Abstract: Methods and apparatuses for performing automated detection of lung slide using a computing device (e.g., an ultrasound system, etc.) are disclosed. In some embodiments, the techniques determine lung sliding using one or more neural networks. In some embodiments, the neural networks are part of a process that determines probabilities of the lung sliding at one or more M-lines. In some embodiments, the techniques display one or more probabilities of lung sliding in a B-mode ultrasound image.

Abstract: Systems and methods of transmitting heat out a medical imaging device are disclosed herein. In one embodiment, a medical imaging device includes a housing having electronics and a heat sink. The heat sink is positioned near a first end of the housing, a groove that is configured to receive at least a portion of an operator's hand is positioned at a second end of the housing. A heat pipe in the housing extends from the electronics toward the first end of the housing and is configured to transfer heat produced by the electronics toward the heat sink and away from the groove.

Abstract: Systems and methods for simultaneous acquisition of pulsed-wave Doppler and color Doppler for retrospective analysis of cardiovascular function are disclosed. In aspects, imaging techniques are used for acquisition of raw partly processed ultrasound data. The ultrasound data is stored in its raw form, synchronized with a simultaneously acquired physiological signal. The stored ultrasound data can then be accessed and processed according to pulsed-wave Doppler and color Doppler imaging techniques to provide both a full frame, or sequence of frames of color Doppler images and a post-acquisition pulsed-wave Doppler signal of a sample volume at one or more locations within the acquisition area using the color Doppler image. Such locations can be selected automatically or by a user, and a pulsed-wave spectrum for the selected location is displayed. As the user moves the sample volume around, the pulsed-wave spectral data is recomputed and redisplayed.

Abstract: In one embodiment, an ultrasound imaging system is configured to receive a set of ultrasound images of a target anatomical region. The set of ultrasound images is combined to create a composite tissue frame. The ultrasound imaging system determines whether an interventional instrument is present within the ultrasound images based on a set of trained classification algorithms based on the set of ultrasound images and the composite tissue frame. If an interventional instrument is detected, the ultrasound imaging system further determines whether an additional ultrasound frame should be captured to image the interventional instrument, and the steer angle to be used for the additional ultrasound image. The ultrasound imaging system determines a linear structure corresponding to the interventional instrument, and creates a blended image showing the interventional instrument and the composite tissue frame.

Abstract: A compound acoustic lens, an ultrasound probe and a medical device that includes the same are described. In some embodiments, a compound acoustic lens for an ultrasound probe includes an outer lens including a first material of a first thickness, and an inner lens mated to the outer lens. The inner lens includes a second material of a second thickness. The overall thickness of the compound acoustic lens is determined as a sum of the first thickness and the second thickness and is less than a thickness of a single-material lens having a same focal length as the compound acoustic lens.

Abstract: Examples herein include methods, systems, and computer program products for utilizing neural networks in ultrasound systems. The methods include processor(s) of a computing device identifying a neural network for implementation on the computing device to generate, based on ultrasound data, inferences and confidence levels for the inferences, the computing device being communicatively coupled via a computing network to an ultrasound machine configured to generate the ultrasound data. The processor(s) implements the neural network on the computing device, including configuring the neural network to generate an inference and a confidence level for at least one image of the images. The processor(s) obtains the ultrasound data including images from the ultrasound machine. The processor(s) determines, for the at least one image, an accuracy of the inference and the confidence level. The processor(s) automatically reconfigures the neural network to increase the accuracy based on the determining the accuracy.

Abstract: In one embodiment, a method is provided. The method includes transmitting a set of ultrasound waves to towards a target area. The set of ultrasound waves are transmitted by a set of ultrasound elements. The set of ultrasound elements are positioned at different locations in a transducer assembly. The method also includes receiving a set of reflections of the set of ultrasound waves. The set of reflections of the set of ultrasound waves are received by the set of ultrasound elements. The method further includes determining a set of correction values for the set of ultrasound elements. Each correction value of the set of correction values represents a refraction of one reflection of the set of reflections as the one reflection passes through a respective ultrasound element of the set of ultrasound elements. The method further includes generating imaging data based on the set of reflections of the set of ultrasound waves and the set of correction values for the set of ultrasound elements.

Abstract: An ultrasound imaging system computes real time physiological parameters from measurements of anatomical features in ultrasound image data using a neural network to identify the location of the anatomical features. In one embodiment, cardiac parameters are computed from endocardial wall tracings in M-mode ultrasound image data that are identified by the neural network.

Abstract: Systems and methods for microvasculature imaging acquisition are disclosed. In aspects, a full frame corresponding to a field of view of an ultrasound scanner is divided into small portions, each of which is individually scanned for a desired period of time at a higher frame rate than the ultrasound scanner is capable of using to scan the full frame. These ultrasound data acquisition techniques enable super-resolution image processing or high-sensitivity microvascular-doppler image processing to be used to track low-intensity, slow-flow microvasculature of an anatomy of a subject.

Abstract: Ultrasound imaging systems for automatically identifying and saving ultrasound images relevant to a needle injection procedure, and associated systems and methods, are described herein. For example, an ultrasound imaging system includes a transducer for transmitting/receiving ultrasound signals during a needle injection procedure, and receive circuitry configured to convert the received ultrasound signals into ultrasound image data. The image data can be stored in a buffer memory. A processor can analyze the image data stored in the buffer memory to identify image data that depicts a specified injection event of the needle injection procedure, and the identified image data can be stored in a memory for archival purposes.

Abstract: Systems and methods for a virtual sonography team are described. An ultrasound system includes an ultrasound scanner that is configured to generate ultrasound data based on reflections of ultrasound signals transmitted by the ultrasound scanner and communicate the ultrasound data over a communication network to at least one display device and an archiver. An ultrasound machine is coupled to the ultrasound scanner and is configured to determine examination data for the ultrasound examination and communicate the examination data to the archiver over the communication network. The display device is configured to generate an ultrasound image based on the ultrasound data as part of an ultrasound examination and communicate the ultrasound image to the archiver for aggregation with the examination data into a patient record of the ultrasound examination.

Abstract: In one embodiment, a method is provided. The method includes transmitting a first set of ultrasound waves to determine whether there is fluid flow at a target area. The first set of ultrasound waves are transmitted at a first pulse repetition frequency. The method also includes determining whether there is fluid flow in a second area based on the first set of ultrasound waves. The second area is between the target area and an ultrasound probe. The method further includes transmitting a second set of ultrasound waves to detect fluid flow at the target area in response to determining that there is fluid flow in the second area between the target area and the ultrasound probe. The second set of ultrasound waves are directed towards the target area. The second set of ultrasound waves are transmitted at a second pulse repetition frequency.

Abstract: An ultrasound imaging system including an image processor configured to receive input data for capturing ultrasound images of a region of interest. The ultrasound images are taken along a first plane; and the input data further includes an indication that a needle will be inserted into the region of interest. The system can capture a plurality of ultrasound images of the region of interest along the first plane. The system can determine one or more high-confidence areas of the region of interest where the needle will intersect the first plane. Each high-confidence area is based on a probability that the needle will intersect the first plane at any portion of the high-confidence area; and display one or more on-screen markers corresponding to the one or more high-confidence areas in conjunction with the plurality of ultrasound images on the display.

Abstract: Systems and methods for noise reduction in ultrasound images are described. These systems and methods include a noise-reduction system that provides a tensor-based approach that mitigates effects of noise processes on ultrasound images and produces “preprocessed” ultrasound images having consistent characteristics, which increases the accuracy and effectiveness of further processing (e.g., via detection and/or segmentation algorithms) of the ultrasound images. In aspects, these techniques enable neural networks, coupled to the noise-reduction system, to generate consistent inferences across different ultrasound images, thereby enhancing a workflow and user experience of an ultrasound operator. Using these techniques further enables the neural networks to be trained with fewer training images, saving time and monetary costs without sacrificing accuracy.

Abstract: Planar phased ultrasound transducer including a first layer including a sheet of piezoelectric material, a piezo frame surrounding an outer perimeter of the sheet of piezoelectric material, and an epoxy material placed between the piezo frame and the sheet of piezoelectric material. The transducer includes a flex frame secured to a back side of the first layer.

Abstract: Systems and methods to detect electromagnetic (EM) emissions on ultrasound systems are described. In some embodiments, an ultrasound system includes an ultrasound scanner that is configured to generate ultrasound data based on reflections of ultrasound signals transmitted by the ultrasound scanner. An ultrasound machine is coupled to the ultrasound scanner and configured to generate an ultrasound image based on the ultrasound data. A circuit is coupled to the ultrasound machine and configured to make a determination whether the ultrasound image is corrupted by a noise process.

Abstract: An ultrasound imaging system computes real time physiological parameters from measurements of anatomical features in ultrasound image data using a neural network to identify the location of the anatomical features. In one embodiment, cardiac parameters are computed from endocardial wall tracings in M-mode ultrasound image data that are identified by the neural network.

Abstract: Systems and methods for an ultrasound scanner with an impact-resistance system are described. In some implementations, the impact-resistance system reduces acceleration components associated with an impact force applied to an enclosure of the ultrasound scanner or directly to an acoustic lens of a transducer array of the ultrasound scanner. The impact-resistance system distributes the acceleration components from the transducer array to the enclosure via couplings with soft and elastic materials. Some of the couplings may be located between the enclosure and elongated members embedded in backing material of the transducer array. Some of the couplings may be located between the enclosure and a flange that extends from the acoustic lens into a channel in the enclosure. Implementing the impact-resistance system described herein improves reliability of the transducer array without sacrificing performance or usability, particularly for ultraportable scanners.

Abstract: Ultrasound imaging systems for automatically adjusting settings according to an position and/or orientation of one or more interfaces. The ultrasound imaging systems can include a probe configured to send and receive ultrasound signals for performing a medical exam, a medical procedure, or both; and a processor configured to: select a diagnostics mode or a procedural mode based on an operating orientation of the ultrasound imaging system or a portion thereof, and adjust one or more settings of the imaging system according to the selected diagnostics mode or the selected procedural mode.

Abstract: The disclosed technology features methods for the manufacture of electrical components such as ultrasound transducers. In particular, the disclosed technology provides methods of patterning electrodes, e.g. in the connection of an ultrasound transducer to an electrical circuit; methods of depositing metal on surfaces; and methods of making integrated matching layers for an ultrasound transducer. The disclosed technology also features ultrasound transducers produced by the methods described herein.