# US 2019/0244356 A1 · Evaluation of lungs via ultrasound

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

- Number: US 2019/0244356 A1
- Document ID: US20190244356A1
- Status: Published application
- Kind: A1
- Application number: 16/269,389
- Filed: 2019-02-06
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: The Cleveland Clinic Foundation
- Applicants: The Cleveland Clinic Foundation
- Inventors: Kamal S. Ayyat; Kenneth R. McCurry; Toshihiro Okamoto; Ajit Moghekar
- Web page: https://patentgrep.com/patent/US20190244356A1

## CPC

- G01N 29/0654: {Imaging}
- G01N 29/4409: {by comparison}
- G01N 29/449: {Statistical methods not provided for in G01N29/4409, e.g. averaging, smoothing and interpolation}
- G06F 18/21: Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F 18/2431: Multiple classes
- G06F 18/40: Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/0016: {involving temporal comparison}
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 10/945: {User interactive design; Environments; Toolboxes}
- 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
- G01N 2291/02475: Tissue characterisation
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/10132: Ultrasound image
- G06T 2207/30061: Lung
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Systems and methods are provided for evaluating a lung via ultrasound. A plurality of ultrasound images are generated at each of a plurality of locations on a lung using an ultrasound imager to provide a plurality of images. Respective grades are assigned to each of the plurality of images according to an amount of B-line artifact in the image to generate a plurality of grades for the lung. A composite score for the lung is calculated from the plurality of grades. The composite score represents a general assessment of the lung. The composite score is provided to a user at an associated output device.

## Claims

### Claim 1

A system comprising:
an ultrasound imager manipulable to image a lung at a plurality of locations to produce a plurality of images;
a processor; and
a non-transitory computer readable medium storing executable instructions, the executable instructions comprising:
a grader interface configured to receive, for each of the plurality of locations, data representing the image or images taken at that location and provide a plurality of grades, each representing the amount of B-line artifact in a corresponding image;
a score calculator configured to determine a composite score representing a general assessment of the lung from the plurality of grades; and
a user interface configured to provide the composite score to a user at an associated output device.

### Claim 2 (depends on 1)

The system of claim 1, wherein the grader interface comprises an input interface for receiving data representing grades assigned by a human expert.

### Claim 3 (depends on 1)

The system of claim 1, wherein each of the plurality of grades are selected from a set of six grades comprising a first grade indicating minimal B-line artifact, a second grade indicating moderate B-line artifact, a third grade indicating significant B-line artifact, a fourth grade indicating severe B-line artifact, a fifth grade indicating the absence of B-line artifact, and a sixth grade indicating consolidation at the imaged location.

### Claim 4 (depends on 3)

The system of claim 3, wherein the first grade is selected when the B-line artifact is present but covers less than twenty-five percent of a region of interest within the image, the second grade is selected when the B-line artifact covers between twenty-five and fifty percent of the region of interest, the third grade is selected when the B-line artifact covers between fifty and seventy-five percent of the region of interest, and the fourth grade is selected when the B-line artifact covers more than seventy-five percent of the image.

### Claim 5 (depends on 3)

The system of claim 3, wherein the score calculator calculates the composite score as:
Score
=
N
G
1
+
2
*
N
G
2
+
3
*
N
G
3
+
4
*
N
G
4
+
5
*
N
C
N
tot
where NG1 is the number of times that the first grade is selected, NG2 is the number of times that the second grade is selected, NG3 is the number of times that the third grade is selected, NG4 is the number of times that the fourth grade is selected, NC is the number of images indicating consolidation, and Ntot is the total number of images.

### Claim 6 (depends on 1)

The system of claim 1, wherein each of the plurality of locations lies along one of a line along an anterior surface of the lung, a line along a lateral surface of the lung, a line along a posterior surface of the lung, and a line along a diaphragmatic surface of the lung.

### Claim 7 (depends on 6)

The system of claim 6, wherein the plurality of locations includes at least one location along each of the line along the anterior surface of the lung, the line along the lateral surface of the lung, the line along the posterior surface of the lung, and the line along the diaphragmatic surface of the lung.

### Claim 8 (depends on 1)

The system of claim 1, wherein the grader interface comprises an image interface configured to receive the plurality of images and an expert system that utilizes a set of extracted features from the image to determine an appropriate grade for the image.

### Claim 9 (depends on 8)

The system of claim 8, the expert system comprising a pattern recognition classifier configured to assign a categorical grade to the image from the set of extracted features.

### Claim 10 (depends on 8)

The system of claim 8, the expert system comprising a regression model configured to assign a numerical grade to the image from the set of extracted features.

### Claim 11 (depends on 1)

The system of claim 1, wherein the score calculator is configured to determine a location score for each location from the plurality of grades and calculate the composite score as an average of the locations scores for the plurality of locations.

### Claim 12

A method comprising:
generating a plurality of ultrasound images at each of a plurality of locations on a lung using an ultrasound imager to provide a plurality of images;
assigning respective grades to each of the plurality of images according to an amount of B-line artifact in the image to generate a plurality of grades for the lung;
calculating a composite score for the lung from the plurality of grades, the composite score representing a general assessment of the lung for transplant into a patient; and
providing the composite score to a user at an associated output device.

### Claim 13 (depends on 12)

The method of claim 12, further comprising calculating a lobe score for each of a plurality of lobes of the lung, representing an amount of extravascular lung water within the lobe, from respective proper subsets of the plurality of grades.

### Claim 14 (depends on 12)

The method of claim 12, wherein assigning respective grades to each of plurality of ultrasound images comprises providing the images to human experts for evaluation.

### Claim 15 (depends on 12)

The method of claim 12, wherein assigning respective grades to each of plurality of ultrasound images comprises selecting each of the plurality of grades from a set of six grades comprising a first grade indicating minimal B-line artifact, a second grade indicating moderate B-line artifact, a third grade indicating significant B-line artifact, a fourth grade indicating severe B-line artifact, a fifth grade indicating the absence of B-line artifact, and a sixth grade indicating consolidation at the imaged location.

### Claim 16 (depends on 15)

The method of claim 15, wherein calculating a composite score for the lung from the plurality of grades comprises assigning a score to each of the plurality of images according to the grade assigned to the image and averaging the scores across the plurality of images.

### Claim 17 (depends on 12)

The method of claim 12, wherein assigning respective grades to each of plurality of ultrasound images comprises providing the images to an expert system.

### Claim 18 (depends on 12)

The method of claim 12, wherein each of the plurality of locations lies along one of a line along an anterior surface of the lung, a line along a lateral surface of the lung, a line along a posterior surface of the lung, and a line along a diaphragmatic surface of the lung.

### Claim 19

A computer program product, storing instructions executable by an associated processor to evaluate a plurality of ultrasound images of a lung, the executable instructions comprising:
a grader interface configured to receive, for each of the ultrasound images, data representing the image, and provide a grade representing the amount of B-line artifact in the image;
a score calculator configured to determine a composite score representing a general assessment of the lung from the plurality of grades; and
a user interface configured to provide the composite score to a user at an associated output device.

### Claim 20 (depends on 19)

The system of claim 19, wherein the grader interface comprises an image interface configured to receive the plurality of images and an expert system that utilizes a set of extracted features from the image to determine the grade for the image.