# US 2022/0068498 A1 · Systems and methods for automatically managing image data

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

- Number: US 2022/0068498 A1
- Document ID: US20220068498A1
- Status: Published application
- Kind: A1
- Application number: 17/465,297
- Filed: 2021-09-02
- Published: 2022-03-03
- Earliest claimed: 2020-09-03
- Assignees: Huron Technologies International Inc.
- Applicants: Huron Technologies International Inc.
- Inventors: Hamid Reza Tizhoosh; Patrick Myles; Savvas Damaskinos
- Web page: https://patentgrep.com/patent/US20220068498A1

## CPC

- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06F 16/51: Indexing; Data structures therefor; Storage structures
- G06F 16/532: Query formulation, e.g. graphical querying
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- 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
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Computer-implemented methods and systems are provided for curating medical images for a medical image database. An example method for curating involves operating a processor to obtain a query medical image, assign the query medical image to an initial set of related images, and generate a similarity indicator for each image of the initial set. The similarity indicator is representative of a measure of similarity between image data of that image and the initial set. The processor is operable to define an intermediate set from the initial set based on the similarity indicators; and generate a relevancy indicator for each image of the intermediate set. The relevancy indicator is representative of a measure of the relevancy between relevance of the image and the intermediate set. The processor is operable to define a curated set of images from the intermediate set based on the relevancy indicators.

## Claims

### Claim 1

A computer-implemented method of curating medical images for a medical image database, the method comprising operating a processor to:
obtain one or more query medical images, each query medical image having an identifier that is representative of image data of that query medical image;
assign each query medical image to at least one initial set of related medical images from the medical image database based on the identifier for that query medical image, the initial set comprising the query medical image and at least one supplemental medical image; and
for each initial set of related medical images,
generate a similarity indicator for each medical image of the initial set, the similarity indicator being representative of a measure of similarity between image data of that medical image and image data of the initial set; and
define an intermediate set of medical images from the initial set based on the similarity indicator of each medical image of the initial set; and
for each intermediate set of related medical images,
generate a relevancy indicator for each medical image of the intermediate set, the relevancy indicator being representative of a measure of the relevancy between the medical image and the intermediate set, the relevancy being representative of correlations between a plurality of relevance parameters associated with the medical image and the intermediate set; and
define a curated set of medical images for storage in the medical image database from the medical images in the intermediate set based on the relevancy indicator of each medical image.

### Claim 2 (depends on 1)

The method of claim 1, wherein the curated set of medical images excludes the query medical image.

### Claim 3 (depends on 1)

The method of claim 1, wherein the curated set of medical images comprises the query medical image.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The method of claim 1 comprises, for each medical image of the intermediate set, normalizing a measure of relevancy between relevance parameters of the query medical image and relevance parameters of medical images of the intermediate set of medical images.

### Claim 6 (depends on 1)

The method of claim 1 comprises:
determining whether the relevancy indicator for a medical image exceeds a first relevancy threshold; and
in response to determining that the relevancy indicator of the medical image does not exceed the first relevancy threshold, excluding the medical image from the curated set of medical images, otherwise including the medical image to the curated set of medical images.

### Claim 7 (depends on 1)

The method of claim 1 comprises storing a version of a medical image in the curated set of medical images.

### Claim 8 (depends on 1)

The method of claim 1 comprises:
determining whether the relevancy indicator of a medical image exceeds a second relevancy threshold; and
in response to determining that the relevancy indicator of the medical image does not exceed the second relevancy threshold, storing a version of the medical image in the curated set of medical images, otherwise storing the medical image in the curated set of medical images.

### Claim at position 9

-15. (canceled)

### Claim 16 (depends on 1)

The method of claim 1 comprises for each intermediate set:
receiving the plurality of relevance parameters for the medical images of the intermediate set;
generating a plurality of membership values by applying a set of input membership functions to the relevance parameters for each medical image of the intermediate set;
generating an output membership function for each medical image of the intermediate set by applying a set of rules to the plurality of membership values for that medical image of the intermediate set to quantify the relevancy of that medical image of the intermediate set; and
generating the relevancy indicator for each of the medical images of the intermediate set by quantifying the output membership function for that medical image.

### Claim at position 11

-19. (canceled)

### Claim 20 (depends on 1)

The method of claim 1 comprises, for each supplemental medical image of the initial set, normalizing a measure of similarity between the identifier of the query medical image and the identifier of the supplemental medical image.

### Claim 21 (depends on 1)

The method of claim 1 comprises:
determining whether the similarity indicator for that medical image exceeds a similarity threshold; and
in response to determining that the similarity indicator for that medical image exceeds the similarity threshold, assigning that medical image to the intermediate set.

### Claim at position 14

-25. (canceled)

### Claim 26

A system for curating medical images for a medical image database, the system comprising:
a communication component to provide access to the one or more images via a network; and
a processor in communication with the communication component, the processor being operable to:
obtain one or more query medical images, each query medical image having an identifier that is representative of image data of that query medical image;
assign each query medical image to at least one initial set of related medical images from the medical image database based on the identifier for that query medical image, the initial set comprising the query medical image and at least one supplemental medical image; and
for each initial set of related medical images,
generate a similarity indicator for each medical image of the initial set, the similarity indicator representing a measure of similarity between image data of that medical image and image data of the initial set; and
define an intermediate set of medical images from the initial set based on the similarity indicator of each medical image of the initial set; and
for each intermediate set of related medical images,
generate a relevancy indicator for each medical image of the intermediate set, the relevancy indicator being representative of a measure of the relevancy between the medical image and the intermediate set, the relevancy being representative of correlations between a plurality of relevance parameters associated with the medical image and the intermediate set; and
define a curated set of medical images for storage in the medical image database from the medical images in the intermediate set based on the relevancy indicator of each medical image.

### Claim 27 (depends on 26)

The system of claim 26, wherein the curated set of medical images excludes the query medical image.

### Claim 28 (depends on 26)

The system of claim 26, wherein the curated set of medical images comprises the query medical image.

### Claim 29

(canceled)

### Claim 30 (depends on 26)

The system claim 26, wherein the processor is operable to for each medical image of the intermediate set, normalize a measure of relevancy between relevance parameters of the query medical image and relevance parameters of medical images of the intermediate set of medical images.

### Claim 31 (depends on 26)

The system of claim 26, wherein the processor is operable to:
determine whether the relevancy indicator for a medical image exceeds a first relevancy threshold; and
in response to determining that the relevancy indicator of the medical image does not exceed the first relevancy threshold, exclude the medical image from the curated set of medical images, otherwise assign the medical image to the curated set of medical images.

### Claim 32 (depends on 26)

The system of claim 26, wherein the processor is operable to store a version of a medical image in the curated set of medical images.

### Claim 33 (depends on 26)

The system of claim 26, wherein the processor is operable to:
determine whether the relevancy indicator of a medical image exceeds a second relevancy threshold; and
in response to determining that the relevancy indicator of the medical image does not exceed the second relevancy threshold, store a version of a medical image in the curated set of medical images, otherwise store the medical image in the curated set of medical images.

### Claim at position 23

-40. (canceled)

### Claim 41 (depends on 26)

The system of claim 26, wherein the processor is operable to, for each intermediate set:
receive the plurality of relevance parameters for each of the medical images of the intermediate set;
generate a plurality of membership values by applying a set of input membership functions to the relevance parameters for each medical image of the intermediate set;
generate an output membership function for each medical image of the intermediate set by applying a set of rules to the plurality of membership values for that medical image of the intermediate set to quantify the relevancy of that medical image of the intermediate set; and
generate the relevancy indicator for each of the medical images of the intermediate set by quantifying the output membership function for that medical image.

### Claim at position 25

-44. (canceled)

### Claim 45 (depends on 26)

The system of claim 26, wherein the processor is operable to, for each supplemental medical image of the initial set, normalize a measure of similarity between the identifier of the query medical image and the identifier of the supplemental medical image.

### Claim 46 (depends on 26)

The system of claim 26, wherein the processor is operable to:
determine whether the similarity indicator for that medical image exceeds a similarity threshold; and
in response to determining that the similarity indicator for that medical image exceeds the similarity threshold, assign that medical image to the intermediate set.

### Claim at position 28

-115. (canceled)
