Abstract: By example, a method for training a model to segment test images, wherein the test images comprise ultrasound image data, includes: receiving, at a self-supervised learning framework, a first plurality of training images, wherein the first plurality of training images include ultrasound data corresponding to patients' livers; processing the first plurality of plurality of training images with a learning algorithm of the self-supervised learning framework, and responsively adapting a trained model; and receiving, at a supervised learning framework, the trained model and a second plurality of training images, wherein the second plurality of training images include ultrasound data corresponding to patients' livers and annotations of the livers, and responsively adapting the trained model.

Abstract: By example, a method includes: receiving ultrasound image data of a patient, including a segmented region corresponding to a liver; automatically identifying an area for a region of interest within the segmented region, wherein the region of interest corresponds to a region in the liver for performing shear-wave elastography; and presenting, on a display, the ultrasound image data and the area for the region of interest.

Abstract: A wearable device for non-invasive monitoring of intracranial pressure includes a wearable structure configured to be secured to a head of a user; an ultrasound transducer positioned to align with an eye of the user when worn; a motorized control mechanism that dynamically adjusts a position and angulation of the ultrasound transducer; a fluid management system that maintains an acoustic coupling between the ultrasound transducer and the eye of the user; an integrated air vent system to regulate pressure, prevent condensation, and maintain imaging quality within the wearable structure; and a processor coupled to the ultrasound transducer. The processor is to employ a reinforcement learning-based control system for optimizing transducer placement; acquire ultrasound images of an optic nerve sheath; analyze the ultrasound images to measure an optic nerve sheath diameter (ONSD); and determine a likelihood of elevated intracranial pressure based on the measured ONSD.

Abstract: Described here are systems and method for using ultrasound to localize a medical device to which an active ultrasound element that can transmits ultrasound energy is attached. Doppler signal data of the medical device are acquired while the active element is transmitting acoustic energy, and the Doppler signal data are processed to detect symmetric Doppler shifts associated with the active element. The systems and methods described in the present disclosure enable tracking and display of one or more locations on or associated with the medical device.

Abstract: Systems and methods for reconstructing, estimating, or otherwise generating unacquired, undetected, unreconstructed, or otherwise unknown ultrasound data using machine learning algorithms are provided. Thus, the systems and methods described in the present disclosure provide for generating unacquired, undetected, unreconstructed, or otherwise unknown data that are not actually and physically acquired with an ultrasound transducer and/or front-end receiver of an ultrasound system.

Abstract: By example, a method includes: receiving ultrasound image data of a patient, including a segmented region corresponding to a liver; automatically identifying an area for a region of interest within the segmented region, wherein the region of interest corresponds to a region in the liver for performing shear-wave elastography; and presenting, on a display, the ultrasound image data and the area for the region of interest.

Abstract: By example, a method for training a model to segment test images, wherein the test images comprise ultrasound image data, includes: receiving, at a self-supervised learning framework, a first plurality of training images, wherein the first plurality of training images include ultrasound data corresponding to patients' livers; processing the first plurality of plurality of training images with a learning algorithm of the self-supervised learning framework, and responsively adapting a trained model; and receiving, at a supervised learning framework, the trained model and a second plurality of training images, wherein the second plurality of training images include ultrasound data corresponding to patients' livers and annotations of the livers, and responsively adapting the trained model.

Abstract: Systems and methods for transmitting non-diffracting acoustic beams are presented herein. In one example, a method for transmitting a non-diffracting acoustic beam with an ultrasound transducer that includes a plurality of transducer elements includes determining a transmit delay function and a transmit apodization function for the ultrasound transducer based on a target axial pressure profile for the acoustic beam for a given configuration of the ultrasound transducer and controlling the ultrasound transducer to transmit the acoustic beam by sending electrical signals to the plurality of transducer elements based on the transmit delay function and the transmit apodization function.

Abstract: A system and method for automatically estimating a hepatorenal index (HRI) from ultrasound images s provided. The method includes acquiring a sequence of ultrasound image data until a desired ultrasound image view is obtained. The method includes segmenting, a liver and a renal cortex in the obtained ultrasound image view. The method includes identifying valid samples in the liver and the renal cortex in the obtained ultrasound image view by excluding invalid samples. The method includes automatically positioning a liver region of interest and a renal cortex region of interest in the obtained ultrasound image view based on the valid samples and at least one criterion. The method includes determining an HRI and causing a display system to present the HRI.

Abstract: Described here are systems and method for using ultrasound to localize a medical device to which an active ultrasound element that can transmits ultrasound energy is attached. Doppler signal data of the medical device are acquired while the active element is transmitting acoustic energy, and the Doppler signal data are processed to detect symmetric Doppler shifts associated with the active element. The systems and methods described in the present disclosure enable tracking and display of one or more locations on or associated with the medical device.

Abstract: Described here are systems and method for using ultrasound to localize a medical device to which an active ultrasound element that can transmits ultrasound energy is attached. Doppler signal data of the medical device are acquired while the active element is transmitting acoustic energy, and the Doppler signal data are processed to detect symmetric Doppler shifts associated with the active element. The systems and methods described in the present disclosure enable tracking and display of one or more locations on or associated with the medical device.

Abstract: A system and method for automatically estimating a hepatorenal index (HRI) from ultrasound images s provided. The method includes acquiring a sequence of ultrasound image data until a desired ultrasound image view is obtained. The method includes segmenting, a liver and a renal cortex in the obtained ultrasound image view. The method includes identifying valid samples in the liver and the renal cortex in the obtained ultrasound image view by excluding invalid samples. The method includes automatically positioning a liver region of interest and a renal cortex region of interest in the obtained ultrasound image view based on the valid samples and at least one criterion. The method includes determining an HRI and causing a display system to present the HRI.

Abstract: Systems and methods for reconstructing, estimating, or otherwise generating unacquired, undetected, unreconstructed, or otherwise unknown ultrasound data using machine learning algorithms are provided. Thus, the systems and methods described in the present disclosure provide for generating unacquired, undetected, unreconstructed, or otherwise unknown data that are not actually and physically acquired with an ultrasound transducer and/or front-end receiver of an ultrasound system.

Abstract: Described here are systems and method for using ultrasound to localize a medical device to which an active ultrasound element that can transmits ultrasound energy is attached. Doppler signal data of the medical device are acquired while the active element is transmitting acoustic energy, and the Doppler signal data are processed to detect symmetric Doppler shifts associated with the active element. The systems and methods described in the present disclosure enable tracking and display of one or more locations on or associated with the medical device.