# US 2025/0152144 A1 · Methods and systems for clinical scoring a lung ultrasound

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

- Number: US 2025/0152144 A1
- Document ID: US20250152144A1
- Status: Published application
- Kind: A1
- Application number: 18/722,255
- Filed: 2022-12-19
- Published: 2025-05-15
- Earliest claimed: 2021-12-23
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: Alvin Chen; Jochen Kruecker; Naveen Balaraju; Shubham Patil
- Web page: https://patentgrep.com/patent/US20250152144A1

## CPC

- A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)}
- G16H 30/40: for processing medical images, e.g. editing
- A61B 8/08: Clinical applications (A61B8/02, A61B8/04, A61B8/06 take precedence)
- G06T 7/0012: {Biomedical image inspection}
- 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
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/30061: Lung
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method (100) for analyzing ultrasound image data, comprising: (i) receiving (120) ultrasound image data for a patient, comprising at least one lung-related clinical feature; (ii) selecting (130) a first clinical feature; (iii) analyzing (140), using an image processing algorithm, the ultrasound image data to extract one or more image parameters of the selected clinical feature, wherein the image processing algorithm is defined to analyze the selected clinical feature; (iv) analyzing (150), using a trained machine learning algorithm, the ultrasound image data to extract one or more learned parameters of the selected clinical feature, wherein the trained machine learning algorithm is trained to analyze the selected clinical feature; (v) combining (160) the image parameters and the learned parameters to generate a final lung-related clinical feature analysis; and (vi) providing (170) the generated final lung-related clinical feature analysis.

## Claims

### Claim 1

A method for analyzing ultrasound image data, comprising:
receiving ultrasound image data for at least a portion of a lung of a patient, the ultrasound image data comprising at least one lung-related clinical feature;
selecting a first of the at least one lung-related clinical feature;
analyzing, using an image processing algorithm, the ultrasound image data to extract one or more image parameters of the selected first lung-related clinical feature, wherein the image processing algorithm is defined to analyze the selected first lung-related clinical feature;
analyzing, using a trained machine learning algorithm, the ultrasound image data to extract one or more learned parameters of the selected first lung-related clinical feature, wherein the trained machine learning algorithm is trained to analyze the selected first lung-related clinical feature;
combining the extracted one or more image parameters and the extracted one or more learned parameters of the selected first lung-related clinical feature to generate a final lung-related clinical feature analysis for the selected first lung-related clinical feature; and
providing, via a user interface, the generated final lung-related clinical feature analysis for the selected first lung-related clinical feature.

### Claim 2 (depends on 1)

The method of claim 1, wherein combining the extracted one or more image parameters and the extracted one or more learned parameters comprises:
concatenating the extracted one or more image parameters and the extracted one or more learned parameters to generate a concatenated vector; and
inputting the concatenated vector into a classifier algorithm, trained on concatenated vectors, to generate the final lung-related clinical feature.

### Claim 3 (depends on 1)

The method of claim 1, wherein combining the extracted one or more image parameters and the extracted one or more learned parameters comprises inputting the one or more image parameters into the trained machine learning algorithm to generate the final lung-related clinical feature.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining, using the final lung-related clinical feature analysis for the selected first lung-related clinical feature, a clinical assessment for the patient;
wherein the step of providing further comprises providing, via the user interface, the determined clinical assessment for the patient.

### Claim 5 (depends on 1)

The method of claim 1, wherein the method is repeated such that:
a second of the at least one lung-related clinical feature is selected;
the selected second lung-related clinical feature is analyzed by the image processing algorithm to extract one or more image parameters of the selected second lung-related clinical feature;
the selected second lung-related clinical feature is analyzed by the trained machine learning algorithm to extract one or more learned parameters of the selected second lung-related clinical feature; and
the extracted one or more image parameters and the extracted one or more learned parameters of the selected second lung-related clinical feature are combined to generate a final lung-related clinical feature analysis for the selected second lung-related clinical feature.

### Claim 6 (depends on 5)

The method of claim 5, wherein providing via the user interface further comprises providing the generated final lung-related clinical feature analysis for the selected second lung-related clinical feature.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
determining, using the final lung-related clinical feature analysis for the selected first lung-related clinical feature and the final lung-related clinical feature analysis for the selected second lung-related clinical feature, a clinical assessment for the patient;
wherein the step of providing further comprises providing, via the user interface, the determined clinical assessment for the patient.

### Claim 8 (depends on 1)

The method of claim 1, wherein providing via the user interface further comprises providing the extracted one or more image parameters and the extracted one or more learned parameters of the selected first lung-related clinical feature.

### Claim 9 (depends on 1)

The method of claim 1, wherein the step of combining comprises combining the extracted one or more image parameters and the extracted one or more learned parameters of each of two or more selected lung-related clinical features to generate a final lung-related clinical feature analysis.

### Claim 10

An ultrasound analysis system configured to analyze ultrasound image data, comprising:
ultrasound image data for at least a portion of a lung of a patient, the ultrasound image data comprising at least one lung-related clinical feature;
an image processing algorithm defined to analyze a selected first lung-related clinical feature;
a trained machine learning algorithm trained to analyze the selected first lung-related clinical feature;
a processor configured to: (i) select the first of the at least one lung-related clinical feature; (ii) analyze, using the image processing algorithm, the ultrasound image data to extract one or more image parameters of the selected first lung-related clinical feature; (iii) analyze, using the trained machine learning algorithm, the ultrasound image data to extract one or more learned parameters of the selected first lung-related clinical feature; (iv) combine the extracted one or more image parameters and the extracted one or more learned parameters of the selected first lung-related clinical feature to generate a final lung-related clinical feature analysis for the selected first lung-related clinical feature; and
a user interface configured to provide the generated final lung-related clinical feature analysis for the selected first lung-related clinical feature.

### Claim 11 (depends on 10)

The system of claim 10, wherein the processor is configured to combine the extracted one or more image parameters and the extracted one or more learned parameters by:
concatenating the extracted one or more image parameters and the extracted one or more learned parameters to generate a concatenated vector; and
inputting the concatenated vector into a classifier algorithm, trained on concatenated vectors, to generate the final lung-related clinical feature.

### Claim 12 (depends on 10)

The system of claim 10, wherein the processor is configured to combine the extracted one or more image parameters and the extracted one or more learned parameters by inputting the one or more image parameters into the trained machine learning algorithm to generate the final lung-related clinical feature.

### Claim 13 (depends on 10)

The system of claim 10, wherein:
the processor is further configured to determine, using at least the final lung-related clinical feature analysis for the selected first lung-related clinical feature, a clinical assessment for the patient; and
the user interface is further configured to provide the determined clinical assessment for the patient.

### Claim 14 (depends on 10, 11, 12, 13)

The system of any of claims 10 to 13, wherein the user interface is further configured to provide the extracted one or more image parameters and the extracted one or more learned parameters of the selected first lung-related clinical feature.

### Claim 15 (depends on 10)

The system of claim 10, wherein the processor is further configured such that:
a second of the at least one lung-related clinical feature is selected;
the selected second lung-related clinical feature is analyzed by the image processing algorithm to extract one or more image parameters of the selected second lung-related clinical feature;
the selected second lung-related clinical feature is analyzed by the trained machine learning algorithm to extract one or more learned parameters of the selected second lung-related clinical feature; and
the extracted one or more image parameters and the extracted one or more learned parameters of the selected second lung-related clinical feature are combined to generate a final lung-related clinical feature analysis for the selected second lung-related clinical feature.
