Abstract: A system and method for dynamically adjusting imaging parameters during an ultrasound scan is provided. The method includes acquiring regular ultrasound image frames based on a first set of imaging parameters and displaying the regular frames at a display system. The method includes intermittently acquiring a test ultrasound image frame based on a second set of imaging parameters having at least one imaging parameter that is different from the first set of imaging parameters. The test frame is not displayed. The method includes determining a regular frame image quality of at least one of the regular frames and a test frame image quality of the test frame. The method includes applying, in response to determining the test frame image quality exceeds the regular frame image quality, the second set of imaging parameters to acquire additional regular frames and displaying the additional regular frames at the display system.

Abstract: Techniques are described for generating reformatted views of a three-dimensional (3D) anatomy scan using deep-learning estimated scan prescription masks. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a mask generation component that employs a pre-trained neural network model to generate masks for different anatomical landmarks depicted in one or more calibration images captured of an anatomical region of a patient. The computer executable components further comprise a reformatting component that reformats 3D image data captured of the anatomical region of the patient using the masks to generate different representations of the 3D image data that correspond to the different anatomical landmarks.

Abstract: A system and method for providing an anatomic orientation indicator with a patient-specific model of an anatomical structure of interest extracted from a three-dimensional (3D) ultrasound volume is provided. The method includes extracting the anatomical structure of interest from the 3D volume and generating a patient-specific model of the anatomical structure of interest. The method includes generating an anatomic orientation indicator including at least one mocked patient anatomy model of an anatomical structure adjacent the anatomical structure of interest at a position and orientation relative the patient-specific model. The method includes displaying the anatomic orientation indicator with the patient-specific model at a same first point of view. The method includes receiving an instruction to change a point of view of the patient-specific model to a second point of view and updating the displaying of the anatomic orientation indicator with the patient-specific model to the second point of view.

Abstract: Systems and methods for tissue specific time gain compensation of an ultrasound image are provided. The method comprises acquiring an ultrasound image of a subject and displaying the ultrasound image over a console. The method further comprises selecting by a user a region within the ultrasound image that requires time gain compensation. The method further comprises carrying out time gain compensation of the user selected region of the ultrasound image. The method further comprises identifying a region having a similar texture to the user selected region and carrying out time gain compensation of the user selected region by an artificial intelligence (AI) based deep learning module.

Abstract: Various methods and systems are provided for stationary CT imaging. In one embodiment, a modular imaging system comprises a plurality of distributed x-ray units releasably coupled to a plurality of detector arrays, with the plurality of distributed x-ray units and the plurality of detector arrays forming a self-supporting structure including a central opening shaped to receive a subject to be imaged. The modular imaging system may image the subject without rotation of the distributed x-ray units or detector arrays around the subject.

Abstract: Systems and methods are provided for quantifying uncertainty of segmentation mask predictions made by machine learning models, where the uncertainty may be used to streamline an anatomical measurement workflow by automatically identifying less certain caliper placements. In one example, the current disclosure teaches receiving an image including a region of interest, determining a segmentation mask for the region of interest using a trained machine learning model, placing a caliper at a position within the image based on the segmentation mask, determining an uncertainty of the position of the caliper, and responding to the uncertainty of the position of the caliper being greater than a pre-determined threshold by displaying a visual indication of the position of the caliper via a display device and prompting a user to confirm or edit the position of the caliper.

Abstract: A method for determining a lesion location in a patient for biopsy along X, Y, and Z axes. The method includes positioning the patient in an examination device to collect examination images showing the lesion. The method includes positioning the patient in a biopsy device configured for holding the patient during the biopsy and collecting a biopsy image of the patient using the biopsy device. The method includes analyzing the biopsy image to determine a measured x-coordinate and a measured y-coordinate of the lesion along the X and Y axes, respectively, analyzing the examination images to determine a calculated z-coordinate along the Z axis of the lesion, and determining the location of the lesion based on the measured x-coordinate and the measured y-coordinate from the biopsy image and the calculated z-coordinate determined from the one or more examination images.

Abstract: Embodiments of the present application provide a magnetic resonance system and a shimming method and an imaging method thereof. The shimming method comprises: performing a scout scan on a subject to be examined, and obtaining phase data of a plurality of slice positions; determining three-dimensional space static magnetic field information according to the phase data of the plurality of slice positions; and determining a shimming value of a slice in a region of interest according to the three-dimensional space static magnetic field information.

Abstract: Methods and systems are provided for adaptive scan control. In one embodiment, a method for an imaging system includes performing, with the imaging system, a first contrast scan of a subject including injection of a contrast agent to the subject; processing projection data of the subject acquired during the first contrast scan to measure a contrast signal of the subject at a monitoring area; estimating a target acquisition timing for a first acquisition of a second contrast scan of the subject based on the contrast signal; and performing, with the imaging system, the second contrast scan of the subject, with the first acquisition performed at the target acquisition timing and without performing any monitoring scans between the first contrast scan and the second contrast scan.

Abstract: In the present invention, a right leg drive RLD monitoring system is employed on a medical computing system/computer, such as an ECG, HEMO and/or EP monitoring, mapping and/or recording system, that includes a number of RLD circuits to be utilized for different procedures or monitoring states to be performed using the system. The RLD monitoring system operates to actively monitor and/or record the feedback voltage to the RLD isolated from the patient. Using the measured feedback voltage data, the RLD monitoring system can identify and determine if the RLD circuit in use is approaching saturation, has reached saturation and the duration the RLD circuit was in saturation. The RLD monitoring system can concurrently and/or subsequently select and/or provide selection information regarding an optimal RLD circuit to be utilized to most effectively perform the desired function of the RLD in the procedure being performed using the monitoring, mapping and/or recording system.

Abstract: A method of manufacturing a lead assembly of a cryogenic system is provided. The method includes developing a three-dimensional (3D) model of a heat exchanger. The heat exchanger includes a plurality of channels extending longitudinally through the heat exchanger from the first end to the second end, the plurality of channels forming a plurality of thermal surfaces within the heat exchanger, the heat exchanger having a transverse cross section. The method further includes modifying the 3D model by at least one of reducing an area of the cross section and increasing the plurality of thermal surfaces. The method also includes additively manufacturing the heat exchanger using an electrically-conductive and thermally-conductive material according to the modified 3D model. Further, the method includes providing a high temperature superconductor (HTS) assembly that includes an HTS strip, and connecting the HTS assembly to the heat exchanger at the second end of the heat exchanger.

Abstract: A connector for connecting with an absorber canister includes a first connection port for detachably communicating with an input port of the absorber canister; a second connection port for detachably communicating with an output port of the absorber canister; and a seal. The seal being sleeved on a sidewall of at least one connection port of the first connection port and the second connection port, and the seal including: an annular ring positioned on an outer sidewall of the at least one connection port; a guide chamfer portion, the guide chamfer portion being annular and extending obliquely from a bottom of the annular ring towards an interior of the at least one connection port; and a lip, the lip being annular and extending from an end portion of the guide chamfer portion in a direction towards or away from the annular ring.

Abstract: A method for making a container for retaining anesthetic agent. The method includes creating two or more parts each having a mating surface, where the container is formed when the mating surfaces of the two or more parts are coupled together, and where a first part of the two or more parts is formed of a material having pores defined within the mating surface thereof. The method further includes processing the mating surface of the first part via friction stir welding to reduce the pores defined therein. The method further includes coupling the two or more parts together such that the mating surfaces contact to create the container configured to retain the anesthetic agent therein.

Abstract: This disclosure proposes to speed up computation time of a convolutional neural network (CNN) by leveraging information specific to a pre-defined region, such as a breast in mammography and tomosynthesis data. In an exemplary embodiment, a method for an image processing system is provided, comprising, generating an output of a trained convolutional neural network (CNN) of the image processing system based on an input image, including a pre-defined region of the input image as an additional input into at least one of a convolutional layer and a fully connected layer of the CNN to limit computations to input image data inside the pre-defined region; and storing the output and/or displaying the output on a display device.

Abstract: A magnetic resonance (MR) imaging acceleration method is provided. The method includes applying, by an MR system, a pulse sequence having a k-space trajectory of a plurality of blades being rotated in k-space, each blade including a plurality of views, wherein the k-space trajectory has an undersampling pattern in the k-space. The method also includes receiving k-space data of a subject acquired by the pulse sequence, reconstructing MR images of the subject based on the k-space data using compressed sensing, and outputting the reconstructed images.

Abstract: Systems and methods are provided for simulating medical images based on previously acquired data and a defined imaging protocol. In an example, a method includes generating a simulated medical image of a patient via virtual imaging based on previously obtained medical images and a scan intent of the virtual imaging, and outputting an imaging protocol based on a virtual protocol of the virtual imaging.

Abstract: Techniques are described for performing active surveillance and learning for machine learning (ML) model authoring and deployment workflows. In an embodiment, a method comprises applying, by a system comprising a processor, a primary ML model trained on a training dataset to data samples excluded from the training dataset to generate inferences based on the data samples. The method further comprises employing, by the system, one or more active surveillance techniques to regulate performance of the primary ML model in association with the applying, wherein the one or more active surveillance techniques comprise at least one of, performing a model scope evaluation of the primary ML model relative to the data samples or using a domain adapted version of the primary ML model to generate the inferences.

Abstract: The present disclosure relates to a method, a system, and a storage medium for segmenting a lung image. The method for segmenting a lung image comprises: obtaining medical image data containing a lung region; performing lung lobe segmentation on the medical image data to generate a plurality of lung lobe data subsets; generating updated lung image data based on one or a plurality of lung lobe data subsets in the plurality of lung lobe data subsets; and performing nidus segmentation on the updated lung image data to generate a segmentation image that identifies a pneumonia nidus.

Abstract: Methods and systems are provided for an oxygen sensor included in a medical gas flow device, such as an anesthesia machine. In one embodiment, a method for a medical gas flow device comprises tracking an output voltage of an oxygen sensor during calibration over time, and, responsive to the output voltage decreasing by at least threshold amount from an initial calibration output voltage, estimating an end-of-life date of the oxygen sensor and outputting a replacement notification.