# US 12,004,900 B2 · System and methods for a measurement tool for medical imaging

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,004,900 B2
- Document ID: US12004900B2
- Status: Granted
- Kind: B2
- Application number: 17/343,619
- Filed: 2021-06-09
- Published: 2022-12-15
- Granted: 2024-06-11
- Earliest claimed: 2021-06-09
- Assignees: GE Precision Healthcare LLC
- Applicants: GE Precision Healthcare LLC
- Inventors: Yelena Tsymbalenko
- Web page: https://patentgrep.com/patent/US12004900B2

## CPC

- A61B 8/0858: {involving measuring tissue layers, e.g. skin, interfaces}
- A61B 8/085: {for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules}
- A61B 8/461: {Displaying means of special interest}
- A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/11: Region-based segmentation
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/50: for simulation or modelling of medical disorders
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Methods and systems are provided for evaluating a subject for a liver disease using ultrasound images. In one example, a method includes, in response to a request to evaluate the liver disease, determining, with a measurement model, that a selected medical image frame of the subject includes a target anatomical view and has an image quality above a threshold image quality, and in response, measuring, with the measurement model, a marker for the liver disease in the selected medical image, and outputting, for display on a display device, the measurement of the marker.

## Claims

### Claim 1

A system, comprising:
a display device; and
an image processing system configured with instructions in non-transitory memory that when executed cause the image processing system to:
determine, based on a first output of a measurement model and a second output of the measurement model, if an ultrasound image frame of a subject includes a target anatomical view and if an image quality of the ultrasound image frame is above a threshold image quality;
if the ultrasound image frame includes the target anatomical view and has an image quality that is above the threshold image quality, obtain, from the measurement model, a measurement of a thickness of visceral fat present in the ultrasound image frame; and
output, for display on the display device, the measurement of the thickness of the visceral fat and an assessment of a liver disease of the subject that is determined based on the measurement of the visceral fat, wherein the measurement model includes one or more deep learning networks that are configured to take the ultrasound image frame as input and produce multiple outputs, including the first output indicating if the ultrasound image frame includes the target anatomical view, the second output indicating the image quality of the ultrasound image frame, and a third output including the measurement of the thickness of the visceral fat, wherein the measurement model is trained to generate the second output after the measurement model is trained to generate the third output, and wherein training the measurement model to generate the second output includes entering a plurality of training ultrasound images of varying quality to the measurement model, determining an accuracy of measured visceral fat of each training ultrasound image, and updating the measurement model based on the accuracy.

### Claim 2 (depends on 1)

The system of claim 1, wherein the threshold image quality is learned by a first deep learning network of the one or more deep learning networks during training of the first deep learning network, wherein determining if the image quality of the ultrasound image frame is above the threshold image quality includes entering the ultrasound image frame as input to the first deep learning network, wherein the first deep learning network is trained to produce the first output, and wherein the first output includes the image quality.

### Claim 3 (depends on 2)

The system of claim 2, wherein the plurality of training ultrasound images of varying quality includes a plurality of sets of ultrasound image frames, each including a higher quality image frame and a subset of image frames generated from the higher quality image frame, each at a progressively lower quality than the higher quality image frame, and wherein to produce the third output, a second deep learning network of the one or more deep learning networks is trained to segment the visceral fat in the ultrasound image frame and measure the thickness of the segmented visceral fat at one or more measurement points.

### Claim 4 (depends on 1)

The system of claim 1, wherein determining if the ultrasound image frame includes the target anatomical view includes entering the ultrasound image frame as input to a second deep learning network of the one or more deep learning networks, wherein the second deep learning network is trained to produce the second output, and wherein the second output includes an anatomical view of the ultrasound image frame and a confidence score that the anatomical view of the ultrasound image frame is the target anatomical view.

### Claim 5 (depends on 4)

The system of claim 4, wherein the instructions are executable to adjust the threshold image quality based on the confidence score, and wherein the target anatomical view is a long axis aortal view of the liver.

### Claim 6 (depends on 1)

The system of claim 1, wherein the assessment of the liver disease includes a graphical indication of a risk of having the liver disease or a current progression of the liver disease, wherein the liver disease is non-alcoholic fatty liver disease.