22 results about "Patient Motion" patented technology

This invention relates to the interdisciplinary field of image recognition and intelligent medical technology, specifically disclosing a method for orthopedic rehabilitation movement recognition and assessment based on image recognition. This method acquires patient motion images using a non-invasive multi-view visual sensor, extracts the three-dimensional coordinates of key skeletal points, and constructs a parametric biomechanical digital twin model integrating joint range of motion, muscle force lines, and ligament tension mechanisms. The key point data is input into a graph neural network for posture recognition, and the digital twin model is simultaneously invoked for physical feasibility verification and posture correction. Finally, the spatiotemporal trajectory similarity is calculated using a standard rehabilitation movement template, generating a comprehensive assessment result including movement completion, safety level, and injury risk. This invention, through the above technical solution, improves the robustness, physiological rationality, and clinical safety of movement recognition.

Devices, systems, and techniques for analyzing video information to objectively identify patient behavior are disclosed. A system may analyze obtained video information of patient motion during a period of time to track one or more anatomical regions through a plurality of frames of the video information and calculate one or more movement parameters of the one or more anatomical regions. The system may also compare the one or more movement parameters to respective criteria for each of a plurality of predetermined patient behaviors and identify the patient behaviors that occurred during the period of time. In some examples, a device may control therapy delivery according to the identified patient behaviors and / or sensed parameters previously calibrated based on the identified patient behaviors.

Systems and techniques can be used to estimate patient state during radiotherapy treatment. For example, a method can include generating, with a preliminary motion model, an extended dictionary of potential patient measurements and corresponding potential patient states. The method can include training, with a machine learning technique, a correspondence motion model that associates input patient measurements with output patient states using the dictionary. The method can include estimating, with a processor, a patient state corresponding to an input image using the correspondence motion model.

The control circuitry is able to access 400 patient-specific multidimensional information and subsequently, at least in part, automatically determine 406 supplementary boundaries for at least a portion of the patient (such as treatment targets and / or one or more organs at risk) based on the multidimensional information. The latter may include determining margins added to the boundaries of at least a portion of the patient. The control circuitry can then, for example, determine 407 the planned treatment volume based at least in part on the supplementary boundaries. These teachings will then allow for the optimization 408 of a patient-specific, radiotherapy-based treatment plan, for example, based on various motion dimensions derived at least in part from the aforementioned multidimensional information.

The application discloses a kind of neural patient rehabilitation training methods based on task training and brain-computer interaction, belong to rehabilitation training technical field, specifically include: based on the motion decoding model corresponding to the training task machine;Real-time acquisition data signal in current rehabilitation training of patient and carry out segmented processing, obtain several independent data blocks, carry out frequency domain conversion to independent data block, extract time-frequency feature and calculate the KL divergence between adjacent data blocks;If the KL divergence of any adjacent independent data block exists is greater than or equal to preset threshold, then obtain historical data signal and modify the motion decoding model, according to the motion decoding model after modification to the patient motion decoding, according to this to patient carries out rehabilitation training, the present application is selected corresponding model according to current rehabilitation training task, dynamic adjustment is combined with real-time signal characteristics, ensure that decoding result and training target are highly matched, improve the rehabilitation training effect of patient.

The invention provides an upper limb rehabilitation dynamic control method based on three-dimensional visual intention recognition, which comprises the following steps: synchronously acquiring three-dimensional visual observation data of upper limbs of a patient and pose data of an execution mechanism of a rehabilitation mechanical arm, constructing an upper limb pose vector containing an upper limb kinematics state, and associating the upper limb pose vector with an external traction displacement increment; based on the upper limb attitude vector and the external drafting displacement increment, generating a passive attitude reference vector representing the theoretical upper limb attitude under the pure passive drafting condition; calculating a residual error between the actually observed upper limb attitude vector and the passive attitude reference vector, and separating an active movement contribution amount of the patient from the residual error; generating a patient motion intention vector containing direction and intensity information based on the active motion contribution; according to the motion intention vector of the patient, an instruction used for controlling the auxiliary torque of the rehabilitation mechanical arm is generated, the real active intention of the patient can be accurately separated and extracted, and stable and accurate dynamic auxiliary control is achieved accordingly.

Methods and systems related to planning and delivering radiation treatment by modalities that move a radiation source along a trajectory relative to a subject while delivering radiation to the subject are provided. An artificial intelligence (AI) agent trained using reinforcement learning (and / or some other suitable form of machine learning) is used to control radiation delivery parameters in an effort to achieve a desired delivery of radiation therapy. In some embodiments, the AI agent selects appropriate control steps (e.g., radiation delivery parameters for a particular time step) while taking into account patient motion, difference(s) in patient anatomical geometry, etc.

A patient monitoring system and method, using an image acquisition device to acquire video data containing a patient, analyzing the video data to obtain activity information of the patient, and displaying on a display unit the monitoring result and the activity information corresponding to the same patient and generated in the same preset time interval, or calculating the activity correlation result of the monitoring result and the patient motion amplitude, and displaying on the display unit the monitoring result and the activity correlation result corresponding to the same patient and in time, which can effectively assist medical staff in objectively analyzing and evaluating the activity of the patient during diagnosis and treatment.

Visualization and robotic systems and methods utilize preoperative three dimensional (3D) images of patient motion and intraoperative, real-time patient motion information to show a target moving relative to medical tool or to control a robotic medical tool in real-time to track the target while the target is biopsied or treated. The systems and methods involve receiving preoperative 3D images of patient motion, displaying guidance for or controlling a robotic tool for navigating a medical tool near the target based on information from a position sensor disposed on the medical tool, tracking intraoperative 3D patient motion using motion sensors disposed on the patient, determining 3D target motion based on the preoperative 3D images and the tracked patient motion, and controlling the medical tool with the robotic tool to track the 3D target motion or displaying the 3D target motion relative to the medical tool.

A method comprises generating, by a control system, a measured model of an elongate instrument based on a measured state of the elongate instrument. The method further comprises generating, by the control system, a predicted model of the elongate instrument based on a reference state of the elongate instrument and a user command. The method further comprises comparing, by the control system, the measured model with the predicted model. The method further comprises determining, by the control system, whether a patient has moved relative to the elongate instrument based on the comparison.

Methods of monitoring a medical instrument are provided. The methods may include receiving state information from a control system in communication with the medical instrument; detecting motion of at least a portion of the medical instrument and comparing the motion of the portion of the medical instrument with a threshold motion value that is based on the state information received from the control system. The methods may further include generating a communication message for presentation to an operator of the medical instrument based on the comparison of the motion with the threshold motion value. Corresponding systems are also provided.

The invention discloses a human motion monitoring system, method and device and a storage medium. In the human motion monitoring system, an image acquisition module acquires N continuous frames of images of a human body on a diagnostic bed through multiple cameras. The image processing module extracts each frame of human body ROI, determines a single frame and integrates ROI area features. And the state recognition module judges the shielding state of each camera based on the characteristics. The motion detection module dynamically determines a human body motion energy value for an unshielded or semi-shielded camera. And the alarm module gives an alarm when a preset condition is met by combining the shielding state and the human body motion energy value. The scheme adopts pure visual analysis, does not depend on internal data of SPECT equipment, has the advantages of flexible deployment and strong compatibility, can effectively identify the occlusion state and accurately detect the motion of the patient, is beneficial to reducing motion artifacts in SPECT imaging, and ensures the imaging quality.

Disclosed herein are systems and methods for applying a stimulus to a target object based on sensed physiological data relating to the target object. A stimulation threshold for when to trigger stimulation of the target object based on a baseline indicating a need for stimulation can be continually adjusted based on the sensed data to more accurately activate stimulation at the appropriate time. To further enhance accuracy, the system can incorporate data from additional sensors, such as an accelerometer, to distinguish between true physiological changes and artifacts caused by patient motion or other bodily activities. This allows for a more robust and reliable calculation of the dynamic baseline.

The utility model relates to the field of walking tests, in particular to a footpath mark monitoring device for a six-minute walking test, which comprises a test footpath and a movable guide rail, distance marks are arranged on the surface of the test footpath, the movable guide rail is arranged on one side of the test footpath, and a mark area is arranged on the other side of the test footpath. A moving seat is arranged at the upper end of the movable guide rail, guide sliding seats are fixedly mounted on the two sides of the lower end face of the moving seat and slidably connected with the upper end of the movable guide rail, and moving wheels are arranged on the two sides of the driving box; the non-invasive cardiac output monitor is additionally arranged, so that the motion state of a patient is synchronously recorded, hemodynamic parameters of the human body are continuously monitored in real time, the change of central functions in the resting, moving and motion processes is evaluated from the angle of hemodynamics, the test effect is improved, the movable guide rail is used for guiding, the movable seat synchronously follows to move, and the test efficiency is improved. And when the patient moves, the noninvasive cardiac output monitor is driven to move synchronously, so that the use of the monitor is facilitated.

A wearable electronic device includes a light sensor configured to sense ambient light, a timer providing a time indicator, a motion sensing unit that senses motion and outputs motion data in dependence on the sensed motion, and a data storage that receives and stores the motion data or other data derived therefrom in association with the time indicator. The timer starts providing the time indicator and the motion sensing unit starts sensing motion after ambient light is sensed by the light sensor.

A device (10), system, method and computer-program product are disclosed for detecting movement of a subject in a diagnostic imaging examination. The device comprises a camera / 3D surface scanning system (11) and an input (14) for receiving a trigger to indicate that a current spatial configuration of the subject is to be maintained for the examination. The device comprises a processor (12) and an output (13), in which the processor (12) is adapted for acquiring reference data of the subject using the camera / 3D system when said trigger is received, and for acquiring further data of the subject using the camera / 3D system after acquiring said reference data. The processor is adapted to compare the reference data, which represents a reference state of the subject at substantially the time that the trigger was received, to the further data, which represents a more recent state of the subject. The processor is adapted to provide output data via said output (13), in which this output data is representative of the comparison of the further data to the reference data so as to indicate movement of the subject with respect to the reference state of the subject.

This system provides a nurse call system that can prevent false detections related to patient motion detection. [Solution] A terminal detection device 10 capable of detecting a mobile terminal 4 via wireless communication with the mobile terminal 4 located in the patient room was installed in each patient room. The terminal detection ID of each terminal detection device 10 and the sensor ID of each mat sensor 9 were stored in the control unit 7, each associated with a patient room, and as a result, the terminal detection device 10 and the mat sensors 9, 9... were stored in association. While the terminal detection device 10 was detecting a mobile terminal 4, the control unit 7 did not interpret the detection as a patient getting out of bed, even if a load was detected on the mat 8 by the mat sensor 9, 9... associated with the patient room where the terminal detection device 10 was installed, and therefore did not notify the nurse call master unit 3.

This invention discloses an intelligent control method and system for a portable infusion aid device, relating to the field of intelligent control of portable infusion aid devices, used to ensure the accuracy of drug delivery and patient medication safety. The method includes: acquiring fluid pressure information within the infusion tubing and patient motion information; performing frequency feature analysis on the fluid pressure information to identify target pressure frequency features; the target pressure frequency features include a first pressure frequency feature related to instantaneous external effects and a second pressure frequency feature related to slow internal changes; identifying motion features of the motion information; the motion features include motion pattern and motion intensity; assessing the degree of correlation between the target pressure frequency features and the motion features; determining a judgment result based on the degree of correlation; the judgment result indicating whether fluid pressure fluctuations are caused by benign activity or predict early tubing abnormalities; and issuing an early warning in response to the judgment result indicating that fluid pressure fluctuations predict early tubing abnormalities.

The invention relates to the technical field of medical health data analysis, and discloses a motion and health index correlation analysis method for hyperlipidemia patients. The method comprises the steps of processing real-time health monitoring data of a patient, extracting a key index trend to construct a personalized health ground state vector, and realizing dynamic quantification of an individual health state. The core is to set up a plurality of motion intervention strategies, perform rehearsal in a simulation environment, and generate a health state evolution graph by mapping a rehearsal result to a health ground state vector. And the system analyzes key nodes of the atlas to determine the optimal intervention opportunity, and formulates a staged exercise prescription comprising specific monitoring points and an adjustment threshold value accordingly. The method has the advantages that individual differences are accurately quantified through vectorization modeling, intervention paths of different motion strategies are predicted through simulated rehearsal, and therefore the personalized level and the prospective decision-making ability of hyperlipidemia patient motion management are improved.

The present invention relates to an medical imaging optimization system comprising a scanning module adapted to carry out a imaging process on a patient, a patient motion detection module adapted to detect motion of a patient during the imaging process and generate motion data when a motion of a patient is detected, and characterized in that said system further comprises a processing unit adapted to receive said patient motion data from the patient motion detection module, analyze the patient motion data in real- time to determine patient motion events, judge whether the patient motion events are relevant and adjust said medical imaging scanning process based on said detected motion data when judged relevant.

The invention discloses a patient monitoring system and method, and the method comprises the steps: collecting video data including a patient through an image collection device, analyzing the video data to obtain the activity information of the patient, and displaying a monitoring result and the activity information corresponding to the same patient and generated in the same preset time interval on a display unit on the same screen, or an activity correlation result of the monitoring result and the movement amplitude of the patient is calculated, and the monitoring result and the activity correlation result which correspond to the same patient and correspond to the same patient in time are displayed on the same screen of the display unit, so that the medical care can be effectively assisted to objectively analyze and evaluate the activity of the patient in the diagnosis and treatment process.

Disclosed herein are systems and methods for applying a stimulus to a target object based on sensed physiological data relating to the target object. A stimulation threshold for when to trigger stimulation of the target object based on a baseline indicating a need for stimulation can be continually adjusted based on the sensed data to more accurately activate stimulation at the appropriate time. To further enhance accuracy, the system can incorporate data from additional sensors, such as an accelerometer, to distinguish between true physiological changes and artifacts caused by patient motion or other bodily activities. This allows for a more robust and reliable calculation of the dynamic baseline.