98 results about "Lung sound" patented technology

The invention discloses a lung sound classification method and system based on a lightweight model, and the method comprises the steps: obtaining to-be-processed lung sound audio data, converting the to-be-processed lung sound audio data into a lung sound frequency spectrum image, inputting the lung sound frequency spectrum image into a pre-trained lung sound classification model for classification and recognition, and obtaining a classification result of the to-be-processed lung sound audio data. The lung sound classification model comprises a feature extraction layer, an attention feature enhancement layer and a classification layer; wherein the feature extraction layer is used for performing feature extraction on an input lung audio spectrum image to obtain a lung audio spectrum feature map; the attention feature enhancement layer is used for performing attention feature enhancement processing and time-frequency feature extraction processing on the extracted lung audio spectrum feature map to obtain time-frequency feature data; and the classification layer is used for carrying out classification prediction identification on the time-frequency characteristic data to obtain a classification result of the to-be-processed lung sound audio data. According to the scheme, the accuracy of lung sound classification is improved while computing resource consumption is remarkably reduced.

The invention discloses an intelligent atomization control method and system for respiratory tract treatment and a storage medium, and relates to the technical field of atomization control. During operation of the system, a multi-mode patient respiratory behavior monitoring module is used for capturing real-time respiratory frequency, depth, rhythm, cough characteristics and atomization efficacy based on a non-contact sonic sensor and lung sound analysis; the method comprises the following steps: monitoring environment humidity, temperature and aerosol diffusion rate in real time, analyzing the influence of the environment humidity, temperature and aerosol diffusion rate on drug mist particle size and sedimentation behavior, controlling atomization particle size through a variable-frequency ultrasonic exciter, calculating to obtain an intelligent atomization curative effect adaptation index AEAI, dynamically adjusting particle size distribution according to the real-time inhalation demand of a patient and environment parameters, and combining with respiration monitoring data to obtain the intelligent atomization curative effect adaptation index AEAI. According to the method, the medicine mist release opportunity is adjusted in real time, threshold value comparison is carried out by monitoring respiratory resistance changes and real-time feedback of lung sound characteristic improvement degree, a medicine release strategy is obtained, and remote doctor viewing and parameter adjusting functions are provided.

The invention relates to the technical field of medical equipment, in particular to a cardiopulmonary sound and electrocardiogram rapid screening system suitable for emergency treatment scenes. The system comprises a heart and lung sound acquisition unit, an electrocardiogram acquisition unit and an intelligent analysis unit. And the intelligent analysis unit realizes signal synchronization by establishing a cross-modal time sequence alignment model, adaptively matches the physiological state by adopting a dynamic time window adjustment mechanism, and introduces multiple rounds of verification processes to ensure the result reliability. The system can automatically complete synchronous collection, feature extraction and fusion analysis of the heart and lung sound and the electrocardiosignals, the diagnosis accuracy is remarkably improved while the screening speed is guaranteed, and reliable technical support is provided for rapid screening of heart and lung diseases in the emergency department.

The invention relates to a heart and lung sound noise reduction method and system based on a sound stethoscope. A traditional heart and lung sound data noise reduction algorithm is poor in performance in a complex environment, so that a doctor cannot give an accurate diagnosis result. The heart and lung sound is acquired through the acquisition module, the heart and lung sound is converted into a digital form through the analog-to-digital converter and stored, then the stored heart and lung sound data is subjected to traditional time-frequency noise reduction processing and deep learning algorithm noise reduction processing, and the deep learning algorithm noise reduction processing comprises construction of a clean heart and lung sound data set and a noise data set. The heart and lung sound data with noise is obtained by randomly synthesizing clean heart and lung sound data and a noise data set, and the obtained data set is subjected to noise reduction and noise removal processing. According to the method, noise reduction and noise removal are further carried out on the sound signals by adopting the traditional and deep learning model algorithms, the signal-to-noise ratio is obviously improved compared with noise data and a traditional method, and cardiopulmonary sound extraction can be carried out in a more complex external environment.

The invention relates to the technical field of respiratory lung sound recognition, in particular to a respiratory lung sound auxiliary recognition method and system for clinical nursing. The invention provides a respiratory lung sound auxiliary identification method and system for clinical nursing, solves the technical problems of data scarcity, complex noise interference and insufficient cross-device generalization ability in lung sound signals through generative data enhancement and cross-modal migration, and combines self-supervised comparative learning and causal feature discovery to identify the respiratory lung sound. Multi-source signal feature fusion and noise robustness improvement are realized, a real-time noise environment is dynamically adapted, the limitation that a traditional method depends on annotation data and feature extraction is easily influenced by hybrid noise is broken through, a full-link closed-loop system from synthetic data generation, cross-modal alignment to causal-driven decision is constructed, and multi-source signal feature fusion and noise robustness improvement are realized. And the accuracy and clinical applicability of clinical lung sound analysis are effectively improved.

The invention relates to the technical field of lung sound signal analysis, in particular to a respiratory lung sound auxiliary identification method and system for clinical nursing. The method comprises the following steps: firstly, acquiring a segmented lung sound signal, a segmented signal component and a segmented respiration signal of each day; further obtaining an initial qualified component according to the correlation characteristics of each segmented signal component and the segmented breathing signal corresponding to the time sequence in combination with the fluctuation rule characteristics of the segmented signal components; further, according to fluctuation difference characteristics of each qualified signal component segment and a time sequence corresponding segment lung sound signal, combining a lung sound law coefficient to obtain a noise influence coefficient of each qualified signal component segment, and screening out a low-noise time period; further obtaining the credibility of each initial qualified component in the current day according to the distribution similar characteristics of low-noise time periods in the initial qualified components of the current day and all historical days in combination with the similar characteristics of noise influence coefficients; and finally, screening based on the credibility to obtain the optimal signal component of the current day.

A smart stethoscope includes: a main body including a plurality of sensors for measuring a user's bio-signals and a power supply unit; and a fixing part coupled to a front side of the main body and provided to be foldable to fix a user's finger, wherein the main body includes: an input unit operated by a user; and a control unit that, when one of measurement modes is selected by the user's operation, measures a bio-signal at a specific sensor from among the plurality of sensors on the basis of the selected measurement mode, and calculates a measurement value corresponding to the measured bio-signal according to a preset algorithm. Accordingly, auscultation can be optimized for a user by changing a measurement frequency by changing the mode according to the user while allowing for auscultation through multi-channels including electrocardiogram, pulse waves, and heart and lung sounds.

The invention provides an auscultation method and an auscultation system for digitally storing and analyzing heart and lung sounds. The auscultation method comprises the following steps: acquiring heart and lung sound signals of a patient by using a sound pickup of a digital stethoscope; the heart and lung sound signals are converted into digital signals through an analog-to-digital conversion chip; carrying out adaptive filtering processing on the digital signal; band-pass filtering is carried out through a signal filtering loop at the rear end of the microphone; identifying and removing environmental noise; performing fast Fourier transform analysis on the preprocessed digital signal; the analysis result is stored in a local storage device; and the heart and lung sound digital signal is transmitted to a remote server through the Wi-Fi module. According to the portable auscultation method and system, through accurate signal collecting and processing, real-time feedback and interaction, powerful data analysis capacity, safe data storage and transmission, portability and usability, the efficiency and accuracy of heart and lung sound diagnosis are remarkably improved, and important technical support is provided for modern medical diagnosis.

The invention relates to a single sensor for detecting cardiopulmonary multi-frequency vibration, belongs to the technical field of medical instruments, and relates to a cardiopulmonary signal detection technology. A single sensor which is formed by fixedly stacking a first transmission part, a piezoelectric film, a second transmission part and an absolute pressure sensor and is used for detecting multi-frequency vibration of the heart and the lung synchronously and stably collects mechanical vibration waves of the chest wall of the human body, and the piezoelectric film is triggered to generate piezoelectric signals capable of reflecting breathing, ultralow-frequency cardiac movement, cardiac vibration and heart and lung sound information of the human body. The absolute pressure sensor is triggered to generate an absolute pressure signal reflecting the fitting degree of the chest wall and the sensor, the application effect of synchronously extracting multi-band mechanical vibration information of the heart and the lung and the fitting degree of the human body on the single sensor is achieved through a signal processing method, and an efficient and portable mode is provided for knowing the activity and state of the heart and the lung.

The invention discloses a physiological sound separation and extraction method, and relates to the technical field of body sound signal processing and analysis. Comprising the steps of collecting human body physiological sound signals, constructing a multi-level signal separation model based on statistical characteristics, sequentially realizing sound signal elimination and extraction of various physiological sound signals, establishing a multi-dimensional characteristic parameter set, and performing intelligent identification and classification on the extracted physiological sound signals in combination with a deep learning classifier. And carrying out physiological and pathological state evaluation according to an identification and classification result. By comprehensively applying various signal processing and classification algorithms, automatic separation and accurate classification of heart sound, lung sound and borborygmus signals are realized, the physiological sound signal processing efficiency and precision are remarkably improved, and clinical doctors can be helped to quickly judge diseased regions and diseased property.

The application belongs to the field of digital medicine, and particularly relates to a chronic obstructive pulmonary disease (COPD) differential system based on digital lung sound, a construction method and application thereof. The system comprises a data acquisition module, a preprocessing module, a conversion module, a data module, a data processing module, a data enhancement training module, a deep learning module, a differential module, a grading module and a display module. Digital lung sound records of candidates are collected, converted into mel spectrograms, and diagnosed by using a deep neural network. The candidates are COPD patients, healthy people, or people suffering from other lung diseases, and the disease grade of the COPD patients is given by a device carrying the differential system. The examination only needs to collect lung sounds in clinical or other places, reduces radiation damage and possible infection risk in the conventional diagnosis process, and provides a scheme for early diagnosis of COPD, and improves the diagnosis efficiency of the respiratory department, especially the COPD disease.

1. Name of the Design Product: Heart Sound Detector (Wireless). 2. Use of the Design Product: For detecting heart sounds and lung sounds. 3. Design Key Points of the Design Product: Lies in the shape. 4. Picture or Photograph that Best Illustrates the Design Key Points: Usage State Diagram. 5. Other Situations Requiring Explanation - Component Description: Component 1 is the main unit of the wireless heart sound detector; Component 2 is the base.

A lung sound analysis system includes a storage means for storing therein the history of auscultation observations on lung sound data of each of auscultation positions of a subject who is a heart failure patient, a calculation means for calculating appearance frequency of abnormal sounds for each of the auscultation positions on the basis of the history, a determination means for determining the sequence of the auscultation positions at which lung sounds are to be auscultated from the subject, on the basis of the calculated appearance frequency, and an acquisition means for giving guidance on the auscultation positions of the subject to an operator according to the determined sequence, and acquiring time-series acoustic signals including lung sounds from a guided auscultation position. The system supports medical decision-making for healthcare professionals monitoring heart failure patients.

A lung sound analysis system includes a storage means for storing therein the history of auscultation observations on lung sound data of each of auscultation positions of a subject who is a heart failure patient, a calculation means for calculating appearance frequency of abnormal sounds for each of the auscultation positions on the basis of the history, a determination means for determining the sequence of the auscultation positions at which lung sounds are to be auscultated from the subject, on the basis of the calculated appearance frequency, and an acquisition means for giving guidance on the auscultation positions of the subject to an operator according to the determined sequence, and acquiring time-series acoustic signals including lung sounds from a guided auscultation position. The system supports medical decision-making for healthcare professionals monitoring heart failure patients.

The utility model belongs to the technical field of medical instruments, and particularly relates to a breathing machine. The breathing machine comprises a breathing machine shell, a breathing module, a sputum excretion module, a main board and a lung sound detection module, a cavity is formed in the breathing machine shell, the breathing module, the sputum excretion module and the main board are arranged in the cavity, and the breathing module is used for assisting a patient in breathing; the lung sound detection module comprises a detection probe and a plug connector, an interface is formed in the respirator shell, the plug connector is plugged in the interface, the detection probe is electrically connected with the plug connector, the detection probe is used for collecting lung sound signals of a human body, and the mainboard can control the sputum excretion module to assist a patient in sputum excretion according to the lung sound signals. According to the sputum excretion device, the respiratory resistance and the sputum deposition condition of a patient can be judged by collecting lung sound signals through the detection probe, the sputum excretion module is started according to the sputum deposition condition to assist the patient in sputum excretion, sputum excretion can be achieved without pulling out a respiratory pipeline of the patient, and secondary infection of the patient is avoided.

The invention discloses a lung sound recognition method based on period synchronization self-supervised cardiopulmonary decoupling. The method comprises the following steps: acquiring a single-channel auscultation audio training sample set and to-be-recognized audio, and preprocessing the single-channel auscultation audio training sample set and the to-be-recognized audio; performing time-frequency analysis on the preprocessed signal to obtain a time-frequency characteristic; calculating cardiac cycle information representation according to the time-frequency characteristics; constructing a cardiopulmonary decoupling recognition model containing coding, decoupling, decoding reconstruction and classification networks, and optimizing model parameters by using a training target containing reconstruction consistency, period synchronization, and characterization decoupling and classification constraint; and during identification, inputting the time-frequency characteristics extracted from the audio to be identified and the cardiac cycle information representation into the trained model, and outputting a lung sound identification result. The method has the advantages that heart sound interference can be restrained under the single-channel condition, recognition accuracy and robustness are improved, training is completed without heart sound labeling, and labeling cost is reduced.

1. The name of this design product: digital stethoscope. 2. Purpose of this product design: This product design is used for auscultating human heart and lung sounds. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention discloses a livestock respiratory rate estimation method, and relates to the technical field of animal health monitoring. The method comprises the following steps: collecting a livestock lung sound stream, segmenting into segments according to a fixed window length, and carrying out initial noise reduction; framing endpoints of the segments are detected, starting points and ending points of inspiration segments are marked, and after a sequence is obtained, a small subset and a large subset are divided according to the number of the inspiration segments; screening the effective inspiration section by using the expiration average duration time in the less set, and screening the effective inspiration section by using the difference value between the time interval of two adjacent inspiration sections and the expiration average duration time and the standard difference value in the more set; after the effective inspiration sections are screened out, the breathing frequency is calculated according to the ratio of the time interval between the head and tail inspiration sections of the target section to the number of effective breathing cycles. The accuracy of livestock respiratory rate detection can be effectively improved.

The present invention discloses a miniature intelligent lung sound collector and its disease diagnosis auxiliary method and system, which relate to the medical field and solve the problem of poor diagnostic effect of existing lung sound collectors and their disease diagnosis auxiliary methods. The system comprises: step S1: respectively obtaining the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient to obtain the patient's lung sound monitoring data; step S2: obtaining and analyzing the period characteristic time difference and the symptom monitoring coefficient corresponding to each symptom monitoring sub-period to obtain the patient's symptom analysis coefficient; step S3: obtaining the patient's condition assessment coefficient by analyzing the lung sound comprehensive frequency deviation, the lung sound period monitoring coefficient and the patient's symptom analysis coefficient, obtaining the patient's condition assessment coefficient threshold and performing numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result. The present invention can improve the accuracy and comprehensiveness of disease auxiliary diagnosis.

A lung sound analysis system includes an acquisition means for acquiring time-series acoustic signals including lung sounds of a subject who is a heart failure patient, a determination means for determining a pause phase of breathing of the subject, a dividing means for dividing the time-series acoustic signals into those in a period of the pause phase of breathing of the subject and those in a period other than the pause phase, according to a result of the determination, and a detection means for detecting abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the division. The system supports medical decision making for healthcare professionals monitoring heart failure patients.

The application discloses a lung sound intelligent quality evaluation method and system fusing structural vibration characteristics, three-axis acceleration original data and lung sound audio data are synchronously collected through a bone conduction vibration sensor and a microphone; the mean square deviation and the impact peak value of the combined acceleration are calculated according to the three-axis acceleration original data, and a fuse type signal quality evaluation is carried out; the lung sound audio data is converted into a logarithmic mel spectrum according to the quality evaluation result, and the acoustic characteristics are extracted through a residual network; meanwhile, the three-axis acceleration original data is converted into a vibration spectrum diagram, the mechanical characteristics are extracted through a lightweight convolutional neural network, and the attention mask is generated through Sigmoid activation; the attention mask is multiplied with the acoustic characteristics element by element, and the fusion characteristics are obtained; the fusion characteristics are input into a classifier, and a lung sound pathological classification result is output. The application can eliminate invalid signals in advance, avoid low-quality data from entering the subsequent network, and significantly improve the lung sound classification robustness in a complex environment.

A lung sound analysis system includes a storage means for storing therein the history of auscultation observations on lung sound data of each of auscultation positions of a subject who is a heart failure patient, a calculation means for calculating appearance frequency of abnormal sounds for each of the auscultation positions on the basis of the history, a determination means for determining the sequence of the auscultation positions at which lung sounds are to be auscultated from the subject, on the basis of the calculated appearance frequency, and an acquisition means for giving guidance on the auscultation positions of the subject to an operator according to the determined sequence, and acquiring time-series acoustic signals including lung sounds from a guided auscultation position. The system supports medical decision-making for healthcare professionals monitoring heart failure patients.

The present invention discloses a wristband electronic device, comprising a device body and a wristband, wherein a microphone is provided in the device body, two lugs spaced apart are provided on one side of the device body, a mounting position is formed between the two lugs, and the device body is further provided with a conducting channel, the inner end of the conducting channel is connected to the microphone, and the outer end of the conducting channel is connected to the mounting position; one end of the wristband is inserted into the mounting position, and the wristband is respectively snapped onto the two lugs on both sides in the width direction; a sound collecting structure is provided on the side of the wristband facing away from the wrist, the sound collecting structure is used to be attached to the chest cavity to collect heart sounds and / or lung sounds; the sound collecting structure is connected to the outer end of the conducting channel through its internal channel to transmit the heart sounds and / or lung sounds to the microphone. The technical solution of the present invention can maintain the continuity of the channel, and the wristband can be removed.

The invention provides a wearable wireless stethoscope early warning device for monitoring acute attack of an asthma patient, the wearable wireless stethoscope early warning device comprises a vest, a first binding belt and a second binding belt, the first binding belt and the second binding belt are arranged on two sides of the vest, two adjusting belts are arranged above the vest, and the two adjusting belts are connected with the vest; a miniature sound signal sensor, a miniature lung sound discriminator and a signal microprocessor are arranged in the vest, the miniature sound signal sensor is used for collecting breathing sound signals, and the miniature lung sound discriminator is used for recognizing dry rale, wet rale and normal breathing sound. The breathing sound of an asthma patient, especially a child patient, is monitored in real time, abnormal breathing sound characteristics are accurately recognized, timely early warning of acute attack is achieved, by means of wireless transmission and a remote diagnosis technology, a doctor can remotely obtain illness state information of the patient, timely diagnosis and treatment guidance is provided for the patient, and the patient experience is improved. The risk caused by acute attack of asthma is reduced, and the health management level of patients is improved.

The invention relates to the technical field of acoustic sensing, in particular to a lung disease recognition device. On one hand, the piezoelectric polyester elastomer film is excellent in flexibility, environmentally friendly, good in biocompatibility and capable of being naturally degraded; the prepared piezoelectric acoustic device is excellent in acoustic performance. On the other hand, the piezoelectric acoustic sensor is integrated in the mask in various modes, the accuracy of lung sound data collection is improved, and the problems that data are inaccurate due to the fact that external interference is too strong during collection, and the adaptability and durability of the piezoelectric acoustic sensor are solved. And on the other hand, the result is more accurate through a self data processing database arranged at the network end. Finally, an electronic auscultation mode combined with a computer is adopted, and by means of the advantages of digitization, visualization, portability, remote performance and the like of the electronic auscultation mode, the problems of shortage of medical resources and high cost existing in existing lung disease recognition and errors of traditional auscultation results are effectively solved.

A lung sound analysis system includes: an acquisition unit that obtains time-series acoustic signals including lung sounds from a heart failure patient; a determination unit that identifies the pause phase of the patient's breathing; a dividing unit that separates the time-series signals into those during the pause phase and those during other phases, based on the determination; a calculation unit that computes an index value representing the quality of the signals outside the pause phase, using the intensity of signals from both phases after separation; and a warning unit that issues alerts based on the calculated index value. The system supports medical decision making for healthcare professionals monitoring heart failure patients.

The invention relates to the technical field of pathological characteristic sound detection, and provides a Velcro rale detection method and system based on respiratory auscultation sound, and the method comprises the steps: firstly determining the collection position of lung sound, obtaining the lung sound data of a subject, carrying out the preprocessing, carrying out the initial feature extraction of a preprocessed respiratory sound data set, and obtaining a frequency spectrum representation; then, a pre-trained double-flow multi-view Velcro rale detection model is used for processing: the Velcro rale characteristic acoustic biomarker features represented by the frequency spectrum are enhanced, feature fusion is performed on the enhanced frequency spectrum representation, and multi-view fusion advanced feature representation is obtained; time domain feature representation is extracted from the preprocessed breath sound data set; and finally, integrating the multi-view fusion advanced feature representation and the time domain feature representation to form multi-dimensional time-frequency joint representation, and outputting a detection result. According to the method, the time-frequency distribution mode of the Velcro rale is fully considered, the Velcro rale is accurately and reliably detected, and a non-invasive, economical and efficient means is provided for early screening of IPF.

A lung sound analysis system includes an acquisition means for acquiring time-series acoustic signals including lung sounds of a subject who is a heart failure patient, a determination means for determining a pause phase of breathing of the subject, a dividing means for dividing the time-series acoustic signals into those in a period of the pause phase of breathing of the subject and those in a period other than the pause phase, according to a result of the determination, and a detection means for detecting abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the division. The system supports medical decision making for healthcare professionals monitoring heart failure patients.

The present application relates to a kind of single sensor-based heart-lung multi-band mechanical wave detection device, belong to medical instrument technical field, it is related to heart-lung signal detection technology.By using the first transmission component, piezoelectric film, second transmission component and absolute pressure sensor fixed layer stack composition single mechanical wave sensor, synchronous stable collection is caused by chest wall vibration piezoelectric film and absolute pressure sensor electric signal, by signal amplification circuit processing, transmission to multi-band signal extraction module, digital piezoelectric signal is decomposed to obtain respiratory wave, ultra-low frequency heart wave, heart shock signal and heart-lung sound signal, digital absolute pressure signal is filtered to obtain static pressure value, the degree of chest wall adhesion is embodied, it is realized that single sensor on synchronous extraction heart-lung multi-band mechanical vibration information, to understand heart-lung activity and state provides a kind of efficient, portable mode.

The purpose of this invention is to analyze the vibrations, including sound emitted by a subject, to detect respiratory diseases in the subject at an early stage and to recommend the subject to a medical institution. The information processing system (100) includes: a signal acquisition unit (201) that acquires a feature signal, including at least one of a heartbeat signal, a respiratory vibration signal, and a body movement signal, and a lung sound signal, extracted from a detection signal output by a sensor (11) that detects vibrations emitted by a subject; a first prediction unit (202) that outputs first prediction information based on the feature signal and the lung sound signal, the first prediction information including at least one of first information related to the possibility that the subject has a respiratory disease and second information related to the respiratory disease suffered by the subject; and an output unit (206) that outputs at least one of the first prediction information and a medical institution recommendation information generated based on the first prediction information.