Near infrared spectroscopy (NIRS)-based peripheral arteriosclerosis blood circulation abnormality detection system and detection method thereof

Abstract

The invention discloses a peripheral arteriosclerosis blood circulation anomaly detection system based on near infrared spectroscopy (NIRS) and a detection method thereof, the peripheral arteriosclerosis blood circulation anomaly detection system based on NIRS not only improves the detection efficiency and accuracy of peripheral arteriosclerosis diseases through technical innovation, but also has wide applicability and practicability, and is suitable for popularization and application. Good market prospects and social values are realized.

Description

Technical Field

[0001] The invention relates to the technical field of medical detection, in particular to a peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS). Background Art

[0002] At present, the diagnosis of PAD mainly relies on Doppler ultrasound, X-ray angiography, computed tomography (CTA) and magnetic resonance imaging (MRI) etc. Although these methods have been widely used in clinical practice, they have certain limitations: high operation complexity, environmental restrictions and radiation risks etc.

[0003] The present invention is a multi-channel peripheral arteriosclerosis detection system based on NIRS, and the system integrates blood oxygen saturation data acquisition, signal characteristic value extraction, data waveform display and peripheral arteriosclerosis diagnosis. NIRS technology can evaluate the hemodynamic state and metabolic activity of tissues by detecting the absorption and scattering of near-infrared light of specific wavelengths by tissues.

[0004] The present invention can realize real-time monitoring of blood oxygen saturation and blood flow in peripheral arteries, and provide a new technical means for the early diagnosis and treatment of peripheral arterial disease. It has the advantages of being non-invasive, real-time, portable, easy to operate, and low-cost. This invention can not only promote technological progress in the fields of biomedical engineering and bioinformatics, but also provide important technical support for the early detection and treatment of cardiovascular diseases, and has important scientific significance and application value. Summary of the invention

[0006] 1. Technical issues to be solved

[0007] In view of the shortcomings of the prior art, the present invention provides a multi-channel peripheral arteriosclerosis detection system based on NIRS, which integrates blood oxygen saturation data acquisition, signal characteristic value extraction, data waveform display and peripheral arteriosclerosis diagnosis. It is suitable for a wide range of people and is easy and quick to use.

[0008] (II) Technical solution

[0009] To achieve the above purpose, the present invention provides the following technical solutions:

[0010] A peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS), comprising:

[0011] a. At least seven detection channels, used to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body respectively;

[0012] b. At least one microcontroller for controlling the signal acquisition and processing of the detection channel;

[0013] c. at least one light source module for emitting near-infrared light of at least two wavelengths;

[0014] d. at least one photodetector for detecting the reflected light intensity of the near-infrared light in human tissue;

[0015] e. at least one signal amplification circuit for amplifying the signal detected by the photodetector;

[0016] f. at least one data processing module for processing the amplified signal according to the Beer-Lambert law and extracting blood oxygen saturation data;

[0017] g. at least one feature extraction module for extracting a low-frequency oscillation signal from the blood oxygen saturation data;

[0018] h. at least one diagnostic model for diagnosing peripheral arteriosclerosis based on the low-frequency oscillation signal.

[0019] Furthermore, the microcontroller is a STM32F4 single chip microcomputer.

[0020] Furthermore, the light source module includes a dual-wavelength LED emission module.

[0021] Furthermore, the signal amplification circuit includes at least one gain amplifier.

[0022] Furthermore, the data processing module includes a modified Beer-Lambert law algorithm.

[0023] Furthermore, the feature extraction module includes a bandpass filter.

[0024] Furthermore, the diagnostic model is based on a random forest algorithm.

[0025] Furthermore, a method for detecting abnormal blood circulation in peripheral arteriosclerosis based on near infrared spectroscopy (NIRS) comprises the following steps:

[0026] a. Collection step: using the detection channel to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body;

[0027] b. Emission step: emitting near-infrared light of at least two wavelengths through the light source module;

[0028] c. Detection step: detecting the reflected light intensity of the near-infrared light in human tissue by the photodetector;

[0029] d. Amplification step: amplifying the signal detected by the photodetector through the signal amplification circuit;

[0030] e. Processing step: processing the amplified signal according to the Beer-Lambert law through the data processing module and extracting blood oxygen saturation data;

[0031] f. Extraction step: extracting the low-frequency oscillation signal in the blood oxygen saturation data through the feature extraction module;

[0032] g. Diagnostic step: diagnose peripheral arteriosclerosis according to the low-frequency oscillation signal using the diagnostic model.

[0033] (III) Beneficial effects

[0034] Compared with the prior art, the present invention provides a peripheral arteriosclerosis blood circulation abnormality detection system and detection method based on near infrared spectroscopy (NIRS), which has the following beneficial effects:

[0035] 1. Through technological innovation, this system integrates blood oxygen saturation data acquisition, signal characteristic value extraction, data waveform display and peripheral arteriosclerosis diagnosis. It is suitable for a wide range of people, easy to operate and has significant medical value, scientific research value and economic value.

[0036] 2. The system combines portability, accuracy and high medical value. It reflects the patient's disease characteristics through low-frequency oscillation signals and uses random forest algorithms for diagnosis, which improves the accuracy and efficiency of diagnosis.

[0037] 3. The system is small in size, easy to operate and highly accurate: The design of this system focuses on user experience. It is small in size and easy to carry. The operation is simple and easy to understand, ensuring the accuracy and efficiency of the detection;

[0038] 4. Reflect the patient's disease characteristics through low-frequency oscillation signals: The system can directly reflect the patient's hemodynamic changes through LFO signals, providing important auxiliary diagnostic information for clinicians;

[0039] 5. Use random forests for peripheral arteriosclerosis diagnosis: The system uses advanced machine learning algorithms to improve the accuracy and efficiency of diagnosis;

[0040] 6. In summary, the NIRS-based peripheral arteriosclerosis blood circulation abnormality detection system of the present invention, through technological innovation, not only improves the detection efficiency and accuracy of peripheral arterial disease, but also has wide applicability and practicality, and has good market prospects and social value. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Technology roadmap;

[0042] Figure 2 The absorption spectrum of hemoglobin to light;

[0043] Figure 3 Second-order gain amplifier module circuit schematic diagram;

[0044] Figure 4 Random forest algorithm model. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in this embodiment to clearly and completely describe the technical solution in this embodiment. Obviously, the described embodiment is only a part of the embodiment of this invention, not all of the embodiments. Based on the embodiments in this invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of this protection.

[0046] Embodiment, a peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS), comprising:

[0047] a. At least seven detection channels, used to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body respectively;

[0048] b. At least one microcontroller for controlling the signal acquisition and processing of the detection channel;

[0049] c. at least one light source module for emitting near-infrared light of at least two wavelengths;

[0050] d. at least one photodetector for detecting the reflected light intensity of the near-infrared light in human tissue;

[0051] e. at least one signal amplification circuit for amplifying the signal detected by the photodetector;

[0052] f. at least one data processing module for processing the amplified signal according to the Beer-Lambert law and extracting blood oxygen saturation data;

[0053] g. at least one feature extraction module for extracting a low-frequency oscillation signal from the blood oxygen saturation data;

[0054] h. at least one diagnostic model for diagnosing peripheral arteriosclerosis based on the low-frequency oscillation signal.

[0055] Furthermore, the microcontroller is a STM32F4 single chip microcomputer.

[0056] Furthermore, the light source module includes a dual-wavelength LED emission module.

[0057] Furthermore, the signal amplification circuit includes at least one gain amplifier.

[0058] Furthermore, the data processing module includes a modified Beer-Lambert law algorithm.

[0059] Furthermore, the feature extraction module includes a bandpass filter.

[0060] Furthermore, the diagnostic model is based on a random forest algorithm.

[0061] Furthermore, a method for detecting abnormal blood circulation in peripheral arteriosclerosis based on near infrared spectroscopy (NIRS) comprises the following steps:

[0062] a. Collection step: using the detection channel to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body;

[0063] b. Emission step: emitting near-infrared light of at least two wavelengths through the light source module;

[0064] c. Detection step: detecting the reflected light intensity of the near-infrared light in human tissue by the photodetector;

[0065] d. Amplification step: amplifying the signal detected by the photodetector through the signal amplification circuit;

[0066] e. Processing step: processing the amplified signal according to the Beer-Lambert law through the data processing module and extracting blood oxygen saturation data;

[0067] f. Extraction step: extracting the low-frequency oscillation signal in the blood oxygen saturation data through the feature extraction module;

[0068] g. Diagnostic step: diagnose peripheral arteriosclerosis according to the low-frequency oscillation signal using the diagnostic model.

[0069] In summary, the peripheral arteriosclerosis blood circulation abnormality detection system and detection method based on near infrared spectroscopy (NIRS) include the following steps when used:

[0070] 1. System hardware main structure: A multi-channel, portable peripheral arteriosclerosis detection system based on NIRS was constructed, covering the positions of both ears, both fingers, and both toes of the human body.

[0071] 2. Optical signal transmission module design:

[0072] Performance index screening: Analyze the performance of the light source, select the appropriate light source wavelength, and optimize signal penetration and detection accuracy.

[0073] Wavelength selection: Based on the propagation characteristics of light in biological tissues, LEDs with wavelengths of 660nm and 920nm are determined as light sources. These two wavelengths can provide better tissue penetration and minimal tissue scattering.

[0074] Driving scheme design: In order to ensure the working efficiency of the light source and minimize the space occupied by the circuit board, a compact and efficient light source driving scheme was developed.

[0075] 3. Photoelectric signal detection module design:

[0076] Photoelectric conversion: According to the NIRS principle and system light source specifications, select an appropriate photoelectric detector to achieve efficient photoelectric signal conversion.

[0077] Signal amplification: Build a high-precision gain amplifier circuit to amplify the converted weak electrical signal to ensure that the signal quality meets the system analog input voltage specifications.

[0078] Data synchronization and transmission: The signal synchronization circuit is developed using the STM32F4 microcontroller to achieve synchronous acquisition of six-channel MOD-pulse data and effectively transmit the data to the host computer for subsequent processing.

[0079] 4. System software design:

[0080] System startup: Perform system hardware self-check and initialization, load sensor configuration, set the initial state of hardware IO channels, and start program running time counting.

[0081] Timing control: Use the MSP430 board I / O port to send control signals to the hardware circuit to achieve precise timing control.

[0082] Signal acquisition and processing: Photoelectric signal acquisition is performed through MOD-pulse, and the signal is amplified and DC components are filtered out through a second-order amplifier circuit and a DC tracker, and then filtered to prepare for data sampling.

[0083] Downsampling and conversion: Downsample the filtered signal, adjust the sampling frequency to match the changes in hemodynamic parameters, apply the modified Beer-Lambert law to convert the light intensity signal into oxygenated hemoglobin (HbO) signal, and display it in real time on the LabVIEW interface.

[0084] 5. Signal transmission protocol design:

[0085] Communication connection analysis: For the six near-infrared channels included in the NIRS system, the communication mechanism between the STM32F4 microcontroller and each MSP430 board is studied to establish an efficient multi-channel signal transmission protocol.

[0086] Signal acquisition protocol design: Develop standardized protocols for driving and signal acquisition to ensure that the equipment can stably collect light intensity signals and perform real-time processing through the PC-side LabVIEW program.

[0087] Data conversion and display: Realize the conversion of light intensity signals into HbO and oxygen-free hemoglobin (Hb) signals, and display the changes of HbO, Hb and LFO data in real time on the user interface.

[0088] 6. Signal processing module design:

[0089] Data processing: Lambert-Beer law is used to convert the light intensity signal to obtain the hemoglobin concentration change signal.

[0090] Result display: The hemoglobin concentration signal is displayed in real time on the interactive interface, providing intuitive physiological data feedback.

[0091] Physiological status analysis: By extracting the LFO signal from the blood oxygen parameters, the changes in blood circulation in patients with peripheral arteriosclerosis can be reflected.

[0092] 7. Feature value extraction and diagnostic model establishment:

[0093] Feature value extraction: Combined with the GSO method, the evaluation limit standard is established and optimized, and the LFO baseline standard for evaluating peripheral blood circulation and blood integrity is constructed.

[0094] Diagnostic model establishment: Establish a peripheral arteriosclerosis diagnostic system based on random forests, analyze the collected data through machine learning algorithms, and realize automated diagnosis.

[0095] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS), characterized in that: include: a. At least seven detection channels, used to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body respectively; b. At least one microcontroller for controlling the signal acquisition and processing of the detection channel; c. at least one light source module for emitting near-infrared light of at least two wavelengths; d. at least one photodetector for detecting the reflected light intensity of the near-infrared light in human tissue; e. at least one signal amplification circuit for amplifying the signal detected by the photodetector; f. at least one data processing module for processing the amplified signal according to the Beer-Lambert law and extracting blood oxygen saturation data; g. at least one feature extraction module for extracting a low-frequency oscillation signal from the blood oxygen saturation data; h. at least one diagnostic model for diagnosing peripheral arteriosclerosis based on the low-frequency oscillation signal.

2. A peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1, characterized in that: The microcontroller is a STM32F4 single chip microcomputer.

3. A peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1 or 2, characterized in that: The light source module includes a dual-wavelength LED emission module.

4. The peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1, characterized in that: The signal amplification circuit includes at least one gain amplifier.

5. The peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1, characterized in that: The data processing module includes a modified Beer-Lambert law algorithm.

6. The peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1, characterized in that: The feature extraction module includes a bandpass filter.

7. The peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to claim 1, characterized in that: The diagnostic model is based on a random forest algorithm.

8. A method for using the peripheral arteriosclerosis blood circulation abnormality detection system based on near infrared spectroscopy (NIRS) according to any one of claims 1 to 7, characterized in that: The following steps are involved: a. Collection step: using the detection channel to collect blood oxygen saturation signals of the left and right earlobes, left and right toes, and left and right fingers of the human body; b. Emission step: emitting near-infrared light of at least two wavelengths through the light source module; c. Detection step: detecting the reflected light intensity of the near-infrared light in human tissue by the photodetector; d. Amplification step: amplifying the signal detected by the photodetector through the signal amplification circuit; e. Processing step: processing the amplified signal according to the Beer-Lambert law through the data processing module and extracting blood oxygen saturation data; f. Extraction step: extracting the low-frequency oscillation signal in the blood oxygen saturation data through the feature extraction module; g. Diagnostic step: diagnose peripheral arteriosclerosis according to the low-frequency oscillation signal using the diagnostic model.

Images