The interface can also include one or more of the following wireless connections: Bluetooth, Wi-Fi, Zigbee, Near Field Communication (NFC), etc. Preferably, as shown in Figure 3, the present disclosure uses a laptop as a portable device, and uses a USB and / or Bluetooth interface as an interface between each sensor and the portable device. When installing the software of the system 100, the driver supporting each sensor device can also be installed at the same time.

[0055] The ultrasonic sensing device 130 is a portable ultrasonic probe designed specifically for muscle assessment, as shown in FIG4A . The ultrasonic probe may adopt one or more of the following ultrasonic modes: A-type ultrasound, B-type ultrasound, and M-type ultrasound, and the collected or reconstructed ultrasonic dimensions may include one or more of the following: one-dimensional, two-dimensional, or three-dimensional ultrasound. Alternatively, a wearable ultrasonic sensing device 170 may also be used, for example, a flexible ultrasonic sensing device or a wearable ultrasonic transducer patch. Preferably, the present disclosure adopts a portable ultrasonic probe 1300 with a force detection function designed specifically for the system 100, which supports a USB interface and a Bluetooth interface, as shown in FIG4B . Among them, the probe 1300 can measure the pressure between it and the skin, so as to better control the probe 1300 so that the user's muscles will not be affected by excessive pressure from the probe and affect the thickness measurement.

[0056] Preferably, the user can sit on a chair. The probe 1300 is placed about 15 cm from the knee and is close to the skin of the thigh for sampling. Optionally, other postures or sampling at different parts can be adopted. For example, different parts of the body can be measured, switching between limbs, such as upper limbs and lower limbs. Since the present disclosure adopts an artificial intelligence model based on deep learning, the sampling method of the model should be the same as the posture and part of the sampling when the system 100 is actually put into use, and detailed guidance is provided by the instruction manual of the system 100. The ultrasound probe can be wired or wireless so that it can be connected to the application of the portable device. Using a wireless probe will make it easier for users or operators (such as caregivers) to use. After several upgrades, the ultrasound probe in the present disclosure has greatly reduced its weight to improve its portability. The sampled image is transmitted to the memory 110 through the interface between the ultrasound sensor device 130 and the portable device, and is processed by the processor 120.

[0057] This disclosure preferably uses the deep learning PyTorch framework and the U-Net model to automatically measure muscle thickness and area. The U-Net algorithm is one of the algorithms that uses a fully convolutional network for semantic segmentation. Specifically, the U-Net algorithm is used to segment the image and measure muscle thickness and area.

[0058] U-Net is used for ultrasound B-mode image segmentation and re-segmentation to calculate, for example, the thickness and area of ​​the rectus femoris muscle of the thigh. Alternatively, other semantic segmentation algorithms may be used, such as fully convolutional networks (FCNs), PSPNet, etc. PyTorch is a full-featured framework for building deep learning models, and is commonly used for machine learning in applications such as image recognition and language processing. Alternatively, other deep learning frameworks may be used, such as TensorFlow, etc. The ultrasound sensing device 130 is designed to understand changes in muscle area, muscle compressibility, and muscle thickness during voluntary contraction.

[0059] Figure 4B shows an exploded view of a portable ultrasound probe 1300 with force detection functionality according to an embodiment of the present disclosure. To prevent inaccurate muscle area detection due to excessive compression force, the inventors have designed a portable ultrasound probe 1300 with force detection functionality. The ultrasound probe 1300 can simultaneously detect the force exerted by the compression probe on the skin while performing ultrasound detection. The exploded view schematically illustrates the components of the ultrasound probe 1300, including: an upper housing 1310, a lower housing 1312, a front cover 1314, a rear end support member 1316, a fastener 1318, a cable 1320 for ultrasound function (for wired connection), an ultrasound probe 1322, a flexible cable 1324, an ultrasound head 1326, a cable 1330 for microprocessor function (for wired connection), a microprocessor 1332, a force sensor 1340, a power management module 1350, and the like. Preferably, the force detection functionality of the ultrasound probe 1300 is implemented using the force sensor 1340 and the microprocessor 1332.

[0060] The portable ultrasound probe 1300 with force detection function can further measure muscle hardness and muscle activity to evaluate muscle quality. In the sampling of muscle hardness testing, the ultrasound probe 1300 continuously measures the rectus femoris muscle on the thigh (about 15 cm from the knee) vertically and measures the deformation of the muscle under different forces. The user can remain still, for example, in a specific position, and then the user or operator presses the probe on the muscle to measure the hardness. The muscle thickness is recorded together with the magnitude of the force, and the muscle hardness (or compressibility) is evaluated by the change in the thickness or area of ​​the muscle under different forces. Muscle activity is another test. When measuring muscle activity, the user can be asked to lift the leg. For example, the user can lift and lower the calf while bending the knee, and observe the change in the thickness or area of ​​the thigh muscle in turn. Muscle activity is evaluated by calculating the change in the thickness or area of ​​the muscle during this process.

[0061] Regarding the force sensing device 140, the present disclosure preferably uses a commercially available handgrip dynamometer 1400 to assess the user's arm muscle strength and integrates it into the system 100. The arm muscle strength is observed by measuring the strength of the non-dominant hand. Generally speaking, according to AWGS, the hand muscle strength of women is greater than 18 kg and that of men is greater than 28 kg. The muscle strength of other parts can also be measured as needed, such as using a tension belt with a sensing function to measure the strength of the waist and leg muscles. The force sensing device 140 can be wired or wireless. The present disclosure preferably connects the handgrip dynamometer 1400 to a portable device via Bluetooth, and data can be automatically transmitted in one direction or two directions during the test to facilitate user use.

[0062] The motion sensing device 150 assesses muscle loss by measuring walking speed or gait. Preferably, the present disclosure adopts a wearable inertial measurement unit (IMU) 1500. The wearable IMU 1500 can use an accelerometer and a gyroscope to detect changes in motion speed and angle, and can also achieve the measurement of stand-up walking (TUG: Time Up and Go). The wearable IMU 1500 of the present disclosure can communicate with a portable device via Bluetooth. As shown in Figure 5, the user ties the wearable IMU 1500 to a waist belt. First, the user stands and returns to the starting point after walking about 3 meters. The wearable IMU 1500 will measure the time taken for this process and calculate the pace and / or gait performance based on the acceleration and / or angle change signals collected during the test. Optionally, a commercially available motion sensor or an IMU equipped on a mobile device (such as a smartphone) can be used to assess the user's athletic ability. In other embodiments, motion information can be extracted through a camera (e.g., a mobile phone) using artificial intelligence technology and computer vision to examine gait performance and be integrated into the system 100.

[0063] While system 100 in FIG3 is equipped with multiple independent sensing devices, those skilled in the art will appreciate that one or more of these sensing devices can be integrated into a single piece of hardware. Each sensing device can perform measurements at different times, such as before and after exercise. System 100 can provide visualization and dynamic assessment of sarcopenia during a user's activity, providing a database system for monitoring and predicting sarcopenia.

[0064] Figures 6 to 16 show schematic diagrams of a user interface (UI) 160 according to an embodiment of the present disclosure. The UI 160 can be presented on an output device. First, log in to the software UI 160 of the system 100 using a username and password. The left side of the page lists tabs for login settings and various functions provided by the software. Figure 6 shows a schematic diagram of creating a user profile on the user profile page when a user uses it for the first time. When the user's name, gender, and year of birth are entered, the system will identify the user's diagnostic threshold. For existing users, this information can be updated at any time. After the user profile is created or updated, the assessment will begin by entering body measurements such as height, weight, and calf circumference. These values ​​can be entered manually or automatically by capturing body parameters using a camera on a portable device. In particular, calf circumference can be measured using a contact or non-contact method using sensors based on ultrasound, infrared, or other sensors integrated into the system hardware, or using a camera-based device. Optionally, the user profile can also be automatically imported into the system 100 via an archive file.

[0065] FIG7 illustrates a schematic diagram of a questionnaire in UI 160 according to an embodiment of the present disclosure. The questionnaire in the present disclosure is designed based on several questions raised in the AWGS consensus, i.e., a SARC-F-based questionnaire. The questionnaire covers lifestyle habits, such as whether the user is prone to falls. The questionnaire will help assess the cognitive status of the user's physical condition. The questionnaire can be entered manually or automatically imported into the system 100 via an archive file.

[0066] FIG8 shows a schematic diagram of muscle size of UI 160 according to an embodiment of the present disclosure. This page combines the input of measurement data of the ultrasonic sensing device 130 (e.g., the portable ultrasonic probe 1300 with force detection function in the present disclosure). As shown in FIG8 , the page provides multiple functions, such as the connection status and settings of the sensing device, posture and position options, starting and stopping the sensing device, real-time dynamic display and storage of image data, parameter setting, analysis and display based on semantic algorithm segmentation and deep learning model, and storage and display of analysis results. UI 160 can also support manual annotation on the image.

[0067] FIG9 shows a schematic diagram of muscle hardness of the UI 160 according to an embodiment of the present disclosure. This page combines the input of measurement data of the ultrasonic sensing device 130 (for example, the portable ultrasonic probe 1300 with a force detection function in the present disclosure). Similar to FIG8 , the page provides multiple functions. In particular, since muscle hardness needs to be coordinated with the force detection function, the page provides a display bar showing the magnitude of the force corresponding to the ultrasonic image frame. In addition, the page also provides the functions of continuous playback of ultrasonic images, frame indexing, and selection of the best result.

[0068] FIG10 shows a schematic diagram of muscle activity in a UI 160 according to an embodiment of the present disclosure. This page incorporates the input of measurement data from an ultrasound sensor device 130 (e.g., a portable ultrasound probe 1300 with force detection functionality in the present disclosure). The page provides multiple functions similar to those in FIG9 .

[0069] Figure 11 shows a schematic diagram of a grip force UI 160 according to an embodiment of the present disclosure. This page incorporates the input of measurement data from a force sensing device 140 (e.g., a hand grip dynamometer 1400 in the present disclosure). The measurement data from the hand grip dynamometer 1400 can be transmitted to the page in a timely manner via Bluetooth.

[0070] FIG12 shows a schematic diagram of a TUG of a UI 160 according to an embodiment of the present disclosure. This page incorporates the input of measurement data from a motion sensing device 150 (e.g., a wearable IMU 1500 in the present disclosure). During testing, the system 100 detects pace and / or gait by collecting signals of acceleration and angle changes.

[0071] The data collected by each sensing device is transmitted to the memory 110 and stored in a wired or wireless manner. These data can be exported in the form of an Excel table for further analysis by professionals, as shown in Figure 13. The present disclosure preferably provides an intuitive and highly readable muscle mass assessment report directly to the user on UI 160, as shown in Figures 14 to 16. Figure 14 shows the user's name, age, gender, experimental date, height, weight, SARC-F score, calf circumference and muscle area measured by the ultrasonic sensing device 130. Figures 15 and 16 show the normal value range of each measurement value, the user's measurement value (or score), the risk assessment result of suffering from sarcopenia indicated by each measurement value alone, and the comprehensive assessment result combined with each measurement value. The muscle mass assessment report can give the user appropriate suggestions based on the assessment results, such as diet, exercise, medication or other treatment suggestions.

[0072] In addition, UI 160 can also integrate functions such as installation instructions and error diagnosis of software and hardware. To facilitate user operation, UI 160 can be set in multiple languages ​​and can be used in bright or dark environments. The system 100 can adjust the ultrasound image in the UI 160 page to a white background or a traditional dark background according to the brightness of the surrounding environment. For example, the system 100 can be provided with a light sensing device to automatically adjust the background, or the UI 160 page can provide options for the user to manually set the background, or a combination of the two. The system 100 can provide voice prompts or text prompts to guide the user on how to complete each step. The user can set up on UI 160 to save the measurement data and evaluation results locally or upload them to a professional medical institution via the network for further analysis or statistics.

[0073] FIG17 shows a flowchart of a method for using system 100. Those skilled in the art will appreciate that these steps do not necessarily need to be completed in sequence, as each measurement can be performed independently. The following steps can be combined with the details of system 100 described above, and therefore some details are omitted.

[0074] In step 1702, the user logs into system 100. In step 1704, it is determined whether the user is a new user. If so, the user can create a user profile in step 1706. For existing users, the user can modify or update existing information. In step 1708, the user completes the SARC-F questionnaire. Users who have already completed the questionnaire and have not changed their preferences can skip this step.

[0075] In step 1710, the user can connect the portable ultrasound probe 1300 with force detection functionality. The user can apply coupling agent to the body part to be tested, such as the thigh area for the rectus femoris muscle as described above. In steps 1712, 1714, and 1716, the ultrasound probe 1300 can be used to sequentially detect changes in muscle size, firmness, and movement. The user can capture the required ultrasound images and data for subsequent analysis. In particular, the user can skip one or more steps based on their individual needs. The user can also measure muscles in other parts of the body, such as the rectus abdominis, biceps, triceps, etc., according to the prompts of the system 100. Data from the ultrasound probe 1300 can be automatically transmitted to the system 100.

[0076] In step 1718, the user can connect the handgrip dynamometer 1400. Preferably, the user uses their non-dominant hand to hold the handgrip dynamometer 1400 for grip strength testing. Data from the non-dominant hand can more accurately reflect the user's muscle condition. After the test is completed, the data from the handgrip dynamometer 1400 can be automatically or manually entered into the system 100 for subsequent analysis.

[0077] In step 1720, the user may wear a belt with the wearable IMU 1500 around their waist and complete the TUG's 3-meter walk and / or gait test, as shown in FIG5 . After the test is completed, the data from the wearable IMU 1500 may be automatically input or manually entered into the system 100 for subsequent analysis.

[0078] The data obtained in the above steps will update the user's data in system 100. Users may omit certain steps based on their own circumstances. For example, they may have previously tested a step when using the system and can confirm that the data for that step has not changed significantly. System 100 can then utilize the previously saved data. System 100 can analyze data from a single sensor using the trained AI integrated within system 100. For example, system 100 uses the AI-based U-Net algorithm to segment ultrasound images and generate analysis data. System 100 can also use the trained AI integrated within system 100 to perform comprehensive analysis of the following data: muscle thickness, muscle cross-sectional area, stiffness, changes in muscle activity, grip strength, TUG data, and SARC-F results. Raw data, intermediate analysis data, and results are all stored in the system 100 database. The database can be a common database type in the art, such as MySQL, SQL Server, or Access. The database and trained AI can be hosted in the system 100's memory or on a cloud server connected to system 100. The system 100 and the user can search, query, and modify the data using, for example, Structured Query Language (SQL), or export it to Excel for review or statistical analysis. Finally, in step 1722, the system 100 outputs a muscle mass assessment report based on the comprehensive analysis results. This report can inform the user of their sarcopenia risk level: low, moderate, or high. The report may also include other information, as shown in Figures 14-16.

[0079] The system 100 can be used in conjunction with other exercise applications, for example, to monitor changes in muscle thickness over a period of time (after exercise, after dieting, etc.). Preferably, an application can be developed on a mobile phone or smartwatch (such as Apple Watch or Huawei, Xiaomi Watch, etc.) to upload the measured muscle data to the mobile phone or watch application.

[0080] The present disclosure can also be implemented as an independent wearable device, for example, integrating various sensing devices, processors and memories into a palm-sized wearable device. For users who experience periodic muscle pain, they can wear it around their biceps and monitor changes in muscle thickness over a period of time. The device can help people with muscle-related diseases, such as polymyalgia rheumatica and periodic paralysis, who experience muscle weakness and stiffness. In other embodiments, it can be used in conjunction with other detection devices (such as blood glucose meters). Optionally, the kit can include different sensing devices that the user can purchase. The user can set different measurement modes in the software and monitor dynamic results through a mobile phone application.

[0081] The system designed in this disclosure provides an easy-to-use sarcopenia assessment tool that incorporates information from physical, functional, and biophysical assessments. This assessment system is based on radiation-free and non-invasive ultrasound testing. It can be carried around the home or while walking, making it easy to use and cost-effective. The system is based on an artificial intelligence model trained on extensive data, providing accurate assessments.

[0082] The present disclosure can be applied to the elderly care technology industry, the healthcare industry, and the mobile application technology Internet suitable for aging.

[0083] The present disclosure is shown and described in detail above in conjunction with the drawings, but the above embodiments should be considered as illustrative rather than restrictive. The present disclosure also includes various combinations, modifications and variations of the exemplary embodiments without departing from the spirit and scope of the present disclosure.

Claims

1. A portable muscle mass assessment system for sarcopenia screening, the system comprising: A memory, wherein the memory is used to store the user's personal information data; an ultrasonic sensing device, configured to measure muscle parameters and transmit ultrasonic sensing data to the memory; a force sensing device, the force sensing device being used to measure muscle force and transmit force sensing data to the memory; a motion sensing device, the motion sensing device being used to measure the user's pace and / or gait during exercise and to transmit the motion sensing data to the memory; A processor is provided for generating an assessment report on whether the user suffers from sarcopenia and the severity of the disease based on the personal information data, the ultrasonic sensing data, the force sensing data and the motion sensing data stored in the memory.

2. The system according to claim 1, wherein: The ultrasonic sensing device is a portable ultrasonic probe with a force detection function, and the portable ultrasonic probe includes a force sensor.

3. The system according to claim 1 or 2, wherein: The muscle parameters include one or more of the following: muscle quantity, muscle thickness, muscle area, muscle hardness, and / or muscle activity.

4. The system according to claim 1 or 2, wherein: The ultrasonic sensing device uses the U-Net algorithm to segment the ultrasonic image and automatically measures the muscle parameters through deep learning PyTorch.

5. The system according to claim 1 or 2, wherein: The force sensing device is a grip force sensor, which is used to detect the arm muscle strength of the user.

6. The system according to claim 1, wherein: The motion sensing device is a wearable inertial measurement unit (IMU) for detecting the user's walking speed and / or gait performance.

7. The system according to claim 1 or 2, wherein: One or more of the following devices can be integrated into one hardware device: the memory, the processor, the ultrasound sensing device, the force sensing device, and / or the motion sensing device.

8. The system according to claim 1 or 2, wherein: Data is transmitted between the ultrasonic sensor device, the force sensor device, the motion sensor device and the memory in a wired or wireless manner.

9. The system according to claim 1 or 2, wherein: The personal information data includes one or more of the following: name, gender, year of birth, height, weight, calf circumference, and / or a questionnaire based on strength, walking assistance, sitting to stand, climbing stairs and falls SARC-F.

10. The system according to claim 1 or 2, further comprising an input device, wherein the input device is used to manually input the user's personal information data into the system or import it through a file.

11. The system according to claim 1 or 2 further comprises an output device, on which a user interface UI is displayed, wherein the UI displays one or more of the following: software and hardware installation instructions, login settings, error diagnosis, the personal information data, settings and startup of each sensing device, the ultrasonic sensing data and / or analysis, the force sensing data and / or analysis, the motion sensing data and / or analysis, and / or the evaluation report.

12. The system according to claim 11, wherein The UI is a display interface of a personal computer, a display interface of a laptop computer, a display interface of a tablet application, a display interface of a mobile phone application, or a display interface of other portable devices.

13. The system according to claim 1, wherein: The evaluation report is saved locally and / or uploaded to the network according to the user's settings.

14. A method for using a portable muscle mass assessment system, the method comprising: A user logs into the system; The system determines whether the user is a new user. If so, a user profile is created for the new user. Otherwise, the old user chooses whether to update the user profile. Users fill out questionnaires; measuring muscle parameters using a connected ultrasonic sensing device and transmitting the ultrasonic sensing data to the system; measuring muscle force using a connected force sensing device and transmitting the force sensing data to the system; Measuring the user's pace and / or gait during exercise using a connected motion sensing device and transmitting the motion sensing data to the system; Comprehensively analyze the personal information data, the ultrasonic sensing data, the force sensing data, and the motion sensing data to generate an evaluation report.

15. The method according to claim 14, wherein The ultrasonic sensing device is a portable ultrasonic sensing device with a force detection function, and the portable ultrasonic sensing device includes a force sensor.

16. The method according to claim 14 or 15, wherein: The muscle parameters include one or more of the following: muscle quantity, muscle thickness, muscle area, muscle hardness, and / or muscle activity.

17. The method according to claim 14 or 15, wherein: The ultrasonic sensing device uses the U-Net algorithm to segment the ultrasonic image and automatically measures the muscle parameters through deep learning PyTorch.

18. The method according to claim 14 or 15, wherein The user profile includes one or more of the following: name, gender, year of birth, height, weight, calf circumference, and the questionnaire is a questionnaire based on strength, walking assistance, standing up from a chair, climbing stairs and falls SARC-F, wherein the user profile and the questionnaire constitute personal information data.

19. The method according to claim 14 or 15, wherein: The comprehensive analysis is based on a trained artificial intelligence deep learning model.

Images