GE Precision Healthcare Patente

Techniques for estimating target radiation doses for medical imaging exams leveraging artificial intelligence (AI) are described. In an example, a method can comprise training an AI model to estimate target dose information for past medical imaging exams using historical exam reports for the past imaging exams and actual radiation dose information included in the historical exam reports indicating actual radiation dosages exposed to past patients as a result of the past imaging exams. Once trained, the AI model is applied to estimate the target dose information for new medical imaging exams prior to performance of the new exams. The target dose information is further provided to the corresponding imaging systems scheduled for the new exams. In some implementations, the target dose information can control the acquisition protocol used for the exams to ensure compliance with the target dose information.

Embodiments of the present disclosure relate to a positioner system for use with an ultrasound probe to treat a subject via neuromodulation, and the techniques for using the same. In certain embodiments, the positioner system may include a receptacle for receiving the ultrasound probe, a pressure applicator to apply a steady pressure to maintain a position of ultrasound probe against the patient's skin, and a slider arm to extend near or above the subject and support the pressure applicator and probe holder. The positioner system may include multiple degrees of freedom to accommodate a subject's clinical needs and/or treatment protocol that utilizes the ultrasound probe.

Some embodiments of the present disclosure include a processor and a memory. The memory includes instructions executable by the processor to receive training data having vitals scores for pre-term infants indicating a healthiness of a pre-term infant having specific vitals measurements. Further, the instructions are executable to receive training data having maternal health parameters and pregnancy parameters for pregnant women that gave birth to pre-term infants. Additionally, the instructions are executable to receive training data having pre-term infant health parameters and birth parameters for the pre-term infants. Further, the instructions are executable to train an artificial intelligence model to infer a viability score by using the maternal parameters training data, pre-term parameters training data, pre-term vitals training data, and supervised learning. Additionally, the viability score indicates a likelihood of survival for a pre-term infant having a vitals score, maternal parameters, and pre-term parameters.

A neonatal care system includes a processor and a memory. The memory includes instructions configured to cause the processor to receive strain amounts corresponding the strain sensors of a tactile sensor array. Additionally, the instructions cause the processor to generate a strain map comprising a visualization of the strain amounts in association with the corresponding X, Y coordinate locations of the strain sensors. Further, the instructions cause the processor to generate a weight map based on the strain map and a strain-weight model. Additionally, the weight map includes weights corresponding to the strain amounts. Further, the instructions cause the processor to identify a patient location. Additionally, the instructions cause the processor to determine a weight of the patient based on the patient location and the weight map

Systems are provided for perioperative care. In an example, a system for tracking phases of anesthesia delivery over a case for a patient includes one or more processors and memory storing instructions executable by the one or more processors to output (802) a GUI including a first visual representation of a default or previously-determined phase of anesthesia delivery for the patient; receive (602) a plurality of monitoring parameters of the patient over an observation window; identify (606), by applying a set of rules to the plurality of monitoring parameters, whether an event signaling a change to a new phase of anesthesia delivery for the patient is detected; based on the event being detected and determined to be a true event, update (617) the GUI to display a second visual representation of the new phase; and based on the event not being detected, maintain (810) the first visual representation on the GUI.

A radiation imaging apparatus (90) includes a substrate (92) and a radiation-sensitive imaging region (96) in the substrate (92) including pixels (60). The radiation imaging apparatus (90) includes a guard region (94) at or immediately adjacent a cut edge (95) of the substrate (92), wherein the guard region (94) reduces the leakage current reaching the radiation-sensitive imaging region (96) from the cut edge (95) when the radiation imaging apparatus (90) is in use. The radiation-sensitive imaging region (96) is electrically reverse biased with respect to the substrate (92). The radiation-sensitive imaging region (96) includes a portion (134) adjacent the guard region (94) that is closest to where incident radiation impacts the radiation imaging apparatus (90). The pixels (60) include a first pixel electrode (146) located in the portion (134) where a first longitudinal end (150) of the first pixel electrode (146) closest to the guard region (94) is a first distance (154) from the guard region (94) that reduces an amount of the leakage current received by the first pixel electrode (146).

Provided is a telescopic cylinder (100) and an X-ray imaging system. The telescopic cylinder includes a plurality of sleeves arranged in a nested configuration and having mutually parallel central axes. Each inner sleeve cooperates with an outer sleeve adjacent thereto to enable relative sliding such that each inner sleeve can extend and collapse relative to that outer sleeve. The telescopic cylinder further includes guide assemblies. Each guide assembly includes rollers and a rail that are configured as a set. The rollers are provided on left and right sidewalls and rear walls of the inner sleeves and the rails are correspondingly provided on left and right sidewalls and rear walls of the outer sleeves. The rollers and the rail in the same guide assembly are provided on an outer wall surface of the inner sleeve and an inner wall surface of the corresponding outer sleeve, respectively, such that the rollers can roll on guide surfaces defined by the rail, thereby guiding movement of the inner sleeve relative to the outer sleeve. The telescopic cylinder has sufficient structural stability and rigidity while allowing smooth extension and collapse, with good operational stability, low susceptibility to failure, easy maintenance, and low space requirements.

The present disclosure relates to an obstacle processing method and apparatus for a medical imaging system, an electronic device, a storage medium, and a program product. The method includes: collecting, by means of a visible light camera, a camera image corresponding to a target workspace of a target subsystem of a medical imaging system, wherein the target workspace is a target movement path or an imaging beam range; detecting an obstacle in the target workspace based on the camera image to obtain an obstacle detection result of the target workspace; and performing obstacle processing on the target workspace in response to the obstacle detection result indicating that an obstacle is detected.

Various methods and systems are provided for a medical imaging system. In one embodiment, a method for imaging a lung of a patient includes identifying (308), within a three-dimensional (3D) volume of ultrasound data of the lung of the patient, a pleural surface of a pleural line, identifying (502) an orthogonal deviation of each voxel of the pleural surface relative to an expected pleural line, and outputting (516) an image rendered from the 3D volume, the image including a plurality of pixels colored based on the orthogonal deviation of each voxel of the pleural surface and depicting the pleural surface as if viewed from an inside of the lung and looking outward.

Various methods and systems are provided for a suction electrode assembly (200), comprising, an electrode housing (204) that surrounds and positions an electrode plate (302), the electrode housing being coupled to a vacuum system (112), a suction dome housing (202) configured to position the electrode housing and comprises a top portion (202a), a bottom portion (202b), and a conical middle portion (202c) with an axially varying wall thickness that couples the top portion and the bottom portion, and wherein the top portion is configured to withstand a force that depresses the top portion, the conical middle portion is configured to concentrically collapse in response to the top portion being depressed, and the bottom portion is configured to contact a surface.

A waveform anomaly detection system (360) is provided that automatically detects and tags waveform data patterns in physiological patient (time-series) data that match predefined, clinically validated patterns (1300, 1400, 1500), to enable clinicians to match and corroborate their own observations with tool-triggered findings. As a result, clinicians may make more informed clinical decisions without having to manually review enormous amounts of time-series data. Additionally, when anomalous waveform patterns (1300, 1400, 1500) are detected, relevant patient data from an electronic medical record (EMR) (350) or similar databases and/or platforms (352) may be automatically retrieved and integrated into the waveform data, such that the integrated data may be viewed together on a display device (140). The data may be stored with the anomalous waveform patterns (1300, 1400, 1500) in a database (354) of the waveform anomaly detection system (360), where analysis results can be accessed conveniently by a caregiver of the patient, for example, using a personal computing device such as a smart phone (140).

The present disclosure relates to the field of medical data management, and in particular to a data playback method and system, and a storage medium. The method includes: acquiring medical data collected by a plurality of medical devices, wherein the medical data includes physiological parameter data of a target subject within a period of time and a medical event related to the target subject; preprocessing the physiological parameter data, wherein the preprocessing comprises: dividing the physiological parameter data into a plurality of data segments in chronological order; in response to the selection of a first time period, preloading a data segment corresponding to the first time period, and caching the preloaded data segment into a data pool; and rendering the preloaded data segment to obtain a waveform graph of the first time period; and concurrently displaying the waveform graph of the first time period and the medical event . By means of a preloading and caching mechanism, embodiments of the present disclosure implement rapid playback and display of medical data collected by a plurality of medical devices within a first time period.

Systems and methods are provided for a sepsis alert engine. In one example, a computing device (102) comprising a display screen (122) displays a menu listing one or more electronic medical records (EMRs) (280) of one or more patients, and is configured to display a sepsis alert GUI (300) accessible from the menu while the one or more EMR systems are in an un-launched state. The sepsis alert GUI displays a sepsis level element (330) identifying a sepsis level for each patient displayed as well as a limited list of criteria (322) that triggered the identified sepsis level. The limited list of criteria is met by patient data obtained from the one or more EMRs and each criterion in the limited list is selectable to launch a pop-up UI (600) with additional information relating to the identified sepsis level, wherein the sepsis level element is assigned to each patient according to a corresponding patient level of care.

An imaging device or system (10), e.g., a mammography imaging system (12), and associated method provides artefact-reduced images (420,422,424) of an object (52). The system (10) and method generates a standard reconstructed volume (410) of the object (52) created from one or more projection images (404) obtained of the object within an angular range of less than +/- 60 degrees relative to the object (52). A resolution enhancement artificial intelligence (414) is applied to the projection images (404) to form an artefact-reduced/quasi-isotropic volume (416), and one or more quasi-isotropic images (420,422,424) obtained therefrom along planes that are orthogonal to the plane of the detector (18) for the mammography imaging system (12) . The resolution of the quasi-isotropic images (420,422,424) is similar to images obtained in a simulated computed tomography imaging procedure and the quasi-isotropic volume (416) can be utilized to provide effective diagnostic images using strain elastography and the digital decompression of the quasi-isotropic volume (416) to create a modifiable digital uncompressed object volume (800).

A maternal fetal monitor includes a display, a processing device, and a memory device. The memory device includes instructions that are executable by the processing device to display a cardiotocogram for a maternal patient and a fetus of the maternal patient. Additionally, the instructions are executable by the processing device to display, in response to a request, an ultrasound image based on a plurality of ultrasound signals that are generated by, and detected by, an ultrasound imaging probe that is in communication with the maternal fetal monitor.

Various methods and systems are provided for a rotary user interface (104) for a touchscreen display (102). In one embodiment, a rotary user interface (104) for a touchscreen display (102) comprises: an alignment touchscreen nib (540); a rotary interface wheel (106); and a rotary touchscreen nib (536) coupled to the rotary interface wheel (106) and rotatable relative to the alignment touchscreen nib (540) via the rotary interface wheel (106). The rotary user interface (104) may further include a confirmation touchscreen nib (548) coupled to the rotary interface wheel (106).

This method for calculating local narrowings from a three-dimensional image of a duct comprises the following steps: - Determining (step E3) a minimum diameter profile of a duct section along the length of the duct; - Defining (step E4) at least one sliding window for examining the duct for which the minimum diameter of the duct at the longitudinal ends of said window is known for each position of said window on the duct; and - Calculating (step E5), for each position of the at least one window, the maximum loss of minimum diameter of the duct within the window with respect to an interpolation of the diameters at the longitudinal ends of the window.

Various methods and systems are provided for reducing an amount of time and resources spent on reviewing digital breast tomosynthesis (DBT) images and corresponding synthetic 2D images. In one example, a method includes receiving a plurality of tomosynthesis data studies, each study comprising a first image set of synthetic two-dimensional (S2D) images, a second image set of slab images, and a third image set of plane images. For each study of the plurality of tomosynthesis data studies, a minimum dataset to be reviewed by a radiologist is determined based on an analysis of the tomosynthesis data by an AI-based system, and the minimum dataset is displayed on a display device rather than the plurality of tomosynthesis data studies.

Described herein are systems and methods for operating and cleaning an incubator heating system (300). A heat engine assembly (304) and an air ducting system (308) of the incubator heating system are removably coupled to a base (312) at a first end (334). The air ducting system comprises a first side duct (384a), a second side duct (384b), and a central duct (702), each having a vent opening (364, 734). The heat engine assembly comprises an air mover (320) positioned between a first heater (318) and a second heater (316). The air mover is configured to pull air into the central duct, direct air from the central duct past each of the first heater and the second heater to heat the air, and direct heated air through and out of each of the first side duct and the second side duct.

The present disclosure relates to a monitor setting method and apparatus, an electronic device, a storage medium, and a program product. The method includes: checking a connection state between a monitor and a dock device; in response to detecting that the monitor is connected to the dock device, automatically reading device information of the dock device from a memory of the dock device; determining, on the basis of the device information of the dock device, that the dock device has been replaced, and automatically generating a location information determination interface; acquiring current location information of the monitor from the location information determination interface; and acquiring target setting information of the monitor matching the current location information, and setting the monitor according to the target setting information.

Methods and systems are provided for detecting and predicting uterine activity (UA) from an ultrasound receive signal and/or electrohysterogram (EHG) data, using a neural network model (420) trained using ultrasound time-series data (402) and/or EHG data as input data (404) and time-series tocodynamometer (toco) data as ground truth data (405). After training, the trained UA detection model (430) may be used to detect a timing, duration, and intensity of uterine contractions in new patients with more accuracy than the toco. An output of the trained UA detection model (430) may also be used to train a UA prediction model (470) to predict a next uterine contraction (1210) based on a series of preceding uterine contractions. As a result, the uterine contractions may be detected and/or predicted during electronic fetal monitoring (EFM) without the use of an additional toco device, reducing a cost of the EFM and a number of sensing devices relied on for the EFM.

Systems are provided for automating bi-plane ultrasound imaging. In one example, an ultrasound imaging system (100) includes a processing circuit (114) having a processor (116) coupled to a memory device (118) storing instructions thereon that, when executed, cause the processing circuit (114) to perform operations. The operations include receiving a first image dataset obtained by an ultrasound probe (106) along two or more planes of a first orientation in a field of view; identifying at least one secondary anatomical feature based on the first image dataset; determining an additional plane oriented according to the at least one secondary anatomical feature in the field of view; automatically aligning a scanning plane of the ultrasound probe (106) with the additional plane; receiving second image data obtained by the ultrasound probe (106) along the additional plane; and displaying a bi-plane image, the bi-plane image based on an image from the first image dataset and the second image data.

A system for predicting a characteristic of a neonate, the system including a ballistographic monitoring device configured to measure movement of the neonate and create a ballistographic signal from the measured movement, a vital measurement device configured to measure a vitals measurement of the neonate and create a vital signal from the vitals measurement, a camera configured to capture an image of the neonate and create a camera signal from the image, a memory including instructions, and at least one processor to execute the instructions to extract a first feature from the ballistographic signal, extract a second feature from the vital signal, extract a third feature from the camera signal, process the first feature, the second feature, and the third feature using a learning model trained to generate a prediction for a characteristic of the neonate, and display the prediction from the learning model on a user interface.

Techniques for predicting and recommending the best medical imaging device for fulling an order are presented. A system receives an order requesting performance of a medical imaging exam on a patient, the order comprising information identifying a modality, a clinical indication and an anatomical region for the exam. The system identifies different medical imaging devices capable of performing the exam based on the modality, and employs one or more first machine learning processes to estimate measures of quality of the exam capable of being generated by the different medical imaging devices based on the order information and historical information regarding historical medical imaging exams performed by the different medical imaging devices that satisfy the order information. The system selects a subset of the different medical imaging devices to recommend for fulfilling the order based on respective measures of quality for the subset satisfying a quality criterion.

A neonatal care system includes a scale having multiple load cells for measuring weight, multiple weight elements having predetermined weights, multiple actuators, a processing device, and a memory storage device. Each of load cells supports one or more of the predetermined weights. The actuators are configured to raise a platform supporting an infant off of the scale, and lower the platform onto the scale. The memory storage device includes instructions executable by the processing device to direct the actuators to raise the platform off of the scale, determine measured weights from the load cells, and determine a drift of each of the load cells by determining a difference between each of the predetermined weights and each of the measured weights.

A tocodynamometer (toco) has a housing configured to be maintained against the abdominal skin of the maternal patient, wherein the housing forms a sealed cavity. A sensing membrane is on a front side of the housing, wherein the sensing membrane is configured to be in contact with the abdominal skin and to deform inward during uterine contractions of the maternal patient. A sensor is located in the sealed cavity of the housing and configured to provide an output based on the inward deformation of the sensing membrane. A processor is within the sealed cavity and configured to receive the output of the sensor and to generate a uterine activity value based thereon. A pressure diffusing membrane is on at least one side of the housing and is configured to expand outward when the sensing membrane deforms inward to mitigate pressure increase within the sealed cavity.

A system can comprise a memory that can store computer executable components. The system can further comprise a processor that can execute at least one of the computer executable components. The computer executable components can comprise a data ingestion component that receives operational data associated with a plurality of healthcare entities; a pressure modeling component that calculates real-time pressure scores for the healthcare entities; a forecasting component that applies an artificial intelligence model to forecast pressure scores for the healthcare entities; a scoring component that assigns pressure levels to healthcare entities; an action recommendation component that identifies one or more prescriptive actions for reducing or preventing forecasted pressure; and a user interface component that displays a graphical interface comprising a pressure forecast visualization, a hot spot summary, and one or more selectable actions.

A computer-implemented method includes obtaining an image of one or more anatomical vessels of a subject (1202), wherein the image is a segmentation of the one or more anatomical vessels from image data acquired with a three-dimensional medical imaging modality. The computer-implemented method further includes obtaining one or more segmentations of plaque in the one or more anatomical vessels of the subject (1204). The computer-implemented method further includes obtaining Fractional Flow Reserve (FFR) information for the one or more anatomical vessels of the subject (1206). The computer-implemented method further includes generating a composite rendering that includes the image of one or more anatomical vessels, at least one of the one or more segmentations of plaque, and the FFR information (1208). The computer-implemented method further includes displaying the composite rendering in a single viewport.

A system is configured to perform actions including obtaining a first 3D medical image from a first medical imaging volume acquisition and a second 3D medical image from a second medical imaging volume acquisition, wherein the first and second medical imaging volume acquisitions are integrally registered to each other. The actions include receiving a selection of a region of interest in the second 3D medical image and performing gradient domain fusion utilizing blending of respective pixel intensities between the region of interest selected in the second 3D medical image and a region in the first 3D medical image corresponding to the region of interest to generate a blended region of interest. The actions include displaying, on a user interface, the first 3D medical image in a first viewport and the blended region of interest in a second viewport located at the region in the first 3D medical image.

A medical imaging system includes a gantry including a bore extending through the gantry. The medical imaging system further includes a table configured to support a subject moving through the bore. The medical imaging system further includes at least one sensor disposed on the table and configured to sense a total weight of a load on the table at two or more different measurement points. The medical imaging system further includes camera configured to generate an image of the table including the subject. The medical imaging system further includes a processor configured to determine a weight of the subject on the table based on at least one signal from the at least one sensor and a second signal from the camera.

Systems and methods for network path selection are herein provided. In one example, a method comprises determining, for each device of one or more devices, connection quality indicators (CQIs) for one or more available network connection paths; and connecting each device to a server via a respective network connection path with a highest CQI of the one or more available network connection paths.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Various methods and systems are provided for an imaging subject support system for an imaging system (100,1102). The imaging subject support system may be a cradle clamping holder (300) comprising: a platform (302); at least one leveling member (322b, 322a), each of which includes at least one rod (324); a coupling clamp (340) that is coupled to the platform (302) at a first end (392) of the platform (302), and where the coupling clamp (340) is adjustable between a first position and a second position; and an attachment plate (330) configured to support an imaging subject, the attachment plate (330) directly or indirectly coupled to the platform (302) at a second end (396) of the platform (302), opposite the first end (392).

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …