53 results about "Fetal heart" patented technology

The invention discloses a fetal heart rate signal data enhancement method based on a conditional diffusion model, and the method comprises the steps: firstly obtaining and preprocessing a fetal heart rate signal, and obtaining a fetal heart rate signal containing noise; then, a noise prediction model based on conditional diffusion is constructed, the noise prediction model based on conditional diffusion comprises a conditional auxiliary information coding module and a noise prediction network module, and the fetal heart rate signal data containing noise are used for training the noise prediction model based on conditional diffusion; and finally, denoising the fetal heart rate signal by using the trained noise prediction model based on conditional diffusion. According to the method, the defects of a traditional generation model in the aspects of training stability, mode diversity and signal quality are effectively overcome, high-quality and high-fidelity data support is provided for fetus health condition evaluation, and a referable mode is provided for a data generation task of a time sequence signal.

The application discloses a kind of fetal heart three-dimensional ultrasound reconstruction methods based on radio frequency identification signal, the device used includes a medical two-dimensional color ultrasound machine, two RFID passive tags, an RFID signal reader connected with three receiving antennas, and PC for RFID signal data processing and three-dimensional color ultrasound reconstruction;RFID reader transmits radio frequency signal and receives RFID passive tag reflection signal, after correcting the phase deviation of receiving signal, the distance between phase determination antenna and RFID passive tag is used, the position and elevation of RFID passive tag are estimated, the moving track of ultrasonic probe is determined, finally the position and angle information extracted by two-dimensional ultrasonic probe are input into three-dimensional ultrasound reconstruction model together with the obtained two-dimensional ultrasonic image, and accurate fetal heart three-dimensional ultrasound is obtained.The application can realize lower cost and higher accuracy, and is especially suitable for fetal heart detection.

The application provides a 3D fetal heart standard section identification method and system, electronic equipment and a storage medium. The method comprises the following steps: generating a Gaussian noise image based on Gaussian distribution, inputting the Gaussian noise image and a 3D fetal heart image into an image conditional latent U-Net network model for feature fusion; inputting the fused features into a variational autoencoder (VAE) to generate a 2D standard section of the 3D fetal heart image; and inputting the 2D standard section into a regression model to obtain a 2D standard section of the 3D fetal heart image. The application generates a Gaussian noise image based on Gaussian distribution, performs noise processing on the photographed 3D fetal heart image, and generates a 2D standard section. The generated 2D standard section is generated based on the 3D fetal heart image and has a certain correlation with the 3D fetal heart image. The 2D standard section generated in this way is used as a reference section, and the finally obtained 2D fetal heart section is more standard.

The invention discloses a fetal heart ultrasound image segmentation method and system based on deep learning, and belongs to the technical field of medical images. Channel-level intelligent weighting is achieved by means of an independent SE module, and semantic conflicts are solved; a pixel-level spatial weight map is generated, spatial-level accurate fusion is realized, and the spatial dimension accuracy is improved. According to the method, morphological semantic features are modeled in a unified mode by means of a region-level feature aggregation framework, the dynamic change rule of heart tissue is learned through region-level shared feature extraction and a pixel-level residual refinement cooperation mechanism, and compared with a previous method, boundary segmentation is clearer, training is accelerated by several times, and clinical diagnosis efficiency and accuracy are improved. The two-dimensional intelligent fusion module and the multi-scale double attention residual feature enhancement module work cooperatively, the PFFM accurately positions edge feature points, the SAFF intelligently adapts and fuses semantic features, and the multi-scale double attention residual feature enhancement module analyzes and captures morphological semantic information hierarchically.

Disclosed is a blood oxygenator for a premature fetus comprising a housing defining a cavity therein, wherein the housing comprises a blood inlet, a blood outlet, a gas inlet, and a gas outlet; and a gas exchanger disposed within the cavity, wherein the gas exchanger comprises a plurality of hollow fibers arranged in a pattern allowing blood to flow past the hollow fibers when in contact with the hollow fibers, wherein the hollow fibers comprise a receiving end in communication with the gas inlet for receiving a sweep gas and an emitting end in communication with the gas outlet from which the sweep gas exits, wherein the oxygenator is designed to rely on the fetal heart as sole blood pump.

The invention discloses a maternal and child internet-of-things equipment data transmission safety protection and abnormity monitoring method and system, and belongs to the technical field of medical internet-of-things safety, and the method comprises the steps: S10, carrying out risk monitoring on related data, including fetal heart monitoring data, dividing the fetal heart monitoring data into fetal movement data, uterine contraction pressure data and fetal heart rate variation data; and S20, risk monitoring is carried out, related information corresponding to the fetal movement data, the uterine contraction pressure data and the fetal heart rate variation data is obtained, the related information comprises text features and byte capacity, and the fetal movement data, the uterine contraction pressure data and the fetal heart rate variation data tampered by an attacker are collected from the text features and the byte capacity. According to the method, data tampering attacks can be effectively identified and defended, meanwhile, the integrity of high-level importance data is guaranteed, the safety of data transmission and the accuracy of anomaly monitoring are improved, and effective safety protection is provided for data protection in the field of medical Internet of Things.

The invention relates to the technical field of medical diagnosis, in particular to a multi-mode Doppler fetal monitor which comprises a TYPE-C connecting line, a uterine contraction probe and a plurality of Doppler fetal heart replaceable probes, and the Doppler fetal heart replaceable probes have different ultrasonic working frequencies. A plurality of Doppler fetal heart replaceable probes with different ultrasonic working frequencies are provided, so that the problem that a single fixed-frequency probe is difficult to adapt to all clinical scenes due to individual differences of pregnant women is fundamentally solved. Specifically, a user or a medical worker can flexibly select and replace the Doppler fetal heart replaceable probe most suitable for the current penetration depth requirement according to the real-time monitoring condition or the judgment of individual differences, so that the optimal penetration depth and signal quality can be obtained under different clinical conditions; and the defects of monitoring blind areas and unstable signals caused by fixed frequency are effectively overcome.

The application discloses a fetal distress diagnosis system based on multi-modal feature fusion of fetal heart rate signals, comprising a signal preprocessing module, a data enhancement module, an expert feature extraction module, a signal feature extraction module, a multi-modal fusion module and an output module. The application fuses expert features and signal features, effectively reduces the misdiagnosis rate of fetal distress, and provides an important basis for fetal monitoring, disease diagnosis and clinical decision-making. A SE-TCN backbone model is designed based on dilated convolution and causal convolution, SEBlock is added in the residual connection channel of TCN, the receptive field of the whole network is effectively increased, and the gradient disappearance phenomenon in the long time sequence classification task is relieved. The application proposes a cross-modal feature fusion mechanism CMFF, which utilizes a multi-head self-attention mechanism and a cross-modal attention score to measure the similarity between different modalities and realizes cross-modal feature fusion according to an adaptive weight factor.

The present application relates to the technical field of medical instruments, and discloses a display method of monitoring waveforms, a fetal monitor and a storage medium, the display method comprising: drawing a preset background grid on a display screen according to a configured paper type specification, the configured paper type specification being a paper type specification of thermal paper; obtaining fetal heart rate data from collected fetal heart data; and drawing a current fetal heart rate waveform on the display screen according to the fetal heart rate data, the current fetal heart rate waveform being drawn on the preset background grid; wherein the display result of the current fetal heart rate waveform is the same as a fetal heart rate waveform printed on the thermal paper according to the fetal heart rate data. The present application can achieve the effect of reproducing the fetal heart rate waveform on the thermal paper on the display screen, thereby improving user satisfaction.

The application discloses a fetal heart rate signal data enhancement method based on a conditional diffusion model. First, a fetal heart rate signal is acquired and preprocessed to obtain a fetal heart rate signal containing noise. Then, a noise prediction model based on conditional diffusion is constructed, the noise prediction model based on conditional diffusion comprises a conditional auxiliary information coding module and a noise prediction network module, and the noise prediction model based on conditional diffusion is trained by using fetal heart rate signal data containing noise. Finally, the trained noise prediction model based on conditional diffusion is used to realize denoising of the fetal heart rate signal. The application effectively overcomes the deficiencies of a traditional generation model in training stability, pattern diversity and signal quality, provides high-quality and high-fidelity data support for fetal health condition evaluation, and provides a referenceable pattern for a data generation task of a time series signal.

The utility model relates to the technical field of fetal heart measuring equipment, and discloses a split type ultrasonic fetus-voice meter which comprises a host unit and a display screen unit which are arranged in a split mode, and the host unit is connected with the display screen unit in a wireless communication mode. And the host unit and the display screen unit are fixedly positioned and connected with each other in a magnetic attraction manner. A display screen unit carrying a display screen and a host unit carrying other parts are arranged in a split mode, the display screen unit and the host unit are combined together through magnetic force, and fetal heart signals of the host unit are transmitted to the display screen unit to be displayed in a wireless transmission mode. A user can hold the display screen unit or place the display screen unit at any position to check real-time data, fatigue caused by long-time head-lowering data checking of a pregnant woman user and inconvenience in operation in the middle and late pregnancy are avoided, user experience and monitoring efficiency are improved, and the problems that an ultrasonic fetus-voice meter in the prior art is prone to causing cervical vertebra fatigue, cable constraint and monitoring interruption are solved.

This invention provides a maternal-fetal dual-body critical value early warning bracelet based on multi-physiological parameter fusion, belonging to the field of wearable monitoring device technology. It includes a bracelet body, an elastic floating sealed maternal physiological data acquisition component, an integrated split abdominal binder acquisition assembly, a main control circuit board, a data processing module, a multi-parameter fusion critical value early warning module, a wireless communication module, and a power supply module. The bracelet and the split abdominal binder collaboratively collect multi-dimensional physiological parameters such as maternal electrocardiogram, blood oxygen, body temperature, uterine contraction pressure, and fetal heart rate. A multi-parameter fusion algorithm is used for comprehensive judgment of critical values, solving the problems of single-device monitoring and delayed early warning in traditional devices, and significantly improving the accuracy of maternal and infant risk identification.

The utility model provides a wearable pregnant woman health monitoring bracelet, belongs to the technical field of pregnant woman health monitoring, and aims to solve the problems that when an existing wearable pregnant woman health monitoring bracelet is used for fetal heart detection of a pregnant woman, the monitoring bracelet needs to be removed or a display needs to be independently detached to be tightly attached to the abdomen, and the display is small and is easily lost after being detached, so that the monitoring is inconvenient. And the dismounting process is tedious. Comprising a bracelet belt, the mounting shell is fixedly connected to the interior of the bracelet belt; the fixed block is fixedly mounted at the upper part of the mounting shell; one end of the connecting line is fixedly connected to the interior of the fixed block; the take-up device is arranged in the connecting wire; the monitor main body is fixedly mounted at one end of the connecting line; the mounting assembly is arranged in the fixing block; and the winding assembly is arranged in the take-up device. The utility model has the advantages of quick disassembly and assembly, loss prevention, convenience in use and the like.

The present application relates to the technical field of teaching training, in particular to a four-step palpation and fetal heart auscultation training method and system with adjustable fetal position; the method of the present application involves basic training and advanced training; the basic training adjusts the fetal position in a fixed order, and the single step is qualified to be locked or unqualified to be reset; the operation process is standardized, the accumulated deviation of the position and posture is eliminated; the four-step palpation is step-by-step practical operation and instant error correction, which conforms to the clinical standard; the data of the fetal position adjustment, palpation and auscultation are quantified and weighted, the operation ability is scientifically evaluated, and the pain points of the lack of standardization and the unscientific evaluation in the traditional training are solved; the advanced training constructs a dynamic fetal position model based on the clinical labor data, simulates the progressive change of the fetal position in the labor, fills in the blank of the dynamic scene, adjusts the position and posture without pre-warning, disposes the error in stages, strengthens the dynamic judgment and emergency ability of the trainee, trains in different difficulty gradients, generates a node evaluation report, and realizes the ability advancement from the basic standardization to the clinical practice.

The invention discloses a fetal distress auxiliary diagnosis system based on continuous wavelet transform and a shallow convolutional neural network, and the system comprises a data obtaining and preprocessing module which is responsible for obtaining an original fetal heart rate signal and carrying out the data preprocessing of the original fetal heart rate signal; the time-frequency characteristic graph construction module is responsible for converting the signals processed by the data acquisition and preprocessing module from one-dimensional data into a two-dimensional time-frequency characteristic graph by using continuous wavelet transform; and the classification and recognition module is responsible for inputting the time-frequency characteristic pattern into a shallow convolutional neural network model and outputting a fetal distress state classification result. According to the method, a one-dimensional time sequence signal is converted into a two-dimensional time-frequency image, and joint distribution information of the signal in a time domain and a frequency domain is subjected to visual coding, so that a shallow convolutional neural network model can fully utilize the advantages of the shallow convolutional neural network model in image processing, deep pathological features hidden in an FHR signal are mined, and the deep pathological features hidden in the FHR signal are extracted. And the defect that the one-dimensional convolution is insensitive to the time sequence is overcome.

This invention provides a method, apparatus, device, and storage medium for predicting the anomaly degree of a fetal heart rate curve. The method includes: acquiring a target fetal heart rate curve and identifying missing data in the target fetal heart rate curve to obtain a corresponding initial mask; dividing the target fetal heart rate curve into several target fetal heart rate curve segments and determining a target mask for each target fetal heart rate curve segment based on the initial mask; analyzing each target fetal heart rate curve segment and its corresponding target mask using a target deep learning model to obtain a target baseline fetal heart rate; obtaining the target variance value and target acceleration number for each target fetal heart rate curve segment based on the target baseline fetal heart rate, and obtaining the target anomaly degree of the target fetal heart rate curve based on the target variance value and target acceleration number. This application aims to determine the anomaly degree of the fetal heart rate curve through a segmented prediction method, which not only improves prediction efficiency but also enhances the interpretability of the prediction process.

This invention discloses an anti-displacement fetal heart rate monitoring belt and its usage method, belonging to the field of medical auxiliary device technology. It includes an anti-slip base belt, a guide belt on the top surface of the anti-slip base belt, a first displacement component on the guide belt, a first elastic band between two first displacement components, a second displacement component on the first elastic band, a fixing mechanism on the second displacement component, and binding mechanisms at both ends of the anti-slip base belt. This invention, using the aforementioned anti-displacement fetal heart rate monitoring belt and its usage method, forms a frame-like fixing structure with upper and lower limits by fixing two anti-slip base belts to the upper and lower abdomen of the pregnant woman, improving the overall anti-slip performance of the belt and effectively limiting its vertical sliding and lateral displacement.

A method for deriving a biometric parameter of a fetal heart is provided. The method includes acquiring a plurality of ultrasound images of a region of interest, wherein the region of interest includes a fetal heart, and comparing the plurality of ultrasound images to a predefined clinical view. A set of ultrasound images related to the predefined clinical view is selected based on the comparison, wherein the set of ultrasound images represents at least one cardiac cycle. Anatomical landmarks of the fetal heart are detected within ultrasound images of the set of ultrasound images and the anatomical landmarks of the fetal heart are detected or tracked across the set of ultrasound images. A biometric parameter of the fetal heart is then determined based on the anatomical landmarks detected or tracked from one or more ultrasound images of the set of ultrasound images.

The invention relates to an ultrasound fetal heart rate monitoring system (100). An ultrasound probe placed on a maternal abdomen provides sensor data. The ultrasound probe is first operated in an imaging mode to obtain an ultrasound image from the ultrasound probe. A trained object detection model is applied to the ultrasound image to determine whether a fetal heart is located in a target region of the ultrasound image addressable by a Doppler mode of the ultrasound probe. If the fetal heart rate is located in the target region, the ultrasound probe is switched to the Doppler mode; a Doppler ultrasound signal is obtained from the ultrasound probe; and the fetal heart rate is computed from the Doppler ultrasound signal.

This invention proposes a method and system for real-time monitoring and assessment of cervical dilation based on the LP labor monitoring system. It belongs to the interdisciplinary technical fields of intelligent obstetric monitoring, biomedical signal processing, and clinical decision support. The method includes: deploying an FBG-BIS flexible patch at the cervix of the parturient woman to directly collect cervical deformation micro-strain signals, generating raw cervical dilation data; simultaneously collecting uterine contraction pressure signals and fetal heart rate signals, generating raw uterine contraction data and raw fetal heart rate data; performing ternary time-series alignment processing on the raw cervical dilation data, raw uterine contraction data, and raw fetal heart rate data using a dynamic time warping algorithm, generating aligned cervical dilation data, uterine contraction data, and fetal heart rate data; and directly measuring cervical dilation using the FBG-BIS flexible patch, improving the accuracy and comprehensiveness of cervical dilation data acquisition and more realistically reflecting the labor process.

The invention relates to the technical field of wearable fetal heart detection, in particular to a fetal heart rate estimation and event detection method and system based on multi-modal quality factor driving, and the method comprises the steps: collecting multi-modal data in multiple channels, and carrying out the alignment; selecting a maternal R peak sequence from the electrocardio data as a time anchor point to construct a maternal heart sound template and a maternal electrocardio template, and calculating a heart sound residual error and an electrocardio residual error; blind source separation is carried out to obtain a plurality of different types of sources, and the sources are preferentially sorted; performing time-frequency transformation on the target source, decomposing a plurality of substrates, applying rhythm constraint to construct a plurality of candidate FHR paths, and cutting; detecting a fetal heart R-peak sequence, comparing the fetal heart R-peak sequence with a maternal R-peak sequence, and estimating a heart rate curve to realize maternal-fetal separation; and constructing a quality factor, classifying the fragment set corresponding to each time window based on the quality factor, and outputting a fetal heart rate result. The fetal heart rate monitoring analysis effect can be improved.

This invention discloses a method for monitoring maternal and infant health status by integrating multi-sensor data, belonging to the field of medical monitoring technology. The method deploys multiple wireless sensor nodes to simultaneously collect abdominal vibration and sound signals. Candidate events are identified through short-time energy detection and grouped into multi-node time windows. For each group of candidate events, hyperbolic positioning is first performed based on the vibration arrival time difference to determine if the signal source is located within the uterine region. Secondly, the arrival time difference of vibration and sound at the same node is used to verify whether it conforms to the laws of sound propagation. Finally, geometric constraint checks are performed based on the consistency of multi-node distance sorting and time delay sorting, as well as the ratio of time delay difference to distance difference. Events that pass the three-layer verification are marked as valid fetal heartbeats and used to calculate fetal heart rate and fetal movement intensity. This invention identifies the authenticity of signals from the source through the spatiotemporal relationship of multiple sensors, helping to improve the accuracy of maternal and infant health status monitoring.

The embodiment of the invention provides a prenatal fetal monitoring method and device, electronic equipment, a storage medium and a program product. The method comprises the steps that a first monitoring interface is displayed, first monitoring information of multiple pregnant women is displayed on the first monitoring interface, and if it is detected that a fetus of at least one pregnant woman in the multiple pregnant women is abnormal, first fetus abnormal information corresponding to the at least one pregnant woman is displayed on the first monitoring interface; in response to a display instruction for the personal monitoring interface of the target pregnant woman, the first monitoring interface is switched to a second monitoring interface, the second monitoring interface displays the fetal heart uterine contraction curve of the target pregnant woman and the corresponding second fetal abnormal information, and the abnormal information of the target pregnant woman is displayed according to an abnormal list display instruction executed in the second monitoring interface. And displaying the exception list in the second time period. The method is used for achieving the effect of automatically prompting abnormal conditions of the pregnant woman and the fetus on the pregnant woman monitoring interface.

The present application relates to the field of medical image processing, particularly to a four-dimensional echocardiogram dynamic segmentation system for congenital heart disease, which acquires four-dimensional echocardiogram data of a fetal heart through an image acquisition module, corrects fetal movement artifacts by using optical flow field time series analysis technology in an optical flow field correction module, improves image quality, aligns heart structures and extracts interventricular septal defect regions through a multi-scale similarity transformation strategy in a heart structure time series alignment module, calculates the edge line diameter and shunt direction of the defect site in a defect analysis module, generates defect parameter information, and generates a congenital heart disease screening report in a result output module, which effectively eliminates image artifacts caused by fetal movement, lays a foundation for subsequent analysis, and accurately analyzes by accurately aligning heart structures to keep the defect site in a stable position in the time sequence.

The utility model relates to the technical field of medical instruments, and discloses a buckle assembly type host unit and a buckle assembly type ultrasonic fetus-voice meter. The buckle assembly type host unit comprises a buckle assembly type host shell assembly and further comprises a host power source, a host PCBA and a probe. The host power supply, the host PCBA and the probe are fixedly positioned in the host shell assembly in a buckling assembly mode, and the host power supply is electrically connected with the host PCBA and the probe respectively. A buckle assembly type design is adopted, screw fixation is omitted, the assembly process is simplified, the production efficiency and the maintenance convenience are improved, meanwhile, the structural compactness and the mechanical property are optimized, the reliability of electrical connection is ensured, and the ultrasonic fetus-voice meter is particularly suitable for portable ultrasonic fetus-voice meters with requirements for miniaturization, light weight and automatic production.

A patient monitoring system includes a set of electrodes configured to obtain a uterine activity (UA) signal and a total abdominal electrical signal from an abdomen of a maternal patient, wherein the total abdominal electrical signal includes at least the UA signal, a maternal heart signal, and a fetal heart signal. At least a subset of the set of electrodes is configured as a low pass filter to obtain the UA signal. A patient monitor is configured to subtract the UA signal from the total abdominal signal to generate a total heart signal containing at least the maternal heart signal and the fetal heart signal, determine a maternal heart rate based on the total heart signal, and output the UA signal and the maternal heart rate.

The invention provides a fetal growth limitation intelligent prediction system and method based on double networks, and relates to the technical field of perinatal medical monitoring, and the system comprises a data collection and preprocessing module which is used for processing collected prenatal fetal heart related data and outputting high-quality data; the fetal heart signal feature extraction module is used for outputting fetal heart feature vectors by adopting a parallel architecture of a convolutional neural network and a long-short-term memory network; the multi-modal feature fusion module is used for outputting a fusion feature vector based on the double-tower structure architecture; the hierarchical classification prediction module is used for modeling a hierarchical structure of FGR clinical diagnosis by adopting a graph neural network GNN, and outputting prediction probabilities of FGR diagnosis, subtype classification and perinatal outcome in combination with an MC loss function optimization model; and the clinical decision support module is used for generating decision result suggestions and visual reports. And the clinical requirements of early accurate identification, subtype classification and perinatal outcome prediction are met.

The application discloses a fetal heart rate pathological signal generation method and system based on a progressive growth architecture. The application acquires a real fetal heart rate signal, and pre-processes the same to form a data set; a progressive generative adversarial network model is constructed, and the data set is trained by using a progressive growth strategy; and a random noise vector is input into the trained generator to synthesize a predicted fetal heart rate signal sample. The application divides a complex long-time sequence generation task into multiple simple subtasks by using a progressive growth training strategy, learns features from coarse-grained structures to fine-grained details in a shallow-to-deep manner, and effectively generates a long sequence, a detailed and rich FHR signal and a high-fidelity FHR signal.

The invention discloses a fetal heart rate pathology signal generation method and system based on a progressive growth architecture. The method comprises the following steps: acquiring a real fetal heart rate signal, and preprocessing the real fetal heart rate signal to form a data set; a progressive generative adversarial network model is constructed, and training is carried out by using the data set and adopting a progressive growth strategy; and inputting a random noise vector into the trained generator, and synthesizing a predicted fetal heart rate signal sample. According to the method, a complex long-time sequence generation task is decomposed into a plurality of simple sub-tasks through a progressive growth training strategy, the characteristics of signals from a coarse-grained structure to fine-grained details are learned from shallow to deep, and long-sequence, rich-detail and high-fidelity FHR signals are effectively generated.

To improve the accuracy of fetal heart rate measurement based on Doppler signals. [Solution] The Doppler signal forming unit 18 has a Doppler deviation frequency f, which is the difference frequency from the transmission frequency. d The Doppler signal TDS is formed to indicate the target Doppler signal. The Doppler signal identification unit 20 identifies whether the target Doppler signal TDS is composed of fetal heart rate components or fetal heart rate components and artifact components by inputting the target Doppler signal TDS into a learning model that has been trained to identify whether the input Doppler signal is composed of fetal heart rate components or fetal heart rate components and artifact components, using Doppler signals composed of fetal heart rate components and Doppler signals composed of fetal heart rate components and artifact components as training data. The heart rate measurement unit 22 measures the fetal heart rate based on the target Doppler signal TDS identified by the Doppler signal identification unit 20 as being composed of fetal heart rate components.