47 results about "Physiological motion" patented technology

The invention discloses a personalized rehabilitation training method based on state monitoring, and particularly relates to the technical field of intelligent medical treatment. According to the method, the technical problems of insufficient individuation, poor safety, limited effect and the like caused by single monitoring dimension, lagging adjustment strategy and lack of self-optimization capability in the existing rehabilitation training are solved. According to the scheme, physiological, motion and subjective multi-dimensional data of a patient are synchronously collected through a multi-source sensor and input into a machine learning model for real-time state evaluation after fusion processing, a personalized training scheme is generated and executed accordingly, meanwhile, parameters are dynamically adjusted according to real-time monitoring data in training, and the training efficiency is improved. And the model and the strategy are optimized by analyzing historical data after the period is ended. According to the invention, safe, accurate and self-adaptive evolution personalized rehabilitation training is realized, and the safety, adaptability and rehabilitation effect of training are improved.

The invention relates to the technical field of image enhancement, in particular to a throat structure and detail high-resolution image enhancement method based on deep learning. The method comprises the following steps: acquiring a low-resolution image of a laryngeal endoscope and corresponding laryngeal three-dimensional image data; the method comprises the following steps: extracting features from a low-resolution image based on a ResNet model, extracting features from three-dimensional image data by using a 3D-ResNet model, constructing a time-varying weight matrix modulated by a sine period in the 3D-ResNet model, so that the physiological motion state of the throat can be perceived in real time in an image enhancement process, and fusing the extracted features by using a cross-scale feature pyramid technology; and a U-Net + + model combined with a sub-pixel convolutional layer is utilized to carry out super-resolution reconstruction on the image subjected to feature fusion processing. According to the design, by introducing an anatomical attention module and a dynamic receptive field adjustment technology, the characteristics of clinical key areas (such as vocal cord free edges and anterior joint areas) can be enhanced in a targeted manner.

The invention discloses a personalized physical training load intelligent regulation and control system based on multi-modal physiological data fusion, and relates to the technical field of intelligent physical training and health monitoring. The system comprises a multi-modal data acquisition module, an intelligent fusion analysis module, a personalized decision module and a real-time regulation and control module. The method comprises the following steps: acquiring physiological, motion and environmental parameters of a user, and performing multi-modal data fusion by using a time sequence-causal attention mechanism to generate a comprehensive physiological state feature vector; a dynamic personalized baseline is established based on a meta-learning framework, a load adjustment decision is generated by adopting a hierarchical reinforcement learning algorithm, and regulation and control safety is ensured through causal reasoning verification; and finally, load adjustment is executed through the real-time regulation and control module to form closed-loop control. According to the method, the problems that in the prior art, training load regulation depends on a single physiological parameter, the individuation degree is insufficient, and decision making is lack of scientificity are solved, and accurate, self-adaptive and safe individualized physical training management is achieved.

The invention relates to the technical field of audio signal processing, in particular to an audio equalization adjustment method and device and a storage medium. The audio equalization adjustment method comprises the following steps: acquiring a physiological movement signal and an environment audio signal of a user; respectively processing the physiological motion signal and the environment audio signal to obtain physiological motion features and environment noise features; performing fusion decision based on the physiological motion features and the environmental noise features to generate a target equilibrium parameter set; and based on the target equalization parameter set, performing equalization adjustment on the audio output signal of the near-to-eye display device. According to the method, the auditory experience of the near-to-eye display equipment in the motion scene can be intelligently optimized.

The invention discloses a bacteriophage virus multi-host prediction method, system and device and a medium, and the method comprises the steps: receiving knee joint data through a sliding window, building a joint physiological kinematics constraint, and building a joint physiological motion optimization equation based on the joint physiological kinematics constraint; solving the joint physiological motion optimization equation to obtain a joint axis and a joint position vector; based on the joint axis and the joint position vector, two groups of joint angles are obtained through acceleration information and angular velocity integration; and solving the weighted average of the two groups of joint angles through complementary filtering to obtain the joint angle. According to the method, the problem of disturbance caused by unstable wearing or external disturbance in the measurement process of the inertial sensing wearable inertial node is solved.

The application discloses an interventional surgery instrument operation track intelligent planning dynamic navigation control method and system, and belongs to the technical field of minimally invasive interventional surgery intelligent navigation. A patient's preoperative three-dimensional medical image and intraoperative two-dimensional perspective image are acquired, and a digital twin model of a surgery region containing anatomical structures and physical properties is constructed; an initial optimal operation track is generated through a rapidly expanding random tree and convex optimization, and an anatomical structure displacement caused by physiological motion is compensated by adopting nonlinear elastic registration based on feature points; dynamic resistance feedback is calculated in combination with an instrument mechanical response model, track correction instructions and feedback signals are output, and a closed-loop navigation is realized by driving an executing mechanism and a main operating handle. The system contains five modules of image processing, track planning, registration compensation, control calculation and executing feedback, can effectively improve operation precision and safety in a complex blood vessel environment, solves problems of interventional surgery hand feeling loss, dynamic adaptation difference and navigation precision deficiency, and is suitable for various blood vessel interventional minimally invasive treatments.

Methods and devices provide physiological movement detection with active sound generation. In some versions, a processor may detect breathing and / or gross body motion. The processor may control producing, via a speaker coupled to the processor, a sound signal in a user's vicinity. The processor may control sensing, via a microphone coupled to the processor, a reflected sound signal. This reflected sound signal is a reflection of the sound signal from the user. The processor may process the reflected sound, such as by a demodulation technique. The processor may detect breathing from the processed reflected sound signal. The sound signal may be produced as a series of tone pairs in a frame of slots or as a phase-continuous repeated waveform having changing frequencies (e.g., triangular or ramp sawtooth). Evaluation of detected movement information may determine sleep states or scoring, fatigue indications, subject recognition, chronic disease monitoring / prediction, and other output parameters.

The invention belongs to the technical field of nuclear medicine imaging, and discloses a radioactive tracer agent distribution quantification optimization method and related equipment, and the method comprises the steps: obtaining scanning bed deformation information, moving track information and physiological motion dynamic information of a patient, and obtaining a radioactive tracer agent distribution quantification optimization result based on the scanning bed deformation information, the moving track information and the physiological motion dynamic information; the method comprises the steps of constructing a multi-source error integrated influence model, performing radioactive tracer distribution reconstruction on original detection data through an OSEM algorithm based on the multi-source error integrated influence model to obtain real distribution information of a radioactive tracer, and performing calculation according to the real distribution information to obtain a standardized uptake value. By means of the method, the accuracy of the radioactive tracer agent distribution quantification result is improved.

The application provides a multimodal sensory-motor closed-loop control system and method for a nerve injury rehabilitation device, and relates to the technical field of intelligent medical rehabilitation devices. The system comprises: a multimodal sensing module that synchronously collects physiological signals, kinematic signals and semantic input signals and adds isogenic hardware time stamps; a subjective and objective alignment processing module that intercepts an asymmetric time window and generates a subjective and objective alignment state slice based on a semantic event anchor point; a multimodal parameter generation module that outputs a machine-resolvable structured control instruction in combination with state characteristics and a clinical background and is verified through a safety shadow network; and a closed-loop physical execution module that synchronously drives a motion intervention loop to output mechanical impedance and a sensory compensation loop to output electrical stimulation within the same hardware synchronous trigger cycle. The application realizes accurate alignment of subjective semantics and objective physiological motion data, synchronous driving of dual-loop execution, reduction of delay and semantic ambiguity, and improvement of safety and adaptability through multiple safety verification.

The invention discloses a nasopharyngeal laryngoscope focus accurate positioning and image recognition system, which comprises a shape sensing subsystem, an absolute positioning subsystem and a data processing module, and is characterized in that the shape sensing subsystem senses deformation in real time through a strain sensor array in a hose, and the absolute positioning subsystem establishes a fixed reference coordinate system through a reference mark; the data processing module fuses the two kinds of data, establishes a dynamically maintained patient coordinate system and achieves accurate positioning and mapping of the laryngoscope tail end position, the system generates a lesion stereoscopic model through multi-view image collection and three-dimensional reconstruction, intelligent matching analysis is conducted in combination with a lesion database, and an evaluation result is provided. Meanwhile, dynamic compensation and self-checking functions are realized based on physiological movement signals, so that the problem of positioning drift caused by movement and physiological movement of a patient in traditional laryngoscopy is effectively solved, and accurate space positioning, three-dimensional visual representation and intelligent diagnosis assistance of a focus are realized; the diagnosis and treatment accuracy and the operation safety of the diseases of the nose and throat department are obviously improved.

The invention relates to the technical field of medical image processing, and provides an image sequence registration method, which comprises the following steps of: firstly, calculating relative displacement of adjacent frames, accumulating to obtain absolute displacement, decomposing the absolute displacement, and extracting trend components representing physiological movement and high-frequency residual errors representing random disturbance; meanwhile, a current frame and a reference frame are input into a displacement fine-tuning network to obtain a displacement fine-tuning amount, then the high-frequency residual error is negated and then weighted with the displacement fine-tuning amount to synthesize compensation displacement, and spatial transformation is carried out on the image. According to the method, motion components are separated, the physiological motion trend is reserved while random jitter is compensated, over-correction caused by integral accumulation errors or end-to-end learning is avoided, and high-precision image sequence registration is achieved.

A sensor 104 for non-contact sensing of a physiological parameter of a body 102 is described. In an embodiment, the sensor 104 comprises: a waveguide, the waveguide comprises a metamaterial and is configured to receive a transmitted signal and to propagate the transmitted signal in a spoof surface plasmon mode along the waveguide to produce an evanescent electromagnetic field and to provide a received signal, wherein the waveguide is placed at a predetermined distance away from the body 102 for non-contact sensing of a perturbation produced by a physiological motion of the body 102 using the evanescent electromagnetic field, the perturbation produces a phase shift between the transmitted signal and the received signal for use in determining the physiological parameter of the body 102. A system 100 and a method 200 for non-contact sensing of a physiological parameter of a body 102 are also described.

The invention relates to the field of medical image processing, and discloses a medical image virtual simulation method and system based on digital twinning. The method comprises the following steps: acquiring original physiological data and carrying out sliding window time sequence sampling to obtain a preliminary physiological movement sequence; extracting position deviation characteristics from the preliminary physiological movement sequence to obtain a dynamic interference distribution matrix; abnormal fluctuation in the dynamic interference distribution matrix is detected, nonlinear supplementary interference samples are generated and fused, and an enhanced interference data field is obtained; performing superposition operation on standard nuclear magnetic imaging data by using the enhanced interference data field to obtain a preliminary simulation image sequence; extracting time dynamic features of the preliminary simulation image sequence and a real clinical artifact image, and comparing the time dynamic features to generate a feature difference chart; and according to the feature difference image, calculating an adaptive fusion weight and performing residual feature completion to obtain a final medical image simulation result. According to the method, high-fidelity reproduction and closed-loop optimization of the dynamic artifacts of the medical image are realized.

A battery-less, wirelessly powered localization system is described. In an embodiment, a wirelessly powered localization system, includes an external Tx antenna that generates a radio frequency (RF) signal that wirelessly powers a set of one or more localizers, an external Rx antenna that receives an output from the localizers, a localizer including: an Rx antenna that receives a radio frequency (RF) signal from an external Tx antenna, a passive four-stage full-wave CMOS rectifier that generates a DC voltage using the received RF signal, a low-dropout regulator that generates a stable DC voltage based on the rectifier-generated voltage, a frequency divider circuit to divide the frequency of received RF signal, and a Tx antenna that outputs an RF signal at the divided frequency to the external Rx antenna.

This application relates to the field of medical image processing technology, and discloses a method and system for lesion analysis of SPECT and spectral CT fusion images. The method includes acquiring SPECT and spectral CT images; identifying at least one anatomical feature point in the spectral CT image and identifying a functional feature point corresponding to the anatomical feature point in the SPECT image; calculating the first spatial coordinates of the anatomical feature point in the spectral CT image and the second spatial coordinates of the functional feature point in the SPECT image; determining the deformation parameters of a local region in the SPECT image based on the difference between the first and second spatial coordinates; and performing spatial transformation processing on the functional distribution features of the local region in the SPECT image to spatially align the processed functional distribution features with the anatomical features in the spectral CT image, actively eliminating image misalignment caused by physiological motion and other factors, and achieving alignment of functional information with anatomical structures.

The invention relates to the technical field of medical data compression, and discloses a lossless compression method for medical image data, which comprises the following steps of: 1, acquiring three-dimensional medical image data and ray beam path data in a radiotherapy plan, and segmenting the three-dimensional medical image data into a plurality of voxel blocks; and performing clinical importance grade labeling on the voxel blocks according to ray beam path data. According to the technical scheme, physiological motion signals of a patient are obtained to generate a displacement time table, motion compensation is executed based on the displacement time table to generate a prediction image, and finally reversible differential storage is conducted on a real image and the prediction image, so that the purposes of fully utilizing time sequence redundancy of three-dimensional medical image data, remarkably improving the compression ratio and improving the image quality are achieved. And compared with the technical scheme that compression is adopted piece by piece and time relevance is not utilized in the prior art, the problems that the compression efficiency is low and excessive storage resources are occupied are solved.

The invention provides a joint reconstruction and dynamic registration method and device, equipment and a medium, and relates to the technical field of image processing. The method comprises the following steps: obtaining a fused feature map through feature extraction operation and feature fusion operation, and carrying out dynamic deformation registration operation on a preprocessed SPECT basic image and a target CT image by using the fused feature map to obtain a registered CT image, a registered SPECT image and a dynamic displacement field for compensating physiological movement. And performing reconstruction operation on the registered SPECT image by using a reconstruction constraint condition, the registered CT image and the dynamic displacement field to obtain a reconstructed SPECT image. According to the method, a joint optimization framework is constructed by deeply embedding dynamic deformation registration into a reconstruction process, so that the SPECT reconstruction can fully utilize CT anatomy prior and displacement field constraint, a traditional serial error chain is broken, and the reconstruction precision and function-anatomy alignment degree are remarkably improved.

The application discloses a kind of military physical action standard identification methods based on multi-modal fusion, to solve the problem that traditional military training relies on subjective evaluation, existing automated method is poor in robustness and cannot quantitatively evaluate action quality.The method first synchronously collects visible light video, infrared video and wearable sensor data when soldier trains;Second, by space-time alignment, construct the semantic vector sequence that fuses human key point coordinates, regional infrared temperature, motion statistical characteristics and heart rate data;Then, use heterogeneous double-channel deep neural network to extract space-time visual features and physiological motion features, and perform deep fusion through cross-attention mechanism.The application realizes the quantitative evaluation of the automation, precision and interpretability of military physical action standard, and improves the recognition robustness and guidance value of evaluation results in complex environment.

The invention provides an active motion compensation method and system for flexible brain electrode implantation. The method comprises the steps that S1, a flexible brain electrode image is collected; s2, estimating a three-dimensional coordinate of a flexible brain electrode implantation target spot; s3, predicting the three-dimensional motion of the moving target based on the prediction result of the three-dimensional coordinates and the estimated time delay, and obtaining a motion prediction track; s4, the sensor coordinate system is converted to the robot, and then the robot adjusts the angle and the position according to the motion prediction track. According to the method, active motion compensation is carried out on the flexible brain electrode implantation equipment under physiological motion, and more than 96% of relative motion between a target and an instrument can be reduced through active compensation.

Embodiments of the present disclosure provide a method and system for positioning a robot and adjusting a posture. The method may include obtaining a first image and a second image of a target object. The first image may be captured using an image capturing apparatus, and the second image may be captured using a medical imaging device. The method may also include determining at least one target region corresponding to at least one target portion of the target object from the first image. The at least one target portion may be less affected by physiological motions than other portions. The method may further include determining positioning information of the robot based on the at least one target region and the second image.

The application relates to the technical field of medical image processing, and provides a registration method of an image sequence. The method first calculates relative displacement of adjacent frames, accumulates the absolute displacement, decomposes the absolute displacement, extracts a trend component representing physiological motion and a high-frequency residual representing random disturbance, simultaneously inputs a current frame and a reference frame into a displacement fine-tuning network to obtain a displacement fine-tuning amount, adds the high-frequency residual after inversion to the displacement fine-tuning amount to obtain a compensation displacement, and performs spatial transformation on the image. The method separates motion components, compensates for random jitter while retaining the physiological motion trend, avoids overcorrection caused by integral accumulation error or end-to-end learning, and realizes high-precision image sequence registration.

Devices for energy harvesting are disclosed herein. The present disclosure concerns a device (400) comprising: an energy harvesting mechanism (422) configured to produce energy from physiological motion of a patient; one or more electrodes (402a, 402b, 402c) configured to deliver electrical stimulation to the patient; a power source (420) operably coupled to the energy harvesting mechanism and the one or more electrodes; processing circuitry (414); and a memory (418) operably coupled to the processing circuitry and storing instructions that, when executed by the processing circuitry, cause the device to perform operations comprising: determining (702) a power output of the energy harvesting mechanism; determining (704) a stimulation signal configured to adjust the physiological motion to increase the power output of the energy harvesting mechanism; delivering (706) the stimulation signal to the patient using the one or more electrodes; and charging (708) the power source using the energy harvesting mechanism.

The anesthesia puncture visual navigation system combining augmented reality with three-dimensional reconstruction belongs to the technical field of anesthesia puncture visual navigation, and comprises a physiological motion monitoring unit, which is used for simultaneously collecting respiratory motion cycle data and soft tissue elastic deformation information, and generating a comprehensive motion state data packet by calculating the correlation coefficient of the respiratory amplitude and the tissue elastic modulus change rate, so that the spatial deviation caused by the respiratory motion and the soft tissue deformation of the patient to the puncture navigation can be effectively compensated, the puncture precision is significantly improved compared with the traditional static navigation system under the normal respiratory state of the patient, the puncture failure rate and the complication risk are effectively reduced, the problem of further precision deterioration caused by the blind application of correction parameters of the traditional system when the registration quality deteriorates is avoided, the dependence on the personal experience of the doctor is reduced, and the problem of complete system failure caused by a single correction mode is avoided.

The present specification relates to an image sequence motion correction method and device based on intensity correction optical flow registration. The method comprises: determining a reference image of each deformed image in a deformed image sequence, performing motion correction on the deformed image by adjusting the weight of the mechanical regularization term of the reference image and the deformed image to obtain the displacement field of the deformed image relative to the reference image; based on the displacement field and the intensity correction value of the finite element node, intensity correction is performed on the reference image; adjusting the weight of the mechanical regularization term, performing motion correction on the deformed image, intensity correction is performed on the first corrected reference image based on the optimized displacement field, and the execution is repeated until the image residual function converges, the deformed image is determined to be corrected, the optimal solution of the weight value of the mechanical regularization term of the deformed image is recorded; and determining the true displacement of the deformed image according to the optimal solution of the weight value. The present specification integrates the mechanical model behind physiological motion and intensity correction technology into the image registration algorithm to reduce image noise and improve algorithm accuracy.

This disclosure provides a method, apparatus, and pilot tone device for acquiring target physiological motion signals. The method includes: acquiring multi-channel complex signals received from multiple channels; and obtaining at least one target motion complex signal with interference removed from the multi-channel complex signals using a motion signal synthesis vector corresponding to at least one target motion signal. Specifically, acquiring data received from multiple channels within a set time period includes data without external interference within a first set sub-time period and data with external interference within a second set sub-time period; obtaining an external interference suppression matrix based on this data, and obtaining data with suppressed external interference based on the data without external interference or the data with external interference and the external interference suppression matrix; obtaining a motion signal correlation matrix of at least one target motion signal in the frequency domain based on the frequency range of at least one target motion signal; and using an eigenvector obtained from the eigenvalues ​​of the motion signal correlation matrix as a motion signal synthesis vector.

Methods and devices provide for detecting physiological motion with active sound generation. In some versions, a processor can detect respiration and / or gross body motion. The processor can control production of a sound signal in the vicinity of a user through a speaker coupled to the processor. The processor can control sensing of a reflected sound signal through a microphone coupled to the processor. The reflected sound signal is a reflection of the sound signal from the user. The processor can process the reflected sound, such as through a demodulation technique. The processor can detect respiration from the processed reflected sound signal. The sound signal can be produced as a series of tone pairs in a time slot frame, or as a phase-continuously repeating waveform with varying frequency (e.g., triangular or ramp sawtooth). Evaluation of the detected motion information can determine sleep state or score, fatigue indication, object identification, chronic disease monitoring / prediction, and other output parameters.

The invention relates to the technical field of medical image processing, in particular to an artificial intelligence assisted self-service cruise three-dimensional C-arm imaging system, which comprises an autonomous cruise module used for autonomously moving and positioning in an operating room and comprising a multi-modal sensing unit, a navigation control unit used for generating a navigation path and a Mecanum wheel omnidirectional moving chassis; the intelligent scanning decision module is used for optimizing scanning parameters and synchronizing with physiological movement of the patient and comprises a patient feature analysis unit, a scanning parameter optimization module unit and a respiratory movement synchronization unit, and the scanning parameter optimization module unit performs optimization decision on an analysis result based on a decision tree and a random forest ensemble learning algorithm; the cloud cooperative control architecture is used for cooperatively completing scanning and reconstruction and comprises an end-side execution unit and a cloud-side reconstruction engine; and the operation process self-learning module is used for optimizing an operation navigation path. The problems that traditional equipment is clumsy in movement, scanning decision depends on experience, and organ motion artifacts are serious are solved.

The embodiment of the invention is suitable for the technical field of medicine, and provides a physiological gating signal generation method and system.The method comprises the steps that a signal probe is controlled to scan a target area, and echo signals fed back by the target area are received; wherein the echo signal can reflect physiological motion information of target tissue in the target area; generating a motion image of the target tissue according to the echo signal, and displaying the motion image; determining a physiological gating signal of the target tissue based on the motion image; the physiological gating signal is used for controlling the medical equipment to perform imaging scanning on the target tissue. By adopting the method, high-quality physiological gating signals can be conveniently acquired, so that artifacts during target tissue imaging are reduced.