Embodiments of the present disclosure are directed to a vessel-wall-monitoring device (100) and a method for identifying the walls of blood vessel in a body. The method includes receiving, by the vessel-wall-monitoring device (100), a plurality of ultrasound echo signals from a transducer, wherein the plurality of ultrasound echo signals are transmitted to the transducer from locations of the blood vessel, extracting at least two consecutive ultrasound frames from the plurality of ultrasound echo signals, determining a shift between the at least two consecutive ultrasound frames by comparing samples of the at least two consecutive ultrasound frames, and identifying, a proximal wall and a distal wall of the blood vessel based on the shift between the at least two consecutive ultrasound frames.

A neural network is trained for estimating patient hemodynamic data using a plurality of extravascular imaging data sets and a plurality of intravascular imaging data sets that are each co-registered to a corresponding extravascular imaging data set. A plurality of hemodynamic data sets are provided, each hemodynamic data set co-registered with the corresponding extravascular imaging data set. The neural network learns what hemodynamic data to expect for a given intravascular imaging data set. An intravascular imaging event is subsequently performed in which an intravascular imaging element is translated within a blood vessel of the patient to produce one or more intravascular images. The neural network uses its training to predict hemodynamic values corresponding to the one or more intravascular images from the intravascular imaging event, and the one or more intravascular images are outputted in combination with the predicted hemodynamic values.

An ultrasonic diagnosis system according to an embodiment of the present disclosure includes a plurality of ultrasonic output patches configured to be attachable to different body parts, a data receiving unit configured to receive data transmitted from the plurality of ultrasonic output patches, a processing unit configured to acquire an imaging result related to the body part by processing the data, and an output unit configured to output the imaging result related to the body part, in which the ultrasonic output patch includes a multichannel ultrasonic transducer array configured to output imaging ultrasonic waves toward the body part and receive the reflected ultrasonic waves, a signal processing module configured to process a signal transmitted to or received from the multichannel ultrasonic transducer array, and a communication module configured to transmit a signal processing result, which is acquired by the signal processing module, to the data receiving unit.

Aspects of the technology described herein relate to wirelessly offloading, from a wearable ultrasound device, ultrasound data sufficient for forming one or more ultrasound images therefrom. The wearable ultrasound device may include an ultrasound patch. Indications that may be monitored with such a device, and therapeutic uses that may be provided by such a device, are also described. Methods and apparatuses are also described for compounding multilines of ultrasound data on an ultrasound device configured to collect the ultrasound data. Additionally, certain aspects of the technology relate to non-uniform grouping of ultrasound transducers that share a transmit/receive circuit in an ultrasound device.

The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.

Aspects of the disclosure provide for methods, systems, and apparatuses, including computer-readable storage media, for lipid detection by identifying fibrotic caps in medical images of blood vessels. A method includes receiving one or more input images of a blood vessel and processing the one or more input images using a machine learning model trained to identify locations of fibrotic caps in blood vessels. The machine learning model is trained using a plurality of training images each annotated with locations of one or more fibrotic caps. A method includes identifying and characterizing fibrotic caps of lipid pools based on differences in radial signal intensities measured at different locations of an input image. A system can generate one or more output images having segments that are visually annotated representing predicted locations of fibrotic caps covering lipidic plaques.

A system for visualization and quantification of ultrasound imaging data according to embodiments of the present disclosure may include a display unit, and a processor communicatively coupled to the display unit and to an ultrasound imaging apparatus for generating an image from ultrasound data representative of a bodily structure and fluid flowing within the bodily structure. The processor may be configured to estimate axial and lateral velocity components of the fluid flowing within the bodily structure, determine a plurality of flow directions within the image based on the axial and lateral velocity components, differentially encode the flow directions based on flow direction angle to generate a flow direction map, and cause the display unit to concurrently display the image including the bodily structure overlaid with the flow direction map.

For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. The machine-learnt multi-task generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. The machine-learnt multi-task generator is trained to output both the 3D segmentation and a complete volume. The 3D segmentation may be used to project to 2D as an input with an ICE image to another network trained to output a 2D segmentation for the ICE image. Display of the 3D segmentation and/or 2D segmentation may guide ablation of tissue in the patient.

The invention provides for a method and an apparatus (300) for positioning an ultrasound patch on a surface of a subject. The apparatus includes a first fixing unit (210) and a second fixing unit (310) adapted to be fixed to a surface of the subject at a first location and second location, respectively, with a space of exposed surface of the subject between them. The apparatus further comprises a holding unit (260) for positioning on the exposed surface of the subject within the space between the fixing units, the holding unit being adapted to receive the ultrasound patch. The holding unit is adapted to be coupled with the first and second fixing units at the surface of the subject and, when the holding unit is coupled to the first fixing unit and the second fixing unit, the position of the holding unit is adjustable relative to the first fixing unit and the second fixing unit.

A transducer array for ultrasound applications includes a plurality of transducer elements that are provided with self-aligned connections to a flexible cable. The array is easy to manufacture and suited for wearable, wireless, and other small ultrasound devices. A simple and efficient method of producing a robust transducer array involves at least partially separating the transducer elements after their connection to their respective conductors.