# US 12,602,786 B2 · Free fluid estimation

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

- Number: US 12,602,786 B2
- Document ID: US12602786B2
- Status: Granted
- Kind: B2
- Application number: 18/129,307
- Filed: 2023-03-31
- Published: 2023-10-05
- Granted: 2026-04-14
- Earliest claimed: 2022-04-01
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: Goutam Ghoshal; Balasundar Iyyavu Raju; Jonathan Fincke
- Web page: https://patentgrep.com/patent/US12602786B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 7/0014: {using an image reference approach}
- G06T 7/62: of area, perimeter, diameter or volume
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30004: Biomedical image processing
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- 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

The present disclosure provides techniques for free fluid estimation including identifying a region of free fluid in an diagnostic image, calculating a free fluid measure based on the region of free fluid identified in the diagnostic image, and generating a volume class for the region of free fluid in the diagnostic image, wherein the volume class is generated by comparison of the free fluid measure to a data set of previously stored free fluid measures. The present disclosure may be implemented as a method, in a device, a computer readable medium, and a system, among other form factors.

## Claims

### Claim 1

A method for free fluid estimation, comprising:
identifying a region of free fluid in an image;
calculating a free fluid measure based on the region of free fluid identified in the image;
generating a volume class for the region of free fluid in the image, wherein the volume class is generated by comparison of the free fluid measure to a data set of previously stored free fluid measures; and
outputting a representation of the volume class to a graphical representation for display,
wherein the graphical representation includes the volume class displayed in the context of at least one of:
a binary classification;
a linear scale;
a plurality of severity levels;
a non-linear scale;
a numerical value; and
a numerical range.

### Claim 2 (depends on 1)

The method for free fluid estimation of claim 1, comprising:
identifying an anatomical structure in the image;
selecting a subset of the data set of previously stored free fluid measures in response to
the anatomical structure identified in the image.

### Claim 3 (depends on 1)

The method for free fluid estimation of claim 1, comprising outputting a representation of the volume class to at least one of:
a graphical representation for display;
a format for billing documentation;
a format for medical record documentation; and
a format for digital storage.

### Claim 4 (depends on 1)

The method for free fluid estimation of claim 1, wherein the data set is organized through a trained neural network based on annotation of previously captured images and free fluid regions.

### Claim 5 (depends on 1)

The method for free fluid estimation of claim 1, wherein the identifying the region of free fluid comprises identification of a first region and a second region different from the first region; and the data set comprises a first data set and a second data set different from the first.

### Claim 6 (depends on 5)

The method for free fluid estimation of claim 5, wherein:
the first data set is organized through a first trained neural network based on annotation of previously captured images and free fluid regions corresponding to the first region; and
the second data set is organized through a second trained neural network based on annotation of previously captured images and free fluid regions corresponding to the second region.

### Claim 7 (depends on 5)

The method for free fluid estimation of claim 5, wherein:
the image comprises a first section of data and a second section of data distinct from the first section;
the first section of data is pre-processed to be used as an input for a first trained model; and
the second section of data is pre-processed for use in a second trained model, wherein the pre-processing for use in the first trained model is distinct from the pre-processing for use in the second trained model.

### Claim 8 (depends on 7)

The method of claim 7, wherein the pre-processing variations can include variations in the way the data for at least one of the first section and the section are modified through at least one of resizing, normalization, data augmentation by applying transformations such as rotation, flipping, cropping, color shifting to the input images, feature extraction, and dimensionality reduction.

### Claim 9 (depends on 1)

The method for free fluid estimation of claim 1, wherein the diagnostic images are obtained by at least one:
ultrasound imaging;
computerized tomography imaging; and
magnetic resonance imaging.

### Claim 10

A system for free fluid estimation, comprising:
a processor; and
a memory comprising instructions that when executed on the processor, cause the processor to:
identify a region of free fluid in an diagnostic image;
calculate a free fluid measure based on the region of free fluid identified in the diagnostic image; and
generate a volume class for the region of free fluid in the diagnostic image, wherein the volume class is generated by comparison of the free fluid measure to a data set of previously stored free fluid measures; and
output a representation of the volume class to a graphical representation for display,
wherein the graphical representation includes the volume class displayed in the context of at least one of:
a binary classification;
a linear scale;
a plurality of severity levels;
a non-linear scale;
a numerical value; and
a numerical range.

### Claim 11 (depends on 10)

The system for free fluid estimation of claim 10, wherein the memory further comprises instructions that when executed on the processor cause the processor to:
identify an anatomical structure in the image; and
select a subset of the data set of previously stored free fluid measures in response to the anatomical structure identified in the image.

### Claim 12 (depends on 10)

The system for free fluid estimation of claim 10, wherein the memory further comprises instructions that when executed on the processor cause the processor to output a representation of the volume class to at least one of:
a graphical representation for display;
a format for billing documentation;
a format for medical record documentation; and
a format for digital storage.

### Claim 13 (depends on 10)

The system for free fluid estimation of claim 10, wherein the data set is organized through a trained neural network based on annotation of previously captured images and free fluid regions.

### Claim 14

A non-transitory computer-readable medium comprising instructions that when executed on a processor cause the processor to:
identify a region of free fluid in an diagnostic image;
calculate a free fluid measure based on the region of free fluid identified in the diagnostic image; and
generate a volume class for the region of free fluid in the diagnostic image, wherein the volume class is generated by comparison of the free fluid measure to a data set of previously stored free fluid measures; and
output a representation of the volume class to a graphical representation for display, wherein the graphical representation includes the volume class displayed in the context of at least one of:
a binary classification;
a linear scale;
a plurality of severity levels;
a non-linear scale;
a numerical value; and
a numerical range.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, further comprising instructions that when executed on a processor cause the processor to:
identify an anatomical structure in the image; and
select a subset of the data set of previously stored free fluid measures in response to the anatomical structure identified in the image.

### Claim 16 (depends on 14)

The non-transitory computer-readable medium of claim 14, further comprising instructions that when executed on a processor cause the processor to output a representation of the volume class to at least one of:
a graphical representation for display;
a format for billing documentation;
a format for medical record documentation; and
a format for digital storage.

### Claim 17 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the data set is organized through a trained neural network based on annotation of previously captured images and free fluid regions.