GE Precision Healthcare

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.

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

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.

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 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.

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.