Device and method for correcting skin color influence in blood oxygen saturation detection result

Abstract

The invention belongs to the technical field of medical detection equipment, and particularly relates to a device and method for correcting skin color influence in a blood oxygen saturation detection result, and the device comprises a blood oxygen detection module, a skin color detection module, a central processing module and a display module; the blood oxygen detection module comprises a first light source and a signal receiving tube; the skin color detection module comprises a second light source, a color sensor and a real-time image acquisition unit; the central processing module is electrically connected with the blood oxygen detection module and the skin color detection module. And the display module is electrically connected with the central processing module and is used for displaying a result of the central processing module. Compared with the prior art, by combining real-time skin color parameters collected by the skin color detection module and utilizing a dynamic correction algorithm of the central processing module, the measurement result is compensated, interference of skin color differences on optical detection is eliminated, the influence of the skin color differences on the blood oxygen measurement result is eliminated, and the blood oxygen saturation degree detection precision of a patient with dark skin is improved.

Description

Technical Field

[0001] This invention belongs to the field of medical testing equipment technology, specifically relating to a device and method for correcting the influence of skin color on blood oxygen saturation test results. Background Technology

[0002] Currently, the main non-invasive method for detecting blood oxygen saturation in clinical practice is optical. This method utilizes the different absorption characteristics of oxyhemoglobin and deoxyhemoglobin in the blood at different wavelengths to calculate the patient's blood oxygen saturation (SpO2). 2 Through the above methods, patients' blood oxygen saturation can be non-invasively and in real time, helping doctors and patients to understand the patient's physical condition in a timely manner and make rapid judgments or treatment plans.

[0003] Recent experimental studies have shown that skin color affects the measurement results of optical pulse oximeters, and this effect significantly overestimates the SaO2 of patients with darker skin. 2 The measurement results showed that the oxygen saturation level increased as blood oxygen saturation decreased. Summary of the Invention

[0004] (a) Technical problems to be solved The purpose of this invention is to provide an apparatus and method for correcting the influence of skin color on blood oxygen saturation test results in order to solve at least one of the above-mentioned problems. This addresses the issue that traditional blood oxygen detection devices in the prior art typically use only light sources of specific wavelengths for detection, making it impossible to distinguish the influence of skin color differences on the measurement results. The invention achieves the effect of effectively eliminating the influence of skin color differences on blood oxygen measurement results through dynamic skin color detection and real-time correction mechanisms, thereby improving the accuracy of blood oxygen saturation detection for patients with dark skin.

[0005] (II) Technical Solution The objective of this invention is achieved through the following technical solution: One of the technical solutions of the present invention is a device for correcting the influence of skin color in blood oxygen saturation detection results, including a blood oxygen detection module, a skin color detection module, a central processing module and a display module; The blood oxygen detection module includes a first light source and a signal receiving tube. The first light source is used to emit red light and infrared light, and the signal receiving tube is used to receive light signals after being transmitted or reflected by human tissue. The skin color detection module includes a second light source, a color sensor, and a real-time image acquisition unit. The light source is used to illuminate the surface of the skin being tested, the color sensor is used to receive reflected light from the skin to obtain the original color signal, and the real-time image acquisition unit is used to continuously capture skin images of the tested area during blood oxygen monitoring. The central processing module is electrically connected to the blood oxygen detection module and the skin color detection module respectively. The central processing module calculates the initial blood oxygen saturation value based on the signal from the central processing unit of the blood oxygen detection module, determines the original skin color parameter based on the original color signal from the skin color detection module, updates the skin color parameter through an image processing algorithm, corrects the initial blood oxygen saturation value based on the final skin color parameter, and obtains and outputs the corrected blood oxygen saturation value. The display module is electrically connected to the central processing module, and the display module is used to display the results of the central processing module.

[0006] Furthermore, multiple blood oxygen detection modules and skin color detection modules are configured, and each of the multiple blood oxygen detection modules and skin color detection modules is electrically connected to the central processing module.

[0007] Furthermore, the first light source includes a light-emitting tube capable of emitting red and infrared light. The red and infrared light can penetrate human tissue and be absorbed by hemoglobin. Blood oxygen saturation is calculated by detecting the difference in light signals after transmission or reflection.

[0008] Furthermore, the second light source includes an LED light source capable of emitting white light, and the color sensor refers to a photoelectric element capable of sensing the RGB components in the light reflected from the skin. Specifically, it can be implemented using a photodiode array or a CMOS sensor, and obtains the original skin color data by measuring the intensity of the reflected light. The real-time image acquisition unit refers to a device that dynamically captures visual information of the skin area, and can be implemented using a miniature camera or an optical scanning module, continuously acquiring skin images to track changes in skin color.

[0009] Furthermore, the central processing module includes a signal processing circuit unit, which amplifies, filters, and performs analog-to-digital conversion on the signal received by the signal receiving tube, and also performs analog-to-digital conversion on the signal received by the color sensor.

[0010] Furthermore, the central processing module includes a skin color parameter-correction coefficient mapping unit and a skin color classification model unit, which are stored in the memory of the central processing module; The skin color parameter-correction coefficient mapping unit and the skin color classification model unit are pre-established through calibration experiments on different skin color models.

[0011] The skin color classification model unit classifies or quantifies skin images based on color space features. Pre-calibration experiments collect blood oxygenation data and actual blood oxygen values ​​corresponding to different skin color parameters on a standard skin color model. After statistical analysis, a table of correspondence between parameters and correction values ​​is generated, and the classification model is trained to recognize skin color features. Through the pre-established mapping relationship and classification model, the correction process does not require real-time calculation of complex parameters; fast and accurate correction can be achieved by directly calling the calibration data.

[0012] Furthermore, the correction coefficient corresponding to the skin color parameter is obtained by querying a pre-stored skin color parameter-correction coefficient mapping table, and the initial blood oxygen saturation value is corrected using this correction coefficient. The original color signal acquired by the color sensor is converted from analog to digital to generate a standardized skin color parameter, which is used as an index key value for matching and querying in the mapping table.

[0013] Furthermore, the image processing algorithm of the central processing module analyzes the statistical characteristics of the skin image in a specific color space through a skin color classification model unit; The statistical features include at least one selected from the group consisting of the H component histogram, the S component histogram of the HSV color space, and the LBP texture histogram calculated from the grayscale image.

[0014] Furthermore, the H-component histogram identifies the skin's base hue by statistically analyzing the proportion of pixels in each hue interval; the S-component histogram determines the intensity of light reflection on the skin surface by statistically analyzing the distribution ratio of low-saturation and high-saturation regions; and the LBP texture histogram quantifies the structural features of the skin's stratum corneum by statistically analyzing the frequency of local texture patterns. These three types of feature vectors are normalized and input into the skin color classification model unit. Through a pre-trained model, they are mapped to skin color classification labels or continuous brightness values. This process allows the skin color parameter calibration coefficients to dynamically adapt to the differences in skin characteristics among different individuals, thereby improving the accuracy of blood oxygen saturation correction results.

[0015] Furthermore, the input to the skin color classification model unit is a feature vector extracted from the skin image, and the output is a classification label for the skin color or a continuous numerical value representing the brightness of the skin color.

[0016] Furthermore, the skin color classification model of the skin color classification model unit is a neural network model, and the feature vector includes a joint vector of color features and texture features.

[0017] Furthermore, the central processing module is connected to a power supply, which is connected to the display module, and the power supply is used to provide power.

[0018] Furthermore, the display module is provided with an external interface and a cloud interface. The external interface is used to connect to hardware devices, and the cloud interface is used to connect to mobile devices.

[0019] The second technical solution of the present invention is a method for correcting the influence of skin color in blood oxygen saturation detection results using the device described above, comprising the following steps: controlling the blood oxygen detection module to work and obtaining an initial blood oxygen saturation value; controlling the skin color detection module to work, obtaining an original color signal and determining skin color parameters; and correcting the initial blood oxygen saturation value based on the skin color parameters to obtain a corrected blood oxygen saturation value.

[0020] Furthermore, the step of determining skin color parameters includes: extracting RGB color space values ​​from the original color signal and converting them into brightness values ​​that characterize skin tone lightness or darkness, or converting them into standard skin color chart index values.

[0021] Furthermore, during continuous blood oxygen saturation monitoring, the steps of acquiring skin color information and making corrections are periodically repeated to achieve dynamic tracking and correction of blood oxygen saturation values.

[0022] The blood oxygen detection module emits red and infrared light through a first light source, and a signal receiving tube receives the light signals transmitted or reflected by human tissue. The skin color detection module uses a second light source to illuminate the surface of the skin being tested; a color sensor receives the reflected light from the skin to obtain the original color signal. A real-time image acquisition unit continuously captures skin images of the tested area during blood oxygen monitoring. The central processing module calculates the initial blood oxygen saturation value based on the signal from the blood oxygen detection module, determines the original skin color parameters based on the original color signal from the skin color detection module, updates the skin color parameters using an image processing algorithm, and corrects the initial blood oxygen saturation value based on the final skin color parameters to obtain the corrected blood oxygen saturation value. The display module displays the results from the central processing module.

[0023] (III) Beneficial Effects Compared with the prior art, the present invention has the following advantages: (1) By capturing and analyzing the optical properties of the skin in real time, this application significantly improves the accuracy of blood oxygen monitoring for patients with dark skin. Especially in the case of low blood oxygen, it solves the deviation caused by the skin, especially dark skin, on the measurement results of pulse oximeter, thereby avoiding the adverse effects of doctors misjudging or delaying the condition of such patients in clinical applications.

[0024] (2) This application improves the quality and accuracy of the signal, providing a reliable data basis for subsequent blood oxygen saturation calculation and skin color parameter determination. Through the integrated signal processing circuit unit, the system structure is simplified and the efficiency and stability of signal processing are improved.

[0025] (3) This application effectively eliminates the interference of skin pigmentation on optical detection. By dynamically fusing the dual data sources of static color signal and real-time image features, it significantly improves the accuracy of blood oxygen saturation measurement for people with dark skin. The periodic parameter update mechanism can adapt to the dynamic changes in skin color caused by changes in ambient light or fluctuations in local blood circulation during the monitoring process, ensuring the continuous reliability of the correction results. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of the device for correcting the influence of skin color on blood oxygen saturation detection results according to the present invention.

[0028] In the diagram: 1-Blood oxygen detection module; 101-First light source; 102-Signal receiving tube; 2-Skin color detection module; 201-Signal receiving tube; 202-Color sensor; 203-Real-time image acquisition unit; 3-Central processing module; 301-Signal processing circuit unit; 302-Skin color parameter-correction coefficient mapping unit; 303-Skin color classification model unit; 4-Display module; 401-External interface; 402-Cloud interface; 5-Power supply. Detailed Implementation

[0029] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0030] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0032] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0033] Additionally, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that practice can be carried out without these specific details.

[0034] The technical solutions provided by the various embodiments of this application are described below with reference to the accompanying drawings. Example 1

[0035] See Figure 1 The present invention provides a device for correcting the influence of skin color on blood oxygen saturation detection results, comprising two blood oxygen detection modules 1, two skin color detection modules 2, a central processing module 3, a display module 4, and a power supply 5.

[0036] The blood oxygen detection module 1 includes a first light source 101 and a signal receiving tube 102. The first light source 101 includes a red LED with a wavelength of 660nm and an infrared LED with a wavelength of 940nm. The signal receiving tube 102 is a silicon photodiode. The skin color detection module 2 includes a second light source 201, a color sensor 202, and a real-time image acquisition unit 203. The second light source 201 is a white LED, the color sensor 202 is an RGB three-color photosensitive element, and the real-time image acquisition unit 203 is a miniature CMOS camera.

[0037] The central processing module 3 uses an ARM Cortex-M4 microcontroller, which integrates signal processing circuits and image processing algorithms. It is electrically connected to the blood oxygen detection module 1 and the skin color detection module 2 respectively. The central processing module 3 calculates the initial blood oxygen saturation value based on the signal from the central processing unit 3 of the blood oxygen detection module, determines the original skin color parameters based on the original color signal from the skin color detection module 2, updates the skin color parameters through image processing algorithms, corrects the initial blood oxygen saturation value based on the final skin color parameters, and obtains and outputs the corrected blood oxygen saturation value. The central processing module 3 includes a signal processing circuit unit 301, a skin color parameter-correction coefficient mapping unit 302, and a skin color classification model unit 303.

[0038] The signal processing circuit unit 301 includes an amplifier, a filter, and an analog-to-digital converter. The light signal received by the signal receiving tube 102 is first amplified by the amplifier, then noise is removed by the filter, and finally the analog signal is converted into a digital signal by the analog-to-digital converter. For the signal received by the color sensor 202, the analog signal is directly processed by the analog-to-digital converter to convert the analog signal into a digital signal.

[0039] The skin color parameter-correction coefficient mapping unit 302 and the skin color classification model unit 303 are stored in the memory of the central processing module 3 and are pre-established through calibration experiments on different skin color models.

[0040] The skin color parameter-correction coefficient mapping unit 302 is implemented using a lookup table. This lookup table contains multiple preset skin color parameter values ​​and corresponding correction coefficient values. In actual use, the skin color detection module first obtains the subject's skin color parameters. Then, it searches the mapping table for the set of data closest to the skin color parameter and obtains the corresponding correction coefficient. Finally, it multiplies the correction coefficient by the initial blood oxygen saturation value to obtain the corrected blood oxygen saturation value.

[0041] The central processing module 3 uses the image processing algorithm of the skin color classification model unit 303 to analyze the statistical characteristics of skin images in a specific color space. The skin color classification model of the skin color classification model unit 303 is a neural network model, and the feature vector includes a joint vector of color features (peak value of H component histogram, mean value of S component histogram) and texture features (LBP texture histogram distribution features). The acquired RGB format skin image is converted to the HSV color space, and the histograms of the H component and S component, as well as the LBP texture histogram calculated from the grayscale image, are calculated. This feature vector is input into the pre-trained skin color classification model, and the model outputs a continuous value representing the brightness of skin color, realizing accurate quantification and classification of skin color.

[0042] Display module 4 is electrically connected to central processing module 3. Display module 4 is used to display the results of central processing module 3. Display module 4 is provided with external interface 401 and cloud interface 402. External interface 401 uses USB Type-C physical interface to connect to hardware devices. Cloud interface 402 integrates Wi-Fi 6 wireless communication chip to establish TCP / IP protocol connection with mobile terminal for connection with mobile terminal.

[0043] Power supply 5 is connected to central processing module 3 and display module 4 for power supply.

[0044] During operation, the red and infrared LEDs of the blood oxygen detection module 1 are alternately lit, and the signal receiving tube 102 collects the reflected light signal. After amplification, filtering, and analog-to-digital conversion, the light signal is input to the central processing module 3. At the same time, the white LED of the skin color detection module 2 is continuously illuminated, and the color sensor 202 acquires the RGB three-channel signal of the skin reflected light every second. After analog-to-digital conversion, the signal is converted into YUV luminance component values ​​that characterize the brightness of the skin color. The CMOS camera of the real-time image acquisition unit 203 captures the skin image at a frame rate of 30fps. The central processing module 3 first calculates the initial blood oxygen saturation based on the ratio of red and infrared light signals, then uses the RGB values ​​of the color sensor 202 to determine the initial skin color parameters. It updates the skin color parameters by analyzing the HSV color space and YUV luminance component values ​​of the skin image. Based on the skin color parameters, it queries the pre-stored mapping table to obtain the correction coefficient. After multiplying the initial blood oxygen saturation value by the correction coefficient, it outputs the result to the LCD screen of the display module 4 for display, and can also be output through the external interface 401.

[0045] Specifically, after the skin color detection module 2 acquires the skin reflection light signal, the original color signal output by the color sensor 202 is converted into RGB values, and further converted into brightness values ​​or standard color card index values. The skin color parameter-correction coefficient mapping unit 302 queries the pre-stored mapping table according to the brightness value or index value to obtain the corresponding correction coefficient. The skin image captured by the real-time image acquisition unit 203 is input into the skin color classification model unit 303, which extracts the peak value of the H component histogram, the mean value of the S component histogram, and the distribution features of the LBP texture histogram in the HSV color space to generate a feature vector. After the feature vector is processed by the skin color classification model unit 303, it outputs continuous skin brightness values ​​to dynamically update the skin color parameters. The central processing module 3 combines the correction coefficients provided by the skin color parameter-correction coefficient mapping unit 302 with the real-time parameters output by the skin color classification model unit 303 to perform weighted correction on the initial blood oxygen saturation value.

[0046] When the skin color classification model unit 303 detects an increase in skin brightness, the correction coefficient provided by the skin color parameter-correction coefficient mapping unit 302 reduces the initial blood oxygen value by a preset ratio, thereby eliminating the light signal absorption deviation caused by dark skin color.

[0047] The same or similar parts between the various embodiments in this specification can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments.

[0048] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A device for correcting the influence of skin color on blood oxygen saturation test results, characterized in that, It includes a blood oxygen detection module (1), a skin color detection module (2), a central processing module (3), and a display module (4); The blood oxygen detection module (1) includes a first light source (101) and a signal receiving tube (102). The first light source (101) is used to emit red light and infrared light, and the signal receiving tube (102) is used to receive light signals transmitted or reflected by human tissue. The skin color detection module (2) includes a second light source (201), a color sensor (202), and a real-time image acquisition unit (203). The second light source (201) is used to illuminate the surface of the skin to be tested. The color sensor (202) is used to receive the reflected light from the skin to obtain the original color signal. The real-time image acquisition unit (203) is used to continuously capture the skin image of the tested area during blood oxygen monitoring. The central processing module (3) is electrically connected to the blood oxygen detection module (1) and the skin color detection module (2) respectively. The central processing module (3) calculates the initial blood oxygen saturation value based on the signal from the central processing unit (3) of the blood oxygen detection module, determines the original skin color parameter based on the original color signal of the skin color detection module (2), updates the skin color parameter through an image processing algorithm, corrects the initial blood oxygen saturation value based on the final skin color parameter, and obtains and outputs the corrected blood oxygen saturation value. The display module (4) is electrically connected to the central processing module (3), and the display module (4) is used to display the results of the central processing module (3).

2. The apparatus for correcting the influence of skin color on blood oxygen saturation detection results according to claim 1, characterized in that, The central processing module (3) includes a signal processing circuit unit (301), which amplifies, filters and performs analog-to-digital conversion on the signal received by the signal receiving tube (102), and performs analog-to-digital conversion on the signal received by the color sensor (202).

3. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 1, characterized in that, The central processing module (3) includes a skin color parameter-correction coefficient mapping unit (302) and a skin color classification model unit (303), which are stored in the memory of the central processing module (3); The skin color parameter-correction coefficient mapping unit (302) and the skin color classification model unit (303) are pre-established through calibration experiments on different skin color models.

4. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 3, characterized in that, The correction coefficient corresponding to the skin color parameter is obtained by querying the pre-stored skin color parameter-correction coefficient mapping table, and the initial blood oxygen saturation value is corrected using the correction coefficient.

5. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 3, characterized in that, The image processing algorithm of the central processing module (3) is to analyze the statistical characteristics of the skin image in a specific color space through the skin color classification model unit (303); The statistical features include at least one selected from the group consisting of the H component histogram, the S component histogram of the HSV color space, and the LBP texture histogram calculated from the grayscale image.

6. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 5, characterized in that, The input of the skin color classification model unit (303) is the feature vector extracted from the skin image, and the output is the classification label of the skin color or a continuous value representing the brightness of the skin color.

7. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 1, characterized in that, The central processing module (3) is connected to the power supply (5), and the power supply (5) is connected to the display module (4). The power supply (5) is used to supply power.

8. The apparatus for correcting the influence of skin color on blood oxygen saturation test results according to claim 1, characterized in that, The display module (4) is provided with an external interface (401) and a cloud interface (402). The external interface (401) is used to connect to hardware devices, and the cloud interface (402) is used to connect to mobile devices.

9. A method for correcting the influence of skin color in blood oxygen saturation detection results using the device as described in any one of claims 1 to 8, characterized in that, Includes the following steps: Control the blood oxygen detection module (1) to work and obtain the initial blood oxygen saturation value; control the skin color detection module (2) to work and obtain the original color signal and determine the skin color parameter; based on the skin color parameter, correct the initial blood oxygen saturation value to obtain the corrected blood oxygen saturation value.

10. The method for correcting the influence of skin color on blood oxygen saturation test results according to claim 9, characterized in that, The step of determining skin color parameters includes: extracting RGB color space values ​​from the original color signal and converting them into brightness values ​​that characterize the lightness and darkness of skin color or into standard skin color chart index values.

Images