公开(公告)号：US20210022707A1

公开(公告)日：2021-01-28

申请号：US17067139

申请日：2020-10-09

Applicant: eXo Imaging, Inc.

Inventor： Yusuf Haque ,  Sandeep Akkaraju ,  Janusz Bryzek

IPC: A61B8/00 ,  B06B1/06 ,  G01S7/52 ,  H01L41/09 ,  A61B8/08 ,  A61B8/14 ,  B06B1/02 ,  G01S7/521 ,  G01S15/89 ,  H01L41/053 ,  H01L41/08

Abstract: An imaging device includes a two dimensional array of piezoelectric elements. Each piezoelectric element includes: a piezoelectric layer; a bottom electrode disposed on a bottom side of the piezoelectric layer and configured to receive a transmit signal during a transmit mode and develop an electrical charge during a receive mode; and a first top electrode disposed on a top side of the piezoelectric layer; and a first conductor, wherein the first top electrodes of a portion of the piezoelectric elements in a first column of the two dimensional array are electrically coupled to the first conductor.

公开(公告)号：US20250044446A1

公开(公告)日：2025-02-06

申请号：US18799921

申请日：2024-08-09

Applicant: Exo Imaging, Inc.

Inventor： Miles WERNICK ,  Sandeep AKKARAJU ,  Drake GUENTHER ,  Kutay ÜSTÜNER ,  Yusuf HAQUE

IPC: G01S15/89 ,  G01S7/52

Abstract: Computer-implemented medical ultrasound imaging methods and systems for performing the methods can be performed using a plurality of frames of an ultrasound image sequence that each having a high image quality to improve the image quality of lower-image-quality frame of the ultrasound image sequence.

公开(公告)号：US20240427014A1

公开(公告)日：2024-12-26

申请号：US18751986

申请日：2024-06-24

Applicant: Exo Imaging, Inc.

Inventor： Yusuf HAQUE ,  Sandeep AKKARAJU ,  Janusz BRYZEK ,  Brian BIRCUMSHAW

IPC: G01S15/89 ,  A61B8/00 ,  A61B8/08 ,  B06B1/06 ,  B81B3/00 ,  G01N29/02 ,  G01N29/04 ,  G01N29/06 ,  G01N29/24 ,  G01N29/26 ,  G01N29/34 ,  G01S7/52 ,  G10K11/34 ,  H10N30/20

Abstract: An imaging device can include a transducer that includes an array of piezoelectric elements formed on a substrate. Each piezoelectric element can include at least one membrane suspended from the substrate, at least one bottom electrode disposed on the membrane, at least one piezoelectric layer disposed on the bottom electrode, and at least one top electrode disposed on the at least one piezoelectric layer. Adjacent piezoelectric elements can be configured to be isolated acoustically from each other. The device is utilized to measure flow or flow along with imaging anatomy.

公开(公告)号：US20240385689A1

公开(公告)日：2024-11-21

申请号：US18319722

申请日：2023-05-18

Applicant: Exo Imaging, Inc.

Inventor： Tony Constantinides

IPC: A61B8/00 ,  G06F3/01

Abstract: An ultrasound imaging system is controlled by pose and/or gesture detection. The system may detect poses or gestures performed by a user, e.g., using a machine learning (ML) model that may include a neural network, and implement a command associated with the detected pose or gesture to control the ultrasound imaging system.

公开(公告)号：US20240385142A1

公开(公告)日：2024-11-21

申请号：US18319706

申请日：2023-05-18

Applicant: Exo Imaging, Inc.

Inventor： Mohammad Afrough ,  Rajeev Sivadasan ,  Jed Davidow ,  Gordon T. Sasamori

IPC: G01N29/06 ,  G01N29/04

Abstract: A visualization of electrical continuity test results for a transducer tile array may be generated according to embodiments herein. The visualization may include an indication, for each channel under test, of whether the channel passed or failed the continuity test, and an indication of whether the transducer tile array is determined to be functional.

公开(公告)号：US20240371288A1

公开(公告)日：2024-11-07

申请号：US18655190

申请日：2024-05-03

Applicant: Exo Imaging, Inc.

Inventor： Saniya SALIM ,  Eric TWARDZICKI ,  Sabina KUGEL ,  Michael PUPO

IPC: G09B5/06 ,  A61B8/00 ,  A61B8/08 ,  G16H40/67

Abstract: A method for providing remote guidance from a skilled resource to a local user during a medical procedure includes transmitting information about the procedure from the local user to the skilled resource and allowing the skilled resource to provide real-time feedback to the local user and/or take remote control of the local user's medical device.

公开(公告)号：US12099150B2

公开(公告)日：2024-09-24

申请号：US17511245

申请日：2021-10-26

Applicant: Exo Imaging, Inc.

Inventor： Liang Wang ,  Yusuf Haque ,  Janusz Bryzek

IPC: B06B1/00 ,  B81B7/00 ,  G01S7/52 ,  G01S15/89

CPC classification number: G01S7/52079 ,  B81B7/008 ,  G01S7/5205 ,  G01S15/8925 ,  B81B2201/0271

Abstract: An ultrasound device for use with various types of imaging. In some embodiments, the ultrasound device may comprise a circuitry substrate and a plurality of transducer chips coupled to the circuitry substrate. In some embodiments, each transducer chip may comprise a microelectromechanical systems (MEMS) component that may include a plurality of ultrasound elements closely packed with one another, an Application-Specific Integrated Circuit (ASIC) that may be operatively coupled to the plurality of ultrasound elements of said MEMS component, and a control unit that may be electrically coupled to each ASIC of the plurality of transducer chips for control thereof. In some embodiments, at least two transducer chips of the plurality of transducer chips may be placed on the circuitry substrate with a separation distance that may be less than an operational wavelength of the ultrasound elements of the MEMS components of said at least two transducer chips.

公开(公告)号：US20240252148A1

公开(公告)日：2024-08-01

申请号：US18609965

申请日：2024-03-19

Applicant: Exo Imaging, Inc.

Inventor： Koosha POURTAHMASI ROSHANDEH ,  Dornoosh ZONOOBI ,  Abhilash RAKKUNEDETH ,  Masood DEHGHAN ,  Jacob JAREMKO

IPC: A61B8/08 ,  G01S15/89 ,  G06N3/02

CPC classification number: A61B8/483 ,  A61B8/5207 ,  G01S15/8915 ,  G01S15/8993 ,  G06N3/02

Abstract: A method includes generating a series of two-dimensional (2D) ultrasound images of a tissue volume associated with a plurality of positions, respectively, along a scanning direction of the tissue volume. The method includes, for a pair of consecutive 2D ultrasound images, using a deep neural network to classify a difference between the pair of consecutive 2D ultrasound images of the series of 2D ultrasound images. The deep neural network is trained to classify differences between images based on one of a plurality of predefined classes. The method includes modifying a number of 2D ultrasound images in the series of 2D ultrasound images based on the classification of the difference between the pair of consecutive 2D ultrasound images of the series of 2D ultrasound images, thereby producing a modified series of 2D ultrasound images. The method includes performing a measurement of tissue using the modified series of 2D ultrasound images.

公开(公告)号：US20240233133A9

公开(公告)日：2024-07-11

申请号：US18494660

申请日：2023-10-25

Applicant: Exo Imaging, Inc.

Inventor： Xuebin QIN ,  Zichen ZHANG ,  Masood DEHGHAN ,  Dornoosh ZONOOBI

IPC: G06T7/143 ,  G06N3/08 ,  G06N7/01 ,  G06T3/40 ,  G16H30/40

CPC classification number: G06T7/143 ,  G06N3/08 ,  G06N7/01 ,  G06T3/40 ,  G16H30/40 ,  G06T2207/10132 ,  G06T2207/20076 ,  G06T2207/20084 ,  G06T2207/30004

Abstract: A device receives an image. The image is applied to a sequence of encoders that includes a first encoder and one or more subsequent encoders, each including a U network encoder which performs convolution neural network processing. The one or more subsequent encoders receive a down-sampled version of the image from a prior encoder. The sequence of encoders form a first dimension orthogonal to the orthogonal dimension. A result of the sequence of encoders is applied to a sequence of decoders that includes a first decoder and one or more subsequent decoders. A respective decoder comprises a U network decoder that performs convolution neural network processing of an up-sampled version of the image from the first decoder. Probability outputs are produced from paired encoders and decoders in the sequence of encoders and the sequence of decoders. The probability outputs are combined to form a final output.

公开(公告)号：US20240212335A1

公开(公告)日：2024-06-27

申请号：US18557233

申请日：2021-10-14

Applicant: Exo Imaging, Inc.

Inventor： Xuebin QIN, I ,  Masood DEHGHAN ,  Dornoosh ZONOOBI

IPC: G06V10/82 ,  G06V10/42

CPC classification number: G06V10/82 ,  G06V10/42

Abstract: There is provided a method of image processing based on a convolutional neural network (CNN). The method includes: receiving an input image; performing a plurality of feature extraction operations using a plurality of convolution layers, respectively, of the CNN based on the input image to produce a plurality of output feature maps, respectively; and producing an output image for the input image based on the plurality of output feature maps of the plurality of convolution layers. In particular, for each of the plurality of feature extraction operations, performing the feature extraction operation using the convolution layer includes: producing the output feature map of the convolution layer based on an input feature map received by the convolution layer and a plurality of weighted coordinate maps; producing the plurality of weighted coordinate maps based on a plurality of coordinate maps and a spatial attention map; and producing the spatial attention map based on the input feature map received by the convolution layer for modifying coordinate information in each of the plurality of coordinate maps to produce the plurality of weighted coordinate maps. There is also provided a corresponding system for image processing based on a CNN.