# US 2023/0054588 A1 · Systems and methods for detecting tissue and shear waves within the tissue > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0054588 A1 - Document ID: US20230054588A1 - Status: Published application - Kind: A1 - Application number: 17/820,802 - Filed: 2022-08-18 - Published: 2023-02-23 - Earliest claimed: 2021-08-20 - Assignees: Sonic Incytes Medical Corp. - Applicants: Sonic Incytes Medical Corp. - Inventors: Mohammad HONARVAR; Caitlin Marie SCHNEIDER; Julio Raul LOBO; Brian Peter STACHNIAK - Web page: https://patentgrep.com/patent/US20230054588A1 ## CPC - A61B 8/085: {for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules} - A61B 8/463: {characterised by displaying multiple images or images and diagnostic data on one display} - A61B 8/485: {involving measuring strain or elastic properties} - A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)} - G06T 7/0002: {Inspection of images, e.g. flaw detection} - G06T 7/11: Region-based segmentation - G06T 7/174: involving the use of two or more images - G06T 2207/10132: Ultrasound image - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30056: Liver; Hepatic - G06T 2207/30168: Image quality inspection - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Example embodiments of the described technology provide systems and methods for ultrasound imaging. An example method may detect the presence of shear waves within a tissue region of a patient. The method may comprise exciting the tissue region of the patient with one or more exciters to induce propagation of shear waves within the tissue. A plurality of ultrasound images of the tissue may be acquired. A first image mask indicating which pixels of the acquired images represent a desired tissue type using a first trained machine learning model may be generated. The method may also comprise generating a second image mask indicating which pixels of the acquired images represent shear waves using a second trained machine learning model. ## Claims ### Claim 1 A method for detecting presence of shear waves within a tissue of interest in a tissue region of a patient, the method comprising: exciting the tissue region of the patient with one or more exciters to induce propagation of shear waves within the tissue region by vibrating the tissue region with the one or more exciters; while exciting the tissue region, acquiring a plurality of ultrasound images of the tissue region with an ultrasonic transducer acoustically coupled to the patient; processing the acquired plurality of ultrasound images to determine characteristics of the shear waves; displaying at least some of the acquired plurality of ultrasound images on a display; and displaying on the display a visual indicator representing a measure of how well the acquired plurality of ultrasound images capture the tissue of interest within the tissue region and a quality measure of shear waves traveling through the tissue of interest, the visual indicator determined at least partially from: a first image mask indicating which pixels of the acquired plurality of ultrasound images represent the tissue of interest, the first image mask generated by inputting one or more of the acquired plurality of ultrasound images into a first machine learning model trained to identify the tissue of interest within one or more input ultrasound images; and a second image mask indicating which pixels of the acquired plurality of ultrasound images represent shear waves usable to determine an elasticity property of the tissue of interest, the second mask generated by inputting one or more of the acquired plurality of ultrasound images and shear wave data corresponding to the shear waves travelling through the tissue of interest into a second machine learning model trained to identify shear waves usable to determine the elasticity property of the tissue of interest. ### Claim 2 (depends on 1) The method of claim 1 comprising cropping at least one of the visual indicator, the first image mask and the second image mask to a fixed two-dimensional or three-dimensional region of interest. ### Claim 3 (depends on 2) The method of claim 2 wherein cropping at least one of the visual indicator, the first image mask and the second image mask comprises maximizing within a crop region the number of pixels of the visual indicator, the first image mask or the second image mask which comprise both the tissue of interest and the shear waves usable to determine the elasticity property of the tissue of interest. ### Claim 4 (depends on 2) The method of claim 2 comprising dynamically varying the region of interest in real time as the acquired plurality of ultrasound images is updated. ### Claim 5 (depends on 1) The method of claim 1 comprising generating the first image mask and the second image mask concurrently. ### Claim 6 (depends on 1) The method of claim 1 wherein the visual indicator indicates at least one of ultrasound signal-to-noise ratio, ability to track tissue displacements, fitting of tissue displacements to known frequencies of input vibrations, shear wave presence and identification of tissue type. ### Claim 7 (depends on 6) The method of claim 6 wherein displaying the visual indicator comprises displaying a numeric representation. ### Claim 8 (depends on 6) The method of claim 6 wherein displaying the visual indicator comprises generating a third image mask, the third image mask generated by combining the first and second image masks together. ### Claim 9 (depends on 8) The method of claim 8 comprising performing a pixel wise logical AND operation to combine the first image mask and the second image mask to yield the third image mask. ### Claim 10 (depends on 8) The method of claim 8 comprising displaying over the displayed at least some of the acquired plurality of ultrasound images at least one of the first image mask, the second image mask and the third image mask. ### Claim 11 (depends on 10) The method of claim 10 comprising displaying the first image mask in a first color, the second image mask in a second color different from the first color and the third image mask in a third color different from the first and second colors. ### Claim 12 (depends on 1) The method of claim 1 wherein the first machine learning model is trained to detect the tissue of interest based on boundaries of the tissue. ### Claim 13 (depends on 12) The method of claim 12 wherein the first machine learning model is trained to segment pixels of the one or more ultrasound images inputted into the first machine learning model into at least a first group corresponding to the tissue of interest and a second group corresponding to tissue other than the tissue of interest. ### Claim 14 (depends on 13) The method of claim 13 wherein the first machine learning model comprises a convolutional neural network. ### Claim 15 (depends on 14) The method of claim 14 wherein the first machine learning model comprises a U-Net convolutional neural network. ### Claim 16 (depends on 1) The method of claim 1 wherein the first image mask comprises a binary mask. ### Claim 17 (depends on 1) The method of claim 1 wherein the first image mask comprises pixel values representing a probability that the corresponding pixels of the acquired plurality of ultrasound images represent the tissue of interest. ### Claim 18 (depends on 1) The method of claim 1 wherein the second machine learning model comprises a convolutional neural network. ### Claim 19 (depends on 18) The method of claim 18 wherein the second machine learning model comprises a U-Net convolutional neural network. ### Claim 20 (depends on 19) The method of claim 19 wherein the second machine learning model comprises a first branch configured to receive as input the shear wave data and a second branch configured to receive as input the one or more ultrasound images inputted into the second machine learning model. ### Claim 21 (depends on 1) The method of claim 1 wherein the shear wave data comprises at least one of: different states of the shear waves in time; a real part and an imaginary part of a phasor representing the shear waves; and a magnitude and phase of the phasor. ### Claim 22 (depends on 1) The method of claim 1 wherein the tissue of interest comprises liver tissue. ### Claim 23 A method for detecting presence of shear waves within liver tissue of a patient, the method comprising: exciting an abdominal region of the patient with one or more exciters to induce propagation of shear waves within the liver tissue by vibrating the abdominal region with the one or more exciters; while exciting the abdominal region, acquiring a plurality of ultrasound images of the abdominal region with an ultrasonic transducer acoustically coupled to the patient; processing the acquired plurality of ultrasound images to determine characteristics of the shear waves; displaying at least some of the acquired plurality of ultrasound images on a display; and displaying on the display a visual indicator representing a measure of how well the acquired plurality of ultrasound images capture the liver tissue within the abdominal region and a quality measure of shear waves traveling through the liver tissue, the visual indicator determined at least partially from: a first image mask indicating which pixels of the acquired plurality of ultrasound images represent the liver tissue, the first image mask generated by inputting one or more of the acquired plurality of ultrasound images into a first machine learning model trained to segment pixels of the one or more ultrasound images inputted into the first machine learning model into at least a first group corresponding to liver tissue and a second group corresponding to tissue other than liver tissue; and a second image mask indicating which pixels of the acquired plurality of ultrasound images represent shear waves usable to determine an elasticity property of the liver tissue, the second mask generated by inputting one or more of the acquired plurality of ultrasound images and shear wave data corresponding to the shear waves travelling through the liver tissue into a second machine learning model trained to identify shear waves usable in a method of elastography of liver tissue to determine the elasticity property of the liver tissue.