Upper limb artery occlusion assessment method and system based on portable multi-camera equipment, terminal equipment and medium

The upper limb artery occlusion assessment method uses a portable multi-camera device to synchronously collect data, combining the signal conduction time difference characteristics with the waveform similarity characteristics. This solves the problems of bulky, invasive and high-cost equipment in existing technologies, and enables convenient arterial occlusion assessment to meet the needs of home or primary medical scenarios.

CN120585303AActive Publication Date: 2025-09-05SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202511063451.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-31
Publication Date
2025-09-05
Estimated Expiration
2045-07-31

AI Technical Summary

Technical Problem

Existing technologies for assessing upper limb artery obstruction have the problems of bulky equipment, invasive or high detection costs, and insufficient portability. These problems make it difficult to meet the needs of early screening and dynamic monitoring in home or primary healthcare scenarios. In addition, the traditional single-site pulse wave signal acquisition method cannot achieve bilateral comparative analysis, affecting early risk identification.

Method used

A portable multi-camera device is used to synchronously collect the reference signal, left-hand pulse wave signal, and right-hand pulse wave signal. The signal conduction time difference feature and signal waveform similarity feature are obtained through feature extraction, and then input into the pre-trained evaluation model to evaluate upper limb artery occlusion.

Benefits of technology

It realizes non-invasive, low-cost and convenient multi-site signal acquisition and analysis, breaks through the interference of local blockage on single signal, and realizes accurate assessment of upper limb artery blockage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120585303A_ABST
    Figure CN120585303A_ABST
Patent Text Reader

Abstract

The invention discloses an upper limb artery occlusion assessment method and system based on portable multi-camera equipment, terminal equipment and a medium, and relates to the technical field of artery occlusion assessment. The method comprises the following steps: acquiring a reference signal, a left hand pulse wave signal and a right hand pulse wave signal based on the portable multi-camera equipment; the reference signal, the left-hand pulse wave signal and the right-hand pulse wave signal are synchronized by taking the acquisition time as reference time; performing feature extraction on the reference signal, the left-hand pulse wave signal and the right-hand pulse wave signal to obtain a signal transduction time difference feature and a signal waveform similarity feature; and inputting the signal transduction time difference feature and the signal waveform similarity feature into a pre-trained evaluation model to obtain an upper limb artery occlusion evaluation result. According to the method, the portable multi-camera equipment is used for collecting physiological signals of three positions of a human body at the same time, and the obstruction condition of the upper limb artery is simply, conveniently and accurately evaluated by using the signal transduction time difference characteristic and the signal waveform similarity characteristic.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of arterial obstruction assessment, and in particular to an upper limb artery obstruction assessment method, system, terminal device, and medium based on a portable multi-camera device. Background Art

[0002] Upper limb arterial obstructive disease, caused by factors such as atherosclerosis and thrombosis, leads to stenosis or occlusion of the arteries, causing upper limb pain, numbness, and ischemic complications, severely impacting patients' quality of life. Clinical assessment relies on imaging techniques such as ultrasound, CT angiography (CT), and MRI. While these techniques can provide anatomical and blood flow information, they also have significant limitations. First, existing assessment methods are highly equipment-dependent, requiring specialized medical equipment and facilities, making them difficult to implement in home or primary care settings and failing to meet routine screening needs. Second, existing methods are invasive or costly. CT and MRI involve radiation exposure or high examination costs, while ultrasound, while non-invasive, relies on operator experience and has poor reproducibility. Furthermore, existing assessment methods lack portability. Traditional equipment is bulky, making mobile testing impractical. Regular monitoring is particularly challenging for elderly or mobility-impaired patients, especially those experiencing physical difficulties. Furthermore, existing methods often intervene only when symptoms become apparent, lacking convenient early warning methods, leading some patients to miss the optimal time for intervention.

[0003] Auxiliary screening for unilateral upper limb arterial obstruction is more challenging. Studies have shown that prolonged pulse wave conduction time and waveform distortion at the fingertips of the affected side can serve as early warning signals of obstruction, but traditional pulse wave signal monitoring requires dedicated contact equipment and can only collect signals from a single location, making bilateral comparison and dynamic assessment impossible. With the development of mobile health technology, the popularity of portable devices has provided a new path for non-invasive physiological signal acquisition, but existing health monitoring functions based on mobile terminals such as mobile phones are mostly limited to single-camera heart rate detection and have not yet involved the synchronous acquisition of multi-channel pulse wave signals and arterial obstruction assessment.

[0004] Therefore, there is an urgent need for a portable, non-invasive, and low-cost method for assessing upper limb arterial obstruction that can overcome the limitations of traditional medical equipment and enable early screening and long-term monitoring in the home setting. However, combining the multi-camera systems of portable devices with physiological signal analysis to achieve reliable arterial obstruction assessment remains a pressing technical challenge. Summary of the Invention

[0005] The technical problem addressed by this invention is that existing technologies for assessing upper limb arterial obstruction primarily rely on imaging methods such as ultrasound, CT, and MRI. These methods suffer from bulky equipment, invasiveness, high testing costs, and limited portability, making them inadequate for early screening and dynamic monitoring in home or primary care settings. For unilateral upper limb arterial obstruction, traditional single-site pulse wave signal acquisition methods cannot achieve bilateral comparative analysis, resulting in delayed assessment of pulse transit time (PTT) and waveform characteristics, hindering early risk identification. Despite advances in mobile health technology, existing portable devices can only monitor heart rate at a single site using a single camera and lack the ability to simultaneously acquire multi-channel pulse wave signals and assess arterial obstruction. Therefore, how to utilize widely available portable devices to achieve non-invasive, low-cost, and convenient multi-site signal acquisition and analysis has become a current technical bottleneck, and an effective solution is urgently needed.

[0006] In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows: In a first aspect, the present invention provides a method for assessing upper limb artery occlusion based on a portable multi-camera device, the method comprising: A reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal are collected based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to a collection time as a reference time; performing feature extraction on the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; The signal conduction time difference feature and the signal waveform similarity feature are input into a pre-trained evaluation model to obtain an upper limb artery occlusion evaluation result.

[0007] In one implementation, the reference signal is a facial pulse wave signal, and the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device includes: Using the first camera of the portable multi-camera device to shoot the face to obtain a facial video; Performing face detection on the facial video to obtain a mask of the facial skin area; Based on the mask of the facial skin area, averaging all pixels of the facial skin area in the facial video to obtain a facial pixel value sequence; Signal preprocessing is performed on the facial pixel value sequence to obtain a facial pulse wave signal.

[0008] In one implementation, the reference signal is a heart vibration signal or a heart sound signal, and the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device includes: Using the acceleration sensor of the portable multi-camera device to collect the heart vibration transmitted by the chest wall, and pre-processing it to obtain a heart vibration signal; Alternatively, the microphone of the portable multi-camera device is used to collect sounds near the heart in the chest and perform preprocessing to obtain a heart sound signal.

[0009] In one implementation, the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device includes: Using the second camera and the third camera of the portable multi-camera device, respectively, a video of the same fingertip of the left hand and the right hand is taken, with the fingertip remaining in contact with the corresponding camera and completely covering the lens, to obtain a video of the left fingertip and a video of the right fingertip; Averaging all pixels of the left fingertip video and the right fingertip video to obtain a pixel value sequence of the left fingertip and a pixel value sequence of the right fingertip; Signal preprocessing is performed on the pixel value sequence of the left fingertip and the pixel value sequence of the right fingertip to obtain a left hand pulse wave signal and a right hand pulse wave signal.

[0010] In one implementation, the evaluation features include a pulse wave transmission time difference and a pulse wave waveform similarity feature, and the feature extraction of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain the signal transmission time difference feature and the signal waveform similarity feature includes: Through the positioning algorithm, all the reference signal feature points, left hand pulse wave signal feature points and right hand pulse wave signal feature points are located, wherein each feature point corresponds one to one in the heartbeat cycle; Calculating a left-hand pulse wave transmission time difference and a right-hand pulse wave transmission time difference based on the reference signal characteristic points, the left-hand pulse wave signal characteristic points, and the right-hand pulse wave signal characteristic points; Based on the reference signal, the left hand pulse wave signal and the right hand pulse wave signal, a left hand pulse wave waveform similarity feature and a right hand pulse wave waveform similarity feature are calculated.

[0011] In one implementation, the calculating the left-hand pulse wave transit time difference and the right-hand pulse wave transit time difference based on the reference signal feature points, the left-hand pulse wave signal feature points, and the right-hand pulse wave signal feature points includes: For each heartbeat cycle, subtract the timestamp of the characteristic point of the reference signal from the timestamp of the characteristic point of the left hand pulse wave signal to obtain the left hand pulse wave transmission time difference; For each heartbeat cycle, the timestamp of the characteristic point of the right hand pulse wave signal is subtracted from the timestamp of the characteristic point of the reference signal to obtain the right hand pulse wave transmission time difference.

[0012] In one implementation, the calculating of the left-hand pulse wave waveform similarity feature and the right-hand pulse wave waveform similarity feature based on the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal includes: For each heartbeat cycle, calculating the similarity between the left hand pulse wave signal and the reference signal to obtain a waveform similarity feature of the left hand pulse wave; For each heartbeat cycle, the similarity between the right hand pulse wave signal and the reference signal is calculated to obtain a waveform similarity feature of the right hand pulse wave.

[0013] In a second aspect, an embodiment of the present invention further provides an upper limb artery occlusion assessment system based on a portable multi-camera device, the system comprising: A signal acquisition module is used to acquire a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to the acquisition time as a reference time; a feature acquisition module, configured to extract features from the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; The upper limb artery obstruction assessment module is used to input the signal conduction time difference feature and the signal waveform similarity feature into a pre-trained assessment model to obtain an upper limb artery obstruction assessment result.

[0014] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a memory, a processor, and an upper limb artery obstruction assessment program based on a portable multi-camera device stored in the memory and executable on the processor. When the processor executes the upper limb artery obstruction assessment program based on a portable multi-camera device, the steps of the upper limb artery obstruction assessment method based on a portable multi-camera device described in any one of the above-mentioned schemes are implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which is stored an upper limb artery obstruction assessment program based on a portable multi-camera device. When the upper limb artery obstruction assessment program based on a portable multi-camera device is executed by a processor, the steps of the upper limb artery obstruction assessment method based on a portable multi-camera device described in any one of the above-mentioned schemes are implemented.

[0016] Beneficial Effects: The present invention discloses a method, system, terminal device, and medium for assessing upper limb artery obstruction based on a portable multi-camera device. The method involves collecting a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal using a portable multi-camera device. The reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized using the acquisition time as a reference time. Feature extraction is performed on the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature. The signal conduction time difference feature and the signal waveform similarity feature are input into a pre-trained assessment model to obtain an upper limb artery obstruction assessment result. In view of the fact that upper limb artery obstruction symptoms often manifest in localized areas of the left and right upper limbs and are reflected in changes in pulse wave conduction time and waveform, the present invention selects a reference signal that is almost unaffected by left and right upper limb obstruction. The portable multi-camera device synchronously collects the human body reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal. A simple assessment algorithm is designed by combining the signal conduction time difference feature and the waveform similarity feature. The present invention is based on the collaborative analysis of three-position signals, breaking through the interference of local blockage on a single signal, and realizing accurate assessment of upper limb artery blockage with a simple and convenient algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flowchart of a specific implementation of a method for assessing upper limb artery occlusion based on a portable multi-camera device provided in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of the upper limb artery occlusion assessment process based on a portable multi-camera device provided by an embodiment of the present invention.

[0019] Figure 3 This is a principle block diagram of an upper limb artery occlusion assessment device based on a portable multi-camera device provided by an embodiment of the present invention.

[0020] Figure 4 This is a block diagram of the internal structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0022] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents, operations, or steps, nor must they be executed in the order described. For example, some operations or steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0023] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should be understood that, to facilitate a clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. For example, the first control information and the second control information are merely used to distinguish different control information and do not limit their order.

[0025] Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0026] It will also be understood that the term "and / or" used in the present description and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0027] In the field of upper limb artery obstruction assessment, existing technologies mainly rely on imaging methods such as ultrasound, CT, and MRI. These technologies have drawbacks such as bulky equipment, invasive or high detection costs, and insufficient portability, making it difficult to meet the needs of early screening and dynamic monitoring in home or primary care settings. For unilateral upper limb artery obstruction, the traditional single-site pulse wave signal acquisition method cannot achieve bilateral comparative analysis, resulting in a lag in the assessment of pulse wave conduction time differences and waveform characteristics, affecting early risk identification. Despite the development of mobile health technology, existing portable devices can only complete single-site heart rate monitoring through a single camera, and lack the ability to synchronously acquire multi-channel pulse wave signals and assess arterial obstruction. Therefore, how to use popular portable devices to achieve non-invasive, low-cost, and convenient multi-site signal acquisition and analysis has become a current technical bottleneck, and an effective solution is urgently needed.

[0028] In the early stages of lumen stenosis or occlusion in upper limb arteries, the PPG signal (Photoplethysmography Signal, used here to represent the pulse wave signal) will show characteristic changes, including significant amplitude attenuation, waveform distortion, and phase delay. These changes can be used to assess the blockage of upper limb arteries by analyzing finger PPG signals at multiple locations. Based on this, Figure 2 The overall process diagram of an upper limb artery occlusion assessment method based on a portable multi-camera device is presented. Figure 2It demonstrates the use of a smartphone with one front camera and two rear cameras as a multi-camera device to complete the algorithm flow of acquisition, calculation, and evaluation. In addition to smartphones, portable devices with multiple cameras such as smart tablets, smart bracelets, smart watches, sports cameras, robot multi-cameras, VR glasses, etc. can also be used. Based on the multi-camera system of the mobile device, the synchronous PPG signals of different peripheral blood vessel endings of the human body are collected, including facial PPG and left and right fingertip PPG. The facial PPG signal is used as a reference signal to calculate the PTT of the left and right hands, and the recognition ability of arterial blockage is enhanced by analyzing the PPG waveform characteristics. Among them, based on the PTT characteristics and waveform characteristics of both hands, machine learning or mathematical models can be used to evaluate the blockage of the upper limb arteries. In addition Figure 2 In addition to using a smartphone to collect facial PPG signals as a baseline signal, the demonstration also demonstrates the use of a portable multi-camera device's accelerometer to collect cardiac signals or a microphone sensor to collect heart sound signals. The pulse wave signals of the left and right hands are compared with the baseline signals to determine their respective pulse wave transmission times and waveform characteristics for use in assessing upper limb obstruction.

[0029] This embodiment provides a method for assessing upper limb artery occlusion based on a portable multi-camera device, such as Figure 1 As shown, the specific steps include: Step S100: collecting a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to a collection time as a reference time.

[0030] In this embodiment, the portable multi-camera device is preferably a mobile device comprising three cameras. The first camera is used to capture facial pulse wave signals and must have a high image acquisition frame rate and low-light sensitivity to ensure that subtle light intensity fluctuations caused by changes in blood flow in the facial skin can be captured in both natural lighting and indoor environments, providing the raw data foundation for subsequent signal processing. During signal acquisition, the camera must remain stable to avoid data distortion caused by motion blur. The arms must also be free from tight clothing to prevent external forces from affecting blood flow in the arms. Loose, comfortable clothing is recommended to facilitate normal blood circulation. The second and third cameras are used to capture pulse wave signals from both hands and must have macro photography capabilities to clearly capture microvascular pulsations in the fingertip skin. During capture, the fingertip must be in physical contact with the lens and completely block the lens aperture to form a closed optical path, avoid interference from ambient light, and ensure that the captured light signal originates solely from changes in light absorption in the fingertip tissue. Furthermore, to lay the foundation for feature extraction of the subsequent three pulse wave signals, it is necessary to ensure that the three pulse wave signals are synchronized with respect to the acquisition time, that is, the timestamps of the three pulse wave signals are synchronized in parallel.

[0031] In one implementation, the reference signal is a facial pulse wave signal, and the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device specifically includes the following steps: Step S110: Use the first camera of the portable multi-camera device to shoot the face to obtain a facial video; Step S120: performing face detection on the facial video to obtain a mask of the facial skin area; Step S130: Based on the mask of the facial skin area, average all pixels of the facial skin area in the facial video to obtain a facial pixel value sequence; Step S140: performing signal preprocessing on the facial pixel value sequence to obtain a facial pulse wave signal.

[0032] In this embodiment, a smartphone is preferably selected as the multi-camera device. The optical parameters of the first camera, preferably the front-facing camera, must meet the requirements for near-infrared light sensing to enhance hemoglobin's sensitivity to light absorption and improve the signal-to-noise ratio of the facial PPG signal. For example, a smartphone with high dynamic range imaging capabilities can be used to ensure that subtle color changes in the facial skin can be stably captured even in complex lighting conditions such as backlighting and indoor lighting.

[0033] After capturing a facial video, face detection is used to obtain a mask of the facial skin area. Specifically, face detection can utilize open-source libraries or deep learning models, such as convolutional neural networks, to automatically identify facial regions. The generated mask must accurately cover key skin areas, such as the forehead and cheeks, while excluding distracting areas like eyebrows and nose shadows. Then, after applying the mask to each frame of the facial video, a smooth sequence of facial pixel values ​​is obtained by calculating the grayscale mean or RGB (Red, Green, Blue) three-channel mean of the pixels within the mask. When averaging the skin area pixels, dynamic interference frames, such as blinking and facial expressions, must be removed to ensure that the pixel value sequence truly reflects arterial blood volume fluctuations. Finally, during the signal preprocessing step, filters can be used to remove baseline drift or extract pulse wave frequency bands. The bandpass filter parameters can be adaptively adjusted based on the heart rate range to retain the valid pulse wave frequency bands. Ultimately, the facial pulse wave signal is obtained through the above processing.

[0034] In one implementation, the reference signal is a heart vibration signal or a heart sound signal, and the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device specifically includes the following steps: S150: Using the acceleration sensor of the portable multi-camera device, collecting cardiac vibrations conducted through the chest wall, and performing preprocessing to obtain cardiac vibration signals; S160, or, using the microphone of the portable multi-camera device, collecting chest sounds near the heart, and performing preprocessing to obtain heart sound signals.

[0035] In this embodiment, a cardiac oscillation signal or a heart sound signal can be used as a reference signal. When collecting cardiac oscillation signals, first place one side of the accelerometer of the portable device close to the left chest wall of the human body and fix it by an elastic strap or hand-held method to ensure that the sensor is in close contact with the chest wall surface to reduce motion displacement interference. The mechanical vibration signal caused by cardiac contraction and expansion is collected by the accelerometer of the portable device. Next, a bandpass filter can be used to remove respiratory motion and high-frequency electromagnetic interference, and polynomial fitting or wavelet transform can be used to eliminate low-frequency drift. Then, the starting point of the cardiac contraction period, such as the maximum amplitude point, is located by a peak detection algorithm to generate a time series of cardiac oscillation signal feature points, complete feature point extraction, and finally form a cardiac oscillation signal.

[0036] To collect heart sound signals, first place the device's microphone close to the left chest to capture the sound. Keep the acoustic path clear and ambient noise low. After acquisition, a bandpass filter is applied to extract the characteristic frequency bands of the heart sounds and suppress low-frequency ambient noise and high-frequency circuit noise. The time-domain signal is converted into a spectrogram using a short-time Fourier transform or wavelet transform. The peak positions of the first and second heart sounds are identified. Using the first heart sound peak as the reference point, the complete cardiac cycle is captured to eliminate signal offsets caused by breathing and movement.

[0037] Finally, a unified device clock timestamp needs to be added to the cardiac vibration signal and heart sound signal to ensure that the reference signal is synchronized with the left hand pulse wave signal and the right hand pulse wave signal.

[0038] In one implementation, the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device specifically includes the following steps: Step S170: Use the second camera and the third camera of the portable multi-camera device to respectively shoot the same fingertips of the left hand and the right hand, with the fingertips maintaining contact with the corresponding cameras and completely covering the lens during shooting, to obtain left fingertip videos and right fingertip videos; Step S180: performing averaging processing on all pixels of the left fingertip video and the right fingertip video to obtain a pixel value sequence of the left fingertip and a pixel value sequence of the right fingertip; Step S190: performing signal preprocessing on the pixel value sequence of the left fingertip and the pixel value sequence of the right fingertip to obtain a left hand pulse wave signal and a right hand pulse wave signal.

[0039] In this embodiment, the second and third cameras are preferably the two rear cameras of a smartphone. The same fingertips to be photographed are preferably the index or middle fingers of both hands, because the capillaries in the fingertips are densely distributed and the signal stability is high. At the same time, the arms should be kept at the same horizontal height during the shooting, and a desktop support can be used to avoid errors in the measurement of pulse wave transit time due to the influence of gravity. Furthermore, during the pixel averaging process, the grayscale or RGB mean of all pixels in the video frame should be directly calculated for the pure fingertip area without background interference to generate a sequence of fingertip pixel values. Subsequent signal preprocessing can also use detrending, filtering and smoothing, etc., synchronized with the facial signal preprocessing process to ensure that the time axis alignment accuracy of the three signals meets the PTT calculation requirements.

[0040] Step S200 , performing feature extraction on the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature.

[0041] In this embodiment, upper limb arteries can become stenotic or occluded due to ruptured atherosclerotic plaques, thromboembolism, or vasculitis. Long-term stenosis or occlusion can cause upper limb pain, numbness, and weakness, particularly during physical activity. Furthermore, the affected limb may experience skin pallor, chills, or a decrease in temperature. In severe cases, this can even lead to necrosis of the fingertips. The heart constantly pumps blood to various parts of the body. Arterial blood flows from the heart through the upper limb arteries to peripheral vascular terminals, such as the fingers. The subtle skin color changes detected by the PPG signal are essentially light absorption fluctuations caused by changes in hemoglobin concentration and oxygenation status. In the early stages of upper limb stenosis or occlusion, the PPG signal exhibits characteristic changes, including significant amplitude attenuation, waveform distortion, and phase delay. This significant amplitude attenuation is due to reduced distal blood perfusion, which weakens arterial blood volume fluctuations. Waveform distortion occurs when the ascending limb is flat and prolonged, reflecting increased blood resistance. The systolic peak becomes broadened, blunted, and less sharp. Absent or blurred dicrotic waves indicate decreased vascular elasticity and reverse blood flow. Phase delay results from obstructed pulse wave conduction. Therefore, analyzing finger PPG signals at multiple locations can be used to assess the prevalence of upper limb arterial obstruction.

[0042] In one implementation, the evaluation features include pulse wave transmission time difference and pulse wave waveform similarity features, and the feature extraction of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain the signal transmission time difference feature and the signal waveform similarity feature specifically includes the following steps: Step S210: Using a positioning algorithm, locate all reference signal feature points, left hand pulse wave signal feature points, and right hand pulse wave signal feature points, wherein each feature point corresponds one-to-one in the heartbeat cycle; Step S220: Calculate the left hand pulse wave transmission time difference and the right hand pulse wave transmission time difference based on the reference signal characteristic points, the left hand pulse wave signal characteristic points, and the right hand pulse wave signal characteristic points; Step S230 : Calculate the left hand pulse wave waveform similarity feature and the right hand pulse wave waveform similarity feature based on the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal.

[0043] In this embodiment, a unified internal clock or external synchronization signal is used to ensure that the time deviation of the three signal acquisitions is less than a preset threshold, ensuring that the pulse wave signals obtained at three locations on the human body are synchronized. Furthermore, since the facial skin is located centrally in the human anatomy, the PPG signal collected from the face can be used as a reference signal when calculating the pulse wave transit time difference between the left and right hands. Alternatively, a cardiac oscillation signal or heart sound signal can be used as a reference signal to calculate the pulse wave transit time difference between the left and right hands. Before calculating the PTT for both hands, methods such as the instantaneous signal-to-noise ratio are used to eliminate signal segments that are severely interfered with by hand noise. For each cardiac cycle, peak location and other methods are used to identify characteristic points of the three synchronized PPG signals, including typical PPG waveform features such as the systolic peak and the maximum slope point. The systolic peak represents the highest point in the pulse waveform, reflecting peak systolic blood flow. The maximum slope point can be the maximum slope point on the rising limb, which represents the maximum slope of the rising edge of the waveform and represents the left ventricular ejection rate. In addition, the dicrotic notch can be used as a feature point to indicate the turning point of the waveform formed by arterial elastic recoil, reflecting vascular compliance. The peak detection algorithm locates the systolic peak apex, and the second-order derivative zero-crossing method identifies the dicrotic notch, ensuring that the feature point types of the three signals within each heartbeat cycle are consistent and the time alignment error is less than the preset threshold. In other words, by setting the systolic peak amplitude threshold or the rising edge slope threshold, the feature points of each heartbeat cycle can be located, ensuring that the feature points of the facial, left hand, and right hand signals are strictly aligned on the time axis for subsequent PTT calculation.

[0044] In one implementation, the calculating of the left-hand pulse wave transit time difference and the right-hand pulse wave transit time difference based on the reference signal feature points, the left-hand pulse wave signal feature points, and the right-hand pulse wave signal feature points specifically includes the following steps: Step S221: For each heartbeat cycle, subtract the timestamp of the reference signal characteristic point from the timestamp of the left hand pulse wave signal characteristic point to obtain the left hand pulse wave transmission time difference; Step S222: For each heartbeat cycle, subtract the timestamp of the reference signal characteristic point from the timestamp of the right hand pulse wave signal characteristic point to obtain the right hand pulse wave transmission time difference.

[0045] In this embodiment, preferably, the peak of each heartbeat cycle of the pulse wave signal is used as a feature point. Figure 2 In the process shown, the facial PPG signal is used as a reference signal as an example. After determining the feature points of each heartbeat cycle, the timestamps of the facial PPG signal feature points are subtracted from the timestamps of the facial PPG signal feature points of the left and right hands to obtain the PTT of both upper limbs. Figure 2 As shown, the PPG-1 is the left hand pulse wave signal, the PPG-2 is the facial pulse wave signal, and the PPG-3 is the right hand pulse wave signal. The PPG-1 peak feature point timestamp in the same heartbeat cycle is subtracted from the PPG-2 peak feature point timestamp to obtain the left hand pulse wave conduction time difference. Similarly, the PPG-3 peak feature point timestamp in the same heartbeat cycle is subtracted from the PPG-2 peak feature point timestamp to obtain the right hand pulse wave conduction time difference. Similarly, if the cardiac signal or heart sound signal is used as the reference signal instead of the facial PPG, the PTT calculation of both upper limbs can also be achieved. Specifically, by locating the cardiac feature point, such as the starting point of the systolic period, and comparing it with the systolic peak feature point timestamp of the PPG signals of both hands, the PTT difference is calculated.

[0046] In one implementation, the calculating of the left-hand pulse wave waveform similarity feature and the right-hand pulse wave waveform similarity feature based on the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal specifically includes the following steps: Step S231: for each heartbeat cycle, calculating the similarity between the left hand pulse wave signal and the reference signal to obtain a waveform similarity feature of the left hand pulse wave; Step S232: For each heartbeat cycle, calculate the similarity between the right hand pulse wave signal and the reference signal to obtain a waveform similarity feature of the right hand pulse wave.

[0047] In this embodiment, Figure 2 In the process shown, the facial PPG signal is used as a reference signal as an example, and the cosine similarity algorithm is used to calculate the waveform similarity. Figure 2As shown, the waveforms of the left hand pulse wave signal PPG-1 and the facial signal PPG-2 are normalized within each heartbeat cycle, and the cosine value of their vectors is calculated. Values ​​closer to 1 indicate more similar waveform morphology. Similarly, the same calculation process is performed on the right hand pulse wave signal PPG-3 and the facial signal to obtain the right hand waveform similarity feature. This method can quantitatively assess the morphological differences between the bilateral upper limb pulse waves and the central reference signal, effectively identifying waveform distortions caused by arterial occlusion, such as amplitude attenuation and a flattened ascending limb, providing multi-dimensional features for determining the degree of occlusion. In addition to using the cosine similarity algorithm to calculate waveform similarity, methods such as Euclidean distance or correlation coefficient can also be used to calculate similarity features between the respective PPG waveforms. These features can further enhance the model's ability to identify arterial occlusion. Similarly, after filtering and preprocessing the heart vibration or heart sound signals through feature point alignment, their waveforms can be morphologically compared with the PPGs of both hands. For example, the first heart sound peak of the cardiac oscillation signal is used as a reference point, and the timing is aligned with the contraction peak of the PPG of both hands, and then the similarity index of the waveform curve is calculated.

[0048] Step S300: Input the signal conduction time difference feature and the signal waveform similarity feature into a pre-trained evaluation model to obtain an upper limb artery occlusion evaluation result.

[0049] In this embodiment, the pre-trained assessment model evaluates pulse wave signals based on assessment features. These assessment features include the aforementioned bimanual PTT features and waveform similarity features. After calculating the assessment features for a set of synchronized pulse wave signals from three locations on the human body, the resulting assessment features are input into the pre-trained assessment model, which then outputs an upper limb artery occlusion assessment result corresponding to this set of data.

[0050] In one implementation, the method further includes: Step S400: Using the evaluation features of a number of normal pulse wave signal samples and the evaluation features of abnormal pulse wave signal samples as training samples, the evaluation model is trained to obtain a pre-trained evaluation model.

[0051] In this embodiment, before training the evaluation model, a large amount of sample data is collected, including normal and abnormal pulse wave signals and their corresponding PTT values ​​and waveform similarity features. This ensures a diverse and representative dataset and improves the model's generalization ability. In addition to PTT and waveform similarity features, other physiological features such as heart rate variability, pulse wave amplitude, and waveform symmetry are considered as model inputs. These features can provide more comprehensive hemodynamic information and enhance the model's predictive power. This evaluation model can be experimented with a variety of machine learning algorithms, such as support vector machines, random forests, and neural networks. Cross-validation and hyperparameter tuning are used to select the optimal model to ensure optimal classification results. The model is trained using the training set and its performance is evaluated on the validation set. The model's precision, recall, and F1 score are evaluated to ensure its effectiveness and reliability in detecting arterial occlusion. The F1 score is the harmonic mean of precision and recall. Ultimately, through training, a pre-trained evaluation model is obtained and used to evaluate samples.

[0052] In summary, the technical solutions in the above embodiments address the characteristic of upper limb artery obstruction, which often manifests locally in the left and right upper limbs and is reflected in pulse wave transmission time and waveform variations. A reference signal, virtually unaffected by upper limb obstruction, is selected. A portable multi-camera device simultaneously captures the human reference signal, the left hand pulse wave signal, and the right hand pulse wave signal. A simplified evaluation algorithm is designed by combining signal transmission time difference characteristics with waveform similarity. This collaborative analysis of signals from three locations overcomes the interference of localized obstruction on a single signal, enabling a simple and convenient algorithm to accurately assess upper limb artery obstruction.

[0053] like Figure 3 As shown in , an embodiment of the present invention provides an upper limb artery obstruction assessment system based on a portable multi-camera device, the system comprising: a signal acquisition module 10 , a feature acquisition module 20 , and an upper limb artery obstruction assessment module 30 .

[0054] Specifically, the pulse wave signal acquisition module 10 is used to collect a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal based on a portable multi-camera device, and the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with the acquisition time as the reference time; the evaluation feature acquisition module 20 is used to extract features of the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; the upper limb artery obstruction assessment module 30 is used to input the signal conduction time difference feature and the signal waveform similarity feature into a pre-trained assessment model to obtain an upper limb artery obstruction assessment result.

[0055] In one implementation, the reference signal is a facial pulse wave signal, and the signal acquisition module includes: A facial video shooting unit, configured to shoot a face using the first camera of the portable multi-camera device to obtain a facial video; A facial skin mask acquisition unit, configured to perform face detection on the facial video to obtain a mask of the facial skin area; a facial pixel value sequence acquisition unit, configured to perform averaging processing on all pixels of the facial skin area in the facial video based on the mask of the facial skin area to obtain a facial pixel value sequence; The facial pixel value sequence preprocessing unit is used to perform signal preprocessing on the facial pixel value sequence to obtain a facial pulse wave signal.

[0056] In one implementation, the reference signal is a heart vibration signal or a heart sound signal, and the signal acquisition module includes: a cardiac oscillation signal acquisition unit, configured to use the acceleration sensor of the portable multi-camera device to collect cardiac oscillations conducted through the chest wall, and perform preprocessing to obtain a cardiac oscillation signal; The heart sound signal acquisition unit is used to use the microphone of the portable multi-camera device to collect the sound near the chest heart and perform preprocessing to obtain the heart sound signal.

[0057] In one implementation, the signal acquisition module includes: A two-hand fingertip video acquisition unit is used to use the second camera and the third camera of the portable multi-camera device to respectively shoot the same fingertips of the left hand and the right hand, so that the fingertips are in contact with the corresponding cameras and completely cover the lens during shooting, thereby obtaining left fingertip videos and right fingertip videos; a two-hand fingertip pixel value sequence acquisition unit, configured to average all pixels of the left fingertip video and the right fingertip video to obtain a left fingertip pixel value sequence and a right fingertip pixel value sequence; The fingertip pixel value sequence preprocessing unit is used to perform signal preprocessing on the pixel value sequence of the left fingertip and the pixel value sequence of the right fingertip to obtain the left hand pulse wave signal and the right hand pulse wave signal.

[0058] In one implementation, the feature acquisition module includes: A feature point acquisition unit, configured to locate all reference signal feature points, left hand pulse wave signal feature points, and right hand pulse wave signal feature points using a positioning algorithm, wherein each feature point corresponds one-to-one in a heartbeat cycle; a signal conduction time difference acquisition unit, configured to calculate a left-hand pulse wave conduction time difference and a right-hand pulse wave conduction time difference based on the reference signal characteristic points, the left-hand pulse wave signal characteristic points, and the right-hand pulse wave signal characteristic points; The signal waveform similarity feature acquisition unit is used to calculate the left hand pulse wave waveform similarity feature and the right hand pulse wave waveform similarity feature based on the reference signal, the left hand pulse wave signal and the right hand pulse wave signal.

[0059] In one implementation, the signal conduction time difference acquisition unit includes: a left hand pulse wave transmission time difference acquisition subunit, configured to, for each heartbeat cycle, subtract the timestamp of the reference signal characteristic point from the timestamp of the left hand pulse wave signal characteristic point to obtain the left hand pulse wave transmission time difference; The right hand pulse wave transmission time difference acquisition subunit is used to subtract the timestamp of the reference signal characteristic point from the timestamp of the right hand pulse wave signal characteristic point for each heartbeat cycle to obtain the right hand pulse wave transmission time difference.

[0060] In one implementation, the signal waveform similarity feature acquisition unit includes: a left hand pulse wave waveform similarity feature acquisition subunit, configured to calculate the similarity between the left hand pulse wave signal and the reference signal for each heartbeat cycle, and obtain a left hand pulse wave waveform similarity feature; The right hand pulse wave waveform similarity feature acquisition subunit is used to calculate the similarity between the right hand pulse wave signal and the reference signal for each heartbeat cycle to obtain the right hand pulse wave waveform similarity feature.

[0061] In one implementation, the system further includes: The evaluation model training module is used to train the evaluation model using the evaluation features of several normal pulse wave signal samples and the evaluation features of abnormal pulse wave signal samples as training samples to obtain a pre-trained evaluation model.

[0062] Based on the above embodiment, the present invention further provides a terminal device, whose principle block diagram can be shown as follows: Figure 4 As shown. The terminal device includes a processor, a memory, a network interface, a display screen, and a temperature sensor connected via a system bus. The processor of the terminal device is used to provide computing and control capabilities. The memory of the terminal device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for assessing upper limb artery occlusion based on a portable multi-camera device is implemented. The display screen of the terminal device can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor of the terminal device is pre-set inside the terminal device to detect the operating temperature of the internal device.

[0063] Those skilled in the art will understand that Figure 4 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the terminal device to which the solution of the present invention is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0064] In one embodiment, a terminal device is provided, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: A reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal are collected based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to a collection time as a reference time; performing feature extraction on the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; The signal conduction time difference feature and the signal waveform similarity feature are input into a pre-trained evaluation model to obtain an upper limb artery occlusion evaluation result.

[0065] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0066] In summary, the present invention discloses a method, system, terminal device, and medium for assessing upper limb artery obstruction based on a portable multi-camera device. The method involves collecting a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal using the portable multi-camera device. The reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized using the acquisition time as a reference time. Feature extraction is performed on the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature. The signal conduction time difference feature and the signal waveform similarity feature are input into a pre-trained assessment model to obtain an upper limb artery obstruction assessment result. In view of the fact that upper limb artery obstruction symptoms often manifest in localized areas of the left and right upper limbs and are reflected in changes in pulse wave conduction time and waveform, the present invention selects a reference signal that is virtually unaffected by left and right upper limb obstruction. The portable multi-camera device synchronously collects the human body reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal. A simple assessment algorithm is designed based on the signal conduction time difference feature and the waveform similarity feature. The present invention is based on the collaborative analysis of three-position signals, breaking through the interference of local blockage on a single signal, and realizing accurate assessment of upper limb artery blockage with a simple and convenient algorithm.

[0067] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for assessing upper limb artery occlusion based on a portable multi-camera device, characterized in that: The method comprises: A reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal are collected based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to a collection time as a reference time; performing feature extraction on the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; The signal conduction time difference feature and the signal waveform similarity feature are input into a pre-trained evaluation model to obtain an upper limb artery occlusion evaluation result.

2. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 1, characterized in that: The reference signal is a facial pulse wave signal, and the method of collecting the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device includes: Using the first camera of the portable multi-camera device to shoot the face to obtain a facial video; Performing face detection on the facial video to obtain a mask of the facial skin area; Based on the mask of the facial skin area, averaging all pixels of the facial skin area in the facial video to obtain a facial pixel value sequence; Signal preprocessing is performed on the facial pixel value sequence to obtain a facial pulse wave signal.

3. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 1, characterized in that: The reference signal is a heart vibration signal or a heart sound signal, and the collecting of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal based on the portable multi-camera device includes: Using the acceleration sensor of the portable multi-camera device to collect the heart vibration transmitted by the chest wall, and pre-processing it to obtain a heart vibration signal; Alternatively, the microphone of the portable multi-camera device is used to collect sounds near the heart in the chest and perform preprocessing to obtain a heart sound signal.

4. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 1, characterized in that: The method of collecting a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal based on a portable multi-camera device includes: Using the second camera and the third camera of the portable multi-camera device, respectively, a video of the same fingertip of the left hand and the right hand is taken, with the fingertip remaining in contact with the corresponding camera and completely covering the lens, to obtain a video of the left fingertip and a video of the right fingertip; Averaging all pixels of the left fingertip video and the right fingertip video to obtain a pixel value sequence of the left fingertip and a pixel value sequence of the right fingertip; Signal preprocessing is performed on the pixel value sequence of the left fingertip and the pixel value sequence of the right fingertip to obtain a left hand pulse wave signal and a right hand pulse wave signal.

5. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 4, characterized in that: The extracting features of the reference signal, the left hand pulse wave signal, and the right hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature includes: Through the positioning algorithm, all the reference signal feature points, left hand pulse wave signal feature points and right hand pulse wave signal feature points are located, wherein each feature point corresponds one to one in the heartbeat cycle; Calculating a left-hand pulse wave transmission time difference and a right-hand pulse wave transmission time difference based on the reference signal characteristic points, the left-hand pulse wave signal characteristic points, and the right-hand pulse wave signal characteristic points; Based on the reference signal, the left hand pulse wave signal and the right hand pulse wave signal, a left hand pulse wave waveform similarity feature and a right hand pulse wave waveform similarity feature are calculated.

6. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 5, characterized in that: The calculating of the left hand pulse wave transmission time difference and the right hand pulse wave transmission time difference based on the reference signal characteristic points, the left hand pulse wave signal characteristic points, and the right hand pulse wave signal characteristic points includes: For each heartbeat cycle, subtract the timestamp of the characteristic point of the reference signal from the timestamp of the characteristic point of the left hand pulse wave signal to obtain the left hand pulse wave transmission time difference; For each heartbeat cycle, the timestamp of the characteristic point of the right hand pulse wave signal is subtracted from the timestamp of the characteristic point of the reference signal to obtain the right hand pulse wave transmission time difference.

7. The upper limb artery occlusion assessment method based on a portable multi-camera device according to claim 5, characterized in that: The calculating of the left hand pulse wave waveform similarity feature and the right hand pulse wave waveform similarity feature based on the reference signal, the left hand pulse wave signal and the right hand pulse wave signal includes: For each heartbeat cycle, calculating the similarity between the left hand pulse wave signal and the reference signal to obtain a waveform similarity feature of the left hand pulse wave; For each heartbeat cycle, the similarity between the right hand pulse wave signal and the reference signal is calculated to obtain a waveform similarity feature of the right hand pulse wave.

8. An upper limb artery occlusion assessment system based on a portable multi-camera device, characterized in that: The system comprises: A signal acquisition module is used to acquire a reference signal, a left-hand pulse wave signal, and a right-hand pulse wave signal based on a portable multi-camera device, wherein the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal are synchronized with respect to the acquisition time as a reference time; a feature acquisition module, configured to extract features from the reference signal, the left-hand pulse wave signal, and the right-hand pulse wave signal to obtain a signal conduction time difference feature and a signal waveform similarity feature; The upper limb artery obstruction assessment module is used to input the signal conduction time difference feature and the signal waveform similarity feature into a pre-trained assessment model to obtain an upper limb artery obstruction assessment result.

9. A terminal device, characterized in that: The terminal device includes a memory, a processor, and an upper limb artery obstruction assessment program based on a portable multi-camera device stored in the memory and executable on the processor. When the processor executes the upper limb artery obstruction assessment program based on the portable multi-camera device, the steps of the upper limb artery obstruction assessment method based on a portable multi-camera device are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an upper limb artery obstruction assessment program based on a portable multi-camera device. When the upper limb artery obstruction assessment program based on a portable multi-camera device is executed by a processor, the steps of the upper limb artery obstruction assessment method based on a portable multi-camera device as described in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Device, system and method for detection of pulse and / or pulse-related information of a patient

    EP3417770A1

  • Eyeglasses to detect abnormal medical events including stroke and migraine

    US10638938B1

  • Method and system for cardiovascular disease assessment and management

    US20160360980A1

  • Method and system for detection of coronary artery disease in a person using a fusion approach

    US20180228444A1

  • Utilizing correlations between PPG signals and iPPG signals to improve detection of physiological responses

    US20200085312A1